Mehmet Baygin1, Sengul Dogan2, Turker Tuncer3, Prabal Datta Barua4, Oliver Faust5, N Arunkumar6, Enas W Abdulhay7, Elizabeth Emma Palmer8, U Rajendra Acharya9. 1. Department of Computer Engineering, College of Engineering, Ardahan University, Ardahan, Turkey. Electronic address: mehmetbaygin@ardahan.edu.tr. 2. Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey. Electronic address: sdogan@firat.edu.tr. 3. Department of Digital Forensics Engineering, College of Technology, Firat University, Elazig, Turkey. Electronic address: turkertuncer@firat.edu.tr. 4. School of Management & Enterprise, University of Southern Queensland, Australia. Electronic address: Prabal.Barua@usq.edu.au. 5. Department of Engineering and Mathematics, Sheffield Hallam University, Sheffield, United Kingdom. Electronic address: oliver.faust@gmail.com. 6. Department of Electronics and Instrumentation, SASTRA University, Thirumalaisamudram, Thanjavur, 613401, India. Electronic address: arun.nura@gmail.com. 7. Biomedical Engineering Department, Faculty of Engineering, Jordan University of Science and Technology, P.O.Box 3030, Irbid, 22110, Jordan. Electronic address: ewabdulhay@just.edu.jo. 8. Department of Medical Genetics, Sydney Children's Hospital, High Street, Randwick, NSW, Australia. Electronic address: elizabeth.palmer@sesiahs.health.nsw.gov.au. 9. Ngee Ann Polytechnic, Department of Electronics and Computer Engineering, 599489, Singapore; Department of Biomedical Engineering, School of Science and Technology, SUSS University, Singapore; Department of Biomedical Informatics and Medical Engineering, Asia University, Taichung, Taiwan. Electronic address: aru@np.edu.sg.
Abstract
BACKGROUND: Autism spectrum disorder is a common group of conditions affecting about one in 54 children. Electroencephalogram (EEG) signals from children with autism have a common morphological pattern which makes them distinguishable from normal EEG. We have used this type of signal to design and implement an automated autism detection model. MATERIALS AND METHOD: We propose a hybrid lightweight deep feature extractor to obtain high classification performance. The system was designed and tested with a big EEG dataset that contained signals from autism patients and normal controls. (i) A new signal to image conversion model is presented in this paper. In this work, features are extracted from EEG signal using one-dimensional local binary pattern (1D_LBP) and the generated features are utilized as input of the short time Fourier transform (STFT) to generate spectrogram images. (ii) The deep features of the generated spectrogram images are extracted using a combination of pre-trained MobileNetV2, ShuffleNet, and SqueezeNet models. This method is named hybrid deep lightweight feature generator. (iii) A two-layered ReliefF algorithm is used for feature ranking and feature selection. (iv) The most discriminative features are fed to various shallow classifiers, developed using a 10-fold cross-validation strategy for automated autism detection. RESULTS: A support vector machine (SVM) classifier reached 96.44% accuracy based on features from the proposed model. CONCLUSIONS: The results strongly indicate that the proposed hybrid deep lightweight feature extractor is suitable for autism detection using EEG signals. The model is ready to serve as part of an adjunct tool that aids neurologists during autism diagnosis in medical centers.
BACKGROUND:Autism spectrum disorder is a common group of conditions affecting about one in 54 children. Electroencephalogram (EEG) signals from children with autism have a common morphological pattern which makes them distinguishable from normal EEG. We have used this type of signal to design and implement an automated autism detection model. MATERIALS AND METHOD: We propose a hybrid lightweight deep feature extractor to obtain high classification performance. The system was designed and tested with a big EEG dataset that contained signals from autismpatients and normal controls. (i) A new signal to image conversion model is presented in this paper. In this work, features are extracted from EEG signal using one-dimensional local binary pattern (1D_LBP) and the generated features are utilized as input of the short time Fourier transform (STFT) to generate spectrogram images. (ii) The deep features of the generated spectrogram images are extracted using a combination of pre-trained MobileNetV2, ShuffleNet, and SqueezeNet models. This method is named hybrid deep lightweight feature generator. (iii) A two-layered ReliefF algorithm is used for feature ranking and feature selection. (iv) The most discriminative features are fed to various shallow classifiers, developed using a 10-fold cross-validation strategy for automated autism detection. RESULTS: A support vector machine (SVM) classifier reached 96.44% accuracy based on features from the proposed model. CONCLUSIONS: The results strongly indicate that the proposed hybrid deep lightweight feature extractor is suitable for autism detection using EEG signals. The model is ready to serve as part of an adjunct tool that aids neurologists during autism diagnosis in medical centers.
Authors: Prabal Datta Barua; Jahmunah Vicnesh; Raj Gururajan; Shu Lih Oh; Elizabeth Palmer; Muhammad Mokhzaini Azizan; Nahrizul Adib Kadri; U Rajendra Acharya Journal: Int J Environ Res Public Health Date: 2022-01-21 Impact factor: 3.390