2018 |
Sudirman, R; Hussin, S S; Airij, A G; Hai, C Z Profile indicator for autistic children using EEG biosignal potential of sensory tasks Conference Institute of Electrical and Electronics Engineers Inc., 2018, ISBN: 9781538612774, (cited By 0). Abstract | Links | BibTeX | Tags: Autistic Children, Biomedical Signal Processing, Brain, Children with Autism, Electroencephalography, Electrophysiology, Entropy Approximations, Independent Component Analysis, MATLAB, Neural Networks, Neurological Problems, Sensory Analysis, Sensory Profiles, Sensory Stimulation, Wavelet Packet Transforms @conference{Sudirman2018136, title = {Profile indicator for autistic children using EEG biosignal potential of sensory tasks}, author = {R Sudirman and S S Hussin and A G Airij and C Z Hai}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85058032461&doi=10.1109%2fICBAPS.2018.8527403&partnerID=40&md5=30dbb1596f4a0529332713c087bd788d}, doi = {10.1109/ICBAPS.2018.8527403}, isbn = {9781538612774}, year = {2018}, date = {2018-01-01}, journal = {2nd International Conference on BioSignal Analysis, Processing and Systems, ICBAPS 2018}, pages = {136-141}, publisher = {Institute of Electrical and Electronics Engineers Inc.}, abstract = {Electroencephalography (EEG) is a measure of voltages caused due to neural activities within the brain. EEG is a recommended tool for diagnosing neurological problems because it is non-invasive and can be recorded over a longer time-period. The children with Autism Spectrum Disorder (ASD) have difficulty in expressing their emotions due to their inability of proper information processing in brain. Therefore, this research aims to build a sensory profile with the help of EEG biosignal potential to distinguish among different sensory responses. The EEG signals acquired in this research identify different emotional states such as positive-thinking or super-learning and light-relaxation and are within the frequency range of 8-12 Hertz. 64 children participated in this research among which 34 were children with ASD and 30 were normal children. The EEG data was recoded while all the children were provided with vestibular, visual, sound, taste and vestibular sensory stimulations. The raw EEG data was filtered with the help of independent component analysis (ICA) using wavelet transform and EEGLAB software. Later, for building the sensory profile, entropy approximation, means and standard deviations were extracted from the filtered EEG signals. Along with that, the filtered EEG data was also fed to a neural networks (NN) algorithm which was implemented in MATLAB. Results from the acquired EEG signals depicted that during the sensory stimulation phase, the responses of all autistic children were in an unstable state. These findings will equip and aid their learning strategy in the future. © 2018 IEEE.}, note = {cited By 0}, keywords = {Autistic Children, Biomedical Signal Processing, Brain, Children with Autism, Electroencephalography, Electrophysiology, Entropy Approximations, Independent Component Analysis, MATLAB, Neural Networks, Neurological Problems, Sensory Analysis, Sensory Profiles, Sensory Stimulation, Wavelet Packet Transforms}, pubstate = {published}, tppubtype = {conference} } Electroencephalography (EEG) is a measure of voltages caused due to neural activities within the brain. EEG is a recommended tool for diagnosing neurological problems because it is non-invasive and can be recorded over a longer time-period. The children with Autism Spectrum Disorder (ASD) have difficulty in expressing their emotions due to their inability of proper information processing in brain. Therefore, this research aims to build a sensory profile with the help of EEG biosignal potential to distinguish among different sensory responses. The EEG signals acquired in this research identify different emotional states such as positive-thinking or super-learning and light-relaxation and are within the frequency range of 8-12 Hertz. 64 children participated in this research among which 34 were children with ASD and 30 were normal children. The EEG data was recoded while all the children were provided with vestibular, visual, sound, taste and vestibular sensory stimulations. The raw EEG data was filtered with the help of independent component analysis (ICA) using wavelet transform and EEGLAB software. Later, for building the sensory profile, entropy approximation, means and standard deviations were extracted from the filtered EEG signals. Along with that, the filtered EEG data was also fed to a neural networks (NN) algorithm which was implemented in MATLAB. Results from the acquired EEG signals depicted that during the sensory stimulation phase, the responses of all autistic children were in an unstable state. These findings will equip and aid their learning strategy in the future. © 2018 IEEE. |
2015 |
Khosrowabadi, R; Quek, C; Ang, K K; Wahab, A; Chen, Annabel S -H Dynamic screening of autistic children in various mental states using pattern of connectivity between brain regions Journal Article Applied Soft Computing Journal, 32 , pp. 335-346, 2015, ISSN: 15684946, (cited By 6). Abstract | Links | BibTeX | Tags: Autism Spectrum Disorders, Biomedical Signal Processing, Brain, Connectivity Feature, Connectivity Pattern, Diseases, Electroencephalography, Face Perceptions, Feature Extraction, Functional Connectivity, Pattern Recognition, Pattern Recognition Techniques @article{Khosrowabadi2015335, title = {Dynamic screening of autistic children in various mental states using pattern of connectivity between brain regions}, author = {R Khosrowabadi and C Quek and K K Ang and A Wahab and S -H Annabel Chen}, url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84927922520&doi=10.1016%2fj.asoc.2015.03.030&partnerID=40&md5=5973f80db5649e5c61e344907819a18b}, doi = {10.1016/j.asoc.2015.03.030}, issn = {15684946}, year = {2015}, date = {2015-01-01}, journal = {Applied Soft Computing Journal}, volume = {32}, pages = {335-346}, publisher = {Elsevier Ltd}, abstract = {In this study, a dynamic screening strategy is proposed to discriminate subjects with autistic spectrum disorder (ASD) from healthy controls. The ASD is defined as a neurodevelopmental disorder that disrupts normal patterns of connectivity between the brain regions. Therefore, the potential use of such abnormality for autism screening is investigated. The connectivity patterns are estimated from electroencephalogram (EEG) data collected from 8 brain regions under various mental states. The EEG data of 12 healthy controls and 6 autistic children (age matched in 7-10) were collected during eyes-open and eyes-close resting states as well as when subjects were exposed to affective faces (happy, sad and calm). Subsequently, the subjects were classified as autistic or healthy groups based on their brain connectivity patterns using pattern recognition techniques. Performance of the proposed system in each mental state is separately evaluated. The results present higher recognition rates using functional connectivity features when compared against other existing feature extraction methods. © 2015 Published by Elsevier B.V.}, note = {cited By 6}, keywords = {Autism Spectrum Disorders, Biomedical Signal Processing, Brain, Connectivity Feature, Connectivity Pattern, Diseases, Electroencephalography, Face Perceptions, Feature Extraction, Functional Connectivity, Pattern Recognition, Pattern Recognition Techniques}, pubstate = {published}, tppubtype = {article} } In this study, a dynamic screening strategy is proposed to discriminate subjects with autistic spectrum disorder (ASD) from healthy controls. The ASD is defined as a neurodevelopmental disorder that disrupts normal patterns of connectivity between the brain regions. Therefore, the potential use of such abnormality for autism screening is investigated. The connectivity patterns are estimated from electroencephalogram (EEG) data collected from 8 brain regions under various mental states. The EEG data of 12 healthy controls and 6 autistic children (age matched in 7-10) were collected during eyes-open and eyes-close resting states as well as when subjects were exposed to affective faces (happy, sad and calm). Subsequently, the subjects were classified as autistic or healthy groups based on their brain connectivity patterns using pattern recognition techniques. Performance of the proposed system in each mental state is separately evaluated. The results present higher recognition rates using functional connectivity features when compared against other existing feature extraction methods. © 2015 Published by Elsevier B.V. |
Testingadminnaacuitm2020-05-28T06:49:14+00:00
2018 |
Profile indicator for autistic children using EEG biosignal potential of sensory tasks Conference Institute of Electrical and Electronics Engineers Inc., 2018, ISBN: 9781538612774, (cited By 0). |
2015 |
Dynamic screening of autistic children in various mental states using pattern of connectivity between brain regions Journal Article Applied Soft Computing Journal, 32 , pp. 335-346, 2015, ISSN: 15684946, (cited By 6). |