Classification of EEG Signal using Independent Component Analysis and Discrete Wavelet Transform based on Linear Discriminant Analysis

Melinda Melinda - Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia
Oktiana Maulisa - Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia
Nissa Nabila - Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia
Yunidar Yunidar - Universitas Syiah Kuala, Banda Aceh, 23111, Indonesia
I Ketut Enriko - PT Telkom Indonesia, Jl. Gatot Subroto Kav 52, Jakarta Selatan 12710, Indonesia


Citation Format:



DOI: http://dx.doi.org/10.30630/joiv.7.3.1219

Abstract


Autism Spectrum Disorder (ASD) is a neurodevelopment syndrome decreasing sufferers' social interaction, communication skills, and emotional expression. Autism syndrome can be detected using an electroencephalogram (EEG). This study utilized the EEG of autistic people to support the classification study of machine learning schemes to produce the best accuracy. One of the best approaches to classify the EEG signal is The Linear Discriminant Analysis (LDA), a machine learning technique to classify autism and normal EEG signals. LDA was chosen because it can maximize the distance between classes and minimize the number of scatters by utilizing between and within-class functions. This method was combined with other methods: Independent Components Analysis (ICA) and Discrete Wavelet Transform (DWT), to improve the accuracy system. ICA removes artifacts or signals other than brain signals that can cause noise in the EEG signal, so the analyzed signal was a complete EEG signal without other factors. DWT can help increase noise suppression in the EEG signal and provide signal information through frequency and time representation. The EEG dataset was collated from 16 children (eight autistic and eight normal). The signals from the dataset were filtered by artifacts using ICA, decomposed by three levels through DWT, and classified using the Linear Discriminant Analysis (LDA) technique. Using the Confusion Matrix, the results reveal the best accuracy of 99%.


Keywords


Autism; Electroencephalogram; Linear Discriminant Analysis; Independent Component Analysis; Discrete Wavelet Transform

Full Text:

PDF

References


B. Arunkumar, S. A. A. Vijay, and K. S. Kumar, "Spectral analysis based differentiation for EEG signals of children with autism," J. Crit. Rev., vol. 7, no. 4, pp. 882–887, 2020, doi: 10.31838/jcr.07.04.168.

G. Brihadiswaran, D. Haputhanthri, S. Gunathilaka, D. Meedeniya, and S. Jayarathna, “EEG-based processing and classification methodologies for autism spectrum disorder: A review,†J. Comput. Sci., vol. 15, no. 8, pp. 1161–1183, 2019, doi: 10.3844/jcssp.2019.1161.1183.

M. Elsabbagh et al., “Global Prevalence of Autism and Other Pervasive Developmental Disorders,†Autism Res., vol. 5, no. 3, pp. 160–179, 2012, doi: 10.1002/aur.239.

A. J. Casson, M. Abdulaal, M. Dulabh, S. Kohli, S. Krachunov, and E. Trimble, Electroencephalogram. 2018.

S. Siuly, Y. Li, and Y. Zhang, EEG Signal Analysis and Classification Techniques and Applications. 2016.

N. Cristianini, “Fisher Linear Discriminant Analysis,†Dict. Bioinforma. Comput. Biol., pp. 1–6, 2014.

“ML | Linear Discriminant Analysis - GeeksforGeeks.†https://www.geeksforgeeks.org/ml-linear-discriminant-analysis/ (accessed Jun. 25, 2022).

M. Z. Al-fFaiz H. A. Abdulkareem, and C. Engineering, “Offline Linear Discriminant Analysis Classification,†vol. 2, no. 3, pp. 1–10, 2019.

S. Calcagno, F. La Foresta, and M. Versaci, “Independent component analysis and discrete wavelet transform for artifact removal in biomedical signal processing,†Am. J. Appl. Sci., vol. 11, no. 1, pp. 57–68, 2014.

S. N. S. Sayed Daud and R. Sudirman, “Artifact removal and brain rhythm decomposition for EEG signal using wavelet approach,†J. Teknol., vol. 78, no. 7–5, pp. 135–143, 2016.

K. Asaduzzaman, M. B. I. Reaz, F. Mohd-Yasin, K. S. Sim, and M. S. Hussain, “A study on discrete wavelet-based noise removal from EEG signals,†Adv. Exp. Med. Biol., vol. 680, pp. 593–599, 2010.

T.-P. Jung et al., “Removing electroencephalographic artifacts from by blind source separation,†Psychophysiology, vol. 37, no. 2, pp. 163–178, 2000.

Z. Khakim and S. Kusrohmaniah, “Dasar - Dasar Electroencephalography (EEG) bagi Riset Psikologi,†Bul. Psikol., vol. 29, no. 1, p. 92, 2021.

E. M. Ali, F. eid ziad Al- Adwan, and Y. M. Al-Naimat, “Autism Spectrum Disorder (ASD); Symptoms, Causes, Diagnosis, Intervention, and Counseling Needs of the Families in Jordan,†Mod. Appl. Sci., vol. 13, no. 5, p. 48, 2019.

N. Handayani, S. H. Pratama, S. N. Khotimah, I. Arif, and F. Haryanto, “Analisis Spektral Daya dan Koherensi EEG Pada Anak Penderita Autism Spectrum Disorders (ASD),†Wahana Fis., vol. 2, no. 2, p. 42, 2017.

N. Fauzan and N. H. Amran, “Brain Waves and Connectivity of Autism Spectrum Disorders,†Procedia - Soc. Behav. Sci., vol. 171, pp. 882–890, 2015.

A. Syahdeini, “Klasifikasi Emosi Dari Data Sinyal EEG Menggunakan Independent Component Analysis (ICA), Wavelet Denoising Dan Multiple Discrimnant Analysis (MDA),†p. 76, 2015.

M. E.J., H. T. van Schie, B. J.L., and J. M. H. de Moor, “Neurofeedback Treatment for Autism Spectrum Disorders – Scientific Foundations and Clinical Practice,†Autism Spectr. Disord. - From Genes to Environ., 2011.

A. Tharwat, “Independent component analysis: An introduction,†Appl. Comput. Informatics, vol. 17, no. 2, pp. 222–249, 2018.

I. Rejer and P. Gorski, “Benefits of ICA in the Case of a Few Channel EEG,†Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, vol. 2015-Novem, pp. 7434–7437, 2015.

P. A. Janardhan and P. K. K. Rao, “Application of Signal Separation Algorithms for Artifact Removal from EEG Signals,†no. 1, pp. 1–6, 2015.

S. Debener, J. Thorne, T. R. Schneider, and F. C. Viola, “Using ICA for the Analysis of Multi-Channel EEG Data,†Simultaneous EEG fMRI Rec. Anal. Appl., vol. 9780195372, pp. 1–23, 2010.

J. Kumar Sharma, Y. Gopal, D. Birla, and M. Lalwani, “An Algorithm for Selecting Compatible Wavelet Function in Electrical Signals to Detect and Localize Disturbances,†Int. J. Appl. Eng. Res., vol. 13, no. 14, pp. 11440–11447, 2018.

P. Chum, S.-M. Park, K.-E. Ko, and K.-B. Sim, “Optimal EEG Feature Extraction using DWT for Classification of Imagination of Hands Movement,†J. Korean Inst. Intell. Syst., vol. 21, no. 6, pp. 786–791, 2011.

Q. Mohi-Ud-Din and A. K. Jayanthy, “EEG feature extraction using wavelet transform for classifying autism spectrum disorder,†Mater. Today Proc., no. xxxx, pp. 2–5, 2021.

S. Z. M. Tumari, R. Sudirman, and A. H. Ahmad, “Selection of a Suitable Wavelet for Cognitive Memory Using Electroencephalograph Signal,†Engineering, vol. 05, no. 05, pp. 15–19, 2013.

Anonymous, “Lesson 2: Discriminant Analysis,†Multivar. Data Analaysis using SPSS, pp. 27–42, 2015.

N. F. M. Radzi, A. C. Soh, A. J. Ishak, M. K. Hassan, and U. K. Mohamad Yusof, “Aromatic herbs classification by using discriminant analysis techniques,†Indones. J. Electr. Eng. Comput. Sci., vol. 5, no. 3, pp. 530–535, 2017.

L. K. Kumar, “Improving efficiency in eeg process using linear discriminant analysis and support vector machine,†Int. J. Recent Technol. Eng., vol. 7, no. 6, pp. 910–913, 2019.

K. M. Ting, “Confusion Matrix,†Encycl. Mach. Learn. Data Min., no. October, pp. 260–260, 2017, doi: 10.1007/978-1-4899-7687-1_50.

M. J. Alhaddad et al., “Diagnosis autism by Fisher Linear Discriminant Analysis FLDA via EEG,†Int. J. Bio-Science Bio-Technology, vol. 4, no. 2, pp. 45–54, 2012.

L. Ribeiro et al., “Analysis of the relationship between EEG signal and aging through Linear Discriminant Analysis (LDA),†Rev. Bras. Eng. Biomédica, vol. 28, pp. 155–168, 2012.

T. ArchanaH. and D. Sachin, “Dimensionality Reduction and Classification through PCA and LDA,†Int. J. Comput. Appl., vol. 122, no. 17, pp. 4–8, 2015.

M. Kołodziej, A. Majkowski, and R. J. Rak, “Linear discriminant analysis as EEG features reduction technique for brain-computer interfaces,†Prz. Elektrotechniczny, vol. 88, no. 3 A, pp. 28–30, 2012.

M. Torres and J. Manuel, “&&( TJHOBMT DMBTTJmDBUJPO using linear and non-linear discriminant methods,†2013.

R. Shoorangiz, S. J. Weddell, and R. D. Jones, EEG-Based Machine Learning: Theory and Applications. 2021.

E. M. Carlos Eduardo, “EEG Brain Mapping of Normal and Learning Disabled Children Using Factor and Linear Discriminant Analyses,†J. Neurol. Neurophysiol., vol. 06, no. 01, pp. 1–7, 2014.

D. Jaime and Sotaquirá Miguel, “EEG Signal Classification Using Power Spectral Feature and Linear Discriminant Analysis: A Brain Computer Interface Application ,†Proc. Eighth Lat. Am. Caribb. Conf. Eng. Technol., no. 2010, p. P#156, 2010.

B. Michał, D. Figurowski, and M. Kubicki, “Comparison of the EEG Signal Classifier LDA, NBC and GNBC Based on Time-Frequency Features,†Pomiary, Autom. Robot., vol. 18, no. 3, pp. 71–75, 2016, doi: 10.14313/PAR.

L. Billeci et al., “An integrated approach for the monitoring of brain and autonomic response of children with Autism Spectrum Disorders during treatment by wearable technologies,†Front. Neurosci., vol. 10, no. JUN, pp. 1–17, 2016, doi: 10.3389/fnins.2016.00276.