Automatic Detection of Mild Cognitive Impairment from EEG Recordings Using Discrete Wavelet Transform Leader and Ensemble Learning Methods

Authors : Afrah SAİD, Hanife GÖKER

Pages : 47-54

Doi:10.24012/dumf.1227520

View : 92 | Download : 118

Publication Date : 2023-03-23

Article Type : Research Paper

Abstract :Mild Cognitive Impairment insert ignore into journalissuearticles values(MCI); is a risk of cognitive decline, commonly referred to as a transitional stage between normal cognition and dementia. Patients with MCI typically progress to Alzheimer\`s disease insert ignore into journalissuearticles values(AD);, which causes cognitive deficits such as deterioration of their thinking abilities. This study aims to detect MCI patients using electroencephalography insert ignore into journalissuearticles values(EEG); signals. The EEG dataset used in this study consists of EEG signals recorded from 18 MCI and 16 control groups. Firstly, EEG signals were denoised using multiscale principal component analysis insert ignore into journalissuearticles values(multiscale PCA);. Then, 36 features were extracted from the EEG signals using the discrete wavelet transform leader insert ignore into journalissuearticles values(DWT leader); feature extraction method. Finally, using the extracted feature vectors, control groups, and MCI groups were classified by ensemble learning algorithms. As a result, AdaBoostM1 algorithm has the highest success with 93.50% accuracy, 93.27% sensitivity, 93.75% specificity, 94.38% precision, 93.82% f1-score, and 86.97% Matthews correlation coefficient insert ignore into journalissuearticles values(MCC);. By achieving quite satisfactory accuracy, this study proves that the ensemble learning algorithm can also be used for MCI detection.
Keywords : Ayrık dalgacık dönüşüm lideri, EEG, topluluk öğrenme, MCI, otomatik tanı