Abstract
Autism is a kind of disorder that impacts the human brain due to which people face some difficulties in interaction and communication with others. The detection and identification of autism at an early stage are a difficult task for researchers. The preprocessing techniques include discrete wavelet transformation (DWT), standard deviation, and mean. DWT helps in preprocessing of the EEG signals, which reduces the noise and decomposes the signals into EEG subbands. In this work, we have discussed various classifiers like SVM, Naïve Bayes, KNN, random forest, decision tree, LSTM, and ANN. These classifiers help to classify the EEG signals into autistic and non-autistic based on the features extracted. When evaluated on the actual dataset obtained from King Abdul-Aziz University(KAU), Saudi Arabia, the techniques produced up to 99.9% encouraging results. This dataset contains 17 subjects, in which there are 4 normal and 13 autistic subjects. We are using the SMOTE technique for data augmentation, which has helped us to improve the performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ibrahim, S., Djemal, R., & Alsuwailem, A. (2018). Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis. Biocybernetics and Biomedical Engineering, 38(1), 16–26.
Acharya, U. R., Yanti, R., Swapna, G., Sree, V. S., Martis, R. J., & Suri, J. S. (2013). Automated diagnosis of epileptic electroencephalogram using independent component analysis and discrete wavelet transform for different electroencephalogram durations. Proceedings of the Institution of Mechanical Engineers, Part H, Journal of Engineering in Medicine.
Sheikhani, A., Behnam, H., Mohammade, M. R., Noroozian, M., & Golabi, P. (2008). Connectivity analysis of quantitative electroencephalogram background activity in autism disorders with short time Fourier transform and coherence values. In Proceedings of the 1st International Congress on Image and Signal Processing (CISP’08) (pp. 207–212). IEEE.
Sheikhani, A., Behnam, H., Mohammadi, M. R., Noroozian, M., & Mohamamadi, M. (2012). Detection of abnormalities for diagnosing of children with autism disorders using of quantitative electroencephalography analysis. Journal of Medical Systems, 36(2), 957–963.
Alhaddad, M. J., Kamel, M. I., Malibary, H. M., Alsaggaf, E. A., Thabit, K., Dahlwi, F., et al. (2012). Diagnosis autism by Fisher linear discriminant analysis FLDA via EEG. International Journal o Bio-Science Bio-Technology, 4, 45–54.
Sheikhani, A., Behnam, H., Mohammadi, M. R., Noroozian, M., & Mohamamadi, M. (2012). Detection of abnormalities for diagnosing of children with autism disorders using of quantitative electroencephalography analysis. Journal of Medical Systems, 36(2), 957–963.
Alhaddad, M. J., Kamel, M. I., Malibary, H. M., Alsaggaf, E. A., Thabit, K., Dahlwi, F., & Hadi, A. A. (2012). Diagnosis autism by Fisher linear discriminant analysis FLDA via EEG. International Journal of Bio-Science and Bio-Technology, 4(2), 45–54.
Delorme, A., & Makeig, S. (2004). EEGLAB an open-source toolbox for analysis of single-trial EEG dynamics. Journal of Neuroscience Methods, 134, 9–21.
Bosl, W. J., Tager-Flusberg, H., & Nelson, C. A. (2018). EEG analytics for early detection of autism spectrum disorder. A data-driven approach. Scientific Reports, 8(1). https://doi.org/10.1038/s41598-018-24318-x
Alsuwailem, A., Djemal, R., & Ibrahim, S. (2018). Electroencephalography (EEG) signal processing for epilepsy and autism spectrum disorder diagnosis. Biocybernetics and Biomedical Engineering, 38(1), 16–26. https://doi.org/10.1016/j.bbe.2017.08.006.
Faust, O., Acharya, U. R., Adeli, H., & Adeli, A. (2015). Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis. Seizure, 26(March), 56–64.
Tawhid, M. N. A., Siuly, S., & Wang, H. (2020). Diagnosis of autism spectrum disorder from EEG using a time-frequency spectrogram. The Institution of Engineering and Technology, Current Trends in Cognitive Science and Brain Computing Research and Applications. https://doi.org/10.1049/el.2020.2646
Ghosh-Dastidar, S., Adeli, H., & Dadmehr, N. (2007). Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection. IEEE Transactions on Biomedical Engineering, 54(9), 1545–1551.
Seo, J.-H., & Kim, Y.-H. (2018). Machine-learning approach to optimize SMOTE ratio in class imbalance dataset for intrusion detection. Computational Intelligence and Neuroscience, 11, Article ID 9704672. https://doi.org/10.1155/2018/9704672
Weinberger, K. Q., & Saul, L. K. (2019). Distance metric learning for large margin nearest neighbor classification. Journal of Machine Learning Research, 10(February), 207–244.
Burges, C. J. C. (1998). A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, 2, 121–167.
Jahromi, A. H., & Taheri, M. (2017). A non-parametric mixture of Gaussian Naive Bayes classifiers based on local independent features. In Artificial Intelligence and Signal Processing Conference (AISP) (pp. 209–212). https://doi.org/10.1109/AISP.2017.8324083
Ray, S. (2019). A quick review of machine learning algorithms. In International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon) 2019 (p. 3539). https://doi.org/10.1109/COMITCon.2019.8862451
Wyner, A. J., Matthew, O., Justin, B., & David, M. (2017). Explaining the success of AdaBoost and random forests as interpolating classifiers. Journal of Machine Learning Research, 18(48), 1–33.
Djemal, R., AlSharabi, K., Ibrahim, S., & Alsuwailem, A. (2017). EEG-based computer aided diagnosis of autism spectrum disorder using wavelet, entropy, and ANN. BioMed Research International, 2017, 1–9. https://doi.org/10.1155/2017/9816591.
Ali, N. A., Radzi, S. A., Jaafar, S., Shamsuddin, S., & Nor, N. K. (2021). LSTM-based electroencephalogram classification on autism spectrum disorder. International Journal of Integrated Engineering, 13(6), 321–329.
Anas, H., Mahmod, K., Mohammed, A., Hussein, M., Khalid, T., Foud, D., & Alsaggaf, E. A. (2012). EEG based autism diagnosis using regularized Fisher linear discriminant analysis. International Journal of Image, Graphics and Signal Processing (IJIGSP), 4, 35–41. https://doi.org/10.5815/ijigsp.2012.03.06.
Tawhid, Md. N. A., Siuly, S., Wang, H., Whittaker, F., Wang, K., & Zhang, Y. (2021). A spectrogram image based intelligent technique for automatic detection of autism spectrum disorder from EEG. PLOS ONE, 16, e0253094. https://doi.org/10.1371/journal.pone.0253094.
Acknowledgements
KAU Brain Computer Interface (BCI) Group provided their own autism dataset, which we highly appreciate.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kumar, A., Agrawal, A. (2023). Development of Machine Learning Approaches for Autism Detection Using EEG Data: A Comparative Study. In: Shakya, S., Du, KL., Ntalianis, K. (eds) Sentiment Analysis and Deep Learning. Advances in Intelligent Systems and Computing, vol 1432. Springer, Singapore. https://doi.org/10.1007/978-981-19-5443-6_25
Download citation
DOI: https://doi.org/10.1007/978-981-19-5443-6_25
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-5442-9
Online ISBN: 978-981-19-5443-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)