Few-Electrode EEG from the Wearable Devices Using Domain Adaptation for Depression Detection

Abstract

Nowadays, major depressive disorder (MDD) has become a crucial mental disease that endangers human health. Good results have been achieved by electroencephalogram (EEG) signals in the detection of depression. However, EEG signals are time-varying, and the distributions of the different subjects’ data are non-uniform, which poses a bad influence on depression detection. In this paper, the deep learning method with domain adaptation is applied to detect depression based on EEG signals. Firstly, the EEG signals are preprocessed and then transformed into pictures by two methods: the first one is to present the three channels of EEG separately in the same image, and the second one is the RGB synthesis of the three channels of EEG. Finally, the training and prediction are performed in the domain adaptation model. The results indicate that the domain adaptation model can effectively extract EEG features and obtain an average accuracy of 77.0 ± 9.7%. This paper proves that the domain adaptation method can effectively weaken the inherent differences of EEG signals, making the diagnosis of different users more accurate.

Neuropsychology and Electroencephalography in Rural Children at Neurodevelopmental Risk: A Scoping Review

“…Case-control ( 8) Randomized ( 4) Studies reporting specific EEG health-related conditions (72) Longitudinal (8) Randomly (4)…”

“…It is economically accessible, non-invasive, functionally sensitive, temporarily precise, and continuously improved for further complex feature extraction in different clinical conditions [6,7]. Classification methods for the sensitive detection of differences between normal and cognitively impaired subjects through the analysis of the electrical activity in the brain have been explored and have shown good reliability, even using a small number of electrodes [8,9]. The EEG functionally probes the CNS to obtain a real-time record of electrical activity [10].…”

A Convolutional Neural Network for SSVEP Identification by Using a Few-Channel EEG

“…With the advancement of electronic technology, many wearable EEG devices have been designed and produced. Owing to their compact structure, light weight and good wearability, wearable EEG devices have gradually been used in BCI applications, such as robot control [ 1 ], remote monitoring [ 2 ] and emotion recognition [ 3 ]. Compared with conventional EEG devices, wearable EEGs typically support a lower number of channels.…”