Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292197
N. Noor
Selamat Datang! (Welcome!) to the First International Conference on BioSignal Analysis, Processing and Systems (ICBAPS 2015). This conference is organized by Razak School of Engineering and Advanced Technology of Universiti Teknologi Malaysia with the collaboration of IEEE Malaysia Signal Processing Chapter as the technical cosponsor. ICBAPS 2015 attracted about 50 papers from 9 different countries from around the globe among which Brazil, Poland, India, United Kingdom, Spain, Turkey USA and Australia. After extensive reviews, about 69% of the papers were accepted for the presentation at the conference.
{"title":"Welcome foreword from the conference chair","authors":"N. Noor","doi":"10.1109/ICBAPS.2015.7292197","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292197","url":null,"abstract":"Selamat Datang! (Welcome!) to the First International Conference on BioSignal Analysis, Processing and Systems (ICBAPS 2015). This conference is organized by Razak School of Engineering and Advanced Technology of Universiti Teknologi Malaysia with the collaboration of IEEE Malaysia Signal Processing Chapter as the technical cosponsor. ICBAPS 2015 attracted about 50 papers from 9 different countries from around the globe among which Brazil, Poland, India, United Kingdom, Spain, Turkey USA and Australia. After extensive reviews, about 69% of the papers were accepted for the presentation at the conference.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121356323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292233
Siti Armiza Mohd Aris, A. H. Jahidin, M. Taib
This study presents a small part of the major study, involved in categorizing EEG calmness. The kNN classifier was used to classify EEG features named as asymmetry index (AsI) which was extracted during relaxed state and non-relaxed state. Results from the previous study showed that the EEG behaviour during both states appear to have more than two groups. The group of four EEG behaviours and three EEG behaviours which was clustered by FCM was validated through kNN. However, to investigate the kNN classification accuracy, the classifier performance measure is essential. Thus for this study purposes, performance measure of the kNN was tested using confusion matrix. Result of performance measure indicates that kNN provide 100% accuracy on three clusters of behaviours which could be proposed as calmness index.
{"title":"Performance measure of the multi-class classification for the EEG calmness categorization study","authors":"Siti Armiza Mohd Aris, A. H. Jahidin, M. Taib","doi":"10.1109/ICBAPS.2015.7292233","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292233","url":null,"abstract":"This study presents a small part of the major study, involved in categorizing EEG calmness. The kNN classifier was used to classify EEG features named as asymmetry index (AsI) which was extracted during relaxed state and non-relaxed state. Results from the previous study showed that the EEG behaviour during both states appear to have more than two groups. The group of four EEG behaviours and three EEG behaviours which was clustered by FCM was validated through kNN. However, to investigate the kNN classification accuracy, the classifier performance measure is essential. Thus for this study purposes, performance measure of the kNN was tested using confusion matrix. Result of performance measure indicates that kNN provide 100% accuracy on three clusters of behaviours which could be proposed as calmness index.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124955384","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292227
Mones Bekdash, V. Asirvadam, N. Kamel
The purpose of this work is to study the effects of the street and traffic lights on the driver reaction in terms to enhance the traffic safety factor. To illustrate the changes in the human response to different colours and to study the effects of intensity on the amplitude and latency of the VEPs components, an experiment is conducted on healthy subjects with a normal or corrected to normal vision using a checkerboard stimulus to achieve the pattern reversal VEPs responses. All the Basic RGB colours (Red, Green Blue) and yellow were used and tested for three levels of intensity (Low, Medium and High). Ensemble Averaging for 100 trials is implemented to extract the VEPs from the electroencephalogram (EEG) background noise. Subjects are fixed to a flickering checkerboard, generating a Steady State VEP (SSVEP) at a frequency of (3.5 Hz). The P1 were extracted and compared. As a baseline the subject responses to the achromatic stimulus is first recorded then the colour study is conducted.
{"title":"Visual evoked potentials response to different colors and intensities","authors":"Mones Bekdash, V. Asirvadam, N. Kamel","doi":"10.1109/ICBAPS.2015.7292227","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292227","url":null,"abstract":"The purpose of this work is to study the effects of the street and traffic lights on the driver reaction in terms to enhance the traffic safety factor. To illustrate the changes in the human response to different colours and to study the effects of intensity on the amplitude and latency of the VEPs components, an experiment is conducted on healthy subjects with a normal or corrected to normal vision using a checkerboard stimulus to achieve the pattern reversal VEPs responses. All the Basic RGB colours (Red, Green Blue) and yellow were used and tested for three levels of intensity (Low, Medium and High). Ensemble Averaging for 100 trials is implemented to extract the VEPs from the electroencephalogram (EEG) background noise. Subjects are fixed to a flickering checkerboard, generating a Steady State VEP (SSVEP) at a frequency of (3.5 Hz). The P1 were extracted and compared. As a baseline the subject responses to the achromatic stimulus is first recorded then the colour study is conducted.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129917640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292229
Hanis Zafirah Binti Kosnan, Norlaili Mat Safri, P. I. Khalid
The aim of the study is to investigate the dynamic features of handwriting and the directional connectivity in brain among young children during basic drawing task. Seven children participated in the study where four of them were female. To exercise motor ability, three different unlined shapes were selected which the subject must gaze and trace on WACOM digitizing tablet. While doing the basic drawing task, brain signals (EEG) were recorded to analyze the information pathway based on partial directed coherence (PDC) method. Result showed that all subjects regardless of gender performed the basic drawing task with preferred rule. Again, regardless of gender, PDC showed that most information sources came from parietal, frontal and occipital areas even-though dynamic features of handwriting (pressure and altitude) showed gender preferences. It is found also that gazing while planning for tracing and actually doing the tracing activity shows almost similar result, i.e. similar sources of information. Based from the pattern of information pathway in the brain among the subjects during gazing, the tracing activity is thought to be well planned. Most of the subjects make use of areas where visual processing, pattern recognition, motor planning and perception midline and route finding are executed during the performances.
{"title":"Dynamic features of handwriting and cortico-cortical functional connectivity during basic geometric drawing based on gender","authors":"Hanis Zafirah Binti Kosnan, Norlaili Mat Safri, P. I. Khalid","doi":"10.1109/ICBAPS.2015.7292229","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292229","url":null,"abstract":"The aim of the study is to investigate the dynamic features of handwriting and the directional connectivity in brain among young children during basic drawing task. Seven children participated in the study where four of them were female. To exercise motor ability, three different unlined shapes were selected which the subject must gaze and trace on WACOM digitizing tablet. While doing the basic drawing task, brain signals (EEG) were recorded to analyze the information pathway based on partial directed coherence (PDC) method. Result showed that all subjects regardless of gender performed the basic drawing task with preferred rule. Again, regardless of gender, PDC showed that most information sources came from parietal, frontal and occipital areas even-though dynamic features of handwriting (pressure and altitude) showed gender preferences. It is found also that gazing while planning for tracing and actually doing the tracing activity shows almost similar result, i.e. similar sources of information. Based from the pattern of information pathway in the brain among the subjects during gazing, the tracing activity is thought to be well planned. Most of the subjects make use of areas where visual processing, pattern recognition, motor planning and perception midline and route finding are executed during the performances.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116200661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292236
Anshu Chittora, H. Patil
In this paper, bispectrum-based feature extraction method is proposed for classification of normal vs. pathological infant cries. Bispectrum is a class of higher order spectral analysis, Bispectrum is computed for all segments of normal as well as pathological cries. Bispectrum is a two-dimensional (i.e., 2-D) feature. A tensor is formed using these bispectrum features and then for feature reduction, higher order singular value decomposition theorem (HOSVD) is applied. Our experimental results show 98.94 % average accuracy of classification with support vector machine (SVM) classifier whereas baseline features, viz., Mel frequency cepstral coefficients (MFCC), perceptual linear prediction coefficients (PLP) and linear prediction coefficients (LPC) gave classification accuracy of 53.99 %, 63.14 % and 63.07 %, respectively. High classification accuracy of bispectrum can be attributed to its ability to capture nonlinearity in the signal.
{"title":"Analysis of normal and pathological infant cries using bispectrum features derived using HOSVD","authors":"Anshu Chittora, H. Patil","doi":"10.1109/ICBAPS.2015.7292236","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292236","url":null,"abstract":"In this paper, bispectrum-based feature extraction method is proposed for classification of normal vs. pathological infant cries. Bispectrum is a class of higher order spectral analysis, Bispectrum is computed for all segments of normal as well as pathological cries. Bispectrum is a two-dimensional (i.e., 2-D) feature. A tensor is formed using these bispectrum features and then for feature reduction, higher order singular value decomposition theorem (HOSVD) is applied. Our experimental results show 98.94 % average accuracy of classification with support vector machine (SVM) classifier whereas baseline features, viz., Mel frequency cepstral coefficients (MFCC), perceptual linear prediction coefficients (PLP) and linear prediction coefficients (LPC) gave classification accuracy of 53.99 %, 63.14 % and 63.07 %, respectively. High classification accuracy of bispectrum can be attributed to its ability to capture nonlinearity in the signal.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126224359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292235
Anshu Chittora, H. Patil, Hardik B. Sailor
In this paper, auditory spectrogram is proposed for analysis of HIE and asthma infant cries. Auditory spectrogram represents a 2-dimensional (i.e., 2-D) pattern of neural activity, distributed along a logarithmic frequency-axis. Features are derived from the auditory spectrograms of each class. These features are then used to train support vector machine (SVM) classifier. Effectiveness of the proposed features is shown by application of proposed features for classification of pathologies. Classification accuracy achieved with SVM classifier with radial basis function (RBF) kernel is 87.67%. Classification performance has been compared with the state-of-the-art method, i.e., Mel Frequency Cepstral Coefficients (MFCC). It has been observed that MFCC features are giving 86.13% classification accuracy. Fusion of proposed features with the MFCC features further improves the classification accuracy to 88.54%. High classification accuracy of auditory spectrogram can be attributed to its ability to retain both formant frequencies and low frequency harmonics.
{"title":"Spectro-temporal analysis of HIE and asthma infant cries using auditory spectrogram","authors":"Anshu Chittora, H. Patil, Hardik B. Sailor","doi":"10.1109/ICBAPS.2015.7292235","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292235","url":null,"abstract":"In this paper, auditory spectrogram is proposed for analysis of HIE and asthma infant cries. Auditory spectrogram represents a 2-dimensional (i.e., 2-D) pattern of neural activity, distributed along a logarithmic frequency-axis. Features are derived from the auditory spectrograms of each class. These features are then used to train support vector machine (SVM) classifier. Effectiveness of the proposed features is shown by application of proposed features for classification of pathologies. Classification accuracy achieved with SVM classifier with radial basis function (RBF) kernel is 87.67%. Classification performance has been compared with the state-of-the-art method, i.e., Mel Frequency Cepstral Coefficients (MFCC). It has been observed that MFCC features are giving 86.13% classification accuracy. Fusion of proposed features with the MFCC features further improves the classification accuracy to 88.54%. High classification accuracy of auditory spectrogram can be attributed to its ability to retain both formant frequencies and low frequency harmonics.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126437248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292219
M. de La Sen, S. Alonso-Quesada, A. Ibeas
This paper relies on the properties of a continuous-time epidemic model with the subpopulations of susceptible-exposed-infectious-recovered epidemic model with finitely distributed delays under a very general, feedback vaccination control rule. The process is subject to eventual perturbations from the equilibrium points which are modeled by Wiener-type noises.
{"title":"On the stability of a delayed SEIR epidemic model with feedback vaccination controls","authors":"M. de La Sen, S. Alonso-Quesada, A. Ibeas","doi":"10.1109/ICBAPS.2015.7292219","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292219","url":null,"abstract":"This paper relies on the properties of a continuous-time epidemic model with the subpopulations of susceptible-exposed-infectious-recovered epidemic model with finitely distributed delays under a very general, feedback vaccination control rule. The process is subject to eventual perturbations from the equilibrium points which are modeled by Wiener-type noises.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124482919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292220
A. M. Ali, Z. M. Yusof, A. K. Kushairy, F. Zaharah H, A. Ismail
Arm rehabilitation activities require continuous monitoring process in order to provide information on rehabilitation results to be analyzed by therapist. The purpose of monitoring is to help them to improve and customize the rehabilitation process. Moreover, a portable and simple home-based rehabilitation device can help patients to improve daily rehabilitation activity. Some previous studies regarding home-based rehabilitation process have shown improvement promoting human movement recovery. But existing rehabilitation devices are expensive and need to be supervised by a physical therapist, which are complicated to be used at home. Some devices are not so efficient to be used at home due to the large size and complex system. In this current work, flex sensor, force sensitive resistors and accelerometer were assessed in order to be implemented as a sensory unit for a portable arm rehabilitation device. The analog signal from the sensors will be conveyed to an Arduino microcontroller for data processing and logging. The device is equipped with online or portable data logging capabilities which can store daily activity results. The results of rehabilitation activity can be used for further monitoring and analysis. Experiments were carried out to determine the feasibility of each sensor towards the design of the new device (Figure 1). The experiments demonstrate the capabilities of the sensors to produce extended information regarding arm movement activities which can be implemented in the design.
{"title":"Development of Smart Glove system for therapy treatment","authors":"A. M. Ali, Z. M. Yusof, A. K. Kushairy, F. Zaharah H, A. Ismail","doi":"10.1109/ICBAPS.2015.7292220","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292220","url":null,"abstract":"Arm rehabilitation activities require continuous monitoring process in order to provide information on rehabilitation results to be analyzed by therapist. The purpose of monitoring is to help them to improve and customize the rehabilitation process. Moreover, a portable and simple home-based rehabilitation device can help patients to improve daily rehabilitation activity. Some previous studies regarding home-based rehabilitation process have shown improvement promoting human movement recovery. But existing rehabilitation devices are expensive and need to be supervised by a physical therapist, which are complicated to be used at home. Some devices are not so efficient to be used at home due to the large size and complex system. In this current work, flex sensor, force sensitive resistors and accelerometer were assessed in order to be implemented as a sensory unit for a portable arm rehabilitation device. The analog signal from the sensors will be conveyed to an Arduino microcontroller for data processing and logging. The device is equipped with online or portable data logging capabilities which can store daily activity results. The results of rehabilitation activity can be used for further monitoring and analysis. Experiments were carried out to determine the feasibility of each sensor towards the design of the new device (Figure 1). The experiments demonstrate the capabilities of the sensors to produce extended information regarding arm movement activities which can be implemented in the design.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"2 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126235652","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292230
M. Hamedi, S. Salleh, C. Ting, S. Samdin, alias mohd noor
Inter-channel time-varying (TV) relationships of scalp neural recordings offer deep understanding of the brain sensory and cognitive functions. This paper develops a state space-based TV multivariate autoregressive (MVAR) model for estimating TV-information flow (IF) recruited by different motor imagery (MI) movements. TV model coefficients are computed through Kalman filter (KF) by incorporating Kalman smoothing approach and expectation-maximization algorithm for model parameter estimation, KS-EM. Volume conduction (VC) problem is also addressed by considering full noise covariate in observation equation. An automated model initialization is also implemented to deliver optimal estimates. TV-partial directed coherence derived from the proposed model is applied for IF analysis. The performance of KS-EM is assessed and compared with dual extended KF and overlapping sliding window-based MVAR models using simulated data. Finally, TV-IF during four different MI movements is studied. Results show the superiority of KS-EM for tracking the rapid signal parameter changes and eliminating the VC effect in the sensor space EEG. Differences in contralateral/ipsilateral TV-IF around alpha and lower beta bands during each MI task reveal the high potential of this feature for BCI applications.
{"title":"Sensor space time-varying information flow analysis of multiclass motor imagery through Kalman Smoother and EM algorithm","authors":"M. Hamedi, S. Salleh, C. Ting, S. Samdin, alias mohd noor","doi":"10.1109/ICBAPS.2015.7292230","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292230","url":null,"abstract":"Inter-channel time-varying (TV) relationships of scalp neural recordings offer deep understanding of the brain sensory and cognitive functions. This paper develops a state space-based TV multivariate autoregressive (MVAR) model for estimating TV-information flow (IF) recruited by different motor imagery (MI) movements. TV model coefficients are computed through Kalman filter (KF) by incorporating Kalman smoothing approach and expectation-maximization algorithm for model parameter estimation, KS-EM. Volume conduction (VC) problem is also addressed by considering full noise covariate in observation equation. An automated model initialization is also implemented to deliver optimal estimates. TV-partial directed coherence derived from the proposed model is applied for IF analysis. The performance of KS-EM is assessed and compared with dual extended KF and overlapping sliding window-based MVAR models using simulated data. Finally, TV-IF during four different MI movements is studied. Results show the superiority of KS-EM for tracking the rapid signal parameter changes and eliminating the VC effect in the sensor space EEG. Differences in contralateral/ipsilateral TV-IF around alpha and lower beta bands during each MI task reveal the high potential of this feature for BCI applications.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126799222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-05-26DOI: 10.1109/ICBAPS.2015.7292238
Ahmed Elmahdy, N. Yahya, N. Kamel, A. Shahid
In this paper, an epileptic seizure event detection algorithm utilizing five features namely singular values, total average power, delta band average power, variance and mean, is proposed. Using CHB-MIT Scalp EEG Database, the calculations of the features are performed over a sliding window of one second. The algorithm was evaluated in terms of accuracy, sensitivity, specificity and failure rate. This investigation used SVM as the classification technique. The performance comparisons are made with techniques based on classical features alone, singular value alone and combination of classical features and singular values. The results show that the proposed algorithm achieves better results than using singular values alone or using classical features alone with an average accuracy of 94.82%.
{"title":"Epileptic seizure detection using singular values and classical features of EEG signals","authors":"Ahmed Elmahdy, N. Yahya, N. Kamel, A. Shahid","doi":"10.1109/ICBAPS.2015.7292238","DOIUrl":"https://doi.org/10.1109/ICBAPS.2015.7292238","url":null,"abstract":"In this paper, an epileptic seizure event detection algorithm utilizing five features namely singular values, total average power, delta band average power, variance and mean, is proposed. Using CHB-MIT Scalp EEG Database, the calculations of the features are performed over a sliding window of one second. The algorithm was evaluated in terms of accuracy, sensitivity, specificity and failure rate. This investigation used SVM as the classification technique. The performance comparisons are made with techniques based on classical features alone, singular value alone and combination of classical features and singular values. The results show that the proposed algorithm achieves better results than using singular values alone or using classical features alone with an average accuracy of 94.82%.","PeriodicalId":243293,"journal":{"name":"2015 International Conference on BioSignal Analysis, Processing and Systems (ICBAPS)","volume":"197 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124927125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：