Major depressive disorder assessment via enhanced k-nearest neighbor method and EEG signals
- PDF / 2,060,307 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 83 Downloads / 185 Views
SCIENTIFIC PAPER
Major depressive disorder assessment via enhanced k‑nearest neighbor method and EEG signals Maryam Saeedi1 · Abdolkarim Saeedi1 · Arash Maghsoudi1 Received: 17 February 2020 / Accepted: 2 July 2020 © Australasian College of Physical Scientists and Engineers in Medicine 2020
Abstract The aim of this paper is to introduce a novel method using short-term EEG signals to separate depressed patients from healthy controls. Five common frequency bands (delta, theta, alpha, beta and gamma) were extracted from the signals as linear features, as well as, wavelet packet decomposition to break down signals into certain frequency bands. Afterwards, two entropy measures, namely sample entropy and approximate entropy were applied on the wavelet packet coefficients as nonlinear features, and significant features were selected via genetic algorithm (GA). Three machine-learning algorithms were used for classification; including support vector machine (SVM), multilayer perceptron (MLP) a novel enhanced K-nearest neighbors (E-KNN), which uses GA to optimize the feature-space distances and provides a feature importance index. The highest accuracy obtained by using frequency-based features was from gamma oscillations which resulted in 91.38%. Performance of nonlinear features were better compared to the frequency-based features and the results showed 94.28% accuracy. The combination of the features showed 98.44% accuracy with the new proposed E-KNN classifier. Keywords Major depressive disorder (MDD) · K-nearest neighbors electroencephalography · Entropy · Wavelet packet · Gamma oscillations
Introduction The world health organization (WHO) has predicted that depression will become the second leading cause of disability by 2020 [1]. If it is diagnosed at an early stage, the patient’s condition will be significantly improved via treatment, medication or lifestyle changes. Electroencephalogram (EEG) is a signal recorded noninvasively and represents the brain electrical activity. Due to its high temporal resolution and reliability, EEG seems to be an effective tool for diagnosis of depression. Hinrikus et al. [2] presented a novel spectral asymmetry index (SASI) which is based on the calculation of relative power differences of two specific frequency bands of the EEG signal. * Arash Maghsoudi [email protected] Maryam Saeedi [email protected] Abdolkarim Saeedi a‑[email protected] 1
Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Their calculations exclude the central frequency band (alpha band) and their analysis is on 30-min recordings of 36 subjects (18 normal and 18 depressed). Puthankattil et al. [3] studied 30 subjects with 5-min EEG recording in resting state condition. Initially an eight-level discrete wavelet transform was used to decompose the signal into high and low frequency components (detail and approximate coefficients respectively), consequently, wavelet entropies (WE) based on the Shannon entropy and relative wavelet energy (RWE
Data Loading...
