ConVnet BiLSTM for ASD Classification on EEG Brain Signal

Authors

  • Nur Alisa Ali (N. A. Ali) Universiti Teknikal Malaysia Melaka (UTeM) https://orcid.org/0000-0002-4299-2162
  • Syafeeza Ahmad Radzi Universiti Teknikal Malaysia Melaka (UTeM), Malaysia
  • Abd Shukur Jaafar Universiti Teknikal Malaysia Melaka (UTeM), Malaysia
  • Norazlin Kamal Nor Hospital Canselor Tuanku Mukhriz, Malaysia

DOI:

https://doi.org/10.3991/ijoe.v18i11.30415

Abstract


As a neurodevelopmental disability, Autism Spectrum Disorder (ASD) is classified as a spectrum disorder.  The availability of an automated technology system to classify the ASD trait would have a significant impact on paediatricians, as it would assist them in diagnosing ASD in children using a quantifiable method. In this paper, we propose a novel autism diagnosis method that is based on a hybrid of the deep learning algorithms. This hybrid consists of a convolutional neural network (ConVnet) architecture that merges two LSTM blocks (BiLSTM) with the other direction of propagation to classify the output state on the brain signal data from electroencephalogram (EEG) on individuals; typically development (TD) and autism (ASD) obtained from the Simon Foundation Autism Research Initiative (SFARI) database to classify the output state. For a 70:30 data distribution, an accuracy of 97.7 percent was achieved. Proposed methods outperformed the current state-of-the art in terms of autism classification efficiency and have the potential to make a significant contribution to neuroscience research, as demonstrated by the results.

Author Biographies

Nur Alisa Ali (N. A. Ali), Universiti Teknikal Malaysia Melaka (UTeM)

Nur Alisa Ali is currently a lecturer in Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia. She is in the stage of writing her thesis. Her research interest is biomedical computer vision and artificial intelligent.

Syafeeza Ahmad Radzi, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia

Assoc Prof Dr Syafeeza Ahmad Radzi received her B. Eng degree (2003) and M. Eng (2005) in Electrical – Electronic & Telecommunication Engineering from Universiti Teknologi Malaysia (UTM) Johor, Malaysia. She also received her Ph.D degree in Electrical Engineering from the same university in 2014. She is currently an associate professor at the Faculty of Electronic Engineering and Computer Engineering, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia. Her research fields include embedded system, pattern recognition, machine learning, deep learning, image processing, biometric, etc. She is currently supervising this research work and can be contacted at syafeeza@utem.edu.my

Abd Shukur Jaafar, Universiti Teknikal Malaysia Melaka (UTeM), Malaysia

Dr Abd Shukur Jaafar received both first and master degree from Universiti Teknologi Malaysia (UTM) in Bachelor of Electrical Engineering (2002) and Master of Engineering in Electronic and Telecommunication (2005). He joined Universiti Teknikal Malaysia Melaka (UTeM) as a lecturer in 2005 and received PhD in Communication System from Lancaster University, UK. Currently his research interest on RF, Microwave circuits, algorithm development for indoor positioning and navigation and artificial intelligent signal processing.

Norazlin Kamal Nor, Hospital Canselor Tuanku Mukhriz, Malaysia

Assoc Prof Dr Norazlin Kamal Nor is an experienced lecturer with a demonstrated history of working in the higher education industry. Skilled in Developmental Paediatrics, Child Protection and Child Maltreatment Prevention, Genetic Epidemiology, Health Promotion, and Healthcare. Strong educational and research background with a Doctor of Philosophy (PhD) focused in Genetic Epidemiology from Johns Hopkins Bloomberg School of Public Health.

Downloads

Published

2022-08-31

How to Cite

Ali, N. A., A. Radzi, S., Jaafar, A. S., & K. Nor, N. (2022). ConVnet BiLSTM for ASD Classification on EEG Brain Signal. International Journal of Online and Biomedical Engineering (iJOE), 18(11), pp. 77–94. https://doi.org/10.3991/ijoe.v18i11.30415

Issue

Section

Papers