Analysis of Psychiatric Disorders from EEG Signals Using  Machine-Learning Techniques

Chowdhury, Md. Makam Ul Hasan; Ahmed, Nadim; Chowdhury, Hasib Arman

IUT Repository Home
→
Electrical and Electronics Engineering (EEE)
→
Thesis
→
Undergraduate
→
2023
→
View Item

dc.contributor.author	Chowdhury, Md. Makam Ul Hasan
dc.contributor.author	Ahmed, Nadim
dc.contributor.author	Chowdhury, Hasib Arman
dc.date.accessioned	2024-01-17T05:59:58Z
dc.date.available	2024-01-17T05:59:58Z
dc.date.issued	2023-05-30
dc.identifier.citation	[1] R. Das, M. R. Hasan, S. Daria, and M. R. Islam, “Impact of COVID-19 pandemic on mental health among general Bangladeshi population: a cross-sectional study,” BMJ Open, vol. 11, no. 4, p. e045727, 2021. [2] A. Al-Ezzi, N. Kamel, I. Faye, and E. Gunaseli, “Analysis of default mode network in social anxiety disorder: EEG resting-state effective connectivity study,” Sensors (Basel), vol. 21, no. 12, p. 4098, 2021. [3] M. J. Rivera, M. A. Teruel, A. Maté, and J. Trujillo, “Diagnosis and prognosis of mental disorders by means of EEG and deep learning: a systematic mapping study,” Artif. Intell. Rev., vol. 55, no. 2, pp. 1209–1251, 2022. [4] Z. Shen et al., “Aberrated multidimensional EEG characteristics in patients with generalized anxiety disorder: A machine-learning based analysis framework,” Sensors (Basel), vol. 22, no. 14, p. 5420, 2022. [5] N. Langer et al., “A benchmark for prediction of psychiatric multimorbidity from resting EEG data in a large pediatric sample,” Neuroimage, vol. 258, no. 119348, p. 119348, 2022. [6] D. Watts, H. Moulden, M. Mamak, C. Upfold, G. Chaimowitz, and F. Kapczinski, “Predicting offenses among individuals with psychiatric disorders - A machine learning approach,” J. Psychiatr. Res., vol. 138, pp. 146–154, 2021. [7] A. Khodayari-Rostamabad, J. P. Reilly, G. Hasey, H. Debruin, and D. Maccrimmon, “Diagnosis of psychiatric disorders using EEG data and employing a statistical decision model,” Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., vol. 2010, pp. 4006–4009, 2010. [8] H. Peng, F. Long, and C. Ding, “Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, no. 8, pp. 1226–1238, 2005. 49 [9] Z. Ghahramani, G. Rey, and E. Hinton, “The EM algorithm for mixtures of factor analyzers,” Psu.edu, 1996. [Online]. Available: https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=766f4465747394d304d16219 7e091f1ae8f7f577. [Accessed: 04-Jun-2023]. [10] S. M. Park et al., “Identification of major psychiatric disorders from resting-state electroencephalography using a machine learning approach,” Front. Psychiatry, vol. 12, p. 707581, 2021. [11] A. A. Rahman et al., “Detection of mental state from EEG signal data: An investigation with machine learning classifiers,” in 2022 14th International Conference on Knowledge and Smart Technology (KST), 2022. [12] C. Ranjith and B. Arunkumar, “An improved Elman neural network based stress detection from EEG signals and reduction of stress using music,” Ripublication.com. [Online]. Available: http://www.ripublication.com/irph/ijert19/ijertv12n1_03.pdf. [Accessed: 04-Jun-2023]. [13] J. Ashford, J. J. Bird, F. Campelo, and D. R. Faria, “Classification of EEG signals based on image representation of statistical features,” in Advances in Intelligent Systems and Computing, Cham: Springer International Publishing, 2020, pp. 449–460. [14] Z. Iscan et al., “Test-retest reliability of freesurfer measurements within and between sites: Effects of visual approval process: Test-Retest Reliability of FreeSurfer Measurements,” Hum. Brain Mapp., vol. 36, no. 9, pp. 3472–3485, 2015 [15] L. Breiman, Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001 [16] S. Bhat, “Detection of polycystic ovary syndrome using machine learning algorithms,” Diss. Dublin, 2021. [17] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273– 297, 1995. [18] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York, NY: Springer, 2009. 50 [19] K. R. Bhatele and S. S. Bhadauria, “Glioma segmentation and classification system based on proposed texture features extraction method and hybrid ensemble learning,” Trait. Du Signal, vol. 37, no. 6, pp. 989–1001, 2020. [20] H. Zhang, L. Wan, and Y. Li, “Prediction of soil organic carbon content using sentinel-1/2 and machine learning algorithms in swamp wetlands in northeast China,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., pp. 1–12, 2023. [21] B. Deepa and K. Ramesh, “Epileptic seizure detection using deep learning through min max scaler normalization,” Int. J. Health Sci. (IJHS), pp. 10981–10996, 2022. [22] A. Fernandez, S. Garcia, F. Herrera, and N. V. Chawla, “SMOTE for learning from imbalanced data: Progress and challenges, marking the 15-year anniversary,” J. Artif. Intell. Res., vol. 61, pp. 863–905, 2018. [23] R. Drikvandi and O. Lawal, “Sparse principal component analysis for natural language processing,” Ann. Data Sci., vol. 10, no. 1, pp. 25–41, 2023. [24] H. Zou and L. Xue, “A selective overview of sparse principal component analysis,” Proc. IEEE Inst. Electr. Electron. Eng., vol. 106, no. 8, pp. 1311–1320, 2018. [25] R. R. Wilcox, “Understanding the practical advantages of modern ANOVA methods,” J. Clin. Child Adolesc. Psychol., vol. 31, no. 3, pp. 399–412, 2002. [26] S. Visa, B. Ramsay, A. Ralescu, and E. VanDerKnaap, “ Confusion matrix-based feature selection,” p. 120, 2011. [27] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, p. 6, 2020. [28] U. Bhowan, M. Johnston, and M. Zhang, “Evolving ensembles in multi-objective genetic programming for classification with unbalanced data,” in Proceedings of the 13th annual conference on Genetic and evolutionary computation, 2011. 51 [29] A. P. Bradley, R. P. W. Duin, P. Paclik, and T. C. W. Landgrebe, “Precision-recall operating characteristic (P-ROC) curves in imprecise environments,” in 18th International Conference on Pattern Recognition, 2006. [30] Z. C. Lipton, C. Elkan, and B. Narayanaswamy, “Thresholding classifiers to maximize F1 score,” arXiv [stat.ML], 2014. [31] A. Anuragi and D. Singh Sisodia, “Alcohol use disorder detection using EEG Signal features and flexible analytical wavelet transform,” Biomed. Signal Process. Control, vol. 52, pp. 384–393, 2019	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/2034
dc.description	Supervised by Mr. Fahim Faisal, Assistant Professor, Department of Electrical and Electronics Engineering (EEE) Islamic University of Technology (IUT) Board Bazar, Gazipur-1704, Bangladesh	en_US
dc.description.abstract	Over the past few years, Psychiatric Disorders (PD) have had a significant impact on global health and their prevalence has been leading towards major adversities like functional disabilities and even suicide. These disorders can be divided into some major and specific categories which show different symptoms and have different remedies accordingly. This study makes an attempt to tackle this problem head on and detect said disorders to allow the patients to take necessary actions before the point of no return. For efficient and trustworthy detection of PD, a Machine Learning (ML) approach has been taken and different algorithms were run on the chosen dataset. The dataset that was used for this study was collected from Neuroimaging (NI), Electroencephalography (EEG), tests which have a variety of distinctive features. It was observed that EEG is a reliable and effective way of collecting brain signals which can later be used in different studies like this one. Judging by the magnitude of the samples taken by the EEG device, it was decided that ML would be a very useful tool in this regard and with good accuracies, an acceptable structure can be created. The goal of this study to make a contribution to application of machine learning algorithms in medical sciences and also to call attention to the capabilities of EEG in the prompt detection of PD. From the findings of this study, it can be observed that very high accuracy was obtained for both the binary and multiclass classifications. The results were tabulated taking samples by using feature selection and feature extraction methods. The highest accuracy for main disorder for multiclass classification was 80.69% and that of the specific disorder was 87.52% both of which used SPARSE PCA feature extraction method. This study makes a solid attempt at addressing this rising issue with a very satisfactory approach and thus makes a fruitful contribution to the medical and data science field for addressing similar adversities in the process	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Electrical and Elecrtonics Engineering(EEE), Islamic University of Technology(IUT), Board Bazar, Gazipur-1704, Bangladesh	en_US
dc.title	Analysis of Psychiatric Disorders from EEG Signals Using Machine-Learning Techniques	en_US
dc.type	Thesis	en_US