Brain-computer interface is a technology that allows operating a device without involving muscles and sound, but directly from the brain through the processed electrical signals. The technology works by capturing electrical or magnetic signals from the brain, which are then processed to obtain information contained therein. Usually, BCI uses information from electroencephalogram (EEG) signals based on various variables reviewed. This study proposed BCI to move external devices such as a drone simulator based on EEG signal information. From the EEG signal was extracted to get motor imagery (MI) and focus variable using wavelet. Then, they were classified by recurrent neural networks (RNN). In overcoming the problem of vanishing memory from RNN, was used long short-term memory (LSTM). The results showed that BCI used wavelet, and RNN can drive external devices of non-training data with an accuracy of 79.6%. The experiment gave AdaDelta model is better than the Adam model in terms of accuracy and value losses. Whereas in computational learning time, Adam's model is faster than AdaDelta's model.
Robot Motion Control Using the Emotiv EPOC EEG SystemjournalBEEI
Brain-computer interfaces have been explored for years with the intent of using human thoughts to control mechanical system. By capturing the transmission of signals directly from the human brain or electroencephalogram (EEG), human thoughts can be made as motion commands to the robot. This paper presents a prototype for an electroencephalogram (EEG) based brain-actuated robot control system using mental commands. In this study, Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) method were combined to establish the best model. Dataset containing features of EEG signals were obtained from the subject non-invasively using Emotiv EPOC headset. The best model was then used by Brain-Computer Interface (BCI) to classify the EEG signals into robot motion commands to control the robot directly. The result of the classification gave the average accuracy of 69.06%.
IRJET- Disentangling Brain Activity from EEG Data using Logistic Regression, ...IRJET Journal
This document discusses using machine learning algorithms to analyze EEG data and predict a person's learning capabilities. It extracts features from raw EEG data, including delta, theta, alpha, beta, and gamma waves. It then applies logistic regression, XGBoost, RNN, and decision trees to classify if a student is confused while learning from videos. The highest accuracy was achieved using XGBoost. Overall, the study aims to develop a system to monitor learning using EEG and analyze the correlation between brain activity and learning capability.
This document provides an overview of brain-computer interfaces (BCI), including their applications, monitoring techniques, machine learning role, and challenges. It discusses how BCIs allow direct communication between the brain and external devices using non-invasive or invasive neuroimaging methods like EEG, fMRI, and PET. Popular BCI applications include controlling robots, drones, wheelchairs as well as developing assistive technologies. Machine learning, especially deep learning, plays an important role in processing brain signals for BCI. Key challenges include uncertainty of brain patterns and difficulty collecting reliable neuroimaging data.
Analysis of EEG data Using ICA and Algorithm Development for Energy Comparisonijsrd.com
This Electroencephalogram (EEG) signal analysis very useful in clinical research and brain computer interface application. EEG signal (brain wave) recordings are highly susceptible from artifacts which are originated from the non-cerebral origin of the brain. EEG detection and rejection of artifacts are necessary for acquiring correct information from EEG signal. Emotiv, Epoc headset can record 16 channels from the scalp of the electrode. EEGLAB allows analysis of EEG signal through Event related potential (ERP) analysis, Independent component analysis (ICA), and time/frequency analysis. Independent component analysis (ICA) may be suitable method for detecting artifacts. We analyzed EEG data which are recorded using emotiv epoc in a different situation for a single person. EEG data are preprocessed by EEGLAB and decomposes the data by the ICA. Using statistical method, analyzed the all the dataset and finding the relationship among the dataset. T- Test shows that EEG pattern is unique in a person. EEG data is divided into different frequency band to find the relationship between the dataset. Also develop the algorithm for calculating energy of dataset for each channel. Comparing the energy for each dataset and each channel to find the maximum and minimum value of energy. In higher frequency range (13-100 Hz) dataset D (meditation) contains maximum value of energy for most channels among all datasets.
SRGE Workshop on Intelligent system and Application, 27 Dec. 2017 in the framework of the int. conf of computer science, information systems, and operation research, ISSR, Cairo University
This document presents a new algorithm for automatically detecting driver drowsiness based on electroencephalography (EEG) using Mahalanobis distance. EEG signals are measured by placing electrodes on the driver's head. Two main approaches for detecting drowsiness are analyzing physical changes like head position and measuring physiological changes like brain activity. This algorithm focuses on the second approach using EEG signals, which can accurately track alertness levels second-to-second. It first establishes a model of alert brain activity using multivariate normal distribution of EEG theta and alpha rhythms. Mahalanobis distance is then used to detect drowsiness by measuring deviation from the alert model.
Variants of Support Vector
Machines (SVM) were employed for classification and also
compared the results with Multi-layered Perceptron (MLP).
Empirical results show that both SVM and MLP were suitable
for such motor imagery classifications with the accuracies 85%
and 85.71% respectively. Among all employed feature extraction
techniques wavelet-based methods specifically the energy-
entropy feature set gave promising results for both the classifiers.
EEG based Brain Computer Interface (BCI) establishes a new channel between human brain and the
surrounding environment in order to disseminate instructions to the outside world. It is based on the
recording of temporary EEG changes during different types of motor imagery such as imagination of
different hand movements. The spatial pattern of activated cortical areas during motor imagery is similar
to that of real time executed movement. Time domain features and frequency domain features are extracted
with emphasis on recognizing discriminative features representing EEG trials recorded during imagination
of different hand movements. Then, classification into different hand movements is carried out.
Robot Motion Control Using the Emotiv EPOC EEG SystemjournalBEEI
Brain-computer interfaces have been explored for years with the intent of using human thoughts to control mechanical system. By capturing the transmission of signals directly from the human brain or electroencephalogram (EEG), human thoughts can be made as motion commands to the robot. This paper presents a prototype for an electroencephalogram (EEG) based brain-actuated robot control system using mental commands. In this study, Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) method were combined to establish the best model. Dataset containing features of EEG signals were obtained from the subject non-invasively using Emotiv EPOC headset. The best model was then used by Brain-Computer Interface (BCI) to classify the EEG signals into robot motion commands to control the robot directly. The result of the classification gave the average accuracy of 69.06%.
IRJET- Disentangling Brain Activity from EEG Data using Logistic Regression, ...IRJET Journal
This document discusses using machine learning algorithms to analyze EEG data and predict a person's learning capabilities. It extracts features from raw EEG data, including delta, theta, alpha, beta, and gamma waves. It then applies logistic regression, XGBoost, RNN, and decision trees to classify if a student is confused while learning from videos. The highest accuracy was achieved using XGBoost. Overall, the study aims to develop a system to monitor learning using EEG and analyze the correlation between brain activity and learning capability.
This document provides an overview of brain-computer interfaces (BCI), including their applications, monitoring techniques, machine learning role, and challenges. It discusses how BCIs allow direct communication between the brain and external devices using non-invasive or invasive neuroimaging methods like EEG, fMRI, and PET. Popular BCI applications include controlling robots, drones, wheelchairs as well as developing assistive technologies. Machine learning, especially deep learning, plays an important role in processing brain signals for BCI. Key challenges include uncertainty of brain patterns and difficulty collecting reliable neuroimaging data.
Analysis of EEG data Using ICA and Algorithm Development for Energy Comparisonijsrd.com
This Electroencephalogram (EEG) signal analysis very useful in clinical research and brain computer interface application. EEG signal (brain wave) recordings are highly susceptible from artifacts which are originated from the non-cerebral origin of the brain. EEG detection and rejection of artifacts are necessary for acquiring correct information from EEG signal. Emotiv, Epoc headset can record 16 channels from the scalp of the electrode. EEGLAB allows analysis of EEG signal through Event related potential (ERP) analysis, Independent component analysis (ICA), and time/frequency analysis. Independent component analysis (ICA) may be suitable method for detecting artifacts. We analyzed EEG data which are recorded using emotiv epoc in a different situation for a single person. EEG data are preprocessed by EEGLAB and decomposes the data by the ICA. Using statistical method, analyzed the all the dataset and finding the relationship among the dataset. T- Test shows that EEG pattern is unique in a person. EEG data is divided into different frequency band to find the relationship between the dataset. Also develop the algorithm for calculating energy of dataset for each channel. Comparing the energy for each dataset and each channel to find the maximum and minimum value of energy. In higher frequency range (13-100 Hz) dataset D (meditation) contains maximum value of energy for most channels among all datasets.
SRGE Workshop on Intelligent system and Application, 27 Dec. 2017 in the framework of the int. conf of computer science, information systems, and operation research, ISSR, Cairo University
This document presents a new algorithm for automatically detecting driver drowsiness based on electroencephalography (EEG) using Mahalanobis distance. EEG signals are measured by placing electrodes on the driver's head. Two main approaches for detecting drowsiness are analyzing physical changes like head position and measuring physiological changes like brain activity. This algorithm focuses on the second approach using EEG signals, which can accurately track alertness levels second-to-second. It first establishes a model of alert brain activity using multivariate normal distribution of EEG theta and alpha rhythms. Mahalanobis distance is then used to detect drowsiness by measuring deviation from the alert model.
Variants of Support Vector
Machines (SVM) were employed for classification and also
compared the results with Multi-layered Perceptron (MLP).
Empirical results show that both SVM and MLP were suitable
for such motor imagery classifications with the accuracies 85%
and 85.71% respectively. Among all employed feature extraction
techniques wavelet-based methods specifically the energy-
entropy feature set gave promising results for both the classifiers.
EEG based Brain Computer Interface (BCI) establishes a new channel between human brain and the
surrounding environment in order to disseminate instructions to the outside world. It is based on the
recording of temporary EEG changes during different types of motor imagery such as imagination of
different hand movements. The spatial pattern of activated cortical areas during motor imagery is similar
to that of real time executed movement. Time domain features and frequency domain features are extracted
with emphasis on recognizing discriminative features representing EEG trials recorded during imagination
of different hand movements. Then, classification into different hand movements is carried out.
My Thesis Topic was "Motor Imagery Signal Classification using EEG and ECoG signal for Brain Computer Interface." I have done my undergraduate thesis on the study, comparison and development of newer algorithms and feature sets related to two class classification problem in Motor Imagery Signal Classification using EEG and ECoG signal for Brain Computer Interface under the supervision of Dr. Mohammad Imamul Hassan Bhuiyan, Professor, Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology.
Iaetsd recognition of emg based hand gesturesIaetsd Iaetsd
This document summarizes research on recognizing electromyography (EMG) signals from hand gestures to control prosthetics using artificial neural networks. EMG signals were collected from muscles during two hand gestures. Thirteen features were extracted from the signals and used to train and test several neural networks with different training algorithms. It was found that networks using the Levenberg-Marquardt algorithm achieved the best performance, with over 90% classification accuracy and the fastest training times, making it most suitable for accurate and rapid prosthetic control based on EMG pattern recognition.
This document discusses feature extraction, classification, and prediction techniques applied to EEG data to discriminate between left and right hand movements. It first provides background on EEG signals and preprocessing. It then examines feature extraction in depth, evaluating various features like mean, standard deviation, and Hjorth parameters. Classification algorithms like LDA, KNN, and neural networks are also analyzed and compared. The best results were obtained by combining Hjorth features, achieving 74% accuracy. Future work to improve these techniques is also mentioned.
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.
Implementation and Evaluation of Signal Processing Techniques for EEG based B...Damian Quinn
This document compares two approaches for classifying EEG signals from a brain-computer interface - a multi-layer perceptron neural network with Levenberg-Marquardt learning, and an Adaptive Neuro-Fuzzy Inference System. It analyzes EEG data from a dataset involving motor imagery tasks of left and right hand movement. Features are extracted from the EEG signals and both the neural network and ANFIS are used to classify the signals based on the features. The performance of the two classification approaches are then compared to determine if the hybrid ANFIS method can outperform the established neural network approach.
This paper aims to classify grasp types from electromyography (EMG) data using artificial neural networks. EMG data was collected from six grasps and decomposed into intrinsic mode functions using empirical mode decomposition. Seven features were extracted from the frequency and time domains. Various feature subsets were used to train a neural network classifier, with the best results achieved using all features except variance from the EMG data and the first three intrinsic mode functions. The paper seeks to recognize intended grasps from EMG input data using neural networks in order to improve prosthetic control.
Efficient And Improved Video Steganography using DCT and Neural NetworkIJSRD
As per the demand of modern communication it is important to establish secret communication which is obtain by seganography .Video Steganography is the technique of hiding some covert message inside a video. The addition of this information to the video is not recognizable through the human eye as modify of a pixel color is negligible. In the proposed method Discrete Cosine Transform (DCT) and neural network is used. Input image is divided into blocks and is processed to generate quantization matrix of cover and stego images by using Discrete Cosine Transform (DCT).And using neural network performance of this method can be further improved. The neural network is trained and on the basis of training and segmentation done, neural network provide efficient positions where data can be merge. The performance and efficiency is measured by PSNR and MSE value.
Performance Comparison of Known ICA Algorithms to a Wavelet-ICA MergerCSCJournals
This document summarizes a research paper that compares the performance of different independent component analysis (ICA) algorithms and a new technique called Cycle Spinning Wavelet-ICA Merger (CTICA) for removing artifacts from electroencephalogram (EEG) signals. It finds that CTICA performs as well as other ICA algorithms like FastICA, JADE, and Radical at denoising EEG signals. The document provides background on EEG signals, common artifacts that contaminate EEG signals, existing techniques like ICA and wavelet transforms for removing artifacts, and prior research combining ICA and wavelets. It also describes the two datasets and methodology used to test CTICA's performance.
Classification of EEG Signal for Epileptic Seizure DetectionusingEMD and ELMIJTET Journal
Abstract—This paper proposes the classification of EEG signal for epilepsy diagnosis. Epilepsy is a neurological disorder which occurs due to synchronous neuronal activity in brain. Empirical Mode Decomposition (EMD), Extreme Learning Machine (ELM) are the techniquedelivered in the proposed method.Input EEG signal, which is available in online as Bonn Database is decomposed into five Intrinsic Mode Functions (IMFs) using EMD.Higher Order Statistical moments such as Variance, Skewness and Kurtosis are drawn out as features from the decomposed signals. Extreme Learning Machine is used as a classifier to classify the EEG signals with the taken features, under various categories that include healthy and ictal, interictal and ictal, Non seizure and seizure, healthy, interictal and ictal. The proposed method gives 100%accuracy, 100%sensitivity in discriminating interictal and ictal, non seizure and seizure, healthy and ictal, healthy, interictal and ictal, 100% specificity in classifying healthy and ictal, interictal and ictal and 100% and 99%accuracy in case of discriminating interictal and ictal, non seizure and seizure.
Neural networks of artificial intelligencealldesign
An artificial neural network (ANN) is a machine learning approach that models the human brain. It consists of artificial neurons that are connected in a network. Each neuron receives inputs, performs calculations, and outputs a value. ANNs can be trained to learn patterns from data through examples to perform tasks like classification, prediction, clustering, and association. Common ANN architectures include multilayer perceptrons, convolutional neural networks, and recurrent neural networks.
- To study the behavior and properties of bio-electric signals.
- Develop a system to identify and recognize patterns of signals on a portable computer.
Feature Extraction Techniques and Classification Algorithms for EEG Signals t...Editor IJCATR
This document reviews techniques for extracting features and classifying EEG signals to detect human stress levels. It discusses EEG signals and how they can provide information about mental states. It also reviews common feature extraction methods like DCT and DWT that can preprocess EEG data by transforming it from the time to frequency domain. Classification algorithms like KNN, LDA, and Naive Bayes that can classify EEG data are also examined. The document proposes a system to use a Neurosky Mindwave EEG headset to record raw EEG signals, preprocess them with DWT, and classify stress levels using a combination of classifiers.
This document provides an overview of applications of fuzzy logic in neural networks. It discusses fuzzy neurons as a combination of fuzzy logic and neural networks where the neuron's activation function is replaced with a fuzzy logic operation. Different types of fuzzy neurons are described, including OR, AND, and OR/AND fuzzy neurons. Supervised learning in fuzzy neural networks is also covered. The document concludes with advantages of fuzzy logic systems over traditional neural networks, such as the ability of fuzzy systems to systematically include linguistic knowledge.
This document discusses using artificial neural networks for hand gesture recognition. It introduces gesture recognition and ANNs, describing how ANNs can be used for gesture recognition by being adaptive systems that change structure based on information flow. The document outlines training ANNs using feedforward and backpropagation algorithms in MATLAB for gesture recognition. It also provides steps of the recognition process and discusses advantages like learning without reprogramming and disadvantages like needing training.
Neural networks are modeled after the human brain and are made up of interconnected nodes that mimic neurons. Machine learning uses neural networks to find patterns in data and make predictions. Recent advances in hardware have enabled more powerful neural networks for applications like image recognition, medical diagnosis, business marketing and user interfaces. However, neural networks require large datasets for training and can become unstable on larger problems. Future applications may include using neural networks in consumer products to aid decision making.
Digital Implementation of Artificial Neural Network for Function Approximatio...IOSR Journals
: The soft computing algorithms are being nowadays used for various multi input multi output
complicated non linear control applications. This paper presented the development and implementation of back
propagation of multilayer perceptron architecture developed in FPGA using VHDL. The usage of the FPGA
(Field Programmable Gate Array) for neural network implementation provides flexibility in programmable
systems. For the neural network based instrument prototype in real time application. The conventional specific
VLSI neural chip design suffers the limitation in time and cost. With low precision artificial neural network
design, FPGA have higher speed and smaller size for real time application than the VLSI design. The
challenges are finding an architecture that minimizes the hardware cost, maximizing the performance,
accuracy. The goal of this work is to realize the hardware implementation of neural network using FPGA.
Digital system architecture is presented using Very High Speed Integrated Circuits Hardware Description
Language (VHDL)and is implemented in FPGA chip. MATLAB ANN programming and tools are used for
training the ANN. The trained weights are stored in different RAM, and is implemented in FPGA. The design
was tested on a FPGA demo board
1) A wearable brain cap is presented that can measure EEG signals without requiring electrical contact with the head using integrated contactless electrodes.
2) The cap is made of flexible polymeric material and the contactless electrodes may be obtained using a new electroactive gel that can read the EEG signals.
3) This cap aims to overcome the discomfort of typical EEG caps and electrodes that require electrolytic gel and time-consuming attachment by providing a fully wearable and portable system for brain-computer interface applications.
Artificial Neural Network and its Applicationsshritosh kumar
Abstract
This report is an introduction to Artificial Neural
Networks. The various types of neural networks are
explained and demonstrated, applications of neural
networks like ANNs in medicine are described, and a
detailed historical background is provided. The
connection between the artificial and the real thing is
also investigated and explained. Finally, the
mathematical models involved are presented and
demonstrated.
The document discusses the syllabus for a course on Neural Networks. The mid-term syllabus covers introduction to neural networks, supervised learning including the perceptron and LMS algorithm. The end-term syllabus covers additional topics like backpropagation, unsupervised learning techniques and associative models including Hopfield networks. It also lists some references and applications of neural networks.
SUITABLE MOTHER WAVELET SELECTION FOR EEG SIGNALS ANALYSIS: FREQUENCY BANDS D...sipij
Wavelet transform (WT) is a powerful modern tool for time-frequency analysis of non-stationary signals such as electroencephalogram (EEG). The aim of this study is to choose the best and suitable mother wavelet function (MWT) for analyzing normal, seizure-free and seizured EEG signals. Several MWTs can be used, but the best MWT is the one that conserves the quasi-totality of information of the original signal on wavelet coefficients and gather more EEG rhythms in terms of frequency. In this study, Daubechies, Symlets and Coiflets orthogonal families were used as bsis mother wavelet functions. The percentage rootmeans square difference (PRD), the signal to noise ratio (SNR) and the simulated frequencies as the selection metrics. Simulation results indicate Daubechies wavelet at level 4 (Db4) as the most suitable MWT for EEG frequency bands decomposition.Furthermore, due to the redundancy of the extracted features, linear discriminant analysis (LDA) is applied for feature selection. Scatter plot showed that the selected feature vector represents the amount of changes in frequency distribution and carries most of the discriminative and representative information about their classes. Then, this study can provide a reference for the selection of a suitable MWT and discriminativefeatures.
Multi-channel of electroencephalogram signal in multivariable brain-computer ...IAESIJAI
Brain-computer interface (BCI) usually uses Electroencephalogram (EEG)
signals as an intermediate device to drive external devices directly from the
brain. The development of BCI capabilities is carried out by involving
multivariable EEG signals as movement commands. EEG signals are
recorded using multi-channel, enriching information if it uses the suitable
method and architecture. This research proposed a two-dimensional
convolutional neural networks (CNN) method to recognize multi-channel
EEG signals. The vertical dimension is the channel, while the horizontal is
the signal sequence. Hence, the signal is connected with the information
time series of the same channel and between channels simultaneously. BCI
was arranged with multivariable signals, specifically motor imagery and
emotion. Both variables have different characteristics, and the information is
from different channels. Therefore, it needs multiple CNNs to recognize the
two variables in the EEG signal. The experiment showed that the accuracy
of multiple 2D-CNN increased to 94.62% compared to 85.44% of single 2D
CNN. Multiple 2D-CNN gave accuracy from 82.04% to 94.62% more than
multiple 1D-CNN. 2D-CNN makes the channel extraction perfect into
vectors to maintain the signal sequence. Signal extraction is essential, so the
used Wavelet filter upgraded accuracy from 73.75% to 94.62%.
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.
My Thesis Topic was "Motor Imagery Signal Classification using EEG and ECoG signal for Brain Computer Interface." I have done my undergraduate thesis on the study, comparison and development of newer algorithms and feature sets related to two class classification problem in Motor Imagery Signal Classification using EEG and ECoG signal for Brain Computer Interface under the supervision of Dr. Mohammad Imamul Hassan Bhuiyan, Professor, Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology.
Iaetsd recognition of emg based hand gesturesIaetsd Iaetsd
This document summarizes research on recognizing electromyography (EMG) signals from hand gestures to control prosthetics using artificial neural networks. EMG signals were collected from muscles during two hand gestures. Thirteen features were extracted from the signals and used to train and test several neural networks with different training algorithms. It was found that networks using the Levenberg-Marquardt algorithm achieved the best performance, with over 90% classification accuracy and the fastest training times, making it most suitable for accurate and rapid prosthetic control based on EMG pattern recognition.
This document discusses feature extraction, classification, and prediction techniques applied to EEG data to discriminate between left and right hand movements. It first provides background on EEG signals and preprocessing. It then examines feature extraction in depth, evaluating various features like mean, standard deviation, and Hjorth parameters. Classification algorithms like LDA, KNN, and neural networks are also analyzed and compared. The best results were obtained by combining Hjorth features, achieving 74% accuracy. Future work to improve these techniques is also mentioned.
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.
Implementation and Evaluation of Signal Processing Techniques for EEG based B...Damian Quinn
This document compares two approaches for classifying EEG signals from a brain-computer interface - a multi-layer perceptron neural network with Levenberg-Marquardt learning, and an Adaptive Neuro-Fuzzy Inference System. It analyzes EEG data from a dataset involving motor imagery tasks of left and right hand movement. Features are extracted from the EEG signals and both the neural network and ANFIS are used to classify the signals based on the features. The performance of the two classification approaches are then compared to determine if the hybrid ANFIS method can outperform the established neural network approach.
This paper aims to classify grasp types from electromyography (EMG) data using artificial neural networks. EMG data was collected from six grasps and decomposed into intrinsic mode functions using empirical mode decomposition. Seven features were extracted from the frequency and time domains. Various feature subsets were used to train a neural network classifier, with the best results achieved using all features except variance from the EMG data and the first three intrinsic mode functions. The paper seeks to recognize intended grasps from EMG input data using neural networks in order to improve prosthetic control.
Efficient And Improved Video Steganography using DCT and Neural NetworkIJSRD
As per the demand of modern communication it is important to establish secret communication which is obtain by seganography .Video Steganography is the technique of hiding some covert message inside a video. The addition of this information to the video is not recognizable through the human eye as modify of a pixel color is negligible. In the proposed method Discrete Cosine Transform (DCT) and neural network is used. Input image is divided into blocks and is processed to generate quantization matrix of cover and stego images by using Discrete Cosine Transform (DCT).And using neural network performance of this method can be further improved. The neural network is trained and on the basis of training and segmentation done, neural network provide efficient positions where data can be merge. The performance and efficiency is measured by PSNR and MSE value.
Performance Comparison of Known ICA Algorithms to a Wavelet-ICA MergerCSCJournals
This document summarizes a research paper that compares the performance of different independent component analysis (ICA) algorithms and a new technique called Cycle Spinning Wavelet-ICA Merger (CTICA) for removing artifacts from electroencephalogram (EEG) signals. It finds that CTICA performs as well as other ICA algorithms like FastICA, JADE, and Radical at denoising EEG signals. The document provides background on EEG signals, common artifacts that contaminate EEG signals, existing techniques like ICA and wavelet transforms for removing artifacts, and prior research combining ICA and wavelets. It also describes the two datasets and methodology used to test CTICA's performance.
Classification of EEG Signal for Epileptic Seizure DetectionusingEMD and ELMIJTET Journal
Abstract—This paper proposes the classification of EEG signal for epilepsy diagnosis. Epilepsy is a neurological disorder which occurs due to synchronous neuronal activity in brain. Empirical Mode Decomposition (EMD), Extreme Learning Machine (ELM) are the techniquedelivered in the proposed method.Input EEG signal, which is available in online as Bonn Database is decomposed into five Intrinsic Mode Functions (IMFs) using EMD.Higher Order Statistical moments such as Variance, Skewness and Kurtosis are drawn out as features from the decomposed signals. Extreme Learning Machine is used as a classifier to classify the EEG signals with the taken features, under various categories that include healthy and ictal, interictal and ictal, Non seizure and seizure, healthy, interictal and ictal. The proposed method gives 100%accuracy, 100%sensitivity in discriminating interictal and ictal, non seizure and seizure, healthy and ictal, healthy, interictal and ictal, 100% specificity in classifying healthy and ictal, interictal and ictal and 100% and 99%accuracy in case of discriminating interictal and ictal, non seizure and seizure.
Neural networks of artificial intelligencealldesign
An artificial neural network (ANN) is a machine learning approach that models the human brain. It consists of artificial neurons that are connected in a network. Each neuron receives inputs, performs calculations, and outputs a value. ANNs can be trained to learn patterns from data through examples to perform tasks like classification, prediction, clustering, and association. Common ANN architectures include multilayer perceptrons, convolutional neural networks, and recurrent neural networks.
- To study the behavior and properties of bio-electric signals.
- Develop a system to identify and recognize patterns of signals on a portable computer.
Feature Extraction Techniques and Classification Algorithms for EEG Signals t...Editor IJCATR
This document reviews techniques for extracting features and classifying EEG signals to detect human stress levels. It discusses EEG signals and how they can provide information about mental states. It also reviews common feature extraction methods like DCT and DWT that can preprocess EEG data by transforming it from the time to frequency domain. Classification algorithms like KNN, LDA, and Naive Bayes that can classify EEG data are also examined. The document proposes a system to use a Neurosky Mindwave EEG headset to record raw EEG signals, preprocess them with DWT, and classify stress levels using a combination of classifiers.
This document provides an overview of applications of fuzzy logic in neural networks. It discusses fuzzy neurons as a combination of fuzzy logic and neural networks where the neuron's activation function is replaced with a fuzzy logic operation. Different types of fuzzy neurons are described, including OR, AND, and OR/AND fuzzy neurons. Supervised learning in fuzzy neural networks is also covered. The document concludes with advantages of fuzzy logic systems over traditional neural networks, such as the ability of fuzzy systems to systematically include linguistic knowledge.
This document discusses using artificial neural networks for hand gesture recognition. It introduces gesture recognition and ANNs, describing how ANNs can be used for gesture recognition by being adaptive systems that change structure based on information flow. The document outlines training ANNs using feedforward and backpropagation algorithms in MATLAB for gesture recognition. It also provides steps of the recognition process and discusses advantages like learning without reprogramming and disadvantages like needing training.
Neural networks are modeled after the human brain and are made up of interconnected nodes that mimic neurons. Machine learning uses neural networks to find patterns in data and make predictions. Recent advances in hardware have enabled more powerful neural networks for applications like image recognition, medical diagnosis, business marketing and user interfaces. However, neural networks require large datasets for training and can become unstable on larger problems. Future applications may include using neural networks in consumer products to aid decision making.
Digital Implementation of Artificial Neural Network for Function Approximatio...IOSR Journals
: The soft computing algorithms are being nowadays used for various multi input multi output
complicated non linear control applications. This paper presented the development and implementation of back
propagation of multilayer perceptron architecture developed in FPGA using VHDL. The usage of the FPGA
(Field Programmable Gate Array) for neural network implementation provides flexibility in programmable
systems. For the neural network based instrument prototype in real time application. The conventional specific
VLSI neural chip design suffers the limitation in time and cost. With low precision artificial neural network
design, FPGA have higher speed and smaller size for real time application than the VLSI design. The
challenges are finding an architecture that minimizes the hardware cost, maximizing the performance,
accuracy. The goal of this work is to realize the hardware implementation of neural network using FPGA.
Digital system architecture is presented using Very High Speed Integrated Circuits Hardware Description
Language (VHDL)and is implemented in FPGA chip. MATLAB ANN programming and tools are used for
training the ANN. The trained weights are stored in different RAM, and is implemented in FPGA. The design
was tested on a FPGA demo board
1) A wearable brain cap is presented that can measure EEG signals without requiring electrical contact with the head using integrated contactless electrodes.
2) The cap is made of flexible polymeric material and the contactless electrodes may be obtained using a new electroactive gel that can read the EEG signals.
3) This cap aims to overcome the discomfort of typical EEG caps and electrodes that require electrolytic gel and time-consuming attachment by providing a fully wearable and portable system for brain-computer interface applications.
Artificial Neural Network and its Applicationsshritosh kumar
Abstract
This report is an introduction to Artificial Neural
Networks. The various types of neural networks are
explained and demonstrated, applications of neural
networks like ANNs in medicine are described, and a
detailed historical background is provided. The
connection between the artificial and the real thing is
also investigated and explained. Finally, the
mathematical models involved are presented and
demonstrated.
The document discusses the syllabus for a course on Neural Networks. The mid-term syllabus covers introduction to neural networks, supervised learning including the perceptron and LMS algorithm. The end-term syllabus covers additional topics like backpropagation, unsupervised learning techniques and associative models including Hopfield networks. It also lists some references and applications of neural networks.
SUITABLE MOTHER WAVELET SELECTION FOR EEG SIGNALS ANALYSIS: FREQUENCY BANDS D...sipij
Wavelet transform (WT) is a powerful modern tool for time-frequency analysis of non-stationary signals such as electroencephalogram (EEG). The aim of this study is to choose the best and suitable mother wavelet function (MWT) for analyzing normal, seizure-free and seizured EEG signals. Several MWTs can be used, but the best MWT is the one that conserves the quasi-totality of information of the original signal on wavelet coefficients and gather more EEG rhythms in terms of frequency. In this study, Daubechies, Symlets and Coiflets orthogonal families were used as bsis mother wavelet functions. The percentage rootmeans square difference (PRD), the signal to noise ratio (SNR) and the simulated frequencies as the selection metrics. Simulation results indicate Daubechies wavelet at level 4 (Db4) as the most suitable MWT for EEG frequency bands decomposition.Furthermore, due to the redundancy of the extracted features, linear discriminant analysis (LDA) is applied for feature selection. Scatter plot showed that the selected feature vector represents the amount of changes in frequency distribution and carries most of the discriminative and representative information about their classes. Then, this study can provide a reference for the selection of a suitable MWT and discriminativefeatures.
Multi-channel of electroencephalogram signal in multivariable brain-computer ...IAESIJAI
Brain-computer interface (BCI) usually uses Electroencephalogram (EEG)
signals as an intermediate device to drive external devices directly from the
brain. The development of BCI capabilities is carried out by involving
multivariable EEG signals as movement commands. EEG signals are
recorded using multi-channel, enriching information if it uses the suitable
method and architecture. This research proposed a two-dimensional
convolutional neural networks (CNN) method to recognize multi-channel
EEG signals. The vertical dimension is the channel, while the horizontal is
the signal sequence. Hence, the signal is connected with the information
time series of the same channel and between channels simultaneously. BCI
was arranged with multivariable signals, specifically motor imagery and
emotion. Both variables have different characteristics, and the information is
from different channels. Therefore, it needs multiple CNNs to recognize the
two variables in the EEG signal. The experiment showed that the accuracy
of multiple 2D-CNN increased to 94.62% compared to 85.44% of single 2D
CNN. Multiple 2D-CNN gave accuracy from 82.04% to 94.62% more than
multiple 1D-CNN. 2D-CNN makes the channel extraction perfect into
vectors to maintain the signal sequence. Signal extraction is essential, so the
used Wavelet filter upgraded accuracy from 73.75% to 94.62%.
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.
Brain computer interface based smart keyboard using neurosky mindwave headsetTELKOMNIKA JOURNAL
This document describes a brain-computer interface (BCI) system that uses a Neurosky Mindwave headset to detect brain signals and control a virtual keyboard. The system collects EEG data in real-time from the headset, analyzes it to extract attention and blink features, and uses those features to scan and select characters on the virtual keyboard. An experiment tested the system on 5 users over multiple sessions and found encouraging results, with users achieving text entry speeds of 1.55-1.8 words per minute, faster than some other BCI keyboard studies.
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/
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.
EEG SIGNAL IDENTIFICATION USING SINGLE-LAYER NEURAL NETWORKIJCI JOURNAL
EEG signal analysis is applied in various fields such as medicine, communication and control. To control based on EEG signals achieved good result, the system must identify effectively EEG signals. In this paper,
a novel approach proposes the EEG signal identification based on image with the EEG signal processing via Wavelet transform and the identification via single-layer neural network. The system model is designed and evaluated with the dataset of 21,000 samples. The accuracy rate can obtain 91.15%.
he main idea of the current work is to use a wireless Electroencephalography (EEG) headset as a remote control for the mouse cursor of a personal computer. The proposed system uses EEG signals as a communication link between brains and computers. Signal records obtained from the PhysioNet EEG dataset were analyzed using the Coif lets wavelets and many features were extracted using different amplitude estimators for the wavelet coefficients. The extracted features were inputted into machine learning algorithms to generate the decision rules required for our application. The suggested real time implementation of the system was tested and very good performance was achieved. This system could be helpful for disabled people as they can control computer applications via the imagination of fists and feet movements in addition to closing eyes for a short period of time
The locomotive disabled people and elderly people cannot control the wheelchair manually. The key
objective of this paper is to help the locomotive disabled and old people to easily manoeuvre without any social
aid through a brainwave-controlled wheelchair. There are various types of wheelchair available in the market
such as Voice controlled wheelchair, Joystick control wheelchair, Smart phone controlled wheelchair, Eye
controlled wheelchair, Mechanical wheelchair. These wheelchairs hold certain limitations for e.g. if the user is
dumb; user cannot access voice controlled wheelchair, etc. Brain-computer interface (BCI) is a new method used
to interface between the human mind and a digital signal processor. An Electroencephalogram (EEG) based BCI
is connected with an artificial reality system to control the movement and direction of a wheelchair. This paper
proposes brainwave controlled wheelchair, which uses the captured EEG signals from the brain. This EEG
signals are then passed to Arduino. It converts into control signals which will in turn help to move the wheelchair
in different direction.
Neural signal processing by mustafa rasheed & zeena saadon & walaa kahtan 2015Mustafa AL-Timemmie
This document outlines chapters in a thesis on neural signal processing techniques. Chapter 1 introduces neural signals and processing, including neural encoding and decoding. Chapter 2 discusses EEG signal processing, including brain waves, EEG recording techniques, amplifiers, filters, and applications like brain-computer interfaces. Chapter 3 covers neural signal processing using different filter types for analysis, including Hanning, Flattop, Blackman-Harris and Kaiser filters. Figures and lists are provided to support the content.
Overview of Machine Learning and Deep Learning Methods in Brain Computer Inte...IJCSES Journal
Research under the field of Brain Computer Interfaces is adapting various Machine Learning and Deep
Learning techniques in recent times. With the advent of modern BCI, the data generated by various devices
is now capable of detecting brain signals more accurately. This paper gives an overview of all the steps
involved in the process of applying Machine Learning as well as Deep Learning methods from Data
Acquisition to application of algorithms. It aims to study techniques currently employed to extract data,
features from brain data, different algorithms employed to draw insights from the extracted features, and
how it can be used in various BCI applications. By this study, I aim to put forward current Machine
Learning and Deep Learning Trends in the field of BCI.
Modelling and Analysis of Brainwaves for Real World InteractionPavan Kumar
This document summarizes a research paper that models and analyzes brain waves for real-world interaction. It describes extracting brain waves using EEG, simulating the signal processing circuitry, and processing the signals using MATLAB. The research demonstrated controlling the speed of a robot based on a person's brain waves and a predefined threshold. This shows the potential for using brain-computer interfaces to control devices.
A Review on Motor Imagery Signal Classification for BCICSCJournals
Brain computer interface (BCI) is an evolving technology from past few years. Scalp recorded electroencephalogram (EEG) based BCI technologies are widely used because of safety, low cost and portability. Millions of people are suffering from stroke worldwide and become disabled. They may lose communication control and fall into the locked in state (LIS) or completely locked in state (CLIS). Motor imagery brain computer interface (MI-BCI) can provide non-muscular channel for communication to those who are suffering from neuronal disorders, only by imagination of different motor tasks e.g. left-right hand and foot movement imagination. EEG signals are time varying, non-stationary random signals which are changes in person to person and occurs at different frequencies. For real time application of such a system efficient classification of motor tasks is required. The biggest challenge in MI-BCI system design is extraction of robust, informative and discriminative features which can be converted into device commands. The main application of MI-BCI is neurorehabilitation and control of wheelchair or robotic limbs. The objective of this paper is to give brief information about different stages of EEG based MI-BCI system. It also includes the review on motor imagery signal classification.
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
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.
Wavelet Based Feature Extraction Scheme Of Eeg Waveformshan pri
This document presents a project on wavelet based feature extraction of electroencephalography (EEG) signals. It discusses using wavelet transforms as an alternative to discrete Fourier transforms for feature extraction from EEG data. The objectives are to improve quality of life for those with disabilities through neuroprosthetics applications of brain-computer interfaces. Wavelet transforms provide advantages over short-time Fourier transforms like multi-resolution analysis and the ability to analyze non-stationary signals. The document outlines the methodology, which includes EEG signal acquisition, wavelet decomposition, coefficient computation, and signal reconstruction in MATLAB.
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.
Technology Development for Unblessed people using BCI: A SurveyMandeep Kaur
This document summarizes research on brain-computer interface (BCI) systems that assist people with disabilities. It first reviews various BCI systems developed between 2000-2009 that use electroencephalography (EEG) signals to help people with conditions like paralysis. It then discusses applications of BCI for people with disabilities, including using mental commands to control assistive devices. Finally, it outlines the general components of a BCI system, including EEG signal acquisition, processing, feature extraction, classification, and applications. The overall purpose is to survey progress in developing BCIs to improve the lives of people with disabilities.
This document summarizes an approach to embedding a human brain with smart devices using depreciated brain-computer interface (BCI) technology. It discusses how BCI systems work by acquiring EEG signals from the brain, preprocessing the signals, classifying them, and using them to control external applications. Specifically, it proposes controlling a tablet through a 1-channel EEG amplifier and non-invasive electrode placement. The document outlines the basic components and applications of BCI systems and describes implementing a basic prototype to test controlling a media player on a tablet using EEG signals processed in MATLAB.
Similar to Brain-computer interface of focus and motor imagery using wavelet and recurrent neural networks (20)
Amazon products reviews classification based on machine learning, deep learni...TELKOMNIKA JOURNAL
In recent times, the trend of online shopping through e-commerce stores and websites has grown to a huge extent. Whenever a product is purchased on an e-commerce platform, people leave their reviews about the product. These reviews are very helpful for the store owners and the product’s manufacturers for the betterment of their work process as well as product quality. An automated system is proposed in this work that operates on two datasets D1 and D2 obtained from Amazon. After certain preprocessing steps, N-gram and word embedding-based features are extracted using term frequency-inverse document frequency (TF-IDF), bag of words (BoW) and global vectors (GloVe), and Word2vec, respectively. Four machine learning (ML) models support vector machines (SVM), logistic regression (RF), logistic regression (LR), multinomial Naïve Bayes (MNB), two deep learning (DL) models convolutional neural network (CNN), long-short term memory (LSTM), and standalone bidirectional encoder representations (BERT) are used to classify reviews as either positive or negative. The results obtained by the standard ML, DL models and BERT are evaluated using certain performance evaluation measures. BERT turns out to be the best-performing model in the case of D1 with an accuracy of 90% on features derived by word embedding models while the CNN provides the best accuracy of 97% upon word embedding features in the case of D2. The proposed model shows better overall performance on D2 as compared to D1.
Design, simulation, and analysis of microstrip patch antenna for wireless app...TELKOMNIKA JOURNAL
In this study, a microstrip patch antenna that works at 3.6 GHz was built and tested to see how well it works. In this work, Rogers RT/Duroid 5880 has been used as the substrate material, with a dielectric permittivity of 2.2 and a thickness of 0.3451 mm; it serves as the base for the examined antenna. The computer simulation technology (CST) studio suite is utilized to show the recommended antenna design. The goal of this study was to get a more extensive transmission capacity, a lower voltage standing wave ratio (VSWR), and a lower return loss, but the main goal was to get a higher gain, directivity, and efficiency. After simulation, the return loss, gain, directivity, bandwidth, and efficiency of the supplied antenna are found to be -17.626 dB, 9.671 dBi, 9.924 dBi, 0.2 GHz, and 97.45%, respectively. Besides, the recreation uncovered that the transfer speed side-lobe level at phi was much better than those of the earlier works, at -28.8 dB, respectively. Thus, it makes a solid contender for remote innovation and more robust communication.
Design and simulation an optimal enhanced PI controller for congestion avoida...TELKOMNIKA JOURNAL
This document describes using a snake optimization algorithm to tune the gains of an enhanced proportional-integral controller for congestion avoidance in a TCP/AQM system. The controller aims to maintain a stable and desired queue size without noise or transmission problems. A linearized model of the TCP/AQM system is presented. An enhanced PI controller combining nonlinear gain and original PI gains is proposed. The snake optimization algorithm is then used to tune the parameters of the enhanced PI controller to achieve optimal system performance and response. Simulation results are discussed showing the proposed controller provides a stable and robust behavior for congestion control.
Improving the detection of intrusion in vehicular ad-hoc networks with modifi...TELKOMNIKA JOURNAL
Vehicular ad-hoc networks (VANETs) are wireless-equipped vehicles that form networks along the road. The security of this network has been a major challenge. The identity-based cryptosystem (IBC) previously used to secure the networks suffers from membership authentication security features. This paper focuses on improving the detection of intruders in VANETs with a modified identity-based cryptosystem (MIBC). The MIBC is developed using a non-singular elliptic curve with Lagrange interpolation. The public key of vehicles and roadside units on the network are derived from number plates and location identification numbers, respectively. Pseudo-identities are used to mask the real identity of users to preserve their privacy. The membership authentication mechanism ensures that only valid and authenticated members of the network are allowed to join the network. The performance of the MIBC is evaluated using intrusion detection ratio (IDR) and computation time (CT) and then validated with the existing IBC. The result obtained shows that the MIBC recorded an IDR of 99.3% against 94.3% obtained for the existing identity-based cryptosystem (EIBC) for 140 unregistered vehicles attempting to intrude on the network. The MIBC shows lower CT values of 1.17 ms against 1.70 ms for EIBC. The MIBC can be used to improve the security of VANETs.
Conceptual model of internet banking adoption with perceived risk and trust f...TELKOMNIKA JOURNAL
Understanding the primary factors of internet banking (IB) acceptance is critical for both banks and users; nevertheless, our knowledge of the role of users’ perceived risk and trust in IB adoption is limited. As a result, we develop a conceptual model by incorporating perceived risk and trust into the technology acceptance model (TAM) theory toward the IB. The proper research emphasized that the most essential component in explaining IB adoption behavior is behavioral intention to use IB adoption. TAM is helpful for figuring out how elements that affect IB adoption are connected to one another. According to previous literature on IB and the use of such technology in Iraq, one has to choose a theoretical foundation that may justify the acceptance of IB from the customer’s perspective. The conceptual model was therefore constructed using the TAM as a foundation. Furthermore, perceived risk and trust were added to the TAM dimensions as external factors. The key objective of this work was to extend the TAM to construct a conceptual model for IB adoption and to get sufficient theoretical support from the existing literature for the essential elements and their relationships in order to unearth new insights about factors responsible for IB adoption.
Efficient combined fuzzy logic and LMS algorithm for smart antennaTELKOMNIKA JOURNAL
The smart antennas are broadly used in wireless communication. The least mean square (LMS) algorithm is a procedure that is concerned in controlling the smart antenna pattern to accommodate specified requirements such as steering the beam toward the desired signal, in addition to placing the deep nulls in the direction of unwanted signals. The conventional LMS (C-LMS) has some drawbacks like slow convergence speed besides high steady state fluctuation error. To overcome these shortcomings, the present paper adopts an adaptive fuzzy control step size least mean square (FC-LMS) algorithm to adjust its step size. Computer simulation outcomes illustrate that the given model has fast convergence rate as well as low mean square error steady state.
Design and implementation of a LoRa-based system for warning of forest fireTELKOMNIKA JOURNAL
This paper presents the design and implementation of a forest fire monitoring and warning system based on long range (LoRa) technology, a novel ultra-low power consumption and long-range wireless communication technology for remote sensing applications. The proposed system includes a wireless sensor network that records environmental parameters such as temperature, humidity, wind speed, and carbon dioxide (CO2) concentration in the air, as well as taking infrared photos.The data collected at each sensor node will be transmitted to the gateway via LoRa wireless transmission. Data will be collected, processed, and uploaded to a cloud database at the gateway. An Android smartphone application that allows anyone to easily view the recorded data has been developed. When a fire is detected, the system will sound a siren and send a warning message to the responsible personnel, instructing them to take appropriate action. Experiments in Tram Chim Park, Vietnam, have been conducted to verify and evaluate the operation of the system.
Wavelet-based sensing technique in cognitive radio networkTELKOMNIKA JOURNAL
Cognitive radio is a smart radio that can change its transmitter parameter based on interaction with the environment in which it operates. The demand for frequency spectrum is growing due to a big data issue as many Internet of Things (IoT) devices are in the network. Based on previous research, most frequency spectrum was used, but some spectrums were not used, called spectrum hole. Energy detection is one of the spectrum sensing methods that has been frequently used since it is easy to use and does not require license users to have any prior signal understanding. But this technique is incapable of detecting at low signal-to-noise ratio (SNR) levels. Therefore, the wavelet-based sensing is proposed to overcome this issue and detect spectrum holes. The main objective of this work is to evaluate the performance of wavelet-based sensing and compare it with the energy detection technique. The findings show that the percentage of detection in wavelet-based sensing is 83% higher than energy detection performance. This result indicates that the wavelet-based sensing has higher precision in detection and the interference towards primary user can be decreased.
A novel compact dual-band bandstop filter with enhanced rejection bandsTELKOMNIKA JOURNAL
In this paper, we present the design of a new wide dual-band bandstop filter (DBBSF) using nonuniform transmission lines. The method used to design this filter is to replace conventional uniform transmission lines with nonuniform lines governed by a truncated Fourier series. Based on how impedances are profiled in the proposed DBBSF structure, the fractional bandwidths of the two 10 dB-down rejection bands are widened to 39.72% and 52.63%, respectively, and the physical size has been reduced compared to that of the filter with the uniform transmission lines. The results of the electromagnetic (EM) simulation support the obtained analytical response and show an improved frequency behavior.
Deep learning approach to DDoS attack with imbalanced data at the application...TELKOMNIKA JOURNAL
A distributed denial of service (DDoS) attack is where one or more computers attack or target a server computer, by flooding internet traffic to the server. As a result, the server cannot be accessed by legitimate users. A result of this attack causes enormous losses for a company because it can reduce the level of user trust, and reduce the company’s reputation to lose customers due to downtime. One of the services at the application layer that can be accessed by users is a web-based lightweight directory access protocol (LDAP) service that can provide safe and easy services to access directory applications. We used a deep learning approach to detect DDoS attacks on the CICDDoS 2019 dataset on a complex computer network at the application layer to get fast and accurate results for dealing with unbalanced data. Based on the results obtained, it is observed that DDoS attack detection using a deep learning approach on imbalanced data performs better when implemented using synthetic minority oversampling technique (SMOTE) method for binary classes. On the other hand, the proposed deep learning approach performs better for detecting DDoS attacks in multiclass when implemented using the adaptive synthetic (ADASYN) method.
The appearance of uncertainties and disturbances often effects the characteristics of either linear or nonlinear systems. Plus, the stabilization process may be deteriorated thus incurring a catastrophic effect to the system performance. As such, this manuscript addresses the concept of matching condition for the systems that are suffering from miss-match uncertainties and exogeneous disturbances. The perturbation towards the system at hand is assumed to be known and unbounded. To reach this outcome, uncertainties and their classifications are reviewed thoroughly. The structural matching condition is proposed and tabulated in the proposition 1. Two types of mathematical expressions are presented to distinguish the system with matched uncertainty and the system with miss-matched uncertainty. Lastly, two-dimensional numerical expressions are provided to practice the proposed proposition. The outcome shows that matching condition has the ability to change the system to a design-friendly model for asymptotic stabilization.
Implementation of FinFET technology based low power 4×4 Wallace tree multipli...TELKOMNIKA JOURNAL
Many systems, including digital signal processors, finite impulse response (FIR) filters, application-specific integrated circuits, and microprocessors, use multipliers. The demand for low power multipliers is gradually rising day by day in the current technological trend. In this study, we describe a 4×4 Wallace multiplier based on a carry select adder (CSA) that uses less power and has a better power delay product than existing multipliers. HSPICE tool at 16 nm technology is used to simulate the results. In comparison to the traditional CSA-based multiplier, which has a power consumption of 1.7 µW and power delay product (PDP) of 57.3 fJ, the results demonstrate that the Wallace multiplier design employing CSA with first zero finding logic (FZF) logic has the lowest power consumption of 1.4 µW and PDP of 27.5 fJ.
Evaluation of the weighted-overlap add model with massive MIMO in a 5G systemTELKOMNIKA JOURNAL
The flaw in 5G orthogonal frequency division multiplexing (OFDM) becomes apparent in high-speed situations. Because the doppler effect causes frequency shifts, the orthogonality of OFDM subcarriers is broken, lowering both their bit error rate (BER) and throughput output. As part of this research, we use a novel design that combines massive multiple input multiple output (MIMO) and weighted overlap and add (WOLA) to improve the performance of 5G systems. To determine which design is superior, throughput and BER are calculated for both the proposed design and OFDM. The results of the improved system show a massive improvement in performance ver the conventional system and significant improvements with massive MIMO, including the best throughput and BER. When compared to conventional systems, the improved system has a throughput that is around 22% higher and the best performance in terms of BER, but it still has around 25% less error than OFDM.
Reflector antenna design in different frequencies using frequency selective s...TELKOMNIKA JOURNAL
In this study, it is aimed to obtain two different asymmetric radiation patterns obtained from antennas in the shape of the cross-section of a parabolic reflector (fan blade type antennas) and antennas with cosecant-square radiation characteristics at two different frequencies from a single antenna. For this purpose, firstly, a fan blade type antenna design will be made, and then the reflective surface of this antenna will be completed to the shape of the reflective surface of the antenna with the cosecant-square radiation characteristic with the frequency selective surface designed to provide the characteristics suitable for the purpose. The frequency selective surface designed and it provides the perfect transmission as possible at 4 GHz operating frequency, while it will act as a band-quenching filter for electromagnetic waves at 5 GHz operating frequency and will be a reflective surface. Thanks to this frequency selective surface to be used as a reflective surface in the antenna, a fan blade type radiation characteristic at 4 GHz operating frequency will be obtained, while a cosecant-square radiation characteristic at 5 GHz operating frequency will be obtained.
Reagentless iron detection in water based on unclad fiber optical sensorTELKOMNIKA JOURNAL
A simple and low-cost fiber based optical sensor for iron detection is demonstrated in this paper. The sensor head consist of an unclad optical fiber with the unclad length of 1 cm and it has a straight structure. Results obtained shows a linear relationship between the output light intensity and iron concentration, illustrating the functionality of this iron optical sensor. Based on the experimental results, the sensitivity and linearity are achieved at 0.0328/ppm and 0.9824 respectively at the wavelength of 690 nm. With the same wavelength, other performance parameters are also studied. Resolution and limit of detection (LOD) are found to be 0.3049 ppm and 0.0755 ppm correspondingly. This iron sensor is advantageous in that it does not require any reagent for detection, enabling it to be simpler and cost-effective in the implementation of the iron sensing.
Impact of CuS counter electrode calcination temperature on quantum dot sensit...TELKOMNIKA JOURNAL
In place of the commercial Pt electrode used in quantum sensitized solar cells, the low-cost CuS cathode is created using electrophoresis. High resolution scanning electron microscopy and X-ray diffraction were used to analyze the structure and morphology of structural cubic samples with diameters ranging from 40 nm to 200 nm. The conversion efficiency of solar cells is significantly impacted by the calcination temperatures of cathodes at 100 °C, 120 °C, 150 °C, and 180 °C under vacuum. The fluorine doped tin oxide (FTO)/CuS cathode electrode reached a maximum efficiency of 3.89% when it was calcined at 120 °C. Compared to other temperature combinations, CuS nanoparticles crystallize at 120 °C, which lowers resistance while increasing electron lifetime.
In place of the commercial Pt electrode used in quantum sensitized solar cells, the low-cost CuS cathode is created using electrophoresis. High resolution scanning electron microscopy and X-ray diffraction were used to analyze the structure and morphology of structural cubic samples with diameters ranging from 40 nm to 200 nm. The conversion efficiency of solar cells is significantly impacted by the calcination temperatures of cathodes at 100 °C, 120 °C, 150 °C, and 180 °C under vacuum. The fluorine doped tin oxide (FTO)/CuS cathode electrode reached a maximum efficiency of 3.89% when it was calcined at 120 °C. Compared to other temperature combinations, CuS nanoparticles crystallize at 120 °C, which lowers resistance while increasing electron lifetime.
A progressive learning for structural tolerance online sequential extreme lea...TELKOMNIKA JOURNAL
This article discusses the progressive learning for structural tolerance online sequential extreme learning machine (PSTOS-ELM). PSTOS-ELM can save robust accuracy while updating the new data and the new class data on the online training situation. The robustness accuracy arises from using the householder block exact QR decomposition recursive least squares (HBQRD-RLS) of the PSTOS-ELM. This method is suitable for applications that have data streaming and often have new class data. Our experiment compares the PSTOS-ELM accuracy and accuracy robustness while data is updating with the batch-extreme learning machine (ELM) and structural tolerance online sequential extreme learning machine (STOS-ELM) that both must retrain the data in a new class data case. The experimental results show that PSTOS-ELM has accuracy and robustness comparable to ELM and STOS-ELM while also can update new class data immediately.
Adaptive segmentation algorithm based on level set model in medical imagingTELKOMNIKA JOURNAL
For image segmentation, level set models are frequently employed. It offer best solution to overcome the main limitations of deformable parametric models. However, the challenge when applying those models in medical images stills deal with removing blurs in image edges which directly affects the edge indicator function, leads to not adaptively segmenting images and causes a wrong analysis of pathologies wich prevents to conclude a correct diagnosis. To overcome such issues, an effective process is suggested by simultaneously modelling and solving systems’ two-dimensional partial differential equations (PDE). The first PDE equation allows restoration using Euler’s equation similar to an anisotropic smoothing based on a regularized Perona and Malik filter that eliminates noise while preserving edge information in accordance with detected contours in the second equation that segments the image based on the first equation solutions. This approach allows developing a new algorithm which overcome the studied model drawbacks. Results of the proposed method give clear segments that can be applied to any application. Experiments on many medical images in particular blurry images with high information losses, demonstrate that the developed approach produces superior segmentation results in terms of quantity and quality compared to other models already presented in previeous works.
Automatic channel selection using shuffled frog leaping algorithm for EEG bas...TELKOMNIKA JOURNAL
Drug addiction is a complex neurobiological disorder that necessitates comprehensive treatment of both the body and mind. It is categorized as a brain disorder due to its impact on the brain. Various methods such as electroencephalography (EEG), functional magnetic resonance imaging (FMRI), and magnetoencephalography (MEG) can capture brain activities and structures. EEG signals provide valuable insights into neurological disorders, including drug addiction. Accurate classification of drug addiction from EEG signals relies on appropriate features and channel selection. Choosing the right EEG channels is essential to reduce computational costs and mitigate the risk of overfitting associated with using all available channels. To address the challenge of optimal channel selection in addiction detection from EEG signals, this work employs the shuffled frog leaping algorithm (SFLA). SFLA facilitates the selection of appropriate channels, leading to improved accuracy. Wavelet features extracted from the selected input channel signals are then analyzed using various machine learning classifiers to detect addiction. Experimental results indicate that after selecting features from the appropriate channels, classification accuracy significantly increased across all classifiers. Particularly, the multi-layer perceptron (MLP) classifier combined with SFLA demonstrated a remarkable accuracy improvement of 15.78% while reducing time complexity.
ResNet-n/DR: Automated diagnosis of diabetic retinopathy using a residual neu...TELKOMNIKA JOURNAL
Diabetic retinopathy (DR) is a progressive eye disease associated with diabetes, resulting in blindness or blurred vision. The risk of vision loss was dramatically decreased with early diagnosis and treatment. Doctors diagnose DR by examining the fundus retinal images to develop lesions associated with the disease. However, this diagnosis is a tedious and challenging task due to growing undiagnosed and untreated DR cases and the variability of retinal changes across disease stages. Manually analyzing the images has become an expensive and time-consuming task, not to mention that training new specialists takes time and requires daily practice. Our work investigates deep learning methods, particularly convolutional neural network (CNN), for DR diagnosis in the disease’s five stages. A pre-trained residual neural network (ResNet-34) was trained and tested for DR. Then, we develop computationally efficient and scalable methods after modifying a ResNet-34 with three additional residual units as a novel ResNet-n/DR. The Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 dataset was used to evaluate the performance of models after applying multiple pre-processing steps to eliminate image noise and improve color contrast, thereby increasing efficiency. Our findings achieved state-of-the-art results compared to previous studies that used the same dataset. It had 90.7% sensitivity, 93.5% accuracy, 98.2% specificity, 89.5% precision, and 90.1% F1 score.
Low power architecture of logic gates using adiabatic techniquesnooriasukmaningtyas
The growing significance of portable systems to limit power consumption in ultra-large-scale-integration chips of very high density, has recently led to rapid and inventive progresses in low-power design. The most effective technique is adiabatic logic circuit design in energy-efficient hardware. This paper presents two adiabatic approaches for the design of low power circuits, modified positive feedback adiabatic logic (modified PFAL) and the other is direct current diode based positive feedback adiabatic logic (DC-DB PFAL). Logic gates are the preliminary components in any digital circuit design. By improving the performance of basic gates, one can improvise the whole system performance. In this paper proposed circuit design of the low power architecture of OR/NOR, AND/NAND, and XOR/XNOR gates are presented using the said approaches and their results are analyzed for powerdissipation, delay, power-delay-product and rise time and compared with the other adiabatic techniques along with the conventional complementary metal oxide semiconductor (CMOS) designs reported in the literature. It has been found that the designs with DC-DB PFAL technique outperform with the percentage improvement of 65% for NOR gate and 7% for NAND gate and 34% for XNOR gate over the modified PFAL techniques at 10 MHz respectively.
International Conference on NLP, Artificial Intelligence, Machine Learning an...gerogepatton
International Conference on NLP, Artificial Intelligence, Machine Learning and Applications (NLAIM 2024) offers a premier global platform for exchanging insights and findings in the theory, methodology, and applications of NLP, Artificial Intelligence, Machine Learning, and their applications. The conference seeks substantial contributions across all key domains of NLP, Artificial Intelligence, Machine Learning, and their practical applications, aiming to foster both theoretical advancements and real-world implementations. With a focus on facilitating collaboration between researchers and practitioners from academia and industry, the conference serves as a nexus for sharing the latest developments in the field.
Introduction- e - waste – definition - sources of e-waste– hazardous substances in e-waste - effects of e-waste on environment and human health- need for e-waste management– e-waste handling rules - waste minimization techniques for managing e-waste – recycling of e-waste - disposal treatment methods of e- waste – mechanism of extraction of precious metal from leaching solution-global Scenario of E-waste – E-waste in India- case studies.
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.
6th International Conference on Machine Learning & Applications (CMLA 2024)ClaraZara1
6th International Conference on Machine Learning & Applications (CMLA 2024) will provide an excellent international forum for sharing knowledge and results in theory, methodology and applications of on Machine Learning & Applications.
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
Using recycled concrete aggregates (RCA) for pavements is crucial to achieving sustainability. Implementing RCA for new pavement can minimize carbon footprint, conserve natural resources, reduce harmful emissions, and lower life cycle costs. Compared to natural aggregate (NA), RCA pavement has fewer comprehensive studies and sustainability assessments.
Recycled Concrete Aggregate in Construction Part III
Brain-computer interface of focus and motor imagery using wavelet and recurrent neural networks
1. TELKOMNIKA Telecommunication, Computing, Electronics and Control
Vol. 18, No. 4, October 2020, pp. 2748~2756
ISSN: 1693-6930, accredited First Grade by Kemenristekdikti, Decree No: 21/E/KPT/2018
DOI: 10.12928/TELKOMNIKA.v18i5.14899 2748
Journal homepage: http://journal.uad.ac.id/index.php/TELKOMNIKA
Brain-computer interface of focus and motor imagery
using wavelet and recurrent neural networks
Esmeralda C. Djamal, Rifqi D. Putra
Department of Informatics, Universitas Jenderal Achmad Yani, Indonesia
Article Info ABSTRACT
Article history:
Received Jun 19, 2019
Revised Apr 8, 2020
Accepted May 1, 2020
Brain-computer interface is a technology that allows operating a device
without involving muscles and sound, but directly from the brain through
the processed electrical signals. The technology works by capturing electrical
or magnetic signals from the brain, which are then processed to obtain
information contained therein. Usually, BCI uses information from
electroencephalogram (EEG) signals based on various variables reviewed.
This study proposed BCI to move external devices such as a drone simulator
based on EEG signal information. From the EEG signal was extracted to get
motor imagery (MI) and focus variable using wavelet. Then, they were
classified by recurrent neural networks (RNN). In overcoming the problem of
vanishing memory from RNN, was used long short-term memory (LSTM).
The results showed that BCI used wavelet, and RNN can drive external devices
of non-training data with an accuracy of 79.6%. The experiment gave
AdaDelta model is better than the Adam model in terms of accuracy and value
losses. Whereas in computational learning time, Adam's model is faster than
AdaDelta's model.
Keywords:
Brain-computer interface
EEG signal
Focus
Motor imagery
Recurrent neural networks
Wavelet
This is an open access article under the CC BY-SA license.
Corresponding Author:
Esmeralda C. Djamal,
Department of Informatics,
Universitas Jenderal Achmad Yani,
Terusan Jenderal Sudirman Cimahi St., Indonesia.
Email: esmeralda.contessa@lecture.unjani.ac.id
1. INTRODUCTION
Humans in every day always carry out activities that involve the movement of limbs. The brain
instructs the resulting action through motor nerves. Every human activity requires a focus on carrying out
activities for particular purposes. Nevertheless, the focus can be influenced by several factors such as
stimulation of sound or vision that can affect the activities being carried out. In meanwhile, the command to
move a limb occurs over a state of mind called motor imagery (MI). However, moving the object can be carried
out without involve gestures, muscles, sounds, and other motor functions. These commands are obtained from
the brain through intermediate devices to translate brain commands, known as the brain-computer interface
(BCI). This system can help people with physical disabilities in moving external devices. Currently, BCI has
been widely used to drive games [1, 2], robots [3], to help post-stroke patients [4] and neuromuscular
disabilities [5].
BCI consists of three parts, particularly command input, intermediate device, and command control.
BCI usually uses standard tools such as electroencephalogram (EEG) signals to translate brain commands [6].
The EEG signal is bioelectric in the brain that is captured on the surface of the scalp. EEG signal has a low
amplitude, non-stationary, and complicated patterns. The signal consists of frequency components such as
2. TELKOMNIKA Telecommun Comput El Control
Brain-computer interface of focus and motor imagery using wavelet and… (Esmeralda C. Djamal)
2749
Alpha waves (8-13 Hz), Beta waves (14-30 Hz), Theta waves (4-7 Hz), Delta waves (0.5-3 Hz), and Gamma
waves (> 30 Hz). EEG signal identified mental task variables as appropriate actions on a computer [7].
Therefore, the representation of EEG signals into the frequency domain is very considerate for
getting conditions particular thoughts. Some previous studies in extracting EEG signals using wavelet
transform [8-11] in BCI. Wavelets can filter signals from precise frequency components. So that method is
proper for non-stationary signals such as EEG. However, with a short time segmentation, it is possible to use
other methods such as fast Fourier transform (FFT) for extracting non-stationary signals [12]. FFT has
advantages in terms of computational speed, although wavelet is usually more accurate. Wavelet extraction
can increase accuracy by 3.6% and accelerate detection time by 0.003 seconds. The last study obtained 93.6%
accuracy of training data, and 90% of non-training data [13].
Some variables that affected EEG signals are determinants of classification in previous studies,
such as emotions [14], disorder [15] and focus [16]. Meanwhile, usually, the EEG signal variable translated
in BCI is focus [16], attention level [17], relax [1], emotion [18, 19], hand grasping imagination [20] and hybrid
of motor imagery and speech imagery [21]. Usually, the studies used one characteristic variable in
the classification process. Previous studies used BCI to move characters in arcade games based on focus
feedback [22], controls for computer applications, or action on imagined conditions of the mind [6] and
wheelchair robotic [23].
In pattern recognition, after extraction features, then into the classification system. In BCI application,
the previous research used some methods such as learning vector quantization (LVQ) [1], recurrent neural
networks (RNN) [24], and convolutional neural networks (CNN) [25]. There was using CNN to BCI game
control [26]. Meanwhile, time series cases often use RNN, which facilitates the connection of sequential data
with past time [19]. In previous studies using RNN to recognize emotions from EEG signals with an accuracy
rate of 87% [14]. This research proposed the BCI model to drive the drone simulator from the focus state and
motor imagery. Models developed using wavelet and recurrent neural networks (RNNs). The drone simulator
is designed to be driven by an imagery motor into four, particularly "forward", "right", "left", and "silent".
Besides, the simulator action added focus factor (two classes: focus or not focus), which is described as
the rotation speed. So that eight classes are obtained.
2. RESEARCH METHOD
This research proposed BCI to drive the drone simulator through EEG signals using wavelet and RNN,
as shown in Figure 1. The system used variable MI and Focus that were processed by simultaneous. So that
are eight classes of both variables. The model used data set with emotiv epoch EEG recording as shown in
Figure 2.
EEG Signals
Praprocessing
Segmentation
Wavelet Extraction
Recurrent Neural
Networks Identification
1st
LSTM Layer
(Relu)
Dropout
Layer
2nd
LSTM Layer
(Sigmoid)
Dense Layer
(Sigmoid)
Weight
Recurrent Neural
Networks Training
EEG Signal
Praprocessing
Segmentation
Wavelet Extraction
Concentration Thingking Forward
Training Data 6400 set
LSTM Layer
1 (Relu)
Dropout Layer
LSTM Layer
2 (Sigmoid)
Dense Layer
(Sigmoid)
Output
Input
Data Training
EEG Signal
256 data points
each segment
every channel
256 data points
each segment
every channel
Concentration Thingking Turn Right
Concentration Thingking Turn Left
Not Concentration Thingking Forward
Not ConcentratIon Thinking Idle
Not Concentration Thingking Turn Right
Not Concentration Thingking Turn Left
Concentration Thingking Idle
Figure 1. BCI based on focus and MI variable of EEG signal
3. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 18, No. 5, October 2020: 2748 - 2756
2750
Imagine Moving Go Forward Imagine Moving Turn Left Imagine Moving Turn Right Imagine Motionless
Instruction Instruction Instruction Instruction
0 10 30 40 60 70 90 100 120
Seconds
Visua
l
Instruction
One Category (30 Seconds)
Instruction Segmen 1 Segmen 2 Segmen 3 Segmen 4 Segmen 5 Segmen 6 Segmen 7 Segmen 8 Segmen 9 Segmen 10
0 10 12 14 16 18 20 22 24 26 28 30
Seconds
Figure 2. Recording scenario
2.2. Wavelet extraction
The wavelet transform can extract the needed signal components, hence reducing the number of data
without losing important information. Besides, this method is suitable for non-stationary signals. The output
of the wavelet transform into a time-domain allows its application as a pre-model [6]. Wavelet transformation
has two main processes, specifically decomposition, that extract a signal into a specific frequency and
reconstruction that recombine extracted signals into their original form [27]. Wavelet works in a convolution
signal with mother wavelet. Various forms of wavelets used for EEG signal extraction from previous studies,
such as Daubechies Haar and Symmlet. The researchers did not specifically mention the basic shape of
the wavelet that gives good accuracy. But in general, the asymmetric Daubechies [7], combine of Daubechies
and Symlet [28] and Symmlet [29]. Both forms are compatible with EEG signal characteristics. One type of
wavelet transform is wavelet packet decomposition (WPD). Wavelet packets are linear combinations of
wavelet functions [9]. A wavelet function has three indices, j: index scale (integer), k: translation coefficient,
n: oscillation parameter and t is time as (1).
𝑊𝑗,𝑘
𝑛
= 2 𝑗/2
𝑊 𝑛(2 𝑗
𝑡 − 𝑘) (1)
The wavelet packet functions are a scaling function )(t and the mother wavelet function )(t .
Wavelet packet functions with higher filter are:
𝑊0,0
2𝑛
= √2 ∑ ℎ(𝑘)𝑊1,𝑘
2𝑛
(2𝑡 − 𝑘)𝑘 (2)
𝑊0,0
2𝑛+1
= √2 ∑ 𝑔(𝑘)𝑊1,𝑘
2𝑛
(2𝑡 − 𝑘)𝑘 (3)
The factor h(k) and g(k) indicate quadrature mirror extraction [30]. The value (h(k) and g(k) related
to the scaling function and the mother wavelet function. The inner product signal f(t) with wavelet packet
functions in a range of t show (4):
𝑊𝑗,𝑘
𝑛
= 𝑓(𝑡)*𝑊𝑗,𝑘
𝑛
= ∑ 𝑓(𝑡)𝑊𝑗,𝑘
𝑛
(2𝑡 − 𝑘)𝑡 (4)
For original signal S, the left-side is obtained in low pass filter h(k) as an approximation coefficient
and the right side as high pass filter g(k) or detail. In (6) showed the scale, translation, and oscillation values.
In (4), the signal can be decomposed into a scale factor j in a particular frequency, either high or low. In this
study, using the standard form Daubechies 4, which consists of four low-pass filter coefficients [29]. Wavelets
decompose signals into specific frequency ranges, such as delta, alpha, beta, theta, and gamma waves, such as
Figure 3.
2.3. Recurrent neural networks
RNN is one method used in Deep Learning for sequential data [31], by looping to store information
from the past [32]. This configuration is shown in Figure 4. RNN is activated with a function such as sigmoid
as Figure 5. RNN has the problems of short memory, so it needs control to forget some parts throughout
the gate. Some of the methods are gated recurrent unit (GRU), backpropagation through time (BPTT), and long
short-term memory (LSTM). This research used the LSTM gate to overcome short-term memory problems or
often called vanishing gradient [14], which has a increase in capability from a single layer [33].
4. TELKOMNIKA Telecommun Comput El Control
Brain-computer interface of focus and motor imagery using wavelet and… (Esmeralda C. Djamal)
2751
1-64 Hz
1-32 Hz 33-64 Hz
1-16 Hz
1-8 Hz 9-16 Hz
17-32 Hz
17-24 Hz 25-32 Hz
9-12 Hz 13-16 Hz1-4 Hz 5-8 Hz
13-14 Hz 15-16 Hz5-6 Hz 7-8 Hz
25-28 Hz 29-32 Hz
29-30 Hz 31-32 Hz
Beta
Alfa / Mu
Teta A D
AAA
AA
AAAA
AD
ADD
ADDD
AAD
AAAD
ADA
ADDA
ADDDDAAADA AAADD ADDDA
AADA
AADD
AADDA AADDD
Gamma
33-48 Hz
DD
DA 49-64 Hz
33-40 Hz
DAD41-48 HzDAA
Figure 3. Wavelet multilevel
Figure 4. Recurrent neural network architecture Figure 5. LSTM cell architecture
The LSTM network consists of modules with repetitive processing, as in Figure 4. Memory in LSTM
is called cells that take input from the previous state (ht-1) and current input (xt). The collection of cells decides
what will be stored in memory and what will be removed from memory. LSTM combines the previous state,
current memory, and input. LSTM has three gates, particularly the forget gate, to determine which eliminating
information from the cell using the sigmoid layer [34]. In (5) with the activation function used is the release
shown in (8).
𝑓𝑡 = 𝜎(𝑊𝑓. [ℎ 𝑡−1, 𝑥𝑡] + 𝑏𝑓) (5)
𝑅𝑒𝐿𝑈(𝑥) = max(0, 𝑥) (6)
The second gate is the input gate (i), which of the sigmoid layer (σ) will be updated, and tanh of
the layer will be formulated as a vector of the updated value. It can be seen at (7) and (8) where xt is input for
each current step time. At this layer, a vector of updated values will be produced [35].
𝑖𝑡 = 𝜎(𝑊𝑓. [ℎ 𝑡−1, 𝑥𝑡] + 𝑏𝑖) (7)
𝐶̃𝑡 = tanh(𝑊𝑐. [ℎ 𝑡−1, 𝑥𝑡] + 𝑏𝑐) (8)
Then the cells of (7), (8) will be updated using (9).
𝐶𝑡 = 𝑓𝑡 ∗ 𝐶𝑡−1 + 𝑖𝑡 ∗ 𝐶̃𝑡 (9)
5. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 18, No. 5, October 2020: 2748 - 2756
2752
Finally, the output gate will be calculated based on cell updates, and the sigmoid layer looks like (10) and (11).
𝑜𝑡 = 𝜎(𝑊𝑜. [ℎ 𝑡−1, 𝑥𝑡] + 𝑏 𝑜) (10)
ℎ 𝑡 = 𝑜𝑡 ∗ tanh(𝐶𝑡) (11)
where 𝜎 is the sigmoid activation function, and tanh as the tanh activation function used for the results of
multiplying the weight of each gate, namely Wf, Wt, Wc, Wo with input values and added bias including bf, bi,
bc, bo. Gate used is gate input it, forget ft,, and output ot. Each passing gate will be searched for hidden state
candidates 𝐶̃𝑡 obtained from the gate calculation with the current hidden state 𝐶𝑡 furthermore, the previously
hidden state Ct-1 to produce the latest hidden state, which is used as the output of the hidden layer.
In the identification layer, there is an effort to minimize the difference between the target output and
the output of computational results. Objective functions are often referred to as cost functions or loss functions
so-called "loss". One of the loss functions that can be used is cross-entropy, as in (12). Where loss is a distance,
S is the result of the activation function, and L is the target of each class label. A loss function is used to
measure convergence in the learning process.
( ) ( )−=
i
ii SLLSLoss log, (12)
In machine learning such RNN, it is essential to set input features. This research used MI and focus
variable, so alpha, mu, beta, and gamma (32-40Hz) waves relate that. Based on Figure 3, we got the waves of
four channels, as shown in Table 1. The BCI works every two seconds. While the RNN configuration is as
shown in Table 2. In the first model, the number of neurons of the model is faced with the same amount as
the input vector with a two-dimensional shape that applies the return sequence to the second LSTM model.
The LSTM model has a one-dimensional vector, which results in the dense layer, which has eight neurons,
according to the number of classes produced.
Table 1. RNN features of BCI
No Component Number of points Description All channel
1 Alpha, Beta, Gamma (9-40 Hz) 128 Four-channel 512
2 Mu (9-14Hz) 24 FC5 and FC6 only 48
Total 560
Table 2. Architecture model recurrent neural networks
Model Neuron Output shape
LSTM 560 1,560
Dropout 0.2 1,560
Dense 8 8
3. RESULTS AND ANALYSIS
The experiment was carried out by comparing the effect of using wavelet as the extraction of alpha,
mu, beta, and gamma waves. Experiments were also carried out on the model in terms of providing the highest
accuracy and considering the computational time of learning. Identification involves eight classes, namely
"Forward", "Right", "Left", and "Silent" each in focus and not. In using BCI, performance depends on
translating variables from the EEG signal being reviewed. Identification performance is very dependent on
the use of extraction methods. Therefore, testing begins with wavelet performance.
3.1. Wavelet extraction
Wavelet extraction uses Daubechies 4 at 9-40Hz, which has been normalized as in Figure 6. Wavelet
extraction is shown in blue compared to the original signal using orange. The EEG signal after going through
wavelet extraction is more stable because it is adjusted to the waves which are in the frequency range. Then
eliminate unused waves and signal noise. The results of each channel are stored sequentially into input vectors.
3.2. Compared between optimization model
This study used three-weight correction models that are adaptive moment estimation (Adam), adaptive
learning estimation (AdaDelta), and stochastic gradient descent (SGD). We experience optimizer models and
optimal learning parameters that higher accuracy and shortest time computing. Adam has a fast convergence
property, but it is only unstable due to very rapid error reduction. Besides the optimizer model, we compared
using wavelet and without wavelet, as in Figure 7 of Accuracy and Figure 8 of losses value. There are three
6. TELKOMNIKA Telecommun Comput El Control
Brain-computer interface of focus and motor imagery using wavelet and… (Esmeralda C. Djamal)
2753
models. Adam and AdaDelta are convergent of 100 epoch learning, except for the SGD model. So that
100 epochs are optimal enough, except with SGD with 500 epoch addition. Each color in Figure 7 and
Figure 8 indicates the testing of training data with wavelet (blue), training data without wavelet (green),
non-training/validation data with wavelet (orange), and validation data without wavelet (red). From the three
models shown in Figure 7 that using wavelet can increase accuracy and reduce computing time. The exact
values of the three models are shown in Table 3. Likewise, the value of Losses from using wavelets for
the three models generally decreases. This result told that wavelet could improve accuracy by reducing
the non-stationary properties of EEG signals.
Figure 6. Wavelet extraction
(a) (b)
(c)
Figure 7. Accuracy of the optimizer model; (a) Adam, (b) AdaDelta (c) SGD
The accuracy of the three models is relatively the same, mainly between 76-80% for validation data
while 100% for training data. Even so, the highest AdaDelta model is 79.81%. The exciting thing is that
the Adam model quickly corrects weights, which causes accuracy to increase rapidly and losses to decrease
at the beginning of the iteration. However, conditions of small fluctuations continue at the end of the epoch.
While the AdaDelta model tends to be stable at the end of the epoch, it achieves longer than the Adam model.
But it is understood that the weight correction method of the Adam model tends to jump like a ball that rolls
easily. Besides, the SGD model had almost no ripples of instability during the training. But the disadvantages
require longer iterations. Even in the 500th epoch, the accuracy is still increasing.
7. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 18, No. 5, October 2020: 2748 - 2756
2754
(a) (b)
(c)
Figure 8. Losses of the optimizer model: (a) Adam, (b) AdaDelta (c) SGD
Table 3. Comparison of loss and accuracy using Adam, AdaDelta, and SGD model
Model epochs
Wavelet Without Wavelet
Train Data Validation Data Train Data Validation Data
Accuracy Loss Accuracy Loss Accuracy Loss Accuracy Loss
Adam 100 98,5 0,0422 78,84 1,0767 100,0 0,0003 76.92 1,4218
AdaDelta 100 100,0 0,0005 79,81 1,3561 100,0 0,0002 74,04 1,3240
SGD 100 17.7 2.0512 17.31 2.0158 32.05 1.9622 22.12 2.0304
SGD 500 100,0 0.0349 77,82 0.9281 100,0 0.0052 77.88 1.1612
From various experiments, showed that RNN and wavelet could be used to support BCI using MI and
Focus variables with an accuracy of almost 80% non-training data. The future experiment needs to look out
the configuration of the input features and channel usage of the EEG signal. So that can improve accuracy.
This research gave the duration of computational learning using Adam, AdaDelta, and SGD optimization with
several configurations. A comparison of the length of time from the three optimizations can be seen in Table 4
with several configurations in 100 epochs.
Table 4. Computing time of 100 epochs
Model Methods Learning time (second)
Adam With Wavelet 516
Without Wavelet 540
AdaDelta With Wavelet 606
Without Wavelet 642
SGD With Wavelet 370
Without Wavelet 380
4. CONCLUSION
This research showed that brain-computer interface could use motor imagery and focus variable of
EEG signal to move drone simulator. Nevertheless, the emphasis is real-time action with other computing time
applications that can be used. Proposed methods using RNN and wavelet could support BCI with MI and focus
variables with an accuracy of almost 80% non-training data. The research gave that the use of wavelet as
a pre-process can improve accuracy, lead to stability, and reduce the training data computation time. This result
is consistent with the hypothesis referring to previous research that wavelet is suitable for non-stationary signals
8. TELKOMNIKA Telecommun Comput El Control
Brain-computer interface of focus and motor imagery using wavelet and… (Esmeralda C. Djamal)
2755
such as EEG signals. In using RNN, it is necessary to pay attention to the optimization model for the correction
of weights and the number of epochs used. Adam's model reaches asymptotically faster, but still fluctuates
at the end of the epoch, so it requires the right number of iterations. The SGD model is quieter in performance
but requires far more epochs. While the AdaDelta model adopts both models, it provides stable and high
accuracy. The next thing to look out for is the configuration of the input features and channel usage of
the EEG signal.
ACKNOWLEDGEMENTS
The research was funded by "PTUPT–Penelitian Terapan Unggulan Perguruan Tinggi" from
the Ministry of Research Technology and Higher Education, Republik Indonesia.
REFERENCES
[1] E. C. Djamal, M. Y. Abdullah, and F. Renaldi, “Brain Computer Interface Game Controlling Using Fast Fourier
Transform and Learning Vector Quantization,” Journal of Telecommunication, Electronic and Computer
Engineering (JTEC), vol. 9, no. 2-5, pp. 71-74, 2017.
[2] M. Van Vliet, A. Robben, N. Chumerin, et al., “Designing a brain-computer interface controlled video-game using
consumer grade EEG hardware,” 2012 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics
for Better and Safer Living, BRC 2012, 2012.
[3] S. Ramesh, M. G. Krishna, and M. Nakirekanti, “Brain Computer Interface System for Mind Controlled Robot using
Bluetooth,” International Journal of Computer Application, vol. 104, no. 15, pp. 20-23, 2014.
[4] B. Várkuti, et al., “Resting State Changes in Functional Connectivity Correlate With Movement Recovery for BCI
and Robot-Assisted Upper-Extremity Training After Stroke,” Neurorehabilitation and Neural Repair, vol. 27, no. 1,
pp. 53-62, 2013.
[5] D. J. McFarland and J. R. Wolpaw, “EEG-Based Brain-Computer Interfaces,” Current Opinion in Biomedical
Engineering, vol. 4, no. Dec, pp. 194-200, 2017.
[6] E. C. Djamal and Suprijanto, “Recognition of Electroencephalogram Signal Pattern against Sound Stimulation using
Spectral of Wavelet,” Tencon 2011, pp. 767-771, 2011.
[7] M. H. Alomari, A. Abubaker, A. Turani, et al., “EEG Mouse: A Machine Learning-Based Brain Computer Interface,”
(IJACSA) International Journal of Advanced Computer Science and Applications, vol. 5, no. 4, pp. 193-198, 2014.
[8] S. Chaudhary, S. Taran, V. Bajaj, and S. Siuly, “A flexible analytic wavelet transform based approach for
motor-imagery tasks classification in BCI applications,” Computer Methods and Programs in Biomedicine, vol. 15,
no. 45, 2020.
[9] H. Göksu, “BCI oriented EEG analysis using log energy entropy of wavelet packets,” Biomedical Signal Processing
and Control, vol. 44, pp. 101-109, 2018.
[10] T. Nguyen, A. Khosravi, D. Creighton, and S. Nahavandi, “EEG signal classification for BCI applications by wavelets
and interval type-2 fuzzy logic systems,” Expert System With Applications, vol. 42, no. 9, pp. 4370-4380, 2015.
[11] A. Khalaf, E. Sejdic, and M. Akcakaya, “Common spatial pattern and wavelet decomposition for motor imagery
EEG- fTCD brain-computer interface,” Journal of Neuroscience Methods, vol. 320, no. April, pp. 98-106, 2019.
[12] F. Ansari, D. R. Edla, S. Dodia, and V. Kuppili, “Brain-Computer Interface for Wheelchair Control Operations:
An Approach based on Fast Fourier Transform and On-Line Sequential Extreme Learning Machine,” Clinical
Epidemiology and Global Health, vol. 7, no. 3, pp. 274-278, 2018.
[13] S. H. Fairclough, “BCI and physiological computing for computer games: Differences, similarities & intuitive
control,” Proceedings of CHI’08, no. 1, pp. 1-6, 2008.
[14] S. Alhagry, A. A. Fahmy, and R. A. El-Khoribi, “Emotion Recognition based on EEG using LSTM Recurrent Neural
Network,” International Journal of Advanced Computer Science and Applications, vol. 8, no. 10, pp. 356-358, 2017.
[15] J. R. Wolpaw, N. Birbaumer, D. J. McFarland, et al., “Brain Computer Interfaces for communication and control,”
Frontiers in Neuroscience, vol. 4, no. 113, pp. 767-791, 2002.
[16] T. J. Choi, J. O. Kim, S. M. Jin, and G. Yoon, “Determination of the Concentrated State Using Multiple EEG
Channels,” International Journal of Computer, Electrical, Automation, Control and Information Engineering, vol. 8,
no. 8, pp. 1359-1362, 2014.
[17] K. G. Smitha, S. Shenjie, K. P. Thomas, and A. P. Vinod, “Two player EEG-based neurofeedback ball game for
attention enhancement,” in International Conference on Systems, Man and Cybernetics, 2014, pp. 3150-3155.
[18] D. Iacoviello, A. Petracca, M. Spezialetti, and G. Placidi, “A real-time classification algorithm for EEG-based BCI driven
by self-induced emotions,” Computer Methods and Programs in Biomedicine, vol. 122, no. 3, pp. 293-303, 2015.
[19] E. C. Djamal, H. Fadhilah, A. Najmurrokhman, A. Wulandari, and F. Renaldi, “Emotion brain-computer interface
using wavelet and recurrent neural networks,” International Journal of Advances in Intelligent Informatics, vol. 6,
no. 1, pp. 1-12, 2020.
[20] E. C. Djamal, Suprijanto, and S. J. Setiadi, “Classification of EEG-Based Hand Grasping Imagination Using
Autoregressive and Neural Networks,” Jurnal Teknologi, vol. 78, no. 6-6, pp. 105-110, 2016.
[21] L. Wang, X. Liu, Z. Liang, Z. Yang, and X. Hu, “Analysis and classification of hybrid BCI based on motor imagery
and speech imagery,” Measurement, vol. 147, p. 106842, 2019.
[22] A. Finke, A. Lenhardt, and H. Ritter, “The MindGame: A P300-based brain-computer interface game,” Neural
Networks, vol. 22, no. 9, pp. 1329-1333, 2009.
9. ISSN: 1693-6930
TELKOMNIKA Telecommun Comput El Control, Vol. 18, No. 5, October 2020: 2748 - 2756
2756
[23] T. I. Voznenko, E. V Chepin, I. Voznenko, et al,, “The Control System Based Based on Extended BCI for a Robotic
Wheelchair,” in Procedia Computer Science, 2018, vol. 123, pp. 522-527.
[24] T. Hosman, et al., “BCI decoder performance comparison of an LSTM recurrent neural network and a Kalman filter
in retrospective simulation,” 2019 9th International IEEE/EMBS Conference on Neural Engineering (NER),
pp. 1066-1071, 2019.
[25] J. Liu, Y. Cheng, and W. Zhang, “Deep learning EEG response representation for brain computer interface,” Chinese
Control Conference, pp. 3518-3523, 2015.
[26] S. Umar, M. Alsulaiman, and G. Muhammad, “Deep Learning for EEG motor imagery classification based on multi-
layer CNNs feature fusion,” Future Generation Computer Systems, vol. 101, pp. 542-554, 2019.
[27] E. A. Mohamed, M. Z. B. Yusoff, N. K. Selman, and A. S. Malik, “Enhancing EEG Signals in Brain Computer
Interface Using Wavelet Transform,” in International Journal of Information and Electronics Engineering, vol. 4,
no. 3, pp. 234-238, 2014.
[28] C. Rodrigues, P. P. Rebouças, E. Peixoto, A. K. N, V. Hugo, and C. De Albuquerque, “Classification of EEG signals
to detect alcoholism using machine learning techniques,” Pattern Recognition Letters, vol. 125, pp. 140-149, 2019.
[29] E. C. Djamal and P. Lodaya, “EEG Based Emotion Monitoring Using Wavelet and Learning Vector Quantization,”
2017 4th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI 2017),
pp. 19-21, 2017.
[30] A. N. Akansu and R. A. Haddad, “Multiresolution signal decomposition,” Academic Press, Second., no. 1, T. R.
Hsing, Ed. Academic Press, pp. 22-25, 2001.
[31] Y. Shen, H. Lu, and J. Jia, “Classification of Motor Imagery EEG Signals with Deep Learning Models,” Lecture
Notes in Computer Science book series, vol. 10559, pp. 181-190, 2017.
[32] J.-S. Wang, Y.-T. Yang, C.-Y. Hsu, and Y. Hsu, “A Recurrent Neural Sleep-Stage Classifier Using Energy Features
of EEG Signals,” Neurocomputing, vol. 104, pp. 105-114, 2013.
[33] A. Mazumder, A. Rakshit, and D. N. Tibarewala, “A Back-Propagation Through Time Based Recurrent Neural
Network Approach for Classification of Cognitive EEG States,” 2015 IEEE International Conference on Engineering
and Technology, no. March, pp. 1-5, 2015.
[34] J. Zhou, M. Meng, Y. Gao, Y. Ma, and Q. Zhang, “Classification of Motor Imagery EEG Using Wavelet Envelope
Analysis and LSTM Networks,” 2018 Chinese Control And Decision Conference (CCDC), pp. 5600-5605, 2018.
[35] Y. Li, J. Huang, H. Zhou, and N. Zhong, “Human Emotion Recognition with Electroencephalographic
Multidimensional Features by Hybrid Deep Neural Networks,” Applied Sciences, vol. 7, no. 10, p. 1060, 2017.
BIOGRAPHIES OF AUTHORS
Esmeralda Contessa Djamal received a Bachelor's degree in Engineering Physics from
Institut Teknologi Bandung in 1994, a Master's degree in Instrument and Control from
Institut Teknologi Bandung in 1998. Since Ph.D. dissertation until now, research on EEG
classification and finished doctoral program from Institut Teknologi Bandung in 2005.
She is a lecturer of Informatics Department, Universitas Jenderal Achmad Yani.
Rifqi Dania Putra received his bachelor's degree in Informatics department from
Universitas Jenderal Achmad Yani in 2019. E-mail: daniaputra24@gmail.com