@conference{Abdullah2019,
title = {Evaluation on Machine Learning Algorithms for Classification of Autism Spectrum Disorder (ASD)},
author = {A A Abdullah and S Rijal and S R Dash},
editor = {Rahim Mustafa Zaaba Norali Noor S B A N B S K A N B A B M Fook C.Y. Yazid H.B.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076493636&doi=10.1088%2f1742-6596%2f1372%2f1%2f012052&partnerID=40&md5=2ec1bd9f6cf1e3afe965cc9e3792f536},
doi = {10.1088/1742-6596/1372/1/012052},
issn = {17426588},
year = {2019},
date = {2019-01-01},
journal = {Journal of Physics: Conference Series},
volume = {1372},
number = {1},
publisher = {Institute of Physics Publishing},
abstract = {Autism Spectrum Disorder (ASD) was characterized by delay in social interactions development, repetitive behaviors and narrow interest, which usually diagnosed with standard diagnostic tools such as Autism Diagnostic Observation Schedule (ADOS) and Autism Diagnostic Interview-Revised (ADIR-R). Previous work has implemented machine-learning methods for the classification of ASD, however they used different types of dataset such as brain images for MRI and EEG, risk genes in genetic profiles and behavior evaluation based on ADOS and ADI-R. Here a trial on using Autism Spectrum Questions (AQ) to build models that have higher potential to classify ASD was developed. In this research, Chi-square and Least Absolute Shrinkage and Selection Operator (LASSO) have been selected as feature selection methods to select the most important features for 3 supervised machine learning algorithms, which are Random Forest, Logistic Regression and K-Nearest Neighbors with K-fold cross validation. The performance was evaluated in which results Logistic Regression scored the highest accuracy with 97.541% using model with 13 selected features based on Chi-square selection method. © 2019 IOP Publishing Ltd. All rights reserved.},
note = {cited By 0},
keywords = {Autism Spectrum Disorders, Behaviour Evaluations, Biomedical Engineering, Brain Mapping, Classification (of information), Decision Trees, Diseases, Feature Extraction, Feature Selection Methods, K Fold Cross Validations, Learning, Least Absolute Shrinkage and Selection Operators, Least Squares Approximations, Logistic Regressions, Machine Learning, Machine Learning Methods, Magnetic Resonance Imaging, Nearest Neighbor Search, Regression Analysis, Supervised Learning, Supervised Machine Learning},
pubstate = {published},
tppubtype = {conference}
}

@conference{Ishak2019156,
title = {Robot selection in robotic intervention for ASD children},
author = {N I Ishak and H.Md. Yusof and S N Sidek and N Rusli},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85062769148&doi=10.1109%2fIECBES.2018.8626679&partnerID=40&md5=4ab38d1996ff4c48913864199d814cc6},
doi = {10.1109/IECBES.2018.8626679},
isbn = {9781538624715},
year = {2019},
date = {2019-01-01},
journal = {2018 IEEE EMBS Conference on Biomedical Engineering and Sciences, IECBES 2018 - Proceedings},
pages = {156-160},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {This paper explains on the selection of a robot that is suitable for engagement with Autism Spectrum Disorder (ASD) children. Many robots were being developed to help these children to improve their behavior, communication skills, social interaction, joint attention and sensitivity. Recent researches done shown that a commercialize robot is better in early intervention therapy for the children because of its robustness and easily can be programmed by the parents and teachers. Instead, the physical appearance of the robot also plays an important feature for robot selection. Comparison studies were made between prototype robots that currently used in Human-Robot Interaction (HRI) and commercial robot. As a result, we proposed to have a commercial robot that is robust, simple, economical, durable and flexible to be changed to any desired form as our medium of interactions. © 2018 IEEE},
note = {cited By 1},
keywords = {Autism Spectrum Disorders, Biomedical Engineering, Commercial Robots, Communication Skills, Early Intervention, Human Robot Interaction, Important Features, Recent Researches, Robotics, Social Interactions},
pubstate = {published},
tppubtype = {conference}
}

@conference{Rusli2016274,
title = {Hottest pixel segmentation based thermal image analysis for children},
author = {N Rusli and H M Yusof and S N Sidek and M H Latif},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85015712176&doi=10.1109%2fIECBES.2016.7843457&partnerID=40&md5=847e69c597caab24e0cd0f4e2cf558c6},
doi = {10.1109/IECBES.2016.7843457},
isbn = {9781467377911},
year = {2016},
date = {2016-01-01},
journal = {IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences},
pages = {274-279},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {In this paper, the first order statistics for gray level intensity defined from thermal image is implemented to govern the significant and distinguishable characteristic pattern in thermal image of affective states. The impact of thresholding mechanism is studied to differentiate between positive affective states (happy) and negative affective states (sad) analysis in response to the stimuli adopted from International Affective Pictures System (IAPS) database. The hottest pixel segmentation technique is applied where it identifies the threshold level in a way to classify the hottest pixel area. The region of interest is narrowed to a forehead region with result of separation analysis made to left and right area. Two experiments have been conducted by using different set of stimuli and the results depicts of asymmetry and differed in culmination pattern for these two affective states. This conclusive result from this study suggests that this feature can be used as one of the important feature to give information of affective states on individuals with autism spectrum disorder (ASD) with least of facial expressions and perhaps would-be use in non-verbal means. © 2016 IEEE.},
note = {cited By 0},
keywords = {Affective State, Autism Spectrum Disorders, Biomedical Engineering, Diseases, Feature Extraction, First-Order Statistics, Forehead Region, Gray Level Intensity, Image Analysis, Image Segmentation, Pixels, Segmentation Techniques, Thermal Image Analysis, Thermal Images},
pubstate = {published},
tppubtype = {conference}
}

@conference{Rusli2016226,
title = {Non-invasive assessment of affective states on individual with autism spectrum disorder: A review},
author = {N B Rusli and S N Sidek and H Md Yusof and M H Abd Latif},
editor = {Ahmad Usman M Y J Ibrahim F. Mohktar M.S.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84952767451&doi=10.1007%2f978-981-10-0266-3_47&partnerID=40&md5=f4aafb2216ef5c9d03ae7a1db352e4bd},
doi = {10.1007/978-981-10-0266-3_47},
issn = {16800737},
year = {2016},
date = {2016-01-01},
journal = {IFMBE Proceedings},
volume = {56},
pages = {226-230},
publisher = {Springer Verlag},
abstract = {Individuals with Autism Spectrum Disorder (ASD) are identified as a group of people who have social interaction and communication impairment. They have difficulty in producing speech and explaining what they meant. They also suffer from emotional or cognitive states requirement that stance challenges to their interest in communicating and socializing. Hence, it is vital to know their emotion to help them develop better skills in social interaction. Emotion can be derived from affective states and can be detected through physical reaction and physiological signals. There are numerous known modalities available to detect the affective states either through invasive and non-invasive methods. In order to evaluate the affective states of individuals with ASD, amongst the methods used are through electrodermal activity (EDA), electromyographic (EMG) activity, and cardiovascular activity (ECG) and blood flow analyses. Though considered non invasive, these methods require sensor to be patched on to the skin causing discomfort to the subjects and might distract their true emotion. We propose non-invasive methods which is also contactless to address the problem to detect emotion of individual with ASD that is through thermal imaging. Through the impact of cutaneous temperature in blood flow, thermal imprint is radiated and can be detected in this method. To date, no research has been reported of the use of thermal imaging analysis of facial skin temperature on the individuals with ASD. In this paper we will justify the method and also discuss the merits and demerits of other methods. © International Federation for Medical and Biological Engineering 2016.},
note = {cited By 1},
keywords = {Affective State, Autism, Biomedical Engineering, Blood, Diseases, Emotion, Facial Expression, Hemodynamics, Infrared Imaging, Noninvasive Medical Procedures, Physiological Signals, Physiology, Signal Detection, Skin, Social Sciences},
pubstate = {published},
tppubtype = {conference}
}

@conference{Hong201651,
title = {A review on assistive tools for autistic patients},
author = {T S Hong and S Mohamaddan and S T S Shazali and N A A Mohtadzar and R A Bakar},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85015656147&doi=10.1109%2fIECBES.2016.7843413&partnerID=40&md5=dad70fbb2785ec386d3c3f8e3134ad1c},
doi = {10.1109/IECBES.2016.7843413},
isbn = {9781467377911},
year = {2016},
date = {2016-01-01},
journal = {IECBES 2016 - IEEE-EMBS Conference on Biomedical Engineering and Sciences},
pages = {51-56},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Persistent difficulties in social skills and social interaction present significant challenges for individuals diagnosed with autism spectrum disorders (ASD). The current literature review provides a comprehensive investigation of studies focused on assistive tools for deficits in social skills or social interaction in those with ASD. Twelve studies that met the inclusion criteria were chosen. Studies were categorized based on Computer-based Intervention (CBI) and Robot-Assisted Behavioral Intervention (RBI). Each study were then evaluated on several aspects. Strengths, limitations and outcomes were discussed. All studies showed positive outcomes. © 2016 IEEE.},
note = {cited By 2},
keywords = {Biomedical Engineering, Components, Engineering, Formatting, Industrial Engineering, Insert, Style, Styling},
pubstate = {published},
tppubtype = {conference}
}

@conference{Abdullah2012144,
title = {Perinatal, maternal and antenatal associated factors for autism: A case control study},
author = {M N Abdullah and W M Z W Mohamad and M R Abdullah and M J Yaacob and M S Baharuddin},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84876762294&doi=10.1109%2fIECBES.2012.6498121&partnerID=40&md5=b14466b2341cc29599332d94d866ea9a},
doi = {10.1109/IECBES.2012.6498121},
isbn = {9781467316668},
year = {2012},
date = {2012-01-01},
journal = {2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2012},
pages = {144-148},
abstract = {Autism disorders are a group of neurodevelopmental disorders which characterized into three main domains which are social interaction impairment, communication delay and repetitive or stereotypic behavior. Many studies had suggested that the risk factors for autism derive from three big factors namely environmental factors, genetic predisposition and vaccine induced. The aim of this study was to investigate the perinatal, maternal and antenatal associated factors on autistic disorder children at Hospital Pulau Pinang and Hospital Bukit Mertajam, Pulau Pinang. A case control study involving 312 cases and control was conducted using data retrieved from hospital records at Pulau Pinang hospital and Bukit Mertajam hospital from 2001 to 2008. The departments involved were Psychiatric, Obstetrics and Gynecology and Record and Management Department. All cases which met the inclusion and exclusion criteria were included in the study. Univariable and multivariable logistic regression were used to explore the perinatal, maternal and antenatal associated factors associated with autistic disorder children. There were seven associated factors contributed most to autistic disorder determination. The factors were maternal age [Adjusted Odds Ratio (OR): 1.41; 95% Confidence Interval (CI): (1.27, 1.57)], maternal smoking reported at first antenatal visit [Adjusted OR: 13.61; 95% CI: (1.87, 99.35)], birth asphyxia [Adjusted OR: 0.35; 95% CI: (0.11, 1.08)], psychiatric history [Adjusted OR: 54.94; 95% CI: (12.07, 250.04)], multiple gestation [Adjusted OR: 4.81; 95% CI: (1.86, 12.45)], parity for more than 4 [Adjusted OR: 0.11; 95% CI: (0.03, 0.47)], parity between 0 and 1 [Adjusted OR: 0.19; 95% CI: (0.07,0.55)], Chinese race compared to the Malay race [Adjusted OR: 10.11; 95% CI: (3.61, 28.30)] and Indian race compared to the Malay race [Adjusted OR: 5.14; 95% CI: (1.38, 19.16)]. The results suggested that autistic disorders were associated with perinatal, maternal and antenatal factors such as delivery, pregnancy and maternal characteristics. © 2012 IEEE.},
note = {cited By 0},
keywords = {Antenatal, ASD, Autism, Autistic, Biomedical Engineering, Case-Control Studies, Delivery, Diseases, Hospitals, Logistics, Maternal, Obstetrics, Parents, Perinatal, Pregnancy, Prenatal, Retrospective, Risk Factor},
pubstate = {published},
tppubtype = {conference}
}

@conference{Hoole2012541,
title = {Autism, EEG and brain electromagnetics research},
author = {P R P Hoole and K Pirapaharan and S A Basar and R Ismail and D L D A Liyanage and S S H M U L Senanayake and S R H Hoole},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84876771339&doi=10.1109%2fIECBES.2012.6498036&partnerID=40&md5=9f9390b30b859a90936c66699c1a5115},
doi = {10.1109/IECBES.2012.6498036},
isbn = {9781467316668},
year = {2012},
date = {2012-01-01},
journal = {2012 IEEE-EMBS Conference on Biomedical Engineering and Sciences, IECBES 2012},
pages = {541-543},
abstract = {There has been a significant increase in the incidence of autism. We report the work on autism by our international group, on the growing attention paid to EEG based diagnosis and the interest in tracing EEG changes to brain electromagnetic signals (BEMS), seeking the cause of autism and the brain regions of its origin. The time- and frequency domain and principal component analysis (PCA) of these EEG signals with a Multilayer Perception Neural Network (MLP) identifies an autistic subject and helps improve classification accuracy. We show differences between a working brain and a relaxed brain, especially in the Alpha waves used for diagnosis. © 2012 IEEE.},
note = {cited By 11},
keywords = {Biomedical Engineering, Brain, Brain Regions, Classification Accuracy, Diseases, EEG Signals, Electromagnetic Signals, Electromagnetics, Electromagnetism, Frequency Domains, International Group, Multilayer Perception Neural Networks, Neuroimaging, Principal Component Analysis},
pubstate = {published},
tppubtype = {conference}
}