This dataset contains EEG recordings from 40 subjects performing various cognitive tasks designed to induce stress. The tasks include a Stroop color-word test, arithmetic problems, and mirror image recognition. EEG was recorded from 32 channels during 25 second trials of each task and preprocessed to remove artifacts. The data are provided in raw and filtered forms along with stress ratings for each task from the subjects. The dataset aims to identify patterns in EEG related to stress from different cognitive challenges.
Application of Hybrid Genetic Algorithm Using Artificial Neural Network in Da...IOSRjournaljce
The main purpose of data mining is to extract knowledge from large amount of data. Artificial Neural network (ANN) has already been applied in a variety of domains with remarkable success. This paper presents the application of hybrid model for stroke disease that integrates Genetic algorithm and back propagation algorithm. Selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In addition the hybrid model that leads to further improvised categorization, accuracy compared to the result produced by genetic algorithm alone. In this study, a new hybrid model of Neural Networks and Genetic Algorithm (GA) to initialize and optimize the connection weights of ANN so as to improve the performance of the ANN and the same has been applied in a medical problem of predicting stroke disease for verification of the results.
This document presents research on classifying data using a new enhanced decision tree algorithm called NEDTA. It first provides background on data mining and decision tree classification techniques. It then discusses existing decision tree algorithms ID3, J48 and NBTree and applies them to a banking dataset to evaluate performance. The objectives are stated as applying the algorithms, evaluating results, comparing performance based on accuracy, time and error rate, and developing an enhanced method. The document outlines the implementation and provides results of applying the existing algorithms in Weka. It compares the accuracy and performance of ID3, J48 and NBTree and finds the new NEDTA algorithm produces better results.
IRJET- Plant Disease Detection and Classification using Image Processing a...IRJET Journal
This document describes a method for detecting and classifying plant diseases using image processing and artificial neural networks. The method involves preprocessing images through grayscaling, resizing and filtering. K-means clustering is used to segment infected leaf regions. Features are extracted from segmented images and fed into feedforward and cascaded feedforward neural networks for disease classification. The method achieved accurate classification of several common plant diseases with fewer iterations and better performance than traditional feedforward backpropagation neural networks. This automatic disease detection approach could help improve agricultural productivity by facilitating early detection on large farms.
Performance Analysis of Various Data Mining Techniques on Banknote Authentica...inventionjournals
In this paper, we describe the functionality features for authenticating in Euro banknotes. We applied different data mining algorithms such as KMeans, Naive Bayes, Multilayer Perceptron, Decision trees (J48), and Expectation-Maximization(EM) to classifying banknote authentication dataset. The experiments are conducted in WEKA. The goal of this project is to obtain the higher authentication rate in banknote classification
This document compares different supervised learning approaches for word sense disambiguation (WSD), including Naive Bayes, Decision Tree, and Decision List classifiers. An experiment is conducted using a dataset of 15 words and their senses from WordNet. The Decision List approach achieves the highest accuracy at 69.12%, followed by Naive Bayes at 58.32% and Decision Tree at 45.14%. While no single approach performed best for all words, overall Decision List provided the most accurate WSD and is presented as the best performing method for this problem among the three approaches studied.
This document summarizes an empirical study comparing several supervised machine learning approaches for word sense disambiguation: Naive Bayes, decision tree, decision list, and support vector machine (SVM). The study used a dataset of 15 words annotated with senses from WordNet and Senseval-3. Each approach was implemented and evaluated based on its accuracy in identifying the correct sense of each word. The results showed that the decision list approach achieved the highest overall accuracy of 69.12%, followed by SVM at 56.11%, naive Bayes at 58.32%, and decision tree at 45.14%. Thus, the study concluded that decision list performed best on this dataset for the task of word sense disambiguation.
Computational model for artificial learning using formal concept analysisAboul Ella Hassanien
The document presents a computational model for artificial learning using formal concept analysis. It proposes using formal concept analysis to describe the classification process and derive classification rules. The model was tested on several datasets and showed improved accuracy over support vector machines and classification and regression trees on most datasets based on various performance metrics. ROC curves were also generated to evaluate model performance. The proposed model aims to better understand and model the classification learning processes involved in human intelligence.
A New Born Child Authentication System using Image Processingrahulmonikasharma
The Missing, swapping, mixing, and illegal adoption of new born child is a global challenge and research done to solve this issue is minimal and least reported in the literature. As per our knowledge, there is no biometric system currently available that can be effectively used for new born child identification. The manual procedure of capturing inked footprints in practice for this purpose is limited for use inside hospitals and is not an effective solution for identification purposes. Hence, a new born child personal authentication system is proposed for this issue based on multi biometrics. The biometric traits considered are the footprint of the new born child and the fingerprint of the mother. An appropriate fusion scheme is implemented to overcome the drawbacks of a single modality. The experimental results are promising and prove to be an effective system.
Application of Hybrid Genetic Algorithm Using Artificial Neural Network in Da...IOSRjournaljce
The main purpose of data mining is to extract knowledge from large amount of data. Artificial Neural network (ANN) has already been applied in a variety of domains with remarkable success. This paper presents the application of hybrid model for stroke disease that integrates Genetic algorithm and back propagation algorithm. Selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In addition the hybrid model that leads to further improvised categorization, accuracy compared to the result produced by genetic algorithm alone. In this study, a new hybrid model of Neural Networks and Genetic Algorithm (GA) to initialize and optimize the connection weights of ANN so as to improve the performance of the ANN and the same has been applied in a medical problem of predicting stroke disease for verification of the results.
This document presents research on classifying data using a new enhanced decision tree algorithm called NEDTA. It first provides background on data mining and decision tree classification techniques. It then discusses existing decision tree algorithms ID3, J48 and NBTree and applies them to a banking dataset to evaluate performance. The objectives are stated as applying the algorithms, evaluating results, comparing performance based on accuracy, time and error rate, and developing an enhanced method. The document outlines the implementation and provides results of applying the existing algorithms in Weka. It compares the accuracy and performance of ID3, J48 and NBTree and finds the new NEDTA algorithm produces better results.
IRJET- Plant Disease Detection and Classification using Image Processing a...IRJET Journal
This document describes a method for detecting and classifying plant diseases using image processing and artificial neural networks. The method involves preprocessing images through grayscaling, resizing and filtering. K-means clustering is used to segment infected leaf regions. Features are extracted from segmented images and fed into feedforward and cascaded feedforward neural networks for disease classification. The method achieved accurate classification of several common plant diseases with fewer iterations and better performance than traditional feedforward backpropagation neural networks. This automatic disease detection approach could help improve agricultural productivity by facilitating early detection on large farms.
Performance Analysis of Various Data Mining Techniques on Banknote Authentica...inventionjournals
In this paper, we describe the functionality features for authenticating in Euro banknotes. We applied different data mining algorithms such as KMeans, Naive Bayes, Multilayer Perceptron, Decision trees (J48), and Expectation-Maximization(EM) to classifying banknote authentication dataset. The experiments are conducted in WEKA. The goal of this project is to obtain the higher authentication rate in banknote classification
This document compares different supervised learning approaches for word sense disambiguation (WSD), including Naive Bayes, Decision Tree, and Decision List classifiers. An experiment is conducted using a dataset of 15 words and their senses from WordNet. The Decision List approach achieves the highest accuracy at 69.12%, followed by Naive Bayes at 58.32% and Decision Tree at 45.14%. While no single approach performed best for all words, overall Decision List provided the most accurate WSD and is presented as the best performing method for this problem among the three approaches studied.
This document summarizes an empirical study comparing several supervised machine learning approaches for word sense disambiguation: Naive Bayes, decision tree, decision list, and support vector machine (SVM). The study used a dataset of 15 words annotated with senses from WordNet and Senseval-3. Each approach was implemented and evaluated based on its accuracy in identifying the correct sense of each word. The results showed that the decision list approach achieved the highest overall accuracy of 69.12%, followed by SVM at 56.11%, naive Bayes at 58.32%, and decision tree at 45.14%. Thus, the study concluded that decision list performed best on this dataset for the task of word sense disambiguation.
Computational model for artificial learning using formal concept analysisAboul Ella Hassanien
The document presents a computational model for artificial learning using formal concept analysis. It proposes using formal concept analysis to describe the classification process and derive classification rules. The model was tested on several datasets and showed improved accuracy over support vector machines and classification and regression trees on most datasets based on various performance metrics. ROC curves were also generated to evaluate model performance. The proposed model aims to better understand and model the classification learning processes involved in human intelligence.
A New Born Child Authentication System using Image Processingrahulmonikasharma
The Missing, swapping, mixing, and illegal adoption of new born child is a global challenge and research done to solve this issue is minimal and least reported in the literature. As per our knowledge, there is no biometric system currently available that can be effectively used for new born child identification. The manual procedure of capturing inked footprints in practice for this purpose is limited for use inside hospitals and is not an effective solution for identification purposes. Hence, a new born child personal authentication system is proposed for this issue based on multi biometrics. The biometric traits considered are the footprint of the new born child and the fingerprint of the mother. An appropriate fusion scheme is implemented to overcome the drawbacks of a single modality. The experimental results are promising and prove to be an effective system.
Jason K. Johnson is a postdoctoral fellow at Los Alamos National Laboratory who received his Ph.D from MIT. His research interests include machine learning, graphical models, and signal processing. He has over 250 citations and has published works in various journals and conferences on topics related to inference in graphical models.
This document discusses improved K-means clustering techniques. It begins with an introduction to data mining and clustering. K-means clustering groups data objects into k clusters by minimizing distances between objects and cluster centers. However, K-means has limitations such as dependency on initialization. The document proposes a new clustering algorithm that uses an iterative relocation technique and distance determination approach to improve upon K-means clustering. It compares the computational complexity of K-means and K-medoids clustering algorithms.
Abstract In this paper, the concept of data mining was summarized and its significance towards its methodologies was illustrated. The data mining based on Neural Network and Genetic Algorithm is researched in detail and the key technology and ways to achieve the data mining on Neural Network and Genetic Algorithm are also surveyed. This paper also conducts a formal review of the area of rule extraction from ANN and GA. Keywords: Data Mining, Neural Network, Genetic Algorithm, Rule Extraction.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
A NOVEL DATA DICTIONARY LEARNING FOR LEAF RECOGNITIONsipij
Automatic leaf recognition via image processing has been greatly important for a number of professionals, such as botanical taxonomic, environmental protectors, and foresters. Learn an over-complete leaf dictionary is an essential step for leaf image recognition. Big leaf images dimensions and training images number is facing of fast and complete data leaves dictionary. In this work an efficient approach applies to construct over-complete data leaves dictionary to set of big images diminutions based on sparse representation. In the proposed method a new cropped-contour method has used to crop the training image. The experiments are testing using correlation between the sparse representation and data dictionary and with focus on the computing time.
Classification Of Iris Plant Using Feedforward Neural Networkirjes
The classification and recognition of type on the basis of individual features and behaviors constitute
a preliminary measure and is an important target in the behavioral sciences. Current statistical methods do not
always yield satisfactory answers. A Feed Forward Artificial Neural Network is the computer model inspired by
the structure of the Human Brain. It views as in the set of artificial nerve cells that are interconnected with the
other neurons. The primary aim of this paper is to demonstrate the process of developing the Artificial Neural
network based classifier which classifies the Iris database. The problem concerns the identification of Iris plant
species on the basis of plant attribute measurements. This paper is related to the use of feed forward neural
networks towards the identification of iris plants on the basis of the following measurements: sepal length, sepal
width, petal length, and petal width. Using this data set a Neural Network (NN) is used for the classification of
iris data set. The EBPA is used for training of this ANN. The results of simulations illustrate the effectiveness of
the neural system in iris class identification.
PREDICTION OF MALIGNANCY IN SUSPECTED THYROID TUMOUR PATIENTS BY THREE DIFFER...cscpconf
This document compares three classification methods - artificial neural networks, decision trees, and logistic regression - for predicting malignancy in thyroid tumor patients using a clinical dataset. It describes each method and applies them to a dataset of 259 thyroid tumor patients. The artificial neural network achieved 98% accuracy on the training set and 92% on the validation set. The decision tree method used 150 cases to build a model and achieved 86% accuracy. Logistic regression analysis resulted in 88% accuracy. The artificial neural network was able to accurately predict malignancy and identified important attributes like multiple nodules and family cancer history.
FEATURE EXTRACTION METHODS FOR IRIS RECOGNITION SYSTEM: A SURVEYijcsit
This document summarizes several feature extraction methods for iris recognition systems. It discusses supervised, unsupervised, and semi-supervised learning approaches for iris recognition. It also reviews related literature on iris recognition techniques, including using wavelet transforms, SVM classifiers, and other feature extraction methods. Tables in the document compare different biometric traits and traditional biometric systems, as well as summarize reviewed articles on iris recognition with their main contributions. The methodology section describes the typical four steps of an iris recognition system: image acquisition, preprocessing, feature extraction, and matching/recognition. It also discusses various iris recognition methods and their performance measures.
TUPLE VALUE BASED MULTIPLICATIVE DATA PERTURBATION APPROACH TO PRESERVE PRIVA...IJDKP
Huge volume of data from domain specific applications such as medical, financial, library, telephone,
shopping records and individual are regularly generated. Sharing of these data is proved to be beneficial
for data mining application. On one hand such data is an important asset to business decision making by
analyzing it. On the other hand data privacy concerns may prevent data owners from sharing information
for data analysis. In order to share data while preserving privacy, data owner must come up with a solution
which achieves the dual goal of privacy preservation as well as an accuracy of data mining task –
clustering and classification. An efficient and effective approach has been proposed that aims to protect
privacy of sensitive information and obtaining data clustering with minimum information loss
This document discusses a thesis that uses machine learning algorithms to diagnose mental illness using MRI brain scans. Specifically, it analyzes schizophrenia, bipolar disorder, and healthy control subject data from multiple imaging modalities. It trains and tests eight machine learning classifiers - support vector machines, k-nearest neighbors, logistic regression, naive Bayes, and random forests - on the raw imaging data as well as data transformed through dimensionality reduction techniques. The results aim to demonstrate the efficacy of these algorithms at classifying subjects based on their brain scans and diagnosing their mental condition.
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.
Recognition of emotional states using EEG signals based on time-frequency ana...IJECEIAES
The recognition of emotions is a vast significance and a high developing field of research in the recent years. The applications of emotion recognition have left an exceptional mark in various fields including education and research. Traditional approaches used facial expressions or voice intonation to detect emotions, however, facial gestures and spoken language can lead to biased and ambiguous results. This is why, researchers have started to use electroencephalogram (EEG) technique which is well defined method for emotion recognition. Some approaches used standard and pre-defined methods of the signal processing area and some worked with either fewer channels or fewer subjects to record EEG signals for their research. This paper proposed an emotion detection method based on time-frequency domain statistical features. Box-and-whisker plot is used to select the optimal features, which are later feed to SVM classifier for training and testing the DEAP dataset, where 32 participants with different gender and age groups are considered. The experimental results show that the proposed method exhibits 92.36% accuracy for our tested dataset. In addition, the proposed method outperforms than the state-of-art methods by exhibiting higher accuracy.
Prognosticating Autism Spectrum Disorder Using Artificial Neural Network: Lev...Avishek Choudhury
Autism spectrum condition (ASC) or autism spectrum disorder (ASD) is primarily identified with the help of behavioral indications encompassing social, sensory and motor characteristics. Although categorized, recurring motor actions are measured during diagnosis, quantifiable measures that ascertain kinematic physiognomies in the movement configurations of autistic persons are not adequately studied, hindering the advances in understanding the etiology of motor mutilation. Subject aspects such as behavioral characters that influences ASD need further exploration. Presently, limited autism datasets concomitant with screening ASD are available, and a majority of them are genetic. Hence, in this study, we used a dataset related to autism screening enveloping ten behavioral and ten personal attributes that have been effective in diagnosing ASD cases from controls in behavior science. ASD diagnosis is time exhaustive and uneconomical. The burgeoning ASD cases worldwide mandate a need for the fast and economical screening tool. Our study aimed to implement an artificial neural network with the Levenberg- Marquardt algorithm to detect ASD and examine its predictive accuracy. Consecutively, develop a clinical decision support system for early ASD identification.
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.
Detection of Aedes aegypti larvae using single shot multibox detector with tr...journalBEEI
The flavivirus epidemiology has reached an alarming rate which haunts the world population including Malaysia. In fact, World Health Organization has proposed and practised many methods of vector control through environmental management, chemical and biological orientations but still cannot fully overcome the problem. This paper proposed a detection of Aedes Aegypti larvae in water storage tank using Single Shot Multibox Detector with transfer learning. The objective of the study was to acquire the training and the performance metrics of the detection. The detection was done using SSD with Inception_V2 through transfer learning. The experimental results revealed that the probability detection scored more than 80% accuracies and there was no false alarm. These results demonstrate the effectiveness of the model approach.
INTEGRATED ASSOCIATIVE CLASSIFICATION AND NEURAL NETWORK MODEL ENHANCED BY US...IJDKP
The document summarizes a proposed methodology that integrates associative classification and neural networks for improved classification accuracy. It begins by introducing association rule mining and associative classification. It then describes using chi-squared analysis and the Gini index for attribute selection and rule pruning to generate a reduced set of rules. These rules are used to train a backpropagation neural network classifier. The methodology is tested on datasets from a public repository, demonstrating improved accuracy over traditional associative classification alone. Future work to integrate optical neural networks is also proposed.
Delineation of techniques to implement on the enhanced proposed model using d...ijdms
In post genomic era with the advent of new technologies a huge amount of complex molecular data are
generated with high throughput. The management of this biological data is definitely a challenging task
due to complexity and heterogeneity of data for discovering new knowledge. Issues like managing noisy
and incomplete data are needed to be dealt with. Use of data mining in biological domain has made its
inventory success. Discovering new knowledge from the biological data is a major challenge in data
mining technique. The novelty of the proposed model is its combined use of intelligent techniques to classify
the protein sequence faster and efficiently. Use of FFT, fuzzy classifier, String weighted algorithm, gram
encoding method, neural network model and rough set classifier in a single model and in an appropriate
place can enhance the quality of the classification system .Thus the primary challenge is to identify and
classify the large protein sequences in a very fast and easy but intellectual way to decrease the time
complexity and space complexity.
Document Classification Using Expectation Maximization with Semi Supervised L...ijsc
As the amount of online document increases, the demand for document classification to aid the analysis and management of document is increasing. Text is cheap, but information, in the form of knowing what classes a document belongs to, is expensive. The main purpose of this paper is to explain the expectation maximization technique of data mining to classify the document and to learn how to improve the accuracy while using semi-supervised approach. Expectation maximization algorithm is applied with both supervised and semi-supervised approach. It is found that semi-supervised approach is more accurate and effective. The main advantage of semi supervised approach is “DYNAMICALLY GENERATION OF NEW CLASS”. The algorithm first trains a classifier using the labeled document and probabilistically classifies the
unlabeled documents. The car dataset for the evaluation purpose is collected from UCI repository dataset in which some changes have been done from our side.
IRJET- A Detailed Study on Classification Techniques for Data MiningIRJET Journal
This document discusses classification techniques for data mining. It provides an overview of common classification algorithms including decision trees, k-nearest neighbors (kNN), and Naive Bayes. Decision trees use a top-down approach to classify data based on attribute tests at each node. kNN identifies the k nearest training examples to classify new data points. Naive Bayes assumes independence between attributes and uses Bayes' theorem for classification. The document also discusses how these techniques are used for data cleaning, integration, transformation and knowledge representation in the data mining process.
Anomaly detection by using CFS subset and neural network with WEKA tools Drjabez
This document summarizes a research paper that proposes a new approach for anomaly detection in computer networks using CFS subset selection and neural networks with WEKA tools. The proposed approach uses CFS to select important features and neural networks like MLP, logistic regression and ELM for classification. Experiments on datasets show the proposed approach has lower execution time, higher anomaly detection rates, and lower CPU utilization compared to other machine learning methods. The approach effectively detects different types of attacks in computer networks.
In the present paper, electroencephalogram (EEG)
data have been used to human identification by computing
sample entropy and graph entropy as feature extractions. Used
two classifier types, which are K-Nearest Neighbors (K-NN) and
Support Vector Machine (SVM). Python and Matlab software
were used in this study and EEG data was collected by UCI
repository . Matlab used when Thirteen channels was applied as
feature extraction . The experimental results show that, Python
software classifies the EEG-UCI data better than MATLAB
environment software where the accuracy of KNN and SVM
were 85.2% and 91.5% respectively.
A Comparative Study of Machine Learning Algorithms for EEG Signal Classificationsipij
In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector
machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM
have been compared. This comparison was conducted to seek a robust method that would produce good
classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG)
signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder
with SVM has been proposed. The EEG dataset used in this research was created by the University of
Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature
engineering. However, our prosed method of autoencoder in combination with SVM produced a similar
accuracy of 65% without using any feature engineering technique. This research shows that this system of
classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally
control a robotic device or an exoskeleton.
Jason K. Johnson is a postdoctoral fellow at Los Alamos National Laboratory who received his Ph.D from MIT. His research interests include machine learning, graphical models, and signal processing. He has over 250 citations and has published works in various journals and conferences on topics related to inference in graphical models.
This document discusses improved K-means clustering techniques. It begins with an introduction to data mining and clustering. K-means clustering groups data objects into k clusters by minimizing distances between objects and cluster centers. However, K-means has limitations such as dependency on initialization. The document proposes a new clustering algorithm that uses an iterative relocation technique and distance determination approach to improve upon K-means clustering. It compares the computational complexity of K-means and K-medoids clustering algorithms.
Abstract In this paper, the concept of data mining was summarized and its significance towards its methodologies was illustrated. The data mining based on Neural Network and Genetic Algorithm is researched in detail and the key technology and ways to achieve the data mining on Neural Network and Genetic Algorithm are also surveyed. This paper also conducts a formal review of the area of rule extraction from ANN and GA. Keywords: Data Mining, Neural Network, Genetic Algorithm, Rule Extraction.
IJRET : International Journal of Research in Engineering and Technology is an international peer reviewed, online journal published by eSAT Publishing House for the enhancement of research in various disciplines of Engineering and Technology. The aim and scope of the journal is to provide an academic medium and an important reference for the advancement and dissemination of research results that support high-level learning, teaching and research in the fields of Engineering and Technology. We bring together Scientists, Academician, Field Engineers, Scholars and Students of related fields of Engineering and Technology
A NOVEL DATA DICTIONARY LEARNING FOR LEAF RECOGNITIONsipij
Automatic leaf recognition via image processing has been greatly important for a number of professionals, such as botanical taxonomic, environmental protectors, and foresters. Learn an over-complete leaf dictionary is an essential step for leaf image recognition. Big leaf images dimensions and training images number is facing of fast and complete data leaves dictionary. In this work an efficient approach applies to construct over-complete data leaves dictionary to set of big images diminutions based on sparse representation. In the proposed method a new cropped-contour method has used to crop the training image. The experiments are testing using correlation between the sparse representation and data dictionary and with focus on the computing time.
Classification Of Iris Plant Using Feedforward Neural Networkirjes
The classification and recognition of type on the basis of individual features and behaviors constitute
a preliminary measure and is an important target in the behavioral sciences. Current statistical methods do not
always yield satisfactory answers. A Feed Forward Artificial Neural Network is the computer model inspired by
the structure of the Human Brain. It views as in the set of artificial nerve cells that are interconnected with the
other neurons. The primary aim of this paper is to demonstrate the process of developing the Artificial Neural
network based classifier which classifies the Iris database. The problem concerns the identification of Iris plant
species on the basis of plant attribute measurements. This paper is related to the use of feed forward neural
networks towards the identification of iris plants on the basis of the following measurements: sepal length, sepal
width, petal length, and petal width. Using this data set a Neural Network (NN) is used for the classification of
iris data set. The EBPA is used for training of this ANN. The results of simulations illustrate the effectiveness of
the neural system in iris class identification.
PREDICTION OF MALIGNANCY IN SUSPECTED THYROID TUMOUR PATIENTS BY THREE DIFFER...cscpconf
This document compares three classification methods - artificial neural networks, decision trees, and logistic regression - for predicting malignancy in thyroid tumor patients using a clinical dataset. It describes each method and applies them to a dataset of 259 thyroid tumor patients. The artificial neural network achieved 98% accuracy on the training set and 92% on the validation set. The decision tree method used 150 cases to build a model and achieved 86% accuracy. Logistic regression analysis resulted in 88% accuracy. The artificial neural network was able to accurately predict malignancy and identified important attributes like multiple nodules and family cancer history.
FEATURE EXTRACTION METHODS FOR IRIS RECOGNITION SYSTEM: A SURVEYijcsit
This document summarizes several feature extraction methods for iris recognition systems. It discusses supervised, unsupervised, and semi-supervised learning approaches for iris recognition. It also reviews related literature on iris recognition techniques, including using wavelet transforms, SVM classifiers, and other feature extraction methods. Tables in the document compare different biometric traits and traditional biometric systems, as well as summarize reviewed articles on iris recognition with their main contributions. The methodology section describes the typical four steps of an iris recognition system: image acquisition, preprocessing, feature extraction, and matching/recognition. It also discusses various iris recognition methods and their performance measures.
TUPLE VALUE BASED MULTIPLICATIVE DATA PERTURBATION APPROACH TO PRESERVE PRIVA...IJDKP
Huge volume of data from domain specific applications such as medical, financial, library, telephone,
shopping records and individual are regularly generated. Sharing of these data is proved to be beneficial
for data mining application. On one hand such data is an important asset to business decision making by
analyzing it. On the other hand data privacy concerns may prevent data owners from sharing information
for data analysis. In order to share data while preserving privacy, data owner must come up with a solution
which achieves the dual goal of privacy preservation as well as an accuracy of data mining task –
clustering and classification. An efficient and effective approach has been proposed that aims to protect
privacy of sensitive information and obtaining data clustering with minimum information loss
This document discusses a thesis that uses machine learning algorithms to diagnose mental illness using MRI brain scans. Specifically, it analyzes schizophrenia, bipolar disorder, and healthy control subject data from multiple imaging modalities. It trains and tests eight machine learning classifiers - support vector machines, k-nearest neighbors, logistic regression, naive Bayes, and random forests - on the raw imaging data as well as data transformed through dimensionality reduction techniques. The results aim to demonstrate the efficacy of these algorithms at classifying subjects based on their brain scans and diagnosing their mental condition.
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.
Recognition of emotional states using EEG signals based on time-frequency ana...IJECEIAES
The recognition of emotions is a vast significance and a high developing field of research in the recent years. The applications of emotion recognition have left an exceptional mark in various fields including education and research. Traditional approaches used facial expressions or voice intonation to detect emotions, however, facial gestures and spoken language can lead to biased and ambiguous results. This is why, researchers have started to use electroencephalogram (EEG) technique which is well defined method for emotion recognition. Some approaches used standard and pre-defined methods of the signal processing area and some worked with either fewer channels or fewer subjects to record EEG signals for their research. This paper proposed an emotion detection method based on time-frequency domain statistical features. Box-and-whisker plot is used to select the optimal features, which are later feed to SVM classifier for training and testing the DEAP dataset, where 32 participants with different gender and age groups are considered. The experimental results show that the proposed method exhibits 92.36% accuracy for our tested dataset. In addition, the proposed method outperforms than the state-of-art methods by exhibiting higher accuracy.
Prognosticating Autism Spectrum Disorder Using Artificial Neural Network: Lev...Avishek Choudhury
Autism spectrum condition (ASC) or autism spectrum disorder (ASD) is primarily identified with the help of behavioral indications encompassing social, sensory and motor characteristics. Although categorized, recurring motor actions are measured during diagnosis, quantifiable measures that ascertain kinematic physiognomies in the movement configurations of autistic persons are not adequately studied, hindering the advances in understanding the etiology of motor mutilation. Subject aspects such as behavioral characters that influences ASD need further exploration. Presently, limited autism datasets concomitant with screening ASD are available, and a majority of them are genetic. Hence, in this study, we used a dataset related to autism screening enveloping ten behavioral and ten personal attributes that have been effective in diagnosing ASD cases from controls in behavior science. ASD diagnosis is time exhaustive and uneconomical. The burgeoning ASD cases worldwide mandate a need for the fast and economical screening tool. Our study aimed to implement an artificial neural network with the Levenberg- Marquardt algorithm to detect ASD and examine its predictive accuracy. Consecutively, develop a clinical decision support system for early ASD identification.
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.
Detection of Aedes aegypti larvae using single shot multibox detector with tr...journalBEEI
The flavivirus epidemiology has reached an alarming rate which haunts the world population including Malaysia. In fact, World Health Organization has proposed and practised many methods of vector control through environmental management, chemical and biological orientations but still cannot fully overcome the problem. This paper proposed a detection of Aedes Aegypti larvae in water storage tank using Single Shot Multibox Detector with transfer learning. The objective of the study was to acquire the training and the performance metrics of the detection. The detection was done using SSD with Inception_V2 through transfer learning. The experimental results revealed that the probability detection scored more than 80% accuracies and there was no false alarm. These results demonstrate the effectiveness of the model approach.
INTEGRATED ASSOCIATIVE CLASSIFICATION AND NEURAL NETWORK MODEL ENHANCED BY US...IJDKP
The document summarizes a proposed methodology that integrates associative classification and neural networks for improved classification accuracy. It begins by introducing association rule mining and associative classification. It then describes using chi-squared analysis and the Gini index for attribute selection and rule pruning to generate a reduced set of rules. These rules are used to train a backpropagation neural network classifier. The methodology is tested on datasets from a public repository, demonstrating improved accuracy over traditional associative classification alone. Future work to integrate optical neural networks is also proposed.
Delineation of techniques to implement on the enhanced proposed model using d...ijdms
In post genomic era with the advent of new technologies a huge amount of complex molecular data are
generated with high throughput. The management of this biological data is definitely a challenging task
due to complexity and heterogeneity of data for discovering new knowledge. Issues like managing noisy
and incomplete data are needed to be dealt with. Use of data mining in biological domain has made its
inventory success. Discovering new knowledge from the biological data is a major challenge in data
mining technique. The novelty of the proposed model is its combined use of intelligent techniques to classify
the protein sequence faster and efficiently. Use of FFT, fuzzy classifier, String weighted algorithm, gram
encoding method, neural network model and rough set classifier in a single model and in an appropriate
place can enhance the quality of the classification system .Thus the primary challenge is to identify and
classify the large protein sequences in a very fast and easy but intellectual way to decrease the time
complexity and space complexity.
Document Classification Using Expectation Maximization with Semi Supervised L...ijsc
As the amount of online document increases, the demand for document classification to aid the analysis and management of document is increasing. Text is cheap, but information, in the form of knowing what classes a document belongs to, is expensive. The main purpose of this paper is to explain the expectation maximization technique of data mining to classify the document and to learn how to improve the accuracy while using semi-supervised approach. Expectation maximization algorithm is applied with both supervised and semi-supervised approach. It is found that semi-supervised approach is more accurate and effective. The main advantage of semi supervised approach is “DYNAMICALLY GENERATION OF NEW CLASS”. The algorithm first trains a classifier using the labeled document and probabilistically classifies the
unlabeled documents. The car dataset for the evaluation purpose is collected from UCI repository dataset in which some changes have been done from our side.
IRJET- A Detailed Study on Classification Techniques for Data MiningIRJET Journal
This document discusses classification techniques for data mining. It provides an overview of common classification algorithms including decision trees, k-nearest neighbors (kNN), and Naive Bayes. Decision trees use a top-down approach to classify data based on attribute tests at each node. kNN identifies the k nearest training examples to classify new data points. Naive Bayes assumes independence between attributes and uses Bayes' theorem for classification. The document also discusses how these techniques are used for data cleaning, integration, transformation and knowledge representation in the data mining process.
Anomaly detection by using CFS subset and neural network with WEKA tools Drjabez
This document summarizes a research paper that proposes a new approach for anomaly detection in computer networks using CFS subset selection and neural networks with WEKA tools. The proposed approach uses CFS to select important features and neural networks like MLP, logistic regression and ELM for classification. Experiments on datasets show the proposed approach has lower execution time, higher anomaly detection rates, and lower CPU utilization compared to other machine learning methods. The approach effectively detects different types of attacks in computer networks.
In the present paper, electroencephalogram (EEG)
data have been used to human identification by computing
sample entropy and graph entropy as feature extractions. Used
two classifier types, which are K-Nearest Neighbors (K-NN) and
Support Vector Machine (SVM). Python and Matlab software
were used in this study and EEG data was collected by UCI
repository . Matlab used when Thirteen channels was applied as
feature extraction . The experimental results show that, Python
software classifies the EEG-UCI data better than MATLAB
environment software where the accuracy of KNN and SVM
were 85.2% and 91.5% respectively.
A Comparative Study of Machine Learning Algorithms for EEG Signal Classificationsipij
In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector
machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM
have been compared. This comparison was conducted to seek a robust method that would produce good
classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG)
signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder
with SVM has been proposed. The EEG dataset used in this research was created by the University of
Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature
engineering. However, our prosed method of autoencoder in combination with SVM produced a similar
accuracy of 65% without using any feature engineering technique. This research shows that this system of
classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally
control a robotic device or an exoskeleton.
A Comparative Study of Machine Learning Algorithms for EEG Signal Classificationsipij
In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector
machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM
have been compared. This comparison was conducted to seek a robust method that would produce good
classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG)
signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder
with SVM has been proposed. The EEG dataset used in this research was created by the University of
Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature
engineering. However, our prosed method of autoencoder in combination with SVM produced a similar
accuracy of 65% without using any feature engineering technique. This research shows that this system of
classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally
control a robotic device or an exoskeleton.
A Comparative Study of Machine Learning Algorithms for EEG Signal Classificationsipij
In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector
machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM
have been compared. This comparison was conducted to seek a robust method that would produce good
classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG)
signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder
with SVM has been proposed. The EEG dataset used in this research was created by the University of
Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature
engineering. However, our prosed method of autoencoder in combination with SVM produced a similar
accuracy of 65% without using any feature engineering technique. This research shows that this system of
classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally
control a robotic device or an exoskeleton.
A COMPARATIVE STUDY OF MACHINE LEARNING ALGORITHMS FOR EEG SIGNAL CLASSIFICATIONsipij
In this paper, different machine learning algorithms such as Linear Discriminant Analysis, Support vector
machine (SVM), Multi-layer perceptron, Random forest, K-nearest neighbour, and Autoencoder with SVM
have been compared. This comparison was conducted to seek a robust method that would produce good
classification accuracy. To this end, a robust method of classifying raw Electroencephalography (EEG)
signals associated with imagined movement of the right hand and relaxation state, namely Autoencoder
with SVM has been proposed. The EEG dataset used in this research was created by the University of
Tubingen, Germany. The best classification accuracy achieved was 70.4% with SVM through feature
engineering. However, our prosed method of autoencoder in combination with SVM produced a similar
accuracy of 65% without using any feature engineering technique. This research shows that this system of
classification of motor movements can be used in a Brain-Computer Interface system (BCI) to mentally
control a robotic device or an exoskeleton.
Data modelling and data processing generated by human eye movements IJECEIAES
Data modeling and data processing are important activities in any scientific research. This research focuses on the modeling of data and processing of data generated by a saccadometer. The approach used is based on the relational data model, but the processing and storage of the data is done with client datasets. The experiments were performed with 26 randomly selected files from a total of 264 experimental sessions. The data from each experimental session was stored in three different formats, respectively text, binary and extensible markup language (XML) based. The results showed that the text format and the binary format were the most compact. Several actions related to data processing were analyzed. Based on the results obtained, it was found that the two fastest actions are respectively loading data from a binary file and storing data into a binary file. In contrast, the two slowest actions were storing the data in XML format and loading the data from a text file, respectively. Also, one of the time-consuming operations turned out to be the conversion of data from text format to binary format. Moreover, the time required to perform this action does not depend in proportion on the number of records processed.
CLASSIFICATION OF ELECTROENCEPHALOGRAM SIGNALS USING XGBOOST ALGORITHM AND SU...IRJET Journal
This document presents a study that uses the XGBoost algorithm and support vector machine to classify electroencephalogram (EEG) signals. The study acquires EEG data from healthy subjects and subjects with epilepsy during seizure and non-seizure periods. It preprocesses the data, extracts features using linear discriminant analysis, and feeds the extracted features into XGBoost and SVM classifiers. The results indicate that XGBoost exhibited superior classification performance compared to SVM for analyzing and classifying EEG signals.
Study and analysis of motion artifacts for ambulatory electroencephalographyIJECEIAES
Motion artifacts contribute complexity in acquiring clean electroencephalography (EEG) data. It is one of the major challenges for ambulatory EEG. The performance of mobile health monitoring, neurological disorders diagnosis and surgeries can be significantly improved by reducing the motion artifacts. Although different papers have proposed various novel approaches for removing motion artifacts, the datasets used to validate those algorithms are questionable. In this paper, a unique EEG dataset was presented where ten different activities were performed. No such previous EEG recordings using EMOTIV EEG headset are available in research history that explicitly mentioned and considered a number of daily activities that induced motion artifacts in EEG recordings. Quantitative study shows that in comparison to correlation coefficient, the coherence analysis depicted a better similarity measure between motion artifacts and motion sensor data. Motion artifacts were characterized with very low frequency which overlapped with the Delta rhythm of the EEG. Also, a general wavelet transform based approach was presented to remove motion artifacts. Further experiment and analysis with more similarity metrics and longer recording duration for each activity is required to finalize the characteristics of motion artifacts and henceforth reliably identify and subsequently remove the motion artifacts in the contaminated EEG recordings.
This document summarizes an approach for automated EEG artifact elimination using machine learning algorithms applied to features extracted from independent component analysis (ICA). The method involves preprocessing the EEG data with filtering and ICA, then generating features from the ICA results like topographic maps and power spectra. Machine learning classifiers like support vector machines and artificial neural networks are trained on the features to classify components as artifacts or EEG. The best performance was 95% accuracy using a neural network classifier trained on features from topographic map filtering and power spectra. This automated approach avoids time-consuming manual classification and enables real-time artifact removal.
Efficient electro encephelogram classification system using support vector ma...nooriasukmaningtyas
Complex modern signal processing is used to automate the analysis of electro encephelogram (EEG) signals. For the diagnosis of seizures, approaches that are simple and precise may be preferable rather than difficult and time-consuming. In this paper, efficient EEG classification system using support vector machine (SVM) and Adaptive learning technique is proposed. The database EEG signals are subjected to temporal and spatial filtering to remove unwanted noise and to increase the detection accuracy of the classifier by selecting the specific bands in which most of the EEG data are present. The neural network based SVM is used to classify the test EEG data with respect to training data. The cost-sensitive SVM with proposed Adaptive learning classifies the EEG signals where the adaptive learning with probability based function helps in prediction of the future samples and this leads in improving the accuracy with detection time. The detection accuracy of the proposed algorithm is compared with existing which shows that the proposed algorithm can classify the EEG signal more effectively.
This document discusses developing a generic EEG classification system using brain signals for brain-computer interface applications. The system architecture includes EEG signal acquisition, preprocessing to remove noise and artifacts, feature extraction using independent component analysis and power spectral density, dimensionality reduction, classification using convolutional neural networks, and postprocessing. The goals are to extract spatial and temporal information from EEG signals to classify different brain states and movements like hand movement, tongue movement, walking, eye blinks, and more. This will help build a robust EEG classification system to be used in various BCI applications.
This document describes a smart home system designed to aid paralyzed individuals living alone. EEG signals are collected from 25 paralyzed subjects to study brain activity related to hunger, thirst, sleepiness, excitement and stress. The EEG data is preprocessed and classified using kNN classifiers to identify the individual's needs. An Internet of Things platform uses the classified EEG data to make logical decisions and control automated modules to meet the person's basic needs. These include modules for feeding, sleep, temperature control and more. Experimental results showed an overall 89.73% accuracy for automating units to fulfill a paralyzed person's basic needs. The system aims to help paralyzed individuals live more independently at home.
During seizures, different types of communication between different parts of the brain are characterized by many state of the art connectivity measures. We propose to employ a set of undirected (spectral matrix, the inverse of the spectral matrix, coherence, partial coherence, and phase-locking value) and directed features (directed coherence, the partial directed coherence) to detect seizures using a deep neural network. Taking our data as a sequence of ten sub-windows, an optimal deep sequence learning architecture using attention, CNN, BiLstm, and fully connected neural networks is designed to output the detection label and the relevance of the features. The relevance is computed using the weights of the model in the activation values of the receptive fields at a particular layer. The best model resulted in 97.03% accuracy using balanced MIT-BIH data subset. Finally, an analysis of the relevance of the features is reported.
Using Brain Waves as New Biometric Feature for Authenticatinga Computer User...Buthainah Hamdy
This document presents a brain-computer interface (BCI) for person authentication using electroencephalography (EEG) signals. The BCI is used to lock and unlock a computer screen based on a user's brain activity. EEG data is collected from 14 sensors while users perform mental tasks. Power spectral density is calculated from the EEG signals and used as features for a two-stage classification system. The system achieves over 78% accuracy in authenticating users based on their brain activity patterns.
Survey analysis for optimization algorithms applied to electroencephalogramIJECEIAES
This paper presents a survey for optimization approaches that analyze and classify electroencephalogram (EEG) signals. The automatic analysis of EEG presents a significant challenge due to the high-dimensional data volume. Optimization algorithms seek to achieve better accuracy by selecting practical features and reducing unwanted features. Forty-seven reputable research papers are provided in this work, emphasizing the developed and executed techniques divided into seven groups based on the applied optimization algorithm particle swarm optimization (PSO), ant colony optimization (ACO), artificial bee colony (ABC), grey wolf optimizer (GWO), Bat, Firefly, and other optimizer approaches). The main measures to analyze this paper are accuracy, precision, recall, and F1-score assessment. Several datasets have been utilized in the included papers like EEG Bonn University, CHB-MIT, electrocardiography (ECG) dataset, and other datasets. The results have proven that the PSO and GWO algorithms have achieved the highest accuracy rate of around 99% compared with other techniques.
This document presents a new approach for ECG feature extraction and heartbeat classification using mathematical morphology. The key points are:
1) Mathematical morphology filtering is used to preprocess the ECG signal before feature extraction in order to normalize variations between heartbeats.
2) Features are extracted from the preprocessed ECG signal and fed into a Kohonen self-organizing map for clustering.
3) A Learning Vector Quantization classifier is then trained on the clustered features to classify heartbeats as normal or abnormal.
4) The method is evaluated on the MIT-BIH Arrhythmia Database and shows improved classification performance over using the original unprocessed ECG signal.
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.
This document discusses the development of a scalable neural network platform for predictive metabonomics. It aims to create a "white box" neural network model that allows users full control over the network architecture. Particle swarm optimization will be used to train the network. The implementation uses C++ and OpenNN libraries in Visual Studio. Future work includes applying neural networks to other applications like structure activity relationships and instrument optimization, and creating a graphical user interface.
0 eeg based 3 d visual fatigue evaluation using cnnHoopeer Hoopeer
This document describes a new multi-scale convolutional neural network (CNN) called MorletInceptionNet that is designed to detect visual fatigue levels using electroencephalogram (EEG) signals as input. The network uses Morlet wavelet-like kernels to extract time-frequency features from the EEG data. It then uses inception modules of different kernel sizes to extract multi-scale temporal features, which are concatenated and fed into fully connected layers for classification. An evaluation of the network on EEG data collected during a visual fatigue experiment showed it achieved better classification accuracy and kappa values than five state-of-the-art methods, demonstrating it is effective at automatically evaluating visual fatigue levels from EEG signals.
Effective electroencephalogram based epileptic seizure detection using suppo...IJECEIAES
Epilepsy is one of the widespread disorders. It is a noncommunicable disease that affects the human nerve system. Seizures are abnormal patterns of behavior in the electricity of the brain which produce symptoms like losing consciousness, attention or convulsions in the whole body. This paper demonstrates an effective electroencephalogram (EEG) based seizure detection method using discrete wavelet transformation (DWT) for signal decomposition to extract features. An automatic channel selection method was proposed by the researcher to select the best channel from 23 channels based on maximum variance value. The records were segmented into a nonoverlapping segment with long 1-S. The support vector machine (SVM) model was used to automatically detect segments that contain seizures, using both frequency and time domain statistical moment features. The experimental result was obtained from 24 patients in CHB-MIT database. The average accuracy is 94.1, sensitivity is 93.5, specificity is 94.6 and the false positive rate average is 0.054.
Digital Health in India_Health Informatics Trained Manpower _DrDevTaneja_15.0...DrDevTaneja1
Digital India will need a big trained army of Health Informatics educated & trained manpower in India.
Presently, generalist IT manpower does most of the work in the healthcare industry in India. Academic Health Informatics education is not readily available at school & health university level or IT education institutions in India.
We look into the evolution of health informatics and its applications in the healthcare industry.
HIMMS TIGER resources are available to assist Health Informatics education.
Indian Health universities, IT Education institutions, and the healthcare industry must proactively collaborate to start health informatics courses on a big scale. An advocacy push from various stakeholders is also needed for this goal.
Health informatics has huge employment potential and provides a big business opportunity for the healthcare industry. A big pool of trained health informatics manpower can lead to product & service innovations on a global scale in India.
At Malayali Kerala Spa Ajman we providing the top quality massage services for our customers.
Our massage center prioritizes efficiency to ensure a quality massage experience for our clients at Malayali Kerala Spa Ajman. We offer a convenient appointment system and precise massage services.
Reach us at Villa No 7, Near Ammar Bin Yasir Street Al Rashidiya 2 - Ajman - United Arab Emirates.
Phone : +971 529818279
At Malayali Kerala Spa Ajman, Full Service includes individualized care for every client. We specifically design each massage session for the individual needs of the client. Our therapists are always willing to adjust the treatments based on the client's instruction and feedback. This guarantees that every client receives the treatment they expect.
By offering a variety of massage services, our Ajman Spa Massage Center can tackle physical, mental, and emotional illnesses. In addition, efficient identification of specific health conditions and designing treatment plans accordingly can significantly enhance the quality of massaging.
At Malayali Kerala Spa Ajman, we firmly believe that everyone should have the option to experience top-quality massage services regularly. To achieve that goal we offer cheap massage services in Ajman.
If you are interested in experiencing transformative massage treatment at Malayali Kerala Spa Ajman, you can use our Ajman Massage Center WhatsApp Number to schedule your next massage session.
Contact @ +971 529818279
Visit @ https://malayalikeralaspaajman.com/
2024 Media Preferences of Older Adults: Consumer Survey and Marketing Implica...Media Logic
When it comes to creating marketing strategies that target older adults, it is crucial to have insight into their media habits and preferences. Understanding how older adults consume and use media is key to creating acquisition and retention strategies. We recently conducted our seventh annual survey to gain insight into the media preferences of older adults in 2024. Here are the survey responses and marketing implications that stood out to us.
NURSING MANAGEMENT OF PATIENT WITH EMPHYSEMA .PPTblessyjannu21
Prepared by Prof. BLESSY THOMAS, VICE PRINCIPAL, FNCON, SPN.
Emphysema is a disease condition of respiratory system.
Emphysema is an abnormal permanent enlargement of the air spaces distal to terminal bronchioles, accompanied by destruction of their walls and without obvious fibrosis.
Emphysema of lung is defined as hyper inflation of the lung ais spaces due to obstruction of non respiratory bronchioles as due to loss of elasticity of alveoli.
It is a type of chronic obstructive
pulmonary disease.
It is a progressive disease of lungs.
nursing management of patient with Empyema pptblessyjannu21
prepared by Prof. BLESSY THOMAS, SPN
Empyema is a disease of respiratory system It is defines as the accumulation of thick, purulent fluid within the pleural space, often with fibrin development.
Empyema is also called pyothorax or purulent pleuritis.
It’s a condition in which pus gathers in the area between the lungs and the inner surface of the chest wall. This area is known as the pleural space.
Pus is a fluid that’s filled with immune cells, dead cells, and bacteria.
Pus in the pleural space can’t be coughed out. Instead, it needs to be drained by a needle or surgery.
Empyema usually develops after pneumonia, which is an infection of the lung tissue. it is mainly caused due in infectious micro-organisms. It can be treated with medications and other measures.
THE SPECIAL SENCES- Unlocking the Wonders of the Special Senses: Sight, Sound...Nursing Mastery
Title: Unlocking the Wonders of the Special Senses: Sight, Sound, Smell, Taste, and Balance
Introduction:
Welcome to our captivating SlideShare presentation on the Special Senses, where we delve into the extraordinary capabilities that allow us to perceive and interact with the world around us. Join us on a sensory journey as we explore the intricate structures and functions of sight, sound, smell, taste, and balance.
The special senses are our primary means of experiencing and interpreting the environment, each sense providing unique and vital information that shapes our perceptions and responses. These senses are facilitated by highly specialized organs and complex neural pathways, enabling us to see a vibrant sunset, hear a symphony, savor a delicious meal, detect a fragrant flower, and maintain our equilibrium.
In this presentation, we will:
Visual System (Sight): Dive into the anatomy and physiology of the eye, exploring how light is converted into electrical signals and processed by the brain to create the images we see. Understand common vision disorders and the mechanisms behind corrective measures like glasses and contact lenses.
Auditory System (Hearing): Examine the structures of the ear and the process of sound wave transduction, from the outer ear to the cochlea and auditory nerve. Learn about hearing loss, auditory processing, and the advances in hearing aid technology.
Olfactory System (Smell): Discover the olfactory receptors and pathways that enable the detection of thousands of different odors. Explore the connection between smell and memory and the impact of olfactory disorders on quality of life.
Gustatory System (Taste): Uncover the taste buds and the five basic tastes – sweet, salty, sour, bitter, and umami. Delve into the interplay between taste and smell and the factors influencing our food preferences and eating habits.
Vestibular System (Balance): Investigate the inner ear structures responsible for balance and spatial orientation. Understand how the vestibular system helps maintain posture and coordination, and explore common vestibular disorders and their effects.
Through engaging visuals, interactive diagrams, and insightful explanations, we aim to illuminate the complexities of the special senses and their profound impact on our daily lives. Whether you're a student, educator, or simply curious about how we perceive the world, this presentation will provide valuable insights into the remarkable capabilities of the human sensory system.
Join us as we unlock the wonders of the special senses and gain a deeper appreciation for the intricate mechanisms that allow us to experience the richness of our environment.
VEDANTA AIR AMBULANCE SERVICES IN REWA AT A COST-EFFECTIVE PRICE.pdfVedanta A
Air Ambulance Services In Rewa works in close coordination with ground-based emergency services, including local Emergency Medical Services, fire departments, and law enforcement agencies.
More@: https://tinyurl.com/2shrryhx
More@: https://tinyurl.com/5n8h3wp8
Test bank advanced health assessment and differential diagnosis essentials fo...rightmanforbloodline
Test bank advanced health assessment and differential diagnosis essentials for clinical practice 1st edition myrick.
Test bank advanced health assessment and differential diagnosis essentials for clinical practice 1st edition myrick.
Test bank advanced health assessment and differential diagnosis essentials for clinical practice 1st edition myrick.
Malayali Kerala Spa in Ajman, one among the top rated massage centre in ajman, welcomes you to experience high quality massage services from massage staffs from all ove rthe world! Being the best spa massage service providers, we take pride in offering traditional massage services of different countries, like
Indian Massage, Kerala Massage, Thai Massage, Pakistani Massage, Russian Massage etc
If you are seeking relaxation, pain relief, or wellness experience, our ajman spa is here for your unique needs and concerns. The services of our experienced therapists, and personalized attention will ensure that each visit will be memorable for you.
Book your appointment today and let us take you to a world of serenity and self-care. Because you deserves the best.
The Ultimate Guide in Setting Up Market Research System in Health-TechGokul Rangarajan
How to effectively start market research in the health tech industry by defining objectives, crafting problem statements, selecting methods, identifying data collection sources, and setting clear timelines. This guide covers all the preliminary steps needed to lay a strong foundation for your research.
"Market Research it too text-booky, I am in the market for a decade, I am living research book" this is what the founder I met on the event claimed, few of my colleagues rolled their eyes. Its true that one cannot over look the real life experience, but one cannot out beat structured gold mine of market research.
Many 0 to 1 startup founders often overlook market research, but this critical step can make or break a venture, especially in health tech.
But Why do they skip it?
Limited resources—time, money, and manpower—are common culprits.
"In fact, a survey by CB Insights found that 42% of startups fail due to no market need, which is like building a spaceship to Mars only to realise you forgot the fuel."
Sudharsan Srinivasan
Operational Partner Pitchworks VC Studio
Overconfidence in their product’s success leads founders to assume it will naturally find its market, especially in health tech where patient needs, entire system issues and regulatory requirements are as complex as trying to perform brain surgery with a butter knife. Additionally, the pressure to launch quickly and the belief in their own intuition further contribute to this oversight. Yet, thorough market research in health tech could be the key to transforming a startup's vision into a life-saving reality, instead of a medical mishap waiting to happen.
Example of Market Research working
Innovaccer, founded by Abhinav Shashank in 2014, focuses on improving healthcare delivery through data-driven insights and interoperability solutions. Before launching their platform, Innovaccer conducted extensive market research to understand the challenges faced by healthcare organizations and the potential for innovation in healthcare IT.
Identifying Pain Points: Innovaccer surveyed healthcare providers to understand their difficulties with data integration, care coordination, and patient engagement. They found widespread frustration with siloed systems and inefficient workflows.
Competitive Analysis: Analyzed competitors offering similar solutions in healthcare analytics and interoperability. Identified gaps in comprehensive data aggregation, real-time analytics, and actionable insights.
Regulatory Compliance: Ensured their platform complied with HIPAA and other healthcare data privacy regulations. This compliance was crucial to gaining trust from healthcare providers wary of data security issues.
Customer Validation: Conducted pilot programs with several healthcare organizations to validate the platform's effectiveness in improving care outcomes and operational efficiency. Gathered feedback to refine features and user interface.
3. R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772 3
Value of the Data
• This dataset of EEG signals is recorded to monitor the stress-induced among individuals
while performing various tasks such as: performing the Stroop color-word test, solving math-
ematical problems, identification of symmetric mirror images, and a state of relaxation. The
goal of the dataset was aimed at capturing the induced stress due to each of the individual
tasks.
• This dataset will help the research communities in the identification of patterns in EEG
elicited due to stress and can also be used to identify perceived stress in an individual.
• Behavioral ratings of stress levels were also collected from the participants for each of the
tasks- Stroop color-word test, arithmetic problem solving, and mirror image recognition task.
The ratings of the individual subjects are also provided with this dataset. These measures
may prove useful for additional analysis that has not yet been explored.
• The dataset can also be utilized in clinical diagnosis for the identification of stress among
subjects.
• Additional research on the source localization of the EEG signals responsible for stress can
be carried out from the data. Classification of EEG signals based on cognitive tasks of an
individual can be used for additional inference. Moreover, the type of task that elicits the
maximum amount of stress can be analyzed from the dataset.
1. Data Description
This dataset is structured in two main folders (/raw_data and /filtered_data). The /raw_data
folder contains the EEG time-series segmented in epochs corresponding to the experimental tri-
als and has been named accordingly to identify the experimental events and the trial. The EEG
data present in the /raw_data folder contains noise and is also corrupted with artifacts. The /fil-
tered_data folder contains the clean EEG data and is free from different artifacts. Both raw and
clean data have been provided to facilitate the research activity as different filtering methods
may be applied by different researchers to remove artifacts from the EEG data. Moreover, a .xls
file named scales.xls is also given along with the EEG data. The file provides the feedback by the
subjects on a scale of 1–10 depending on the stress levels experienced by the subject during a
particular task in a trial. Besides, a .locs file named as Coordinates.locs has also been provided to
facilitate the plotting of the EEG data. Moreover, another folder named /artifact_removal is also
provided which contains the code for artifact removal. The correct_EEG.m file provides the code
for the artifact removal procedure implemented in Matlab. The /artifact_removal folder contains
two .mat files namely Corrupted_EEG.mat and Cleaned_EEG.mat which represent a sample EEG
recording before and after the removal of artifacts respectively. The two files have been provided
in the folder for the purpose of demonstration of the Matlab code and have been extracted from
subject 10 while performing the arithmetic task. It is to be noted that both raw EEG data and
filtered EEG data have been uploaded to the portal. The /filtered data folder contains the fil-
tered EEG data of all the segmented trials which have been obtained using the correct_EEG.m
file provided in the /artifact_removal folder and the /raw_data folder contains the unfiltered raw
EEG data. The artifact removal procedure has been described in the data pre-processing section.
The EEG data provided in the folders are segmented according to the respective tasks- Stroop
color-word test, arithmetic task, mirror image recognition task, and a state of relaxation. The
corresponding files are provided in EEGLAB format and can be loaded into EEGLAB using ‘Load
existing dataset’ from the ‘File’ menu. In order to visualize individual channels, ‘Channel data
(scroll)’ from the ‘Plot’ menu has to be selected to generate the plot (Figs. 6 and 7 are generated
using the described procedure). The description of the corresponding experimental tasks and the
methodology to generate the data are described in the next section.
The past decade has witnessed an ever-increasing growth in the field of brain-computer in-
terface (BCI). BCI’s have been developed for various applications like motor imagery, prosthesis,
emotion recognition, etc. Emotion plays a significant role in cognition, motivation, perception,
4. 4 R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772
creativity, attention, learning, and decision-making [4]. The visualization of mental states has a
lot of potentials and can greatly aid psychologists in diagnosing mental disorders.
The primary goal of this dataset is to capture the level of stress elicited in individuals while
performing different types of tasks such as performing the Stroop color-word test, solving arith-
metic problems, and recognizing symmetric mirror images. The dataset can be used to identify
the levels of stress induced in an individual, while performing different tasks.
2. Description of the Different Mental Tasks
The dataset is created to primarily monitor the stress induced in an individual while per-
forming different cognitive tasks. The different cognitive tasks considered for the experiment
are: the Stroop color word test, arithmetic problem solving, and recognition of symmetric im-
ages. The different tasks are described below.
2.1. Stroop color word test
The Stroop Color- Word Test (SCWT) is a neuropsychological test used to assess the cognitive
inference ability while processing multiple stimuli [1]. SCWT has been used in the literature
[2] to induce stress in subjects and therefore has been adopted in the present work. The subjects
are asked to identify the names of colors printed in different color patches. Accordingly, there
are two conditions- congruent condition and incongruent condition. In congruent condition, the
name of the color matches with the color of the ink with which the word is printed and in
incongruent condition, the name of the color does not match with the ink with which the word
is printed. Both the conditions are represented in Fig. 1(a) and Fig. 1(b), respectively. 11 such
impulses comprising of both congruent and incongruent conditions are presented to the subject
in a trial during the course of the experiment.
2.2. Mirror image recognition task
Images have also been used in the literature to induce various types of emotions [3,4] and
thus have been adopted in the present work to induce stress in the subjects. In the proposed
work, mirror images are presented to the subject and is asked to identify whether the displayed
images are symmetric or asymmetric to each other. Fig. 2(a) and (b) shows one such symmetric
and asymmetric mirror images used in the present work respectively. The mirror images have
been designed so as to induce stress in students during the course of experimentation. 8 such
images have been used in the proposed work for eliciting stress in individuals during a trial.
2.3. Arithmetic problem solving task
Arithmetic problem solving task is known to elicit stress in individuals [5]. In the proposed
work, the subject is asked to mentally solve the problem and respond with a thumbs up or
thumbs down gesture depending on whether the answer displayed on the screen is a correct
solution for the arithmetic problem or not. Fig. 3 depicts one such arithmetic stimuli used in the
proposed work. 6 such arithmetic stimuli involving different arithmetic operators are presented
in a trial to the subject during the course of the experiment.
5. R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772 5
Fig. 1. (a) Congruent condition in SCWT. (b) Incongruent condition in SCWT.
3. Experimental Design, Materials and Methods
The data were collected primarily from the students studying in the institute. 14 female and
26 male students participated in the experiment. The age of the subjects ranged from 18 to
25 years with a mean age of 21.5 years. The subjects were asked to solve the tasks within a
specified time. Written consent was obtained from the individual subject before participating in
the experiment. EEG data were recorded from 32-channels using Emotiv Epoc Flex gel kit at a
sampling frequency of 128 Hz. The channels considered for recording the brain activity were- CZ,
FZ, Fp1, F7, F3, FC1, C3, FC5, FT9, T7, CP5, CP1, P3, P7, PO9, O1, PZ, OZ, O2, PO10, P8, P4, CP2, CP6,
T8, FT10, FC6, C4, FC2, F4, F8, and, Fp2. Fig. 4 shows the placement of the different electrodes on
the head of an individual. CMS and DRL are two reference electrodes connected to the left and
the right mastoid region of the head respectively. Three trials were recorded for an individual
subject. The trail recording paradigm is described in the next section.
6. 6 R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772
Fig. 2. (a) Symmetric mirror image. (b) Asymmetric mirror image.
3.1. Data recording methodology
The experiment is set up by the experimenters in the beginning. Then the EEG device is
mounted over the subject and instructions are given to the subject regarding the experiment.
Then the experimenter starts to record the EEG data and the subject is asked to perform the
various tasks. The subject is initially asked to relax for 25 s where relaxing music is played to
ease the subject. After which, the instructions for the Stroop color-word test is shown to the
subjects. The subject is asked to perform the Stroop color-word test for 25 s. The subject then
relaxes for 5 s and then the instructions for the next task are displayed for 10 s. In the next
7. R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772 7
Fig. 3. An Arithmetic task stimuli.
Fig. 4. Placement of the 32 electrodes.
8. 8 R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772
Table 1
Tabular representation of verbal feedback from the observer after each trial on a scale of 1–10.
Trial_1 Trial_2 Trial_3
Subject
No.
Stroop
Color-word
Test
Arithmetic
Task
Mirror Image
Recognition
Task
Stroop
Color-word
Test
Arithmetic
Task
Mirror Image
Recognition
Task
Stroop
Color-word
Test
Arithmetic
Task
Mirror Image
Recognition
Task
1 3 6 3 2 7 5 4 4 7
2 5 3 4 4 3 4 3 7 5
3 4 5 3 5 3 5 5 8 7
4 4 5 3 2 3 5 5 7 5
5 6 6 6 2 5 3 3 5 7
6 2 5 4 3 4 3 5 8 6
7 4 5 5 3 3 3 6 6 3
8 4 3 5 3 6 6 3 5 6
9 4 3 6 4 4 4 6 7 4
10 4 3 4 3 4 5 5 6 4
11 4 7 3 5 6 5 5 5 6
12 2 5 7 5 5 4 3 8 6
13 3 3 5 2 3 4 1 3 5
14 3 3 4 2 6 4 4 6 3
15 5 9 6 3 7 5 5 6 5
16 1 4 4 1 5 6 6 8 5
17 8 8 9 4 6 8 6 7 7
18 6 6 5 5 5 6 7 9 6
19 6 4 6 3 2 4 3 4 1
20 7 10 9 5 10 9 6 10 8
21 9 7 8 9 8 8 9 7 8
22 5 9 8 6 8 8 5 7 6
23 1 3 2 1 4 2 5 8 4
24 1 4 2 1 2 1 4 5 7
25 2 2 1 2 2 1 5 5 7
26 8 6 7 7 6 8 6 4 5
27 3 5 5 2 3 4 3 5 3
28 7 7 8 5 7 7 4 6 5
29 6 6 7 6 8 7 5 6 6
30 5 7 6 5 8 6 4 7 5
31 4 10 8 3 9 7 7 6 3
32 1 5 5 1 1 2 3 7 6
33 3 5 4 2 3 2 6 8 3
34 1 2 3 1 3 1 3 2 2
35 1 6 5 1 5 2 5 4 6
36 6 4 4 3 5 4 5 5 5
37 4 6 5 2 5 3 6 8 4
38 5 6 4 3 5 6 3 4 5
39 3 6 4 3 5 5 5 6 3
40 5 3 5 5 4 6 3 4 4
phase, the subject is shown different mirror images and is asked to identify whether the images
are symmetric or asymmetric and respond with a thumbs up or thumbs down gesture depend-
ing on whether the images displayed represent symmetric mirror images or not. The mirror
image symmetry task is carried out for 25 s, after which the subject again relaxes for 5 s and
then the instructions for the next task are displayed for 10 s. Finally, the subject is instructed to
solve arithmetic problems where the subject is asked to mentally solve the problem and respond
with a thumbs up or thumbs down gesture depending on whether the answer displayed on the
screen is a correct solution for the corresponding arithmetic problem or not. The arithmetic task
is also carried out for 25 s. The completion of the arithmetic task marks the completion of a
trial. Moreover, when the subject is responding, an operator also gives feedback as to whether
the answers provided by the subject are incorrect or correct.
After finishing an individual trial, the subject is asked to rate the tasks on a scale of 1–10 de-
pending on the level of stress experienced during the particular tasks. A rating of 10 on the scale
represents a high level of stress being induced on the subjects and a rating of 1 representing the
minimal amount of stress being experienced by the subjects.
After collecting the responses from the subject, the next trial is recorded. The next trial is
repeated in the same order, but with a different set of questions as the subject might become
familiarized with the questions. 3 trials were recorded from an individual subject. Fig. 5 repre-
sents the trail recording paradigm followed in the experiment and Table 1 lists the individual
ratings for different tasks in a trial given by a specific subject.
9. R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772 9
Fig.
5.
Trial
recording
paradigm.
10. 10 R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772
Fig. 6. EEG Data of Subject 10 before artifact removal.
3.2. Data pre-processing
The raw data was imported and clipped in Matlab R2019a. Band-pass filtering in the range of
0.5–45 Hz was applied to the data initially. The collected data were contaminated with different
types of artifacts. Fig. 6 represents one such plot of EEG data before artifact removal for subject
10 while performing the arithmetic task in the third trial. The figure has been generated using
the EEGLAB toolbox as described in the data description section. It is evident from Fig. 6 that
the EEG data is corrupted with different types of artifacts.
Components containing artifacts (i.e., eye movements, eye blinks, muscular activity, etc.) were
identified and removed using a combination of Savitzky-Golay filter and wavelet thresholding
[6,7]. Artifacts are signals caused by muscle movements and eye movements which corrupt the
original EEG signal. Savitzky-Golay smoothing filters are used to "smooth out" a noisy signal. The
Savitzky-Golay filter is created with a frame length of 127 and an order of 5. The Savitzky-Golay
smoothing filters are used to create a reference signal, which is subtracted from the EEG data
to remove the average trend in the EEG data. After removing the average trend from the EEG
signal, wavelet thresholding is applied to remove the components which have amplitude values
over a certain threshold in different scales. The signal is decomposed up to 4 levels with ‘db2’
(Daubechies 2) as the mother wavelet. A threshold of 0.8 times the standard deviation of the
detailed coefficient at the third level of decomposition is selected for thresholding. The thresh-
olding removes the remaining components which were not removed after subtraction of the av-
erage trend from the EEG. The artifact removal procedure has been given in the correct_EEG.m
file within the /artifact_removal folder.
Both Raw EEG data and filtered EEG data have been uploaded to facilitate research as differ-
ent artifact removal methods can be applied by different researchers on the EEG data which can
make the analysis more efficient.
Fig. 7 represents the corrected version of the EEG represented in Fig. 6. It can be observed
from Fig. 7 that the artifact removal procedure adopted in the proposed work efficiently removes
the artifacts from the EEG data and preserves good correlation in the EEG data.
11. R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772 11
Fig. 7. EEG Data of Subject 10 after artifact removal.
Fig. 8. EEG topography plot from clean data.
3.3. Naming convention
EEG data files contain four types of event codes: (i) Mat files that correspond to the relax-
ation phase are marked as ‘relax’. Please note that the files also mark the subject and the trials.
(ii) Mat files that correspond to the Stroop color-word test are marked as ‘Stroop’ (iii) Mat files
that correspond to the mirror image recognition task are marked as ‘Mirror_image’ and (iv) Mat
files that correspond to the arithmetic problems are marked as ‘Arithmetic’. Fig. 8 represents
the topographic plot of the CZ electrode of subject 17 w.r.t the different tasks performed by the
subject. The plots have been generated by using the ‘topoplot’ function available in the EEGLAB
toolbox.
3.4. Observer’s feedback
After each trial, the subject’s feedback in terms of the level of stress experienced during dif-
ferent tasks is taken on a scale of 1 to 10. The ratings have been taken to correlate the EEG
data to the amount of stress experienced by the subjects. A rating of 10 on the scale represents
12. 12 R. Ghosh, N. Deb and K. Sengupta et al. / Data in Brief 40 (2022) 107772
a high level of stress getting induced on the subjects and a rating of 1 represents the minimal
amount of stress getting induced on the subjects.
Ethics Statement
Ethical approval was obtained from the Institutional Ethics Committee, Gauhati University,
reference no. GUIEC/2019/019 dated: 15/10/2019. The experiment involved human subjects in
research whose participation was completely consensual, anonymous, and voluntary. Before opt-
ing to partake in the study, the participants were informed about the nature of the study. The
data collection was conducted according to the Declaration of Helsinki.
Consent from Participants
Informed consent was obtained from all the subjects participating in the study.
Declaration of Competing Interest
The authors declare that there is no known competing financial interests or personal rela-
tionships which have, or could have influenced the work reported in this article.
CRediT Author Statement
Rajdeep Ghosh: Conceptualization, Methodology, Data curation, Project administration;
Nabamita Deb: Conceptualization, Supervision, Writing – original draft; Kaushik Sengupta: In-
vestigation, Software, Validation; Anurag Phukan: Investigation, Writing – review & editing;
Nitin Choudhury: Software, Data curation; Sreshtha Kashyap: Visualization; Souvik Phadikar:
Formal analysis; Ramesh Saha: Writing – review & editing; Pranesh Das: Conceptualization;
Nidul Sinha: Conceptualization, Methodology; Priyanka Dutta: Visualization.
Acknowledgments
The research work is funded by NPIU-MHRD, Govt. of India under the CRS Project entitled
“Monitoring Stress in Students using EEG” with CRS-Id-:- 1-5770264050.
References
[1] F. Scarpina, S. Tagini, The Stroop color and word test, Front. Psychol. 8 (2017) 557 1-8.
[2] X. Hou, Y. Liu, O. Sourina, W. Mueller-Wittig, CogniMeter: EEG-based emotion, mental workload and stress visual
monitoring, in: Proceedings of the International Conference on Cyberworlds, Visby, Sweden, 2015, pp. 153–160.
[3] K.S. Rahnuma, A. Wahab, N. Kamaruddin, H. Majid, EEG analysis for understanding stress based on affective model
basis function, in: Proceedings of the IEEE 15th International Symposium on Consumer Electronics (ISCE), Singapore,
2011, pp. 592–597.
[4] S.A. Hosseini, M.A. Khalilzadeh, M.B. Naghibi-Sistani, S.M. Homam, Emotional stress recognition using a new fusion
link between electroencephalogram and peripheral signals, Iran J. Neurol. 14 (3) (2015) 142–151.
[5] C. Kirschbaum, K.M. Pirke, D.H. Hellhammer, The Trier Social Stress Test—–a tool for investigating psychobiological
stress responses in a laboratory setting, Neuropsychobiology 28 (1, 2) (1993) 76—81.
[6] P. Gajbhiye, N. Mingchinda, W. Chen, S.C. Mukhopadhyay, T. Wilaiprasitporn, R.K. Tripathy, Wavelet domain optimized
Savitzky–Golay filter for the removal of motion artifacts From EEG recordings, IEEE Trans. Instrum. Meas. 70 (2021)
1–11.
[7] S. Phadikar, N. Sinha, R. Ghosh, Automatic eyeblink artifact removal from EEG signal using wavelet transform with
heuristically optimized threshold, IEEE J. Biomed. Health Inform. 25 (2) (2021) 475–484.