This document summarizes a study that developed a hybrid machine learning approach for detecting driver drowsiness using electroencephalogram (EEG) signals. The study extracted features from single-channel EEG recordings in the time, frequency, and power spectral density domains. Various machine learning classifiers were tested on the features, including support vector machine, random forest, decision tree, and neural networks. The optimized random forest classifier achieved 98.5% accuracy in detecting drowsiness, with a fast processing time of 13 milliseconds. This high accuracy and speed demonstrate that the proposed hybrid approach outperforms existing methods for EEG-based driver drowsiness detection.
Survey analysis for optimization algorithms applied to electroencephalogramIJECEIAES
This paper presents a survey for optimization approaches that analyze and classify electroencephalogram (EEG) signals. The automatic analysis of EEG presents a significant challenge due to the high-dimensional data volume. Optimization algorithms seek to achieve better accuracy by selecting practical features and reducing unwanted features. Forty-seven reputable research papers are provided in this work, emphasizing the developed and executed techniques divided into seven groups based on the applied optimization algorithm particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), grey wolf optimizer (GWO), Bat, Firefly, and other optimizer approaches). The main measures to analyze this paper are accuracy, precision, recall, and F1-score assessment. Several datasets have been utilized in the included papers like EEG Bonn University, CHB-MIT, electrocardiography (ECG) dataset, and other datasets. The results have proven that the PSO and GWO algorithms have achieved the highest accuracy rate of around 99% compared with other techniques.
Driving sleepiness detection using electrooculogram analysis and grey wolf o...IJECEIAES
In modern society, providing safe and collision-free travel is essential. Therefore, detecting the drowsiness state of the driver before its ability to drive is compromised. For this purpose, an automated hybrid sleepiness classification system that combines the artificial neural network and gray wolf optimizer is proposed to distinguish human Sleepiness and fatigue. The proposed system is tested on data collected from 15 drivers (male and female) in alert and sleep-deprived conditions where physiological signals are used as sleep markers. To evaluate the performance of the proposed algorithm, k-nearest neighbors (k-NN), support vector machines (SVM), and artificial neural networks (ANN) classifiers have been used. The results show that the proposed hybrid method provides 99.6% accuracy, while the SVM classifier provides 93.0% accuracy when the kernel is (RBF) and outlier (0.1). Furthermore, the k-NN classifier provides 96.7% accuracy, whereas the standalone ANN algorithm provides 97.7% accuracy.
Wavelet-Based Approach for Automatic Seizure Detection Using EEG SignalsIRJET Journal
This document presents a wavelet-based approach for automatically detecting seizures using EEG signals. EEG data is decomposed into detailed and approximate coefficients using discrete wavelet transform up to the fourth level. Statistical features are extracted from the wavelet coefficients and the most significant features are selected using the Wilcoxon rank-sum test. Three classifiers - SVM, kNN, and ensemble subspace kNN - are used to classify EEG segments as pre-ictal, inter-ictal, or ictal. The proposed method achieves 100% classification accuracy when discriminating between healthy and epileptic EEG signals on the neurology and sleep centre EEG database.
Electroencephalography-based brain-computer interface using neural networksTELKOMNIKA JOURNAL
This study aimed to develop a brain-computer interface that can control an electric wheelchair using electroencephalography (EEG) signals. First, we used the Mind Wave Mobile 2 device to capture raw EEG signals from the surface of the scalp. The signals were transformed into the frequency domain using fast Fourier transform (FFT) and filtered to monitor changes in attention and relaxation. Next, we performed time and frequency domain analyses to identify features for five eye gestures: opened, closed, blink per second, double blink, and lookup. The base state was the opened-eyes gesture, and we compared the features of the remaining four action gestures to the base state to identify potential gestures. We then built a multilayer neural network to classify these features into five signals that control the wheelchair’s movement. Finally, we designed an experimental wheelchair system to test the effectiveness of the proposed approach. The results demonstrate that the EEG classification was highly accurate and computationally efficient. Moreover, the average performance of the brain-controlled wheelchair system was over 75% across different individuals, which suggests the feasibility of this approach.
Prediction Model for Emotion Recognition Using EEGIRJET Journal
The document describes a study that compares different machine learning models for emotion recognition using EEG data. The study uses EEG data collected from patients with depression and healthy controls. It extracts features from the EEG data, including linear and nonlinear parameters from different frequency bands. It then uses classifiers like random forest, KNN, CNN, and LSTM to classify emotions as positive, negative or neutral. The random forest model achieved the best accuracy for identifying depression patients' emotions. The study provides a framework for EEG data collection, preprocessing, feature extraction and applying different machine learning models to optimize emotion recognition from EEG signals.
CLASSIFICATION OF ELECTROENCEPHALOGRAM SIGNALS USING XGBOOST ALGORITHM AND SU...IRJET Journal
This document presents a study that uses the XGBoost algorithm and support vector machine to classify electroencephalogram (EEG) signals. The study acquires EEG data from healthy subjects and subjects with epilepsy during seizure and non-seizure periods. It preprocesses the data, extracts features using linear discriminant analysis, and feeds the extracted features into XGBoost and SVM classifiers. The results indicate that XGBoost exhibited superior classification performance compared to SVM for analyzing and classifying EEG signals.
This document describes a smart home system designed to aid paralyzed individuals living alone. EEG signals are collected from 25 paralyzed subjects to study brain activity related to hunger, thirst, sleepiness, excitement and stress. The EEG data is preprocessed and classified using kNN classifiers to identify the individual's needs. An Internet of Things platform uses the classified EEG data to make logical decisions and control automated modules to meet the person's basic needs. These include modules for feeding, sleep, temperature control and more. Experimental results showed an overall 89.73% accuracy for automating units to fulfill a paralyzed person's basic needs. The system aims to help paralyzed individuals live more independently at home.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
Survey analysis for optimization algorithms applied to electroencephalogramIJECEIAES
This paper presents a survey for optimization approaches that analyze and classify electroencephalogram (EEG) signals. The automatic analysis of EEG presents a significant challenge due to the high-dimensional data volume. Optimization algorithms seek to achieve better accuracy by selecting practical features and reducing unwanted features. Forty-seven reputable research papers are provided in this work, emphasizing the developed and executed techniques divided into seven groups based on the applied optimization algorithm particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), grey wolf optimizer (GWO), Bat, Firefly, and other optimizer approaches). The main measures to analyze this paper are accuracy, precision, recall, and F1-score assessment. Several datasets have been utilized in the included papers like EEG Bonn University, CHB-MIT, electrocardiography (ECG) dataset, and other datasets. The results have proven that the PSO and GWO algorithms have achieved the highest accuracy rate of around 99% compared with other techniques.
Driving sleepiness detection using electrooculogram analysis and grey wolf o...IJECEIAES
In modern society, providing safe and collision-free travel is essential. Therefore, detecting the drowsiness state of the driver before its ability to drive is compromised. For this purpose, an automated hybrid sleepiness classification system that combines the artificial neural network and gray wolf optimizer is proposed to distinguish human Sleepiness and fatigue. The proposed system is tested on data collected from 15 drivers (male and female) in alert and sleep-deprived conditions where physiological signals are used as sleep markers. To evaluate the performance of the proposed algorithm, k-nearest neighbors (k-NN), support vector machines (SVM), and artificial neural networks (ANN) classifiers have been used. The results show that the proposed hybrid method provides 99.6% accuracy, while the SVM classifier provides 93.0% accuracy when the kernel is (RBF) and outlier (0.1). Furthermore, the k-NN classifier provides 96.7% accuracy, whereas the standalone ANN algorithm provides 97.7% accuracy.
Wavelet-Based Approach for Automatic Seizure Detection Using EEG SignalsIRJET Journal
This document presents a wavelet-based approach for automatically detecting seizures using EEG signals. EEG data is decomposed into detailed and approximate coefficients using discrete wavelet transform up to the fourth level. Statistical features are extracted from the wavelet coefficients and the most significant features are selected using the Wilcoxon rank-sum test. Three classifiers - SVM, kNN, and ensemble subspace kNN - are used to classify EEG segments as pre-ictal, inter-ictal, or ictal. The proposed method achieves 100% classification accuracy when discriminating between healthy and epileptic EEG signals on the neurology and sleep centre EEG database.
Electroencephalography-based brain-computer interface using neural networksTELKOMNIKA JOURNAL
This study aimed to develop a brain-computer interface that can control an electric wheelchair using electroencephalography (EEG) signals. First, we used the Mind Wave Mobile 2 device to capture raw EEG signals from the surface of the scalp. The signals were transformed into the frequency domain using fast Fourier transform (FFT) and filtered to monitor changes in attention and relaxation. Next, we performed time and frequency domain analyses to identify features for five eye gestures: opened, closed, blink per second, double blink, and lookup. The base state was the opened-eyes gesture, and we compared the features of the remaining four action gestures to the base state to identify potential gestures. We then built a multilayer neural network to classify these features into five signals that control the wheelchair’s movement. Finally, we designed an experimental wheelchair system to test the effectiveness of the proposed approach. The results demonstrate that the EEG classification was highly accurate and computationally efficient. Moreover, the average performance of the brain-controlled wheelchair system was over 75% across different individuals, which suggests the feasibility of this approach.
Prediction Model for Emotion Recognition Using EEGIRJET Journal
The document describes a study that compares different machine learning models for emotion recognition using EEG data. The study uses EEG data collected from patients with depression and healthy controls. It extracts features from the EEG data, including linear and nonlinear parameters from different frequency bands. It then uses classifiers like random forest, KNN, CNN, and LSTM to classify emotions as positive, negative or neutral. The random forest model achieved the best accuracy for identifying depression patients' emotions. The study provides a framework for EEG data collection, preprocessing, feature extraction and applying different machine learning models to optimize emotion recognition from EEG signals.
CLASSIFICATION OF ELECTROENCEPHALOGRAM SIGNALS USING XGBOOST ALGORITHM AND SU...IRJET Journal
This document presents a study that uses the XGBoost algorithm and support vector machine to classify electroencephalogram (EEG) signals. The study acquires EEG data from healthy subjects and subjects with epilepsy during seizure and non-seizure periods. It preprocesses the data, extracts features using linear discriminant analysis, and feeds the extracted features into XGBoost and SVM classifiers. The results indicate that XGBoost exhibited superior classification performance compared to SVM for analyzing and classifying EEG signals.
This document describes a smart home system designed to aid paralyzed individuals living alone. EEG signals are collected from 25 paralyzed subjects to study brain activity related to hunger, thirst, sleepiness, excitement and stress. The EEG data is preprocessed and classified using kNN classifiers to identify the individual's needs. An Internet of Things platform uses the classified EEG data to make logical decisions and control automated modules to meet the person's basic needs. These include modules for feeding, sleep, temperature control and more. Experimental results showed an overall 89.73% accuracy for automating units to fulfill a paralyzed person's basic needs. The system aims to help paralyzed individuals live more independently at home.
International Journal of Engineering Research and Applications (IJERA) is an open access online peer reviewed international journal that publishes research and review articles in the fields of Computer Science, Neural Networks, Electrical Engineering, Software Engineering, Information Technology, Mechanical Engineering, Chemical Engineering, Plastic Engineering, Food Technology, Textile Engineering, Nano Technology & science, Power Electronics, Electronics & Communication Engineering, Computational mathematics, Image processing, Civil Engineering, Structural Engineering, Environmental Engineering, VLSI Testing & Low Power VLSI Design etc.
A nonlinearities inverse distance weighting spatial interpolation approach ap...IJECEIAES
Spatial interpolation of a surface electromyography (sEMG) signal from a set of signals recorded from a multi-electrode array is a challenge in biomedical signal processing. Consequently, it could be useful to increase the electrodes' density in detecting the skeletal muscles' motor units under detection's vacancy. This paper used two types of spatial interpolation methods for estimation: Inverse distance weighted (IDW) and Kriging. Furthermore, a new technique is proposed using a modified nonlinearity formula based on IDW. A set of EMG signals recorded from the noninvasive multi-electrode grid from different types of subjects, sex, age, and type of muscles have been studied when muscles are under regular tension activity. A goodness of fit measure (R2) is used to evaluate the proposed technique. The interpolated signals are compared with the actual signals; the Goodness of fit measure's value is almost 99%, with a processing time of 100msec. The resulting technique is shown to be of high accuracy and matching of spatial interpolated signals to actual signals compared with IDW and Kriging techniques.
A machine learning algorithm for classification of mental tasks.pdfPravinKshirsagar11
In this article, a contemporary tack of mental tasks on cognitive parts of humans is appraised using two different approaches such as wavelet transforms at a discrete time (DWT) and support vector machine (SVM). The put forth tack is instilled with the electroencephalogram (EEG) database acquired in real-time from CARE Hospital, Nagpur. Additional data is also acquired from a brain-computer interface (BCI). In the working model, signals from the database are wed out into different frequency sub-bands using DWT. Initially, updated statistical features are obtained from different frequency sub-bands. This type of representation defines the wavelet co-efficient which is introduced for reducing the measurement of data. Then, the projected method is realized using SVM for segregating both port and veracious hand movement. After segregation of EEG signals, results are achieved with an accuracy of 92% for BCI competition paradigm III and 97.89% for B-alert machine.
A comparative study of wavelet families for electromyography signal classific...journalBEEI
The document presents a study comparing different wavelet families for classifying electromyography (EMG) signals based on discrete wavelet transform (DWT). The proposed method involves decomposing EMG signals into sub-bands using DWT, extracting statistical features from each sub-band, and using support vector machines (SVM) for classification. Results showed that the sym14 wavelet at the 8th decomposition level achieved the best classification performance for detecting neuromuscular disorders. The study demonstrates that the proposed DWT-based approach can effectively classify EMG signals and help diagnose neuromuscular conditions.
Modelling and Analysis of EEG Signals Based on Real Time Control for Wheel ChairIJTET Journal
Free versatility is center to having the capacity to perform exercises of day by day living without anyone else's input. In this proposed framework introduce an imparted control construction modeling that couples the knowledge and cravings of the client with the exactness of a controlled wheelchair. Outspread Basis Function system was utilized to characterize the predefined developments, for example, rest, forward, regressive, left and right of the wheelchair. This EEG-based cerebrum controlled wheelchair has been produced for utilization by totally incapacitated patients. The proposed outline incorporates a novel methodology for selecting ideal terminal positions, a progression of sign transforming and an interface to a controlled wheelchair.The Brain Controlled Wheelchair (BCW) is a basic automated framework intended for individuals, for example, bolted in individuals, who are not ready to utilize physical interfaces like joysticks or catches. The objective is to add to a framework usable in healing centers and homes with insignificant base alterations, which can help these individuals recover some portability. Also, it is explored whether execution in the STOP interface would be influenced amid movement, and discovered no modification with respect to the static performance.Finally, the general procedure was assessed and contrasted with other cerebrum controlled wheelchair ventures. Notwithstanding the overhead needed to choose the destination on the interface, the wheelchair is quicker than others .It permits to explore in a commonplace indoor environment inside a sensible time. Accentuation was put on client's security and comfort,the movement direction procedure guarantees smooth, protected and unsurprising route, while mental exertion and exhaustion are minimized by lessening control to destination determination.
Transfer learning for epilepsy detection using spectrogram imagesIAESIJAI
Epilepsy stands out as one of the common neurological diseases. The neural activity of the brain is observed using electroencephalography (EEG). Manual inspection of EEG brain signals is a slow and arduous process, which puts heavy load on neurologists and affects their performance. The aim of this study is to find the best result of classification using the transfer learning model that automatically identify the epileptic and the normal activity, to classify EEG signals by using images of spectrogram which represents the percentage of energy for each coefficient of the continuous wavelet. Dataset includes the EEG signals recorded at monitoring unit of epilepsy used in this study to presents an application of transfer learning by comparing three models Alexnet, visual geometry group (VGG19) and residual neural network ResNet using different combinations with seven different classifiers. This study tested the models and reached a different value of accuracy and other metrics used to judge their performances, and as a result the best combination has been achieved with ResNet combined with support vector machine (SVM) classifier that classified EEG signals with a high success rate using multiple performance metrics such as 97.22% accuracy and 2.78% the value of the error rate.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Novel method to find the parameter for noise removal from multi channel ecg w...eSAT Journals
This document presents a novel method for removing noise from multi-channel electrocardiogram (ECG) waveforms using a multi-swarm optimization (MSO) approach. The method involves extracting features from ECG data, using MSO to identify an optimal cutoff frequency parameter for a finite impulse response (FIR) filter, and applying the FIR filter using the identified parameter to remove noise from the ECG signals. The MSO approach divides particles into multiple swarms that each focus on a region of the search space, helping to overcome sensitivity to initial positions found in traditional particle swarm optimization. The resulting filtered ECG signals are evaluated against original clean signals to validate the noise removal performance of the MSO-identified cutoff frequency parameter and
Motor Imagery based Brain Computer Interface for Windows Operating SystemIRJET Journal
This document summarizes a research paper that proposes a motor imagery-based brain computer interface (MI-BCI) to allow physically challenged individuals to control basic functions of a Windows operating system using only their brain activity. The MI-BCI system uses an 8-channel EEG device to capture brainwaves while a subject imagines moving their arm or blinking their eyes. A convolutional neural network (CNN) classifier is trained on the EEG data to identify 7 possible commands: left, right, up, down mouse movement or left/right click, or an idle state. The trained CNN achieved an average accuracy of 92.85% in identifying commands. A Python program integrates the EEG data stream, CNN classifier, and Windows mouse/
Embedded system for upper-limb exoskeleton based on electromyography controlTELKOMNIKA JOURNAL
A major problem in an exoskeleton based on electromyography (EMG) control with pattern recognition-based is the need for more time to train and to calibrate the system in order able to adapt for different subjects and variable. Unfortunately, the implementation of the joint prediction on an embedded system for the exoskeleton based on the EMG control with non-pattern recognition-based is very rare. Therefore, this study presents an implementation of elbow-joint angle prediction on an embedded system to control an upper limb exoskeleton based on the EMG signal. The architecture of the system consisted of a bio-amplifier, an embedded ARMSTM32F429 microcontroller, and an exoskeleton unit driven by a servo motor. The elbow joint angle was predicted based on the EMG signal that is generated from biceps. The predicted angle was obtained by extracting the EMG signal using a zero-crossing feature and filtering the EMG feature using a Butterworth low pass filter. This study found that the range of root mean square error and correlation coefficients are 8°-16° and 0.94-0.99, respectively which suggest that the predicted angle is close to the desired angle and there is a high relationship between the predicted angle and the desired angle.
A new eliminating EOG artifacts technique using combined decomposition method...TELKOMNIKA JOURNAL
Normally, the collected EEG signals from the human scalp cortex by using the non-invasive EEG collection methods were contaminated with artifacts, like an eye electrical activity, leading to increases in the challenges in analyzing the electroencephalogram for obtaining useful clinical information. In this paper, we do a comparison of using two decomposing methods (DWT and EMD) with CCA technique or High Pass Filter, for the elimination of eye artifacts from EEG. The eye artifacts (EOG) signals were extracted from the un-cleaned or raw EEG signals by DWT and EMD with CCA approach or H.P.F. The root means square error ratio of the uncontaminated EEG signal to the contaminated EEG signal with eye artifacts were the performance indicators for both elimination methods, which indicate that the combined CCA method outperforms the combined H.P.F method in the elimination of eye blinking contamination artifact from the EEG signal.
EEG SIGNAL CLASSIFICATION USING LDA AND MLP CLASSIFIERhiij
Electroencephalography (EEG) is the recording of electrical activities along the scalp. EEG measures
voltage fluctuations resulting from ionic current flows within the neurons of the brain. Diagnostic
applications generally focus on the spectral content of EEG, which is the type of neural oscillations that
can be observed in EEG signal. EEG is most often used to diagnose epilepsy, which causes obvious
abnormalities in EEG readings. This powerful property confirms the rich potential for EEG analysis and
motivates the need for advanced signal processing techniques to aid clinicians in their interpretations.
This paper describes the application of Wavelet Transform (WT) for the processing of
Electroencephalogram (EEG) signals. Furthermore, the linear discriminant analysis (LDA) is applied for
feature selection and dimensionality reduction where the informative and discriminative two-dimension
features are used as a benchmark for classification purposes through a Multi-Layers Perceptron (MLP)
neural network. For five classification problems, the proposed model achieves a high sensitivity,
specificity and accuracy of 100%.Finally, the comparison of the results obtained with the proposed
methods and those obtained with previous literature methods shows the superiority of our approach for
EEG signals classification and automated diagnosis
Health electroencephalogram epileptic classification based on Hilbert probabi...IJECEIAES
This paper has proposed a new classification method based on Hilbert probability similarity to detect epileptic seizures from electroencephalogram (EEG) signals. Hilbert similarity probability-based measure is exploited to measure the similarity between signals. The proposed system consisted of models based on Hilbert probability similarity (HPS) to predict the state for the specific EEG signal. Particle swarm optimization (PSO) has been employed for feature selection and extraction. Furthermore, the used dataset in this study is Bonn University's publicly available EEG dataset. Several metrics are calculated to assess the performance of the suggested systems such as accuracy, precision, recall, and F1-score. The experimental results show that the suggested model is an effective tool for classifying EEG signals, with an accuracy of up to 100% for two-class status.
IRJET- An Efficient Approach for Removal of Ocular Artifacts in EEG-Brain Com...IRJET Journal
This document summarizes a research paper that proposes a method to remove ocular artifacts from electroencephalogram (EEG) signals. Ocular artifacts are contaminants in EEG signals caused by eye blinks and movements that can distort the brain activity being measured. The proposed method uses discrete wavelet transform (DWT) to isolate the ocular artifact components in the frequency domain. It then applies adaptive noise cancellation (ANC) to the wavelet coefficients to remove the artifact components without damaging the underlying brain activity signal. The method is intended to enable more effective analysis of EEG data for applications like diagnosing epilepsy and developing brain-computer interfaces.
Motor Imagery Recognition of EEG Signal using Cuckoo Search Masking Empirical...ijtsrd
Brain Computer Interface BCI aims at providing an alternate means of communication and control to people with severe cognitive or sensory motor disabilities. Brain Computer Interface in electroencephalogram EEG is of great important but it is challenging to manage the non stationary EEG. EEG signals are more vulnerable to contamination due to noise and artifacts. In our proposed work, we used Cuckoo Search Masking Empirical Mode decomposition to ignore such vulnerable things. Initially, the features of EEG signals are taken such as Energy, AR Coefficients, Morphological features and Fuzzy Approximate Entropy. Then, for Feature extraction method, Masking Empirical Mode Decomposition MEMD is applied to deal with motor imagery MI recognition tasks. The EEG signal is decomposed by MEMD and hybrid features are then extracted from the first two intrinsic mode functions IMFs . After the extracted features, Cuckoo Search algorithm is used to select the significant features. Different weights for the relevance and redundancy in the fitness function of the proposed algorithm are used to further improve their performance in terms of the number of features and the classification accuracy and finally they are fed into Linear Discriminant Analysis for classification. This analysis produces models whose accuracy is as good as more complex method. The results show that our proposed method can achieve the highest accuracy, maximal MI, recall as well as precision for Motor Imagery Recognition tasks. Our proposed method is comparable or superior than existing method. Jaipriya D ""Motor Imagery Recognition of EEG Signal using Cuckoo-Search Masking Empirical Mode Decomposition"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-2 , February 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30020.pdf
Paper Url : https://www.ijtsrd.com/engineering/electronics-and-communication-engineering/30020/motor-imagery-recognition-of-eeg-signal-using-cuckoo-search-masking-empirical-mode-decomposition/jaipriya-d
Photoacoustic technology for biological tissues characterizationjournalBEEI
The existing photoacoustics (PA) imaging systems showed mixed performance in imaging characteristic and signal-to-noise ratio (SNR). This work presents the use of an in-house assembled PA system using a modulating laser beam of wavelength 633 nm for two-dimensional (2D) characterization of biological tissues. The differentiation of the tissues in this work is based on differences in their light absorption, wherein the produced photoacoustic signal detected by a transducer was translated into phase value that corresponds to the peak amplitude of optical absorption of tissue namely fat, liver and muscle. This work found fat tissue to produce the strongest PA signal with mean ± standard deviation (SD) phase value = 2.09 ± 0.31 while muscle produced the least signal with phase value = 1.03 ± 0.17. This work discovered the presence of stripes pattern in the reconstructed images of fat and muscle resulted from their structural properties. In addition, a comparison is made in an attempt to better assess the performance of the developed system with the related ones. This work concluded that the developed system may use as an alternative, noninvasive and label-free visualization method for characterization of biological tissues in the future.
Epilepsy is one of the prominent and disturbing neurological disorder and many
people across the world are victims of this problem. The sudden motor disturbances in
the brain cause and trigger these seizures. Due to the hypersynchronous discharges
happening on the cortical regions of the brain, the activities of the motor becomes
abnormal and so seizures are triggered. The seizures caused due to epilepsy are quite
heterogeneous in nature and so diagnosing it is quite challenging.
Electroencephalography (EEG) is the most widely used instrument for the detection of
epileptic seizures. In this work, Haar and Sym8 wavelets are employed to extract the
wavelet features at level 4 from EEG signals. The extracted features like alpha, beta,
theta, gamma and delta are classified through the Soft Discriminant Classifier (SDC) to
obtain the epilepsy risk level from EEG signals. The final results show that when Haar
wavelet is employed and classified with SDC, an average classification accuracy of
95.20% is obtained and when Sym8 wavelet is utilized and classified with SDC, an
average classification accuracy of 94.68% is obtained.
This document summarizes a research paper that presents a non-invasive method for estimating consciousness level using EEG signals. The method uses two electrodes to collect bio-potential signals from the brain, which are then amplified, filtered, and analyzed using fast Fourier transform (FFT) to extract the beta wave frequency range associated with different consciousness levels. Results from drug and alcohol experiments on subjects showed that their brain wave frequencies shifted towards the alpha range when intoxicated, indicating a loss of consciousness. The frequency analysis provides a way to continuously monitor consciousness level.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document describes a study that aims to predict the results of visual field perimetry tests for glaucoma detection using data from optical coherence tomography (OCT) scans. The study involves using optical character recognition to extract data from OCT scan reports, pre-processing the data, and then applying regression techniques from data mining to identify patterns in the data that could be used to predict perimetry test results. Cross-validation is used to assess the accuracy of the predictive model. The document provides background on glaucoma and discusses other existing techniques for glaucoma detection such as confocal scanning laser ophthalmology and scanning laser polarimetry.
Effective electroencephalogram based epileptic seizure detection using suppo...IJECEIAES
Epilepsy is one of the widespread disorders. It is a noncommunicable disease that affects the human nerve system. Seizures are abnormal patterns of behavior in the electricity of the brain which produce symptoms like losing consciousness, attention or convulsions in the whole body. This paper demonstrates an effective electroencephalogram (EEG) based seizure detection method using discrete wavelet transformation (DWT) for signal decomposition to extract features. An automatic channel selection method was proposed by the researcher to select the best channel from 23 channels based on maximum variance value. The records were segmented into a nonoverlapping segment with long 1-S. The support vector machine (SVM) model was used to automatically detect segments that contain seizures, using both frequency and time domain statistical moment features. The experimental result was obtained from 24 patients in CHB-MIT database. The average accuracy is 94.1, sensitivity is 93.5, specificity is 94.6 and the false positive rate average is 0.054.
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
More Related Content
Similar to Drivers’ drowsiness detection based on an optimized random forest classification and single-channel electroencephalogram
A nonlinearities inverse distance weighting spatial interpolation approach ap...IJECEIAES
Spatial interpolation of a surface electromyography (sEMG) signal from a set of signals recorded from a multi-electrode array is a challenge in biomedical signal processing. Consequently, it could be useful to increase the electrodes' density in detecting the skeletal muscles' motor units under detection's vacancy. This paper used two types of spatial interpolation methods for estimation: Inverse distance weighted (IDW) and Kriging. Furthermore, a new technique is proposed using a modified nonlinearity formula based on IDW. A set of EMG signals recorded from the noninvasive multi-electrode grid from different types of subjects, sex, age, and type of muscles have been studied when muscles are under regular tension activity. A goodness of fit measure (R2) is used to evaluate the proposed technique. The interpolated signals are compared with the actual signals; the Goodness of fit measure's value is almost 99%, with a processing time of 100msec. The resulting technique is shown to be of high accuracy and matching of spatial interpolated signals to actual signals compared with IDW and Kriging techniques.
A machine learning algorithm for classification of mental tasks.pdfPravinKshirsagar11
In this article, a contemporary tack of mental tasks on cognitive parts of humans is appraised using two different approaches such as wavelet transforms at a discrete time (DWT) and support vector machine (SVM). The put forth tack is instilled with the electroencephalogram (EEG) database acquired in real-time from CARE Hospital, Nagpur. Additional data is also acquired from a brain-computer interface (BCI). In the working model, signals from the database are wed out into different frequency sub-bands using DWT. Initially, updated statistical features are obtained from different frequency sub-bands. This type of representation defines the wavelet co-efficient which is introduced for reducing the measurement of data. Then, the projected method is realized using SVM for segregating both port and veracious hand movement. After segregation of EEG signals, results are achieved with an accuracy of 92% for BCI competition paradigm III and 97.89% for B-alert machine.
A comparative study of wavelet families for electromyography signal classific...journalBEEI
The document presents a study comparing different wavelet families for classifying electromyography (EMG) signals based on discrete wavelet transform (DWT). The proposed method involves decomposing EMG signals into sub-bands using DWT, extracting statistical features from each sub-band, and using support vector machines (SVM) for classification. Results showed that the sym14 wavelet at the 8th decomposition level achieved the best classification performance for detecting neuromuscular disorders. The study demonstrates that the proposed DWT-based approach can effectively classify EMG signals and help diagnose neuromuscular conditions.
Modelling and Analysis of EEG Signals Based on Real Time Control for Wheel ChairIJTET Journal
Free versatility is center to having the capacity to perform exercises of day by day living without anyone else's input. In this proposed framework introduce an imparted control construction modeling that couples the knowledge and cravings of the client with the exactness of a controlled wheelchair. Outspread Basis Function system was utilized to characterize the predefined developments, for example, rest, forward, regressive, left and right of the wheelchair. This EEG-based cerebrum controlled wheelchair has been produced for utilization by totally incapacitated patients. The proposed outline incorporates a novel methodology for selecting ideal terminal positions, a progression of sign transforming and an interface to a controlled wheelchair.The Brain Controlled Wheelchair (BCW) is a basic automated framework intended for individuals, for example, bolted in individuals, who are not ready to utilize physical interfaces like joysticks or catches. The objective is to add to a framework usable in healing centers and homes with insignificant base alterations, which can help these individuals recover some portability. Also, it is explored whether execution in the STOP interface would be influenced amid movement, and discovered no modification with respect to the static performance.Finally, the general procedure was assessed and contrasted with other cerebrum controlled wheelchair ventures. Notwithstanding the overhead needed to choose the destination on the interface, the wheelchair is quicker than others .It permits to explore in a commonplace indoor environment inside a sensible time. Accentuation was put on client's security and comfort,the movement direction procedure guarantees smooth, protected and unsurprising route, while mental exertion and exhaustion are minimized by lessening control to destination determination.
Transfer learning for epilepsy detection using spectrogram imagesIAESIJAI
Epilepsy stands out as one of the common neurological diseases. The neural activity of the brain is observed using electroencephalography (EEG). Manual inspection of EEG brain signals is a slow and arduous process, which puts heavy load on neurologists and affects their performance. The aim of this study is to find the best result of classification using the transfer learning model that automatically identify the epileptic and the normal activity, to classify EEG signals by using images of spectrogram which represents the percentage of energy for each coefficient of the continuous wavelet. Dataset includes the EEG signals recorded at monitoring unit of epilepsy used in this study to presents an application of transfer learning by comparing three models Alexnet, visual geometry group (VGG19) and residual neural network ResNet using different combinations with seven different classifiers. This study tested the models and reached a different value of accuracy and other metrics used to judge their performances, and as a result the best combination has been achieved with ResNet combined with support vector machine (SVM) classifier that classified EEG signals with a high success rate using multiple performance metrics such as 97.22% accuracy and 2.78% the value of the error rate.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
Novel method to find the parameter for noise removal from multi channel ecg w...eSAT Journals
This document presents a novel method for removing noise from multi-channel electrocardiogram (ECG) waveforms using a multi-swarm optimization (MSO) approach. The method involves extracting features from ECG data, using MSO to identify an optimal cutoff frequency parameter for a finite impulse response (FIR) filter, and applying the FIR filter using the identified parameter to remove noise from the ECG signals. The MSO approach divides particles into multiple swarms that each focus on a region of the search space, helping to overcome sensitivity to initial positions found in traditional particle swarm optimization. The resulting filtered ECG signals are evaluated against original clean signals to validate the noise removal performance of the MSO-identified cutoff frequency parameter and
Motor Imagery based Brain Computer Interface for Windows Operating SystemIRJET Journal
This document summarizes a research paper that proposes a motor imagery-based brain computer interface (MI-BCI) to allow physically challenged individuals to control basic functions of a Windows operating system using only their brain activity. The MI-BCI system uses an 8-channel EEG device to capture brainwaves while a subject imagines moving their arm or blinking their eyes. A convolutional neural network (CNN) classifier is trained on the EEG data to identify 7 possible commands: left, right, up, down mouse movement or left/right click, or an idle state. The trained CNN achieved an average accuracy of 92.85% in identifying commands. A Python program integrates the EEG data stream, CNN classifier, and Windows mouse/
Embedded system for upper-limb exoskeleton based on electromyography controlTELKOMNIKA JOURNAL
A major problem in an exoskeleton based on electromyography (EMG) control with pattern recognition-based is the need for more time to train and to calibrate the system in order able to adapt for different subjects and variable. Unfortunately, the implementation of the joint prediction on an embedded system for the exoskeleton based on the EMG control with non-pattern recognition-based is very rare. Therefore, this study presents an implementation of elbow-joint angle prediction on an embedded system to control an upper limb exoskeleton based on the EMG signal. The architecture of the system consisted of a bio-amplifier, an embedded ARMSTM32F429 microcontroller, and an exoskeleton unit driven by a servo motor. The elbow joint angle was predicted based on the EMG signal that is generated from biceps. The predicted angle was obtained by extracting the EMG signal using a zero-crossing feature and filtering the EMG feature using a Butterworth low pass filter. This study found that the range of root mean square error and correlation coefficients are 8°-16° and 0.94-0.99, respectively which suggest that the predicted angle is close to the desired angle and there is a high relationship between the predicted angle and the desired angle.
A new eliminating EOG artifacts technique using combined decomposition method...TELKOMNIKA JOURNAL
Normally, the collected EEG signals from the human scalp cortex by using the non-invasive EEG collection methods were contaminated with artifacts, like an eye electrical activity, leading to increases in the challenges in analyzing the electroencephalogram for obtaining useful clinical information. In this paper, we do a comparison of using two decomposing methods (DWT and EMD) with CCA technique or High Pass Filter, for the elimination of eye artifacts from EEG. The eye artifacts (EOG) signals were extracted from the un-cleaned or raw EEG signals by DWT and EMD with CCA approach or H.P.F. The root means square error ratio of the uncontaminated EEG signal to the contaminated EEG signal with eye artifacts were the performance indicators for both elimination methods, which indicate that the combined CCA method outperforms the combined H.P.F method in the elimination of eye blinking contamination artifact from the EEG signal.
EEG SIGNAL CLASSIFICATION USING LDA AND MLP CLASSIFIERhiij
Electroencephalography (EEG) is the recording of electrical activities along the scalp. EEG measures
voltage fluctuations resulting from ionic current flows within the neurons of the brain. Diagnostic
applications generally focus on the spectral content of EEG, which is the type of neural oscillations that
can be observed in EEG signal. EEG is most often used to diagnose epilepsy, which causes obvious
abnormalities in EEG readings. This powerful property confirms the rich potential for EEG analysis and
motivates the need for advanced signal processing techniques to aid clinicians in their interpretations.
This paper describes the application of Wavelet Transform (WT) for the processing of
Electroencephalogram (EEG) signals. Furthermore, the linear discriminant analysis (LDA) is applied for
feature selection and dimensionality reduction where the informative and discriminative two-dimension
features are used as a benchmark for classification purposes through a Multi-Layers Perceptron (MLP)
neural network. For five classification problems, the proposed model achieves a high sensitivity,
specificity and accuracy of 100%.Finally, the comparison of the results obtained with the proposed
methods and those obtained with previous literature methods shows the superiority of our approach for
EEG signals classification and automated diagnosis
Health electroencephalogram epileptic classification based on Hilbert probabi...IJECEIAES
This paper has proposed a new classification method based on Hilbert probability similarity to detect epileptic seizures from electroencephalogram (EEG) signals. Hilbert similarity probability-based measure is exploited to measure the similarity between signals. The proposed system consisted of models based on Hilbert probability similarity (HPS) to predict the state for the specific EEG signal. Particle swarm optimization (PSO) has been employed for feature selection and extraction. Furthermore, the used dataset in this study is Bonn University's publicly available EEG dataset. Several metrics are calculated to assess the performance of the suggested systems such as accuracy, precision, recall, and F1-score. The experimental results show that the suggested model is an effective tool for classifying EEG signals, with an accuracy of up to 100% for two-class status.
IRJET- An Efficient Approach for Removal of Ocular Artifacts in EEG-Brain Com...IRJET Journal
This document summarizes a research paper that proposes a method to remove ocular artifacts from electroencephalogram (EEG) signals. Ocular artifacts are contaminants in EEG signals caused by eye blinks and movements that can distort the brain activity being measured. The proposed method uses discrete wavelet transform (DWT) to isolate the ocular artifact components in the frequency domain. It then applies adaptive noise cancellation (ANC) to the wavelet coefficients to remove the artifact components without damaging the underlying brain activity signal. The method is intended to enable more effective analysis of EEG data for applications like diagnosing epilepsy and developing brain-computer interfaces.
Motor Imagery Recognition of EEG Signal using Cuckoo Search Masking Empirical...ijtsrd
Brain Computer Interface BCI aims at providing an alternate means of communication and control to people with severe cognitive or sensory motor disabilities. Brain Computer Interface in electroencephalogram EEG is of great important but it is challenging to manage the non stationary EEG. EEG signals are more vulnerable to contamination due to noise and artifacts. In our proposed work, we used Cuckoo Search Masking Empirical Mode decomposition to ignore such vulnerable things. Initially, the features of EEG signals are taken such as Energy, AR Coefficients, Morphological features and Fuzzy Approximate Entropy. Then, for Feature extraction method, Masking Empirical Mode Decomposition MEMD is applied to deal with motor imagery MI recognition tasks. The EEG signal is decomposed by MEMD and hybrid features are then extracted from the first two intrinsic mode functions IMFs . After the extracted features, Cuckoo Search algorithm is used to select the significant features. Different weights for the relevance and redundancy in the fitness function of the proposed algorithm are used to further improve their performance in terms of the number of features and the classification accuracy and finally they are fed into Linear Discriminant Analysis for classification. This analysis produces models whose accuracy is as good as more complex method. The results show that our proposed method can achieve the highest accuracy, maximal MI, recall as well as precision for Motor Imagery Recognition tasks. Our proposed method is comparable or superior than existing method. Jaipriya D ""Motor Imagery Recognition of EEG Signal using Cuckoo-Search Masking Empirical Mode Decomposition"" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-4 | Issue-2 , February 2020,
URL: https://www.ijtsrd.com/papers/ijtsrd30020.pdf
Paper Url : https://www.ijtsrd.com/engineering/electronics-and-communication-engineering/30020/motor-imagery-recognition-of-eeg-signal-using-cuckoo-search-masking-empirical-mode-decomposition/jaipriya-d
Photoacoustic technology for biological tissues characterizationjournalBEEI
The existing photoacoustics (PA) imaging systems showed mixed performance in imaging characteristic and signal-to-noise ratio (SNR). This work presents the use of an in-house assembled PA system using a modulating laser beam of wavelength 633 nm for two-dimensional (2D) characterization of biological tissues. The differentiation of the tissues in this work is based on differences in their light absorption, wherein the produced photoacoustic signal detected by a transducer was translated into phase value that corresponds to the peak amplitude of optical absorption of tissue namely fat, liver and muscle. This work found fat tissue to produce the strongest PA signal with mean ± standard deviation (SD) phase value = 2.09 ± 0.31 while muscle produced the least signal with phase value = 1.03 ± 0.17. This work discovered the presence of stripes pattern in the reconstructed images of fat and muscle resulted from their structural properties. In addition, a comparison is made in an attempt to better assess the performance of the developed system with the related ones. This work concluded that the developed system may use as an alternative, noninvasive and label-free visualization method for characterization of biological tissues in the future.
Epilepsy is one of the prominent and disturbing neurological disorder and many
people across the world are victims of this problem. The sudden motor disturbances in
the brain cause and trigger these seizures. Due to the hypersynchronous discharges
happening on the cortical regions of the brain, the activities of the motor becomes
abnormal and so seizures are triggered. The seizures caused due to epilepsy are quite
heterogeneous in nature and so diagnosing it is quite challenging.
Electroencephalography (EEG) is the most widely used instrument for the detection of
epileptic seizures. In this work, Haar and Sym8 wavelets are employed to extract the
wavelet features at level 4 from EEG signals. The extracted features like alpha, beta,
theta, gamma and delta are classified through the Soft Discriminant Classifier (SDC) to
obtain the epilepsy risk level from EEG signals. The final results show that when Haar
wavelet is employed and classified with SDC, an average classification accuracy of
95.20% is obtained and when Sym8 wavelet is utilized and classified with SDC, an
average classification accuracy of 94.68% is obtained.
This document summarizes a research paper that presents a non-invasive method for estimating consciousness level using EEG signals. The method uses two electrodes to collect bio-potential signals from the brain, which are then amplified, filtered, and analyzed using fast Fourier transform (FFT) to extract the beta wave frequency range associated with different consciousness levels. Results from drug and alcohol experiments on subjects showed that their brain wave frequencies shifted towards the alpha range when intoxicated, indicating a loss of consciousness. The frequency analysis provides a way to continuously monitor consciousness level.
IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com
This document describes a study that aims to predict the results of visual field perimetry tests for glaucoma detection using data from optical coherence tomography (OCT) scans. The study involves using optical character recognition to extract data from OCT scan reports, pre-processing the data, and then applying regression techniques from data mining to identify patterns in the data that could be used to predict perimetry test results. Cross-validation is used to assess the accuracy of the predictive model. The document provides background on glaucoma and discusses other existing techniques for glaucoma detection such as confocal scanning laser ophthalmology and scanning laser polarimetry.
Effective electroencephalogram based epileptic seizure detection using suppo...IJECEIAES
Epilepsy is one of the widespread disorders. It is a noncommunicable disease that affects the human nerve system. Seizures are abnormal patterns of behavior in the electricity of the brain which produce symptoms like losing consciousness, attention or convulsions in the whole body. This paper demonstrates an effective electroencephalogram (EEG) based seizure detection method using discrete wavelet transformation (DWT) for signal decomposition to extract features. An automatic channel selection method was proposed by the researcher to select the best channel from 23 channels based on maximum variance value. The records were segmented into a nonoverlapping segment with long 1-S. The support vector machine (SVM) model was used to automatically detect segments that contain seizures, using both frequency and time domain statistical moment features. The experimental result was obtained from 24 patients in CHB-MIT database. The average accuracy is 94.1, sensitivity is 93.5, specificity is 94.6 and the false positive rate average is 0.054.
Similar to Drivers’ drowsiness detection based on an optimized random forest classification and single-channel electroencephalogram (20)
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...IJECEIAES
Medical image analysis has witnessed significant advancements with deep learning techniques. In the domain of brain tumor segmentation, the ability to
precisely delineate tumor boundaries from magnetic resonance imaging (MRI)
scans holds profound implications for diagnosis. This study presents an ensemble convolutional neural network (CNN) with transfer learning, integrating
the state-of-the-art Deeplabv3+ architecture with the ResNet18 backbone. The
model is rigorously trained and evaluated, exhibiting remarkable performance
metrics, including an impressive global accuracy of 99.286%, a high-class accuracy of 82.191%, a mean intersection over union (IoU) of 79.900%, a weighted
IoU of 98.620%, and a Boundary F1 (BF) score of 83.303%. Notably, a detailed comparative analysis with existing methods showcases the superiority of
our proposed model. These findings underscore the model’s competence in precise brain tumor localization, underscoring its potential to revolutionize medical
image analysis and enhance healthcare outcomes. This research paves the way
for future exploration and optimization of advanced CNN models in medical
imaging, emphasizing addressing false positives and resource efficiency.
Embedded machine learning-based road conditions and driving behavior monitoringIJECEIAES
Car accident rates have increased in recent years, resulting in losses in human lives, properties, and other financial costs. An embedded machine learning-based system is developed to address this critical issue. The system can monitor road conditions, detect driving patterns, and identify aggressive driving behaviors. The system is based on neural networks trained on a comprehensive dataset of driving events, driving styles, and road conditions. The system effectively detects potential risks and helps mitigate the frequency and impact of accidents. The primary goal is to ensure the safety of drivers and vehicles. Collecting data involved gathering information on three key road events: normal street and normal drive, speed bumps, circular yellow speed bumps, and three aggressive driving actions: sudden start, sudden stop, and sudden entry. The gathered data is processed and analyzed using a machine learning system designed for limited power and memory devices. The developed system resulted in 91.9% accuracy, 93.6% precision, and 92% recall. The achieved inference time on an Arduino Nano 33 BLE Sense with a 32-bit CPU running at 64 MHz is 34 ms and requires 2.6 kB peak RAM and 139.9 kB program flash memory, making it suitable for resource-constrained embedded systems.
Advanced control scheme of doubly fed induction generator for wind turbine us...IJECEIAES
This paper describes a speed control device for generating electrical energy on an electricity network based on the doubly fed induction generator (DFIG) used for wind power conversion systems. At first, a double-fed induction generator model was constructed. A control law is formulated to govern the flow of energy between the stator of a DFIG and the energy network using three types of controllers: proportional integral (PI), sliding mode controller (SMC) and second order sliding mode controller (SOSMC). Their different results in terms of power reference tracking, reaction to unexpected speed fluctuations, sensitivity to perturbations, and resilience against machine parameter alterations are compared. MATLAB/Simulink was used to conduct the simulations for the preceding study. Multiple simulations have shown very satisfying results, and the investigations demonstrate the efficacy and power-enhancing capabilities of the suggested control system.
Neural network optimizer of proportional-integral-differential controller par...IJECEIAES
Wide application of proportional-integral-differential (PID)-regulator in industry requires constant improvement of methods of its parameters adjustment. The paper deals with the issues of optimization of PID-regulator parameters with the use of neural network technology methods. A methodology for choosing the architecture (structure) of neural network optimizer is proposed, which consists in determining the number of layers, the number of neurons in each layer, as well as the form and type of activation function. Algorithms of neural network training based on the application of the method of minimizing the mismatch between the regulated value and the target value are developed. The method of back propagation of gradients is proposed to select the optimal training rate of neurons of the neural network. The neural network optimizer, which is a superstructure of the linear PID controller, allows increasing the regulation accuracy from 0.23 to 0.09, thus reducing the power consumption from 65% to 53%. The results of the conducted experiments allow us to conclude that the created neural superstructure may well become a prototype of an automatic voltage regulator (AVR)-type industrial controller for tuning the parameters of the PID controller.
An improved modulation technique suitable for a three level flying capacitor ...IJECEIAES
This research paper introduces an innovative modulation technique for controlling a 3-level flying capacitor multilevel inverter (FCMLI), aiming to streamline the modulation process in contrast to conventional methods. The proposed
simplified modulation technique paves the way for more straightforward and
efficient control of multilevel inverters, enabling their widespread adoption and
integration into modern power electronic systems. Through the amalgamation of
sinusoidal pulse width modulation (SPWM) with a high-frequency square wave
pulse, this controlling technique attains energy equilibrium across the coupling
capacitor. The modulation scheme incorporates a simplified switching pattern
and a decreased count of voltage references, thereby simplifying the control
algorithm.
A review on features and methods of potential fishing zoneIJECEIAES
This review focuses on the importance of identifying potential fishing zones in seawater for sustainable fishing practices. It explores features like sea surface temperature (SST) and sea surface height (SSH), along with classification methods such as classifiers. The features like SST, SSH, and different classifiers used to classify the data, have been figured out in this review study. This study underscores the importance of examining potential fishing zones using advanced analytical techniques. It thoroughly explores the methodologies employed by researchers, covering both past and current approaches. The examination centers on data characteristics and the application of classification algorithms for classification of potential fishing zones. Furthermore, the prediction of potential fishing zones relies significantly on the effectiveness of classification algorithms. Previous research has assessed the performance of models like support vector machines, naïve Bayes, and artificial neural networks (ANN). In the previous result, the results of support vector machine (SVM) were 97.6% more accurate than naive Bayes's 94.2% to classify test data for fisheries classification. By considering the recent works in this area, several recommendations for future works are presented to further improve the performance of the potential fishing zone models, which is important to the fisheries community.
Electrical signal interference minimization using appropriate core material f...IJECEIAES
As demand for smaller, quicker, and more powerful devices rises, Moore's law is strictly followed. The industry has worked hard to make little devices that boost productivity. The goal is to optimize device density. Scientists are reducing connection delays to improve circuit performance. This helped them understand three-dimensional integrated circuit (3D IC) concepts, which stack active devices and create vertical connections to diminish latency and lower interconnects. Electrical involvement is a big worry with 3D integrates circuits. Researchers have developed and tested through silicon via (TSV) and substrates to decrease electrical wave involvement. This study illustrates a novel noise coupling reduction method using several electrical involvement models. A 22% drop in electrical involvement from wave-carrying to victim TSVs introduces this new paradigm and improves system performance even at higher THz frequencies.
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...IJECEIAES
Climate change's impact on the planet forced the United Nations and governments to promote green energies and electric transportation. The deployments of photovoltaic (PV) and electric vehicle (EV) systems gained stronger momentum due to their numerous advantages over fossil fuel types. The advantages go beyond sustainability to reach financial support and stability. The work in this paper introduces the hybrid system between PV and EV to support industrial and commercial plants. This paper covers the theoretical framework of the proposed hybrid system including the required equation to complete the cost analysis when PV and EV are present. In addition, the proposed design diagram which sets the priorities and requirements of the system is presented. The proposed approach allows setup to advance their power stability, especially during power outages. The presented information supports researchers and plant owners to complete the necessary analysis while promoting the deployment of clean energy. The result of a case study that represents a dairy milk farmer supports the theoretical works and highlights its advanced benefits to existing plants. The short return on investment of the proposed approach supports the paper's novelty approach for the sustainable electrical system. In addition, the proposed system allows for an isolated power setup without the need for a transmission line which enhances the safety of the electrical network
Bibliometric analysis highlighting the role of women in addressing climate ch...IJECEIAES
Fossil fuel consumption increased quickly, contributing to climate change
that is evident in unusual flooding and draughts, and global warming. Over
the past ten years, women's involvement in society has grown dramatically,
and they succeeded in playing a noticeable role in reducing climate change.
A bibliometric analysis of data from the last ten years has been carried out to
examine the role of women in addressing the climate change. The analysis's
findings discussed the relevant to the sustainable development goals (SDGs),
particularly SDG 7 and SDG 13. The results considered contributions made
by women in the various sectors while taking geographic dispersion into
account. The bibliometric analysis delves into topics including women's
leadership in environmental groups, their involvement in policymaking, their
contributions to sustainable development projects, and the influence of
gender diversity on attempts to mitigate climate change. This study's results
highlight how women have influenced policies and actions related to climate
change, point out areas of research deficiency and recommendations on how
to increase role of the women in addressing the climate change and
achieving sustainability. To achieve more successful results, this initiative
aims to highlight the significance of gender equality and encourage
inclusivity in climate change decision-making processes.
Voltage and frequency control of microgrid in presence of micro-turbine inter...IJECEIAES
The active and reactive load changes have a significant impact on voltage
and frequency. In this paper, in order to stabilize the microgrid (MG) against
load variations in islanding mode, the active and reactive power of all
distributed generators (DGs), including energy storage (battery), diesel
generator, and micro-turbine, are controlled. The micro-turbine generator is
connected to MG through a three-phase to three-phase matrix converter, and
the droop control method is applied for controlling the voltage and
frequency of MG. In addition, a method is introduced for voltage and
frequency control of micro-turbines in the transition state from gridconnected mode to islanding mode. A novel switching strategy of the matrix
converter is used for converting the high-frequency output voltage of the
micro-turbine to the grid-side frequency of the utility system. Moreover,
using the switching strategy, the low-order harmonics in the output current
and voltage are not produced, and consequently, the size of the output filter
would be reduced. In fact, the suggested control strategy is load-independent
and has no frequency conversion restrictions. The proposed approach for
voltage and frequency regulation demonstrates exceptional performance and
favorable response across various load alteration scenarios. The suggested
strategy is examined in several scenarios in the MG test systems, and the
simulation results are addressed.
Enhancing battery system identification: nonlinear autoregressive modeling fo...IJECEIAES
Precisely characterizing Li-ion batteries is essential for optimizing their
performance, enhancing safety, and prolonging their lifespan across various
applications, such as electric vehicles and renewable energy systems. This
article introduces an innovative nonlinear methodology for system
identification of a Li-ion battery, employing a nonlinear autoregressive with
exogenous inputs (NARX) model. The proposed approach integrates the
benefits of nonlinear modeling with the adaptability of the NARX structure,
facilitating a more comprehensive representation of the intricate
electrochemical processes within the battery. Experimental data collected
from a Li-ion battery operating under diverse scenarios are employed to
validate the effectiveness of the proposed methodology. The identified
NARX model exhibits superior accuracy in predicting the battery's behavior
compared to traditional linear models. This study underscores the
importance of accounting for nonlinearities in battery modeling, providing
insights into the intricate relationships between state-of-charge, voltage, and
current under dynamic conditions.
Smart grid deployment: from a bibliometric analysis to a surveyIJECEIAES
Smart grids are one of the last decades' innovations in electrical energy.
They bring relevant advantages compared to the traditional grid and
significant interest from the research community. Assessing the field's
evolution is essential to propose guidelines for facing new and future smart
grid challenges. In addition, knowing the main technologies involved in the
deployment of smart grids (SGs) is important to highlight possible
shortcomings that can be mitigated by developing new tools. This paper
contributes to the research trends mentioned above by focusing on two
objectives. First, a bibliometric analysis is presented to give an overview of
the current research level about smart grid deployment. Second, a survey of
the main technological approaches used for smart grid implementation and
their contributions are highlighted. To that effect, we searched the Web of
Science (WoS), and the Scopus databases. We obtained 5,663 documents
from WoS and 7,215 from Scopus on smart grid implementation or
deployment. With the extraction limitation in the Scopus database, 5,872 of
the 7,215 documents were extracted using a multi-step process. These two
datasets have been analyzed using a bibliometric tool called bibliometrix.
The main outputs are presented with some recommendations for future
research.
Use of analytical hierarchy process for selecting and prioritizing islanding ...IJECEIAES
One of the problems that are associated to power systems is islanding
condition, which must be rapidly and properly detected to prevent any
negative consequences on the system's protection, stability, and security.
This paper offers a thorough overview of several islanding detection
strategies, which are divided into two categories: classic approaches,
including local and remote approaches, and modern techniques, including
techniques based on signal processing and computational intelligence.
Additionally, each approach is compared and assessed based on several
factors, including implementation costs, non-detected zones, declining
power quality, and response times using the analytical hierarchy process
(AHP). The multi-criteria decision-making analysis shows that the overall
weight of passive methods (24.7%), active methods (7.8%), hybrid methods
(5.6%), remote methods (14.5%), signal processing-based methods (26.6%),
and computational intelligent-based methods (20.8%) based on the
comparison of all criteria together. Thus, it can be seen from the total weight
that hybrid approaches are the least suitable to be chosen, while signal
processing-based methods are the most appropriate islanding detection
method to be selected and implemented in power system with respect to the
aforementioned factors. Using Expert Choice software, the proposed
hierarchy model is studied and examined.
Enhancing of single-stage grid-connected photovoltaic system using fuzzy logi...IJECEIAES
The power generated by photovoltaic (PV) systems is influenced by
environmental factors. This variability hampers the control and utilization of
solar cells' peak output. In this study, a single-stage grid-connected PV
system is designed to enhance power quality. Our approach employs fuzzy
logic in the direct power control (DPC) of a three-phase voltage source
inverter (VSI), enabling seamless integration of the PV connected to the
grid. Additionally, a fuzzy logic-based maximum power point tracking
(MPPT) controller is adopted, which outperforms traditional methods like
incremental conductance (INC) in enhancing solar cell efficiency and
minimizing the response time. Moreover, the inverter's real-time active and
reactive power is directly managed to achieve a unity power factor (UPF).
The system's performance is assessed through MATLAB/Simulink
implementation, showing marked improvement over conventional methods,
particularly in steady-state and varying weather conditions. For solar
irradiances of 500 and 1,000 W/m2
, the results show that the proposed
method reduces the total harmonic distortion (THD) of the injected current
to the grid by approximately 46% and 38% compared to conventional
methods, respectively. Furthermore, we compare the simulation results with
IEEE standards to evaluate the system's grid compatibility.
Enhancing photovoltaic system maximum power point tracking with fuzzy logic-b...IJECEIAES
Photovoltaic systems have emerged as a promising energy resource that
caters to the future needs of society, owing to their renewable, inexhaustible,
and cost-free nature. The power output of these systems relies on solar cell
radiation and temperature. In order to mitigate the dependence on
atmospheric conditions and enhance power tracking, a conventional
approach has been improved by integrating various methods. To optimize
the generation of electricity from solar systems, the maximum power point
tracking (MPPT) technique is employed. To overcome limitations such as
steady-state voltage oscillations and improve transient response, two
traditional MPPT methods, namely fuzzy logic controller (FLC) and perturb
and observe (P&O), have been modified. This research paper aims to
simulate and validate the step size of the proposed modified P&O and FLC
techniques within the MPPT algorithm using MATLAB/Simulink for
efficient power tracking in photovoltaic systems.
Adaptive synchronous sliding control for a robot manipulator based on neural ...IJECEIAES
Robot manipulators have become important equipment in production lines, medical fields, and transportation. Improving the quality of trajectory tracking for
robot hands is always an attractive topic in the research community. This is a
challenging problem because robot manipulators are complex nonlinear systems
and are often subject to fluctuations in loads and external disturbances. This
article proposes an adaptive synchronous sliding control scheme to improve trajectory tracking performance for a robot manipulator. The proposed controller
ensures that the positions of the joints track the desired trajectory, synchronize
the errors, and significantly reduces chattering. First, the synchronous tracking
errors and synchronous sliding surfaces are presented. Second, the synchronous
tracking error dynamics are determined. Third, a robust adaptive control law is
designed,the unknown components of the model are estimated online by the neural network, and the parameters of the switching elements are selected by fuzzy
logic. The built algorithm ensures that the tracking and approximation errors
are ultimately uniformly bounded (UUB). Finally, the effectiveness of the constructed algorithm is demonstrated through simulation and experimental results.
Simulation and experimental results show that the proposed controller is effective with small synchronous tracking errors, and the chattering phenomenon is
significantly reduced.
Remote field-programmable gate array laboratory for signal acquisition and de...IJECEIAES
A remote laboratory utilizing field-programmable gate array (FPGA) technologies enhances students’ learning experience anywhere and anytime in embedded system design. Existing remote laboratories prioritize hardware access and visual feedback for observing board behavior after programming, neglecting comprehensive debugging tools to resolve errors that require internal signal acquisition. This paper proposes a novel remote embeddedsystem design approach targeting FPGA technologies that are fully interactive via a web-based platform. Our solution provides FPGA board access and debugging capabilities beyond the visual feedback provided by existing remote laboratories. We implemented a lab module that allows users to seamlessly incorporate into their FPGA design. The module minimizes hardware resource utilization while enabling the acquisition of a large number of data samples from the signal during the experiments by adaptively compressing the signal prior to data transmission. The results demonstrate an average compression ratio of 2.90 across three benchmark signals, indicating efficient signal acquisition and effective debugging and analysis. This method allows users to acquire more data samples than conventional methods. The proposed lab allows students to remotely test and debug their designs, bridging the gap between theory and practice in embedded system design.
Detecting and resolving feature envy through automated machine learning and m...IJECEIAES
Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.
Smart monitoring technique for solar cell systems using internet of things ba...IJECEIAES
Rapidly and remotely monitoring and receiving the solar cell systems status parameters, solar irradiance, temperature, and humidity, are critical issues in enhancement their efficiency. Hence, in the present article an improved smart prototype of internet of things (IoT) technique based on embedded system through NodeMCU ESP8266 (ESP-12E) was carried out experimentally. Three different regions at Egypt; Luxor, Cairo, and El-Beheira cities were chosen to study their solar irradiance profile, temperature, and humidity by the proposed IoT system. The monitoring data of solar irradiance, temperature, and humidity were live visualized directly by Ubidots through hypertext transfer protocol (HTTP) protocol. The measured solar power radiation in Luxor, Cairo, and El-Beheira ranged between 216-1000, 245-958, and 187-692 W/m 2 respectively during the solar day. The accuracy and rapidity of obtaining monitoring results using the proposed IoT system made it a strong candidate for application in monitoring solar cell systems. On the other hand, the obtained solar power radiation results of the three considered regions strongly candidate Luxor and Cairo as suitable places to build up a solar cells system station rather than El-Beheira.
An efficient security framework for intrusion detection and prevention in int...IJECEIAES
Over the past few years, the internet of things (IoT) has advanced to connect billions of smart devices to improve quality of life. However, anomalies or malicious intrusions pose several security loopholes, leading to performance degradation and threat to data security in IoT operations. Thereby, IoT security systems must keep an eye on and restrict unwanted events from occurring in the IoT network. Recently, various technical solutions based on machine learning (ML) models have been derived towards identifying and restricting unwanted events in IoT. However, most ML-based approaches are prone to miss-classification due to inappropriate feature selection. Additionally, most ML approaches applied to intrusion detection and prevention consider supervised learning, which requires a large amount of labeled data to be trained. Consequently, such complex datasets are impossible to source in a large network like IoT. To address this problem, this proposed study introduces an efficient learning mechanism to strengthen the IoT security aspects. The proposed algorithm incorporates supervised and unsupervised approaches to improve the learning models for intrusion detection and mitigation. Compared with the related works, the experimental outcome shows that the model performs well in a benchmark dataset. It accomplishes an improved detection accuracy of approximately 99.21%.
artificial intelligence and data science contents.pptxGauravCar
What is artificial intelligence? Artificial intelligence is the ability of a computer or computer-controlled robot to perform tasks that are commonly associated with the intellectual processes characteristic of humans, such as the ability to reason.
› ...
Artificial intelligence (AI) | Definitio
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Sinan KOZAK
Sinan from the Delivery Hero mobile infrastructure engineering team shares a deep dive into performance acceleration with Gradle build cache optimizations. Sinan shares their journey into solving complex build-cache problems that affect Gradle builds. By understanding the challenges and solutions found in our journey, we aim to demonstrate the possibilities for faster builds. The case study reveals how overlapping outputs and cache misconfigurations led to significant increases in build times, especially as the project scaled up with numerous modules using Paparazzi tests. The journey from diagnosing to defeating cache issues offers invaluable lessons on maintaining cache integrity without sacrificing functionality.
Comparative analysis between traditional aquaponics and reconstructed aquapon...bijceesjournal
The aquaponic system of planting is a method that does not require soil usage. It is a method that only needs water, fish, lava rocks (a substitute for soil), and plants. Aquaponic systems are sustainable and environmentally friendly. Its use not only helps to plant in small spaces but also helps reduce artificial chemical use and minimizes excess water use, as aquaponics consumes 90% less water than soil-based gardening. The study applied a descriptive and experimental design to assess and compare conventional and reconstructed aquaponic methods for reproducing tomatoes. The researchers created an observation checklist to determine the significant factors of the study. The study aims to determine the significant difference between traditional aquaponics and reconstructed aquaponics systems propagating tomatoes in terms of height, weight, girth, and number of fruits. The reconstructed aquaponics system’s higher growth yield results in a much more nourished crop than the traditional aquaponics system. It is superior in its number of fruits, height, weight, and girth measurement. Moreover, the reconstructed aquaponics system is proven to eliminate all the hindrances present in the traditional aquaponics system, which are overcrowding of fish, algae growth, pest problems, contaminated water, and dead fish.
Discover the latest insights on Data Driven Maintenance with our comprehensive webinar presentation. Learn about traditional maintenance challenges, the right approach to utilizing data, and the benefits of adopting a Data Driven Maintenance strategy. Explore real-world examples, industry best practices, and innovative solutions like FMECA and the D3M model. This presentation, led by expert Jules Oudmans, is essential for asset owners looking to optimize their maintenance processes and leverage digital technologies for improved efficiency and performance. Download now to stay ahead in the evolving maintenance landscape.
Applications of artificial Intelligence in Mechanical Engineering.pdfAtif Razi
Historically, mechanical engineering has relied heavily on human expertise and empirical methods to solve complex problems. With the introduction of computer-aided design (CAD) and finite element analysis (FEA), the field took its first steps towards digitization. These tools allowed engineers to simulate and analyze mechanical systems with greater accuracy and efficiency. However, the sheer volume of data generated by modern engineering systems and the increasing complexity of these systems have necessitated more advanced analytical tools, paving the way for AI.
AI offers the capability to process vast amounts of data, identify patterns, and make predictions with a level of speed and accuracy unattainable by traditional methods. This has profound implications for mechanical engineering, enabling more efficient design processes, predictive maintenance strategies, and optimized manufacturing operations. AI-driven tools can learn from historical data, adapt to new information, and continuously improve their performance, making them invaluable in tackling the multifaceted challenges of modern mechanical engineering.
Rainfall intensity duration frequency curve statistical analysis and modeling...bijceesjournal
Using data from 41 years in Patna’ India’ the study’s goal is to analyze the trends of how often it rains on a weekly, seasonal, and annual basis (1981−2020). First, utilizing the intensity-duration-frequency (IDF) curve and the relationship by statistically analyzing rainfall’ the historical rainfall data set for Patna’ India’ during a 41 year period (1981−2020), was evaluated for its quality. Changes in the hydrologic cycle as a result of increased greenhouse gas emissions are expected to induce variations in the intensity, length, and frequency of precipitation events. One strategy to lessen vulnerability is to quantify probable changes and adapt to them. Techniques such as log-normal, normal, and Gumbel are used (EV-I). Distributions were created with durations of 1, 2, 3, 6, and 24 h and return times of 2, 5, 10, 25, and 100 years. There were also mathematical correlations discovered between rainfall and recurrence interval.
Findings: Based on findings, the Gumbel approach produced the highest intensity values, whereas the other approaches produced values that were close to each other. The data indicates that 461.9 mm of rain fell during the monsoon season’s 301st week. However, it was found that the 29th week had the greatest average rainfall, 92.6 mm. With 952.6 mm on average, the monsoon season saw the highest rainfall. Calculations revealed that the yearly rainfall averaged 1171.1 mm. Using Weibull’s method, the study was subsequently expanded to examine rainfall distribution at different recurrence intervals of 2, 5, 10, and 25 years. Rainfall and recurrence interval mathematical correlations were also developed. Further regression analysis revealed that short wave irrigation, wind direction, wind speed, pressure, relative humidity, and temperature all had a substantial influence on rainfall.
Originality and value: The results of the rainfall IDF curves can provide useful information to policymakers in making appropriate decisions in managing and minimizing floods in the study area.
Rainfall intensity duration frequency curve statistical analysis and modeling...
Drivers’ drowsiness detection based on an optimized random forest classification and single-channel electroencephalogram
1. International Journal of Electrical and Computer Engineering (IJECE)
Vol. 13, No. 3, June 2023, pp. 3398~3406
ISSN: 2088-8708, DOI: 10.11591/ijece.v13i3.pp3398-3406 3398
Journal homepage: http://ijece.iaescore.com
Drivers’ drowsiness detection based on an optimized random
forest classification and single-channel electroencephalogram
Mouad Elmouzoun Elidrissi1
, Elmaati Essoukaki1,2
, Lhoucine Ben Taleb2
, Azeddine Mouhsen1
,
Mohammed Harmouchi1
1
Laboratory of Radiation-Matter and Instrumentation, Faculty of Sciences and Techniques, Hassan First University of Settat,
Settat, Morocco
2
Higher Institute of Health Sciences, Hassan First University of Settat, Settat, Morocco
Article Info ABSTRACT
Article history:
Received Jul 20, 2022
Revised Sep 26, 2022
Accepted Oct 1, 2022
The state of functioning (posture) of a driver at the wheel of a car involves a
complex set of psychological, physiological, and physical parameters. This
combination induces fatigue, which manifests itself in repeated yawning,
stinging eyes, a frozen gaze, a stiff and painful neck, back pain, and other
signs. The driver may fight fatigue for a few moments, but it inevitably leads
to drowsiness, periods of micro-sleep, and then falling asleep. At the first
signs of drowsiness, the risk of an accident becomes immense. In Morocco,
drowsiness at the wheel is the cause of 1/3 of fatal accidents on the freeways.
Thus, in this paper, a new hybrid data analysis and an efficient machine
learning algorithm are designed to detect the drowsiness of drivers who spend
most of their time behind the wheel over long distances (older than 35 years).
This analysis is based on a single channel of electroencephalogram (EEG)
recordings using time, frequency fast Fourier transform (FFT), and power
spectral density (PSD) analysis. To distinguish between the two states of
alertness and drowsiness, several features were extracted from each domain
(time, FFT, and PSD), and subjected to different classifier architectures to
conduct a general comparison and achieve the highest detection accuracy
(98.5%) and best time consumption (13 milliseconds).
Keywords:
Drivers’ drowsiness detection
Electroencephalogram signals
processing
Machine learning
Python processing
This is an open access article under the CC BY-SA license.
Corresponding Author:
Mouad Elmouzoun Elidrissi
Laboratory of Radiation-Matter and Instrumentation, Faculty of Sciences and Techniques, Hassan First
University of Settat
Settat 26002, Morocco
Email: M.elmouzounelidrissi@uhp.ac.ma
1. INTRODUCTION
While driving, a complex connection of our brain signals is established, which can cause the driver to
feel tired and, even more so, to feel drowsy and fall asleep (drowsiness is a transitional state between the
waking and sleeping states), leading to dangerous and fatal accidents [1], [2]. In addition, the monotony of
highways and especially driving long distances and for many hours are other factors that can cause drowsiness
in the driver [3].
In Morocco, a 33.33% rate of fatal accidents on the highways is caused by drowsiness [4], [5]. This
gave us the opportunity to think about how to solve this serious tragedy, concluding that it is to develop an
intelligent and hybrid algorithm for automatic early detection of drowsiness, which will warn the driver to take
precautions. The aim of this work is to improve our previous algorithms for predicting driver drowsiness, and
to overcome the weaknesses and limitations of existing systems in terms of speed and accuracy of detection.
Many previous works present techniques based on sensor signals to detect drowsiness, both in
literature and commercially. Some have developed a smart glasses system that detects drowsiness based on eye
2. Int J Elec & Comp Eng ISSN: 2088-8708
Drivers’ drowsiness detection based on an optimized random forest … (Mouad Elmouzoun Elidrissi)
3399
closure by sending infrared light between an emitter and a receiver, or by adding other information such as
micro-falls of the head subtracted from accelerometers and gyroscopic sensors [6]. The use of accelerometers
and an infrared transceiver have been used but implemented on a wearable cap instead of glasses. Nevertheless,
these methods have multiple limitations in real driving situations, especially in the absence of physiological
parameters. For example, the driver can make different actions and movements that are normal but can be
attributed to signs of drowsiness based on sensor signals.
Some authors proposed a non-invasive eye-tracking method based on an optical correlator to estimate
eye state, which will then be used to detect driving fatigue. An accuracy of 99.9% was achieved for the
estimation of the eye state at different situations [7]. Other systems based on face detection have also been
developed, based on image processing and analysis of the eye and head states in addition to physiological
signals such as respiratory signals and electrocardiogram (ECG) [8]–[10]. This idea has many limitations such
as eye detection and tracking error due to eye shape for some subjects (e.g., Chinese population), camera
direction and camera discomfort. Another non-intrusive technique was introduced, where the authors used
thermal imaging to analyze the variations in respiratory rhythms under the nose region in a normal state and in
drowsiness to identify the drowsy state, they were able to achieve a detection accuracy of 90% [11]. The idea
of using a thermal camera solved the problem of non-detection at night or even in the absence of light of
previous facial imaging-based systems.
In 2010, a study focused on the analysis of physiological signals such as electrocardiogram (ECG)
[12] or using electrooculogram (EOG) signals in 2013 [13]. The analysis of EEG signals becomes the main
field in the study of human body phenomena such as epilepsy, sleep apnea, and especially the study of awake
and drowsiness states based on the difference between brain waves.
The difference between works is basically in the method of signals analysis (algorithms), the
classification method, or the number of electrodes and even their position. A study cited the use of 32 electrodes
for the acquisition before extracting the spectrum entropy, approximate entropy, sample entropy, and fuzzy
entropy. So as to feed a support vector machine (SVM) with a radial basis function (RBF) kernel to achieve an
accuracy of 98.75% [14]. Decreasing the number of electrodes down to 24 was also performed besides using
the logarithm of energy, and chaotic feature extraction such as Petrosian and Higuchi fractal dimension or also
empirical mode decomposition (EMD) [15], [16]. The accuracies obtained were 83.3% and 84.8%,
respectively, or even 12 electrodes [17], where they proposed a method to explore the spectrogram of each
EEG channel using the short-time Fourier transform (STFT), and the discrete Fourier transform (DFT). The
accuracy reached an average of 91.72% after using the linear kernel of the SVM classifier. Another study
developed a method based on fast Fourier transform (FFT) to calculate the spectrum and signal power spectral
density (PSD) instead of STFT and showed an accuracy of 88.8% [18].
A method based on a single EEG channel parietal-zero-occipital-zero (Pz-Oz) and the zero means that
the electrodes are placed in the midline sagittal plane of the skull), was proposed to detect drowsiness using
the decomposition of the signal into frequency sub-bands according to a time-domain distribution called Haar
wavelet packet transform (WPT) [19]. These techniques are the most widely used in these studies, whether
brain waves are decomposed into Delta [<4 Hz], Theta [4 to 8 Hz], Alpha [8 to 16 Hz], Beta [16 to 32 Hz], and
Gamma [>32 Hz] bands. In general, the increase in Theta waves and the decrease in Alpha waves correspond
to a high level of transition from the awake to the drowsy state. The discrete wavelet transform (DWT), Tunable
Q-factor wavelet transform (TQWT), and continuous wavelet transform (CWT) have also been discussed in
previous works [20]–[22], respectively. These works have shown high detection accuracy of up to 91.842%.
The positions of the electrodes used are important to extract the most significant signals to detect drowsiness
when the number of these electrodes is reduced, according to the international 10 to 20 system, especially if a
single channel of EEG recordings is used, as in our proposal.
The complexity is reduced due to the absence of a large number of electrodes, but it is more difficult
to extract all the information from a single channel. Therefore, in this paper, we present a novel EEG signal
analysis method based on hybrid features extracted from the time and spectral domains and our optimized
random forest (RF) classification architecture to predict driver drowsiness, which achieved 98.5% of detection
accuracy in 13 milliseconds, overcoming all the limitations of existing methods that we will explain in the next
section.
2. METHOD
The objective of this paper is to develop a hybrid algorithm for drowsiness detection that encompasses
three signal processing domains (temporal, and spectral using FFT, and PSD) and achieves a higher
performance of speed and accuracy than the cited works. Each of the domains has been performed and tested
separately, the distribution of features is analyzed to eliminate those that decrease the accuracy, and finally
using the total of the most significant ones, then building different machine learning models to test their
accuracies and maintain the best. The target population, as mentioned previously, is drivers working in
3. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 3, June 2023: 3398-3406
3400
transportation, who spend the majority of their time driving long distances and are over 35 years old. However,
in terms of algorithm approval, we used an open database with an average of subjects aged 18 years (between
17 and 26 years).
2.1. Acquisition phase
The data used in this article were obtained from the Physionet database [23]. EEG signals were
recorded monopolar using the 23-channel Neurocom EEG system (Ukraine, XAI-MEDICA). The 36 subjects
were of both genders, aged 16-24 years (an average of 18 years).
Electrodes were placed according to the international 10 to 20 system. All electrodes were referenced
to the interconnected ear reference electrodes (Ref). To remove artifacts from the EEG segments, a low-pass
filter with a cutoff frequency of 30 Hz and a power-line notch filter (50 Hz) were used. This database is
published for use in research work due to the high quality of its signals.
The data is available in European data format (.edf), so we took 6 male and female subjects of different
ages (an average of 18 years) and converted the data file into a comma-separated values (.csv) extension with
3s EEG signal segments using Python and started our processing algorithm. In this work, we focused on a
single channel of EEG recordings FP1-Ref. FP1 is known to be an optimal location for detecting sleepiness,
studies based on the FP1 spot also showed a high correlation for detecting the sleepiness state [24].
2.2. Processing method
The EEG recordings were free from artifacts, as all noises were filtered out during recording, as
described in the European Commission Study (section 2.1). After the EEG recordings were collected/acquired,
a first arrangement was applied to the data in order to prepare them for the extraction of the selected features.
The second step consists of grouping all features into a vector following the form of the classifier, dividing
them into training and test inputs, adding the corresponding label, and finally obtaining the confusion matrix
containing all the results about the applied training method. Here is the flowchart of our method presented in
Figure 1.
Figure 1. Flowchart of the treatment method
2.2.1. Time domain analysis
The objective of this step is the extraction of features in the time domain, i.e., the processing of the
potential difference generated by the electrodes but considering first the single channel (Fp1-Ref) instead of
the total of 23 electrodes, in order to reduce the hardware consumption and to keep the analysis in real-time,
as shown in Figure 2. The detection of the drowsy state must be based on several parameters that make the
difference between the two states, awake and drowsy, these characteristic parameters are called "features". The
more these features are well dispersed between the two states, the more efficient and accurate the detection is.
Data Acquisition
& Preprocessing
Data Arrangement
Fourier Domain
Time Domain
Power Spectral
Density Domain
Features
Extraction
Features Selection
& Vectorization
Classification
Predictive Model
4. Int J Elec & Comp Eng ISSN: 2088-8708
Drivers’ drowsiness detection based on an optimized random forest … (Mouad Elmouzoun Elidrissi)
3401
In this work, the features chosen and extracted are the median, the mean, the standard deviation (Std), the
variance (Var), the root mean square (RMS), the minima (Min), the maxima (Max), and a new parameter that
we called mean of peaks (MOP) which represents the average of all the peaks of the signal.
Figure 2. EEG signals recorded from 23 electrodes (left) and Fp1-Ref (right)
2.2.2. Frequency domain analysis
a. Fast Fourier transform approach
This second analysis starts by switching from the time domain to the frequency domain and extracting
the most significant features. It aims at computing the one-dimensional DFT by a function that computes the
one-dimensional n-point DFT with the efficient FFT algorithm.
For 0 ⩽ k ⩽ N – 1
Xk = ∑ 𝑥𝑛𝑒−2𝜋𝑖
𝑘𝑛
𝑁
𝑛−1
𝑛=0
(1)
After calculating the Fourier transform of all the data, in the same way as in the time domain, the
features were extracted but were in the complex domain (real and imaginary values), so we adopted a method
to convert these real and imaginary value into a pure real value in order to start our classification step. This
method consists in calculating the modulus of the features.
𝐹𝑖 = 𝑅𝑒(𝐹𝑖) + 𝑖 ∗ 𝐼𝑚(𝐹𝑖)
|Fi| = √𝑅𝑒
2 + 𝐼𝑚
2 (2)
𝐹𝑖 is the extracted feature number 𝑖.
b. Power spectral density approach
In this section, the spectrum was estimated based on Burg’s algorithm, which estimates the power
spectral density of the data of each segment. PSD represents the spectral power per unit frequency. Using this
technique, we might be able to distinguish the two states, especially after extracting the eight features
mentioned earlier but this time from the spectrum of each sample/segment.
PSD =
1
𝑁
∑ 𝑌(𝑛)𝑒−2𝑘
𝑛
𝑁
𝑁−1
𝑘=0
=
1
𝑁
𝑋𝑘 (3)
2.3. Classification
In this step, different analyses were adopted to obtain the best accuracy in drowsiness detection. Each
approach (time, FFT, PSD) was tested separately and went through different classifier architectures, and then
a method combining all the approaches was used (hybrid algorithm) to get the best efficiency of our proposed
method based on the best classifier. The classifiers used in our study are SVM with its RBF kernel, RF,
multilayer perceptron (MLP), nearest centroid (NC), K-nearest neighbors (KNN), Gaussian process, decision
tree (DT), optimized decision tree (ODT), and finally stochastic gradient descent (SGD).
A general study on these classifiers is done to compare their efficiency and accuracy depending on
the type of data used which are random signals (EEG signals). This means that the most meaningful method is
5. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 3, June 2023: 3398-3406
3402
to analyze our data and train a classifier that has a random architecture instead of a linear architecture. In the
following section, we will show the results obtained for several aspects of our study.
3. RESULTS AND DISCUSSION
In this section, we will provide all the results of our proposed method, these results are the major sign
of the performance of our model. The training and test scores (accuracies) indicate the ability of the model to
predict drowsiness against all predictions made, the recall (sensitivity or also called success rate) is the ability
to detect drowsiness when the subject is actually drowsy, the F1-score gives an idea of the prediction rate of
sleepiness and wakefulness and the total accuracy of the classifier. The results are based on four parameters,
their total is called the confusion matrix of a classifier.
True positive (TP): Prediction is positive (Drowsy state is predicted) and X is Drowsy.
True negative (TN): Prediction is negative (Awake state is predicted) and X is Awake.
False positive (FP): Prediction is positive (Drowsy state is predicted) and X is Awake.
False negative (FN): Prediction is negative (Awake state is predicted) and X is Drowsy.
Based on these parameters, we could calculate our different scoring outputs.
Precision =
𝑇𝑃
𝑇𝑃+𝐹𝑃
(4)
Recall =
𝑇𝑃
𝑇𝑃+𝐹𝑁
(5)
Accuracy =
𝑇𝑃+𝑇𝑁
𝑇𝑃+𝐹𝑃+𝑇𝑁+𝐹𝑁
(6)
F1 − score = 2 ∗
𝑝𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛∗𝑟𝑒𝑐𝑎𝑙𝑙
𝑝𝑟𝑒𝑐𝑖𝑠𝑖𝑜𝑛+𝑟𝑒𝑐𝑎𝑙𝑙
(7)
Tables 1 to 4 show all the results obtained when we trained different models using only the PSD
domain features extracted from EEG data samples in Table 1, FFT-only features in Table 2, time-only features
in Table 3, and our hybrid approach of features selection in Table 4.
Table 1. Performance comparison between different classifiers applied on only PSD features
Classifier Precision Accuracy Recall F1-score D/A
SVM (RBF kernel) 70.4% 71.9% 75.9% 0.71 / 0.71
Gaussian process 49.1% 49.1% 100% 0.00 / 0.66
Stochastic gradient descent 50.2% 50.2% 100% 0.00 / 0.67
Multi-layer perceptron 49.8% 49.8% 100% 0.00 / 0.66
Nearest centroid 54.6% 57% 86.3% 0.39 / 0.67
Random forest 49.7% 49.7% 100% 0.00 / 0.66
K-nearest neighbors 90.6% 90.6% 90.8% 0.90 / 0.91
Table 2. Performance comparison between different classifiers applied on only FFT features
Classifier Precision Accuracy Recall F1-score D/A
SVM (RBF kernel) 84.6% 86.5% 89.7% 0.86 / 0.87
Gaussian process 63.7% 68.9% 87.6% 0.62 / 0.74
Stochastic gradient descent 49.7% 49.7% 100% 0.00 / 0.66
Multi-layer perceptron 69.4% 74.1% 84.1% 0.72 / 0.76
Nearest centroid 69.6% 72.9% 82.6% 0.70 / 0.76
Random forest 96.7% 96.5% 96.1% 0.97 / 0.96
K-nearest neighbors 93.3% 92.9% 92.4% 0.93 / 0.93
Table 3. Performance comparison between different classifiers applied on only time features
Classifier Precision Accuracy Recall F1-score D/A
SVM (RBF kernel) 92.0% 93.3% 94.5% 0.93 / 0.93
Gaussian process 49.0% 49.0% 100% 0.00 / 0.66
Stochastic gradient descent 50.5% 50.5% 100% 0.00 / 0.66
Multi-layer perceptron 48.9% 48.9% 100% 0.00 / 0.66
Nearest centroid 84.4% 88.4% 95.0% 0.87 / 0.89
Random forest 93.5% 94.6% 95.5% 0.95 / 0.95
K-nearest neighbors 95.8% 94.1% 92.3% 0.94 / 0.94
6. Int J Elec & Comp Eng ISSN: 2088-8708
Drivers’ drowsiness detection based on an optimized random forest … (Mouad Elmouzoun Elidrissi)
3403
Table 4. Performance comparison between different classifiers applied on our hybrid method
Classifier Precision Accuracy Recall F1-score D/A
SVM (RBF kernel) 85.3% 87.8% 91.3% 0.87 / 0.88
Gaussian process 53.2% 56.0% 96.1% 0.27 / 0.68
Stochastic gradient descent 59.9% 65.5% 90.4% 0.55/ 0.72
Multi-layer perceptron 70.7% 75.6% 85.5% 0.73 / 0.78
Nearest centroid 68.7% 73.4% 85.3% 0.70 / 0.76
Random forest 98.2% 98.5% 98.0% 0.98 / 0.98
K-nearest neighbors 93.2% 93.1% 92.6% 0.93 / 0.93
As a result, our proposed method (hybrid approach) presented in Table 4 showed a remarkable
performance improvement in terms of accuracy. The accuracy reached 98.5% for drowsiness detection based
on our chosen features. To justify these good results here is for example the distribution of some randomly
chosen features along the extracted data lines. We can also observe that the classifiers that obtain the best
accuracy are RF and KNN, due to the adherence between the nature of our EEG signals (which has a random
distribution) and the architecture of these classifiers presented in Figure 2.
To show that our results are far from so-called overfitting and to justify these good results, in Figure 3
we present a distribution of randomly selected features (standard deviation and variance) extracted from awake
and drowsy subjects over all EEG data row samples, and we notice that the features extracted from each state
of the subjects are very distinct and could summarize that we are dealing with two different states called classes.
Figure 3. Features distribution along the total rows of EEG data extracted
It can be clearly seen that the two classes awake (from 0 to 3,599) and drowsy (from 3,600 to 7,199)
are well separated, except for the distribution of the characteristics of some subjects, but in general, the
classification reached a high percentage of detection (98.5%). In order to situate our method, a two-axis study
was conducted to compare all previous work that used the same dataset and the single-channel-based
processing shown in Table 5. Achieving higher accuracy of a system depends on two studies: either we use a
large data segment to give the classifier a higher margin for training and testing, or we try to build the analysis
on robust features. As shown in Table 5, our proposed method performed best using only 3-second data
segments instead of 5 s, 10 s, or 30 s segments.
7. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 3, June 2023: 3398-3406
3404
In terms of time consumption, this Table 6 compares the classifiers used and the time taken during
the entire training process from data entry to classifier output (prediction). By comparing these results in
Table 6, we conclude that the runtime is different from one classifier to another. But in terms of time and
accuracy, the RF classifier is the most efficient and effective for our work. The final phase was to save our
(trained) model and use it to predict the state of new subjects to validate our work and calculate the prediction
time. The state of these subjects used for approval was already known and tested by our new hybrid model.
The average prediction time was 13 milliseconds as shown in Table 6 and Figure 4. The reason why
the RF and KNN classifiers show the highest accuracies in each approach is that our data type is compatible
with the nature of the classifier. Using a nonlinear classifier for random, nonlinear data like ours (EEG signals)
is the best method for building a predictive model. Linear classifiers will not be as effective as nonlinear ones
due to the non-possibility of finding a linear separator between the distribution of the data called a hyperplane.
Table 5. Comparison of performance between our and existing models obtained using Physionet EEG
database and single-EEG-channel approach
Work Platform used Sampling frequency Size of segments Processing method Classification method Accuracy
Proposed Python 100 Hz 3s Hybrid RF 98.50%
[25] Python 100 Hz 3s Hybrid ODT 96.40%
[26] Python 100 Hz 3s Hybrid DT 95.70%
[27] MATLAB 100 Hz 5s WPT ET 94.45%
[28] -- -- -- TQWT ELM 91.80%
[29] MATLAB 250 Hz 30s STFT, TQWT LSTM 94.31%
[18] MATLAB 250 Hz 30s FFT ANN 88.80%
[30] iPad app 512 Hz 10s PSD SVM 72.70%
Table 6. Time comparison between the different classifiers used
Classifier Accuracy Time (s)
Random forest 98.5% 0.013
Optimized decision tree 96.4% 0.053
Decision tree 95.7% 0.065
SVM (RBF kernel) 87.8% 0.985
Gaussian process 56.0% 12.57
Stochastic gradient descent 65.5% 0.366
Multi-layer perceptron 75.6% 5.144
Nearest centroid 73.4% 0.006
K-nearest neighbors 93.1% 0.142
Figure 4. Output of our model showing the total time consumed
4. CONCLUSION
The proposed method represents a new hybrid method based on time processing (FFT, and PSD
techniques) to predict sleepiness from physiological signals (EEG signals), this work shows an interesting
performance improvement under three axes: the software used (Python), the prediction accuracy (98.5%) and
the prediction time (0.013 s). Using the features extracted from the three domains (time, FFT, and PSD), we
were able to train different classifiers to predict sleepiness and compared each of them to get an overview and
concluded that our method offered the best performance among all existing works.
The only limitation of this work is that the average age used is related to the database used (18 years)
which is different from the target population (over 35 years). This limitation will be overcome once we have
realized our own prototype (hardware acquisition system).
- - - Execution time is : 0.01146554946899414 seconds - - -
‘Attention !!! Subject is drowsy ‘
- - - Execution time is : 0.014030694961547852 seconds - - -
‘Subject is Awake ‘
8. Int J Elec & Comp Eng ISSN: 2088-8708
Drivers’ drowsiness detection based on an optimized random forest … (Mouad Elmouzoun Elidrissi)
3405
ACKNOWLEDGEMENTS
The author is extremely grateful for receiving an excellence scholarship from the National Center of
Scientific and Technical Research (CNRST Morocco).
REFERENCES
[1] Narsa, “Collection of statistics on road traffic injuries 2016,” (in French), Narsa, 2016. Accessed: Mar. 11, 2022. [Online],
Available: http://narsa.ma/sites/default/files/2021-08/recueil 2020.pdf
[2] “Collection of statistics on road traffic injuries 2017,” (in French) Ministère de l'Equipement, du Transport, de la Logistique et de
l’Eau Royaume du Maroc, 2017. Accessed: Mar, 11, 2022. [Online], Available: http://www.equipement.gov.ma/AR/Infrastructures-
routieres/Reseau-Routier-du-Maroc/Documents/RECUEIL%20ACCIDENTS%202017.pdf
[3] T. Wijayanto, S. R. Marcillia, G. Lufityanto, B. B. Wisnugraha, T. G. Alma, and R. U. Abdianto, “The effect of situation awareness
on driving performance in young sleep-deprived drivers,” IATSS Research, vol. 45, no. 2, pp. 218–225, Jul. 2021, doi:
10.1016/j.iatssr.2020.10.002.
[4] Narsa, “Physical accidents,” (in French), Narsa, 2020. Accessed: Mar. 11, 2022. [Online], Available:
https://narsa.ma/sites/default/files/2021-08/recueil%202020.pdf (accessed Mar. 11, 2022).
[5] Narsa, “On the final statistical data on road traffic accidents with injuries for the year 2019,” (in French), Narsa, 2019. Accessed:
Mar. 11, 2022. [Online], Available: https://narsa.ma/sites/default/files/2020-11/Comm%20accid%202019%20%281%29.pdf
(accessed Mar. 11, 2022).
[6] W. Chang, L. Chen, and Y. Chiou, “Design and implementation of a drowsiness-fatigue-detection system based on wearable smart
glasses to increase road safety,” IEEE Transactions on Consumer Electronics, vol. 64, no. 4, pp. 461–469, Nov. 2018, doi:
10.1109/TCE.2018.2872162.
[7] E. Ouabida, A. Essadike, and A. Bouzid, “Optical correlator based algorithm for driver drowsiness detection,” Optik, vol. 204, Feb.
2020, doi: 10.1016/j.ijleo.2019.164102.
[8] C. Jacobé de Naurois, C. Bourdin, C. Bougard, and J.-L. Vercher, “Adapting artificial neural networks to a specific driver enhances
detection and prediction of drowsiness,” Accident Analysis & Prevention, vol. 121, pp. 118–128, Dec. 2018, doi:
10.1016/j.aap.2018.08.017.
[9] S. Dhanalakshmi, J. J. Rosepet, G. L. Rosy, and M. Philominal, “Drowsy driver identification using MATLAB,” International
Journal for Research in Applied Science and Engineering Technology, vol. 4, no. 4, pp. 198–205, 2016.
[10] A. Dash and B. N. Tripathy, “Prototype drowsiness detection system,” National Institute of Technology Rourkela, 2012.
[11] S. E. H. Kiashari, A. Nahvi, H. Bakhoda, A. Homayounfard, and M. Tashakori, “Evaluation of driver drowsiness using respiration
analysis by thermal imaging on a driving simulator,” Multimedia Tools and Applications, vol. 79, no. 25–26, pp. 17793–17815, Jul.
2020, doi: 10.1007/s11042-020-08696-x.
[12] M. Tasaki, M. Sakai, M. Watanabe, H. Wang, and D. Wei, “Evaluation of drowsiness during driving using electrocardiogram - a
driving simulation study,” in 2010 10th IEEE International Conference on Computer and Information Technology, Jun. 2010,
pp. 1480–1485. doi: 10.1109/CIT.2010.264.
[13] M. L. Jackson et al., “The utility of automated measures of ocular metrics for detecting driver drowsiness during extended
wakefulness,” Accident Analysis & Prevention, vol. 87, pp. 127–133, Feb. 2016, doi: 10.1016/j.aap.2015.11.033.
[14] Z. Mu, J. Hu, and J. Min, “Driver fatigue detection system using electroencephalography signals based on combined entropy
features,” Applied Sciences, vol. 7, no. 2, Feb. 2017, doi: 10.3390/app7020150.
[15] Z. Mardi, S. N. Ashtiani, and M. Mikaili, “EEG-based drowsiness detection for safe driving using chaotic features and statistical
tests,” Journal of Medical Signals & Sensors, vol. 1, no. 2, 2011, doi: 10.4103/2228-7477.95297.
[16] R. Kaur and K. Singh, “Drowsiness detection based on EEG signal analysis using EMD and trained neural network,” International
Journal of Science and Research (IJSR), vol. 2, no. 10, pp. 157–161, 2013.
[17] Ç. İ. Acı, M. Kaya, and Y. Mishchenko, “Distinguishing mental attention states of humans via an EEG-based passive BCI using
machine learning methods,” Expert Systems with Applications, vol. 134, pp. 153–166, Nov. 2019, doi: 10.1016/j.eswa.2019.05.057.
[18] I. Belakhdar, W. Kaaniche, R. Djemal, and B. Ouni, “Single-channel-based automatic drowsiness detection architecture with a
reduced number of EEG features,” Microprocessors and Microsystems, vol. 58, pp. 13–23, Apr. 2018, doi:
10.1016/j.micpro.2018.02.004.
[19] T. L. T. da Silveira, A. J. Kozakevicius, and C. R. Rodrigues, “Automated drowsiness detection through wavelet packet analysis of
a single EEG channel,” Expert Systems with Applications, vol. 55, pp. 559–565, Aug. 2016, doi: 10.1016/j.eswa.2016.02.041.
[20] N. Gurudath and H. B. Riley, “Drowsy driving detection by EEG analysis using wavelet transform and K-means clustering,”
Procedia Computer Science, vol. 34, pp. 400–409, 2014, doi: 10.1016/j.procs.2014.07.045.
[21] S. K. Khare and V. Bajaj, “Optimized tunable Q wavelet transform based drowsiness detection from electroencephalogram signals,”
IRBM, vol. 43, no. 1, pp. 13–21, Feb. 2022, doi: 10.1016/j.irbm.2020.07.005.
[22] Y. Jiao, Y. Deng, Y. Luo, and B.-L. Lu, “Driver sleepiness detection from EEG and EOG signals using GAN and LSTM networks,”
Neurocomputing, vol. 408, pp. 100–111, Sep. 2020, doi: 10.1016/j.neucom.2019.05.108.
[23] A. L. Goldberger et al., “PhysioBank, PhysioToolkit, and PhysioNet,” Circulation, vol. 101, no. 23, Jun. 2000, doi:
10.1161/01.CIR.101.23.e215.
[24] A. M. Strijkstra, D. G. M. Beersma, B. Drayer, N. Halbesma, and S. Daan, “Subjective sleepiness correlates negatively with global
alpha (8–12 Hz) and positively with central frontal theta (4–8 Hz) frequencies in the human resting awake electroencephalogram,”
Neuroscience Letters, vol. 340, no. 1, pp. 17–20, Apr. 2003, doi: 10.1016/S0304-3940(03)00033-8.
[25] M. E. Elidrissi, E. Essoukaki, L. Ben Taleb, A. Mouhsen, and M. Harmouchi, “A new hybrid and optimized algorithm for drivers’
drowsiness detection,” IAES International Journal of Artificial Intelligence (IJ-AI), vol. 11, no. 3, pp. 1101–1107, Sep. 2022, doi:
10.11591/ijai.v11.i3.pp1101-1107.
[26] M. E. Elidrissi et al., “Automatic drowsiness detection based on a single channel of EEG signals using a hybrid analysis and decision
tree classification method under python,” in Proceedings of the 2nd International Conference on Big Data, Modelling and Machine
Learning, 2021, pp. 301–305. doi: 10.5220/0010732900003101.
[27] B. V. Phanikrishna and S. Chinara, “Automatic classification methods for detecting drowsiness using wavelet packet transform
extracted time-domain features from single-channel EEG signal,” Journal of Neuroscience Methods, vol. 347, p. 108927, Jan. 2021,
doi: 10.1016/j.jneumeth.2020.108927.
[28] V. Bajaj, S. Taran, S. K. Khare, and A. Sengur, “Feature extraction method for classification of alertness and drowsiness states EEG
signals,” Applied Acoustics, vol. 163, Jun. 2020, doi: 10.1016/j.apacoust.2020.107224.
9. ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 13, No. 3, June 2023: 3398-3406
3406
[29] U. Budak, V. Bajaj, Y. Akbulut, O. Atila, and A. Sengur, “An effective hybrid model for EEG-based drowsiness detection,” IEEE
Sensors Journal, vol. 19, no. 17, pp. 7624–7631, Sep. 2019, doi: 10.1109/JSEN.2019.2917850.
[30] M. Ogino and Y. Mitsukura, “Portable drowsiness detection through use of a prefrontal single-channel electroencephalogram,”
Sensors, vol. 18, no. 12, Dec. 2018, doi: 10.3390/s18124477.
BIOGRAPHIES OF AUTHORS
Mouad Elmouzoun Elidrissi was born on September 10, 1996 in Casablanca,
Morocco. He is a Ph.D. student and received his master’s degree in biomedical engineering:
instrumentation and maintenance from the Faculty of Science and Technology Settat, in 2019.
His research areas include EEG signals analysis for drivers’ drowsiness detection, machine
learning model conception, and application of artificial intelligence for drivers and road safety.
He works at the Laboratory of Radiation-Matter and Instrumentation (RMI), Faculty of
Sciences and Technology, Hassan 1st University, Morocco. BP: 577, route de Casablanca.
Settat, Morocco. His research areas are in machine learning and artificial intelligence,
EEG signal processing, and biomedical instrumentation. He can be contacted at
m.elmouzounelidrissi@uhp.ac.ma.
Elmaati Essoukaki was born on January 1, 1990. He is currently a professor of
Instrumentation and Biomedical Engineering at Higher Institute of Health Sciences (ISSS),
Hassan First University. His research interests include Instrumentation and Biomedical
Engineering, biomedical imaging, and signal processing. He holds several publications and
innovation patents in the fields of biophysics and biomedical engineering. He can be contacted
at e.essoukaki@uhp.ac.ma.
Lhoucine Ben Taleb was born on February 20, 1991. He is a professor of
Electrical and Biomedical Engineering at Hassan First University (UHP), Morocco, since
2021. After having a master’s degree from UHP (2014), he obtained a Ph.D. in 2020 from the
same university specialty in electrical and biomedical engineering (in the Laboratory of
Radiation-Matter and Instrumentation). Ben Taleb has taught courses in instrumentation for
functional exploration and therapeutic applications, medical imaging technologies as well as
microcontrollers and programmable logic controllers. He has published several scientific
papers, and he is an inventor of one patent and a co-inventor of another one. He can be
contacted at l.bentaleb@uhp.ac.ma.
Azeddine Mouhsen was born on July 10, 1967 and is now a professor of Physics
at Hassan First University, Morocco, since 1996. He holds a Ph.D. from Bordeaux I University
(France) in 1995 and a thesis from Moulay Ismail University, Morocco, in 2001. He specializes
in instrumentation and measurements, sensors, applied optics, energy transfer, and radiation-
matter interactions. Azeddine Mouhsen has taught courses in physical sensors, chemical
sensors, instrumentation, systems technology, digital electronics, and industrial data
processing. He has published over 30 papers and he is the co-inventor of one patent. Actually,
he is the Director of the Laboratory of Radiation-Matter and Instrumentation. He can be
contacted at az.mouhsen@gmail.com.
Mohammed Harmouchi was born in Sefrou, Morocco, in 1959. He is in charge
of the master’s degree in biomedical engineering: instrumentation and maintenance. He is the
Ex-Director of the Laboratory of Radiation-Matter and Instrumentation, Hassan First
University, Settat, Morocco, where he is currently a professor of Higher Education and the Ex-
Head of the Department of Applied Physics, Faculty of Science and Technology. He holds
several publications and innovation patents in the fields of biophysics and biomedical
engineering. (Based on document published on October 9, 2020). He can be contacted at
mharmouchi14@gmail.com.