@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}
}

@conference{Sudirman2014626,
title = {Sensory responses of autism via electroencephalography for Sensory Profile},
author = {R Sudirman and S S Hussin},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84946435600&doi=10.1109%2fICCSCE.2014.7072794&partnerID=40&md5=3e6f1cfe19eae4fad359d2493aebd7e0},
doi = {10.1109/ICCSCE.2014.7072794},
isbn = {9781479956869},
year = {2014},
date = {2014-01-01},
journal = {Proceedings - 4th IEEE International Conference on Control System, Computing and Engineering, ICCSCE 2014},
pages = {626-631},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {The aim of this study is to investigate the brain signals of autism children through electroencephalography (EEG) associated to physical tasks. The physical task was meant to stimulate the sensitivity correlation of sensory response of a child. A group of autism children was chosen for this study and were given by five sensory stimulations which are audio, taste, touch, visual and vestibular. The acquisition of brain signals was acquainted using EEG Neurofax 9200 and the electrode positions were using 10-20 International System placements. The preprocessing signals were analyzed using independent component analysis (ICA) using EEGLAB Software and Discrete Wavelet Transform (DWT). The alpha wave was selected by level 6 decomposition and the extracted features represents the characteristic of the sensory task. The means, standard deviations and approximation entropy were extracted on the clean signals and forms into Sensory Profile (Sensory Profiling). From the overall results, the behavior of each autism children has been observed unstable emotion while running the sensory stimulation. The observation also helps to improve their learning strategy for the future work in assessment. © 2014 IEEE.},
note = {cited By 3},
keywords = {Autism, Discrete Wavelet Transforms, Diseases, Electroencephalography, Electrophysiology, Independent Component Analysis, International System, Learning, Sensory Analysis, Sensory Profiles, Sensory Profiling, Sensory Stimulation, Signal Processing, Standard Deviation, Wavelet Packet Transforms},
pubstate = {published},
tppubtype = {conference}
}