EEG-based Depression Detection Using Convolutional Neural Network with Demographic Attention Mechanism

Zhang, Xiaowei; Li, Junlei; Hou, Kechen; Hu, Bin; Shen, Jian; Pan, Jui-Wen

doi:10.1109/embc44109.2020.9175956

Cited by 23 publications

(12 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…hemispheric asymmetry [22] and functional connectivity expressed in terms of PLI [20] and cross correlation [22]. Classification using functional connectivity [20], [22] as input of 2D CNN shows better accuracy in comparison to 1D CNN [14].…”

Section: Resultsmentioning

confidence: 99%

“…Acharya et al [13] used a 13layer convolutional neural network (CNN) over 15 healthy and 15 depressed subjects and obtained classification accuracies of 96% and 93.5% for the right and left hemispheres, respectively. A combination of 1D EEG data along with demographic information including gender and age are fed into a 1D CNN achieving 75.29% classification accuracy was also reported in [14]. In addition, [15] proposed a combined model of CNN and long short-term memory (LSTM) for onedimensional EEG (1D-EEG) signals and achieved a classification accuracy of 98.32% for 33 depressed and 30 healthy controls.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

Automated Diagnosis of Major Depressive Disorder Using Brain Effective Connectivity and 3D Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 97%

Automated Diagnosis of Major Depressive Disorder Using Brain Effective Connectivity and 3D Convolutional Neural Network

et al. 2021

View full text Add to dashboard Cite

“…Moreover, the employment of more data or other techniques such as LSTM might improve the accuracy. X. Zhang et al [43] experimented with two models of MDD prediction which were the employment of one-dimensional Convolutional Neural Network (1-D CNN) with and without demographic attention mechanism to indicate the effects of EEG signals and demographic information integration on accuracy. In order to prepare data, discrete wavelet transform and Kalman filtering methods were adopted to omit noisy signals.…”

Section: Deep Learning Methods For Depression Detection Using Eeg Signalsmentioning

confidence: 99%

Depression Diagnosis by Deep Learning Using EEG Signals: A Systematic Review

Safayari¹,

Bolhasani²

2021

Preprint

View full text Add to dashboard Cite

Depression is considered by WHO as the main contributor to global disability and it poses dangerous threats to approximately all aspects of human life, in particular public and private health. This mental disorder is usually characterized by considerable changes in feelings, routines, or thoughts. With respect to the fact that early diagnosis of this illness would be of critical importance ineffective treatment, some development has occurred in the purpose of depression detection. EEG signals reflect the working status of the human brain by which are considered the most proper tools for a depression diagnosis. Deep learning algorithms have the capacity of pattern discovery and extracting features from the raw data which is fed into them. Owing to this significant characteristic of deep learning, recently, these methods have intensely utilized in the diverse field of researches, specifically medicine and healthcare. Thereby, in this article, we aimed to review all papers concentrated on using deep learning to detect or predict depressive subjects with the help of EEG signals as input data. Regarding the adopted search method, we finally evaluated 22 articles between 2016 and 2021. This article which is organized according to the systematic literature review (SLR) method, provides complete summaries of all exploited studies and compares the noticeable aspects of them. Moreover, some statistical analysis performs to gain a depth perception of the general ideas of the latest researches in this area. A pattern of a five-step procedure was also established by which almost all reviewed articles fulfilled the goal of depression detection. Finally, open issues and challenges in this way of depression diagnosis or prediction and suggested works as the future directions discussed.

show abstract

“…A dynamic fusion strategy is proposed to integrate positive and negative emotional information. Zhang et al (2020) combined demographic factors in EEG modeling and depression detection, integrating gender and age factors into a 1D CNN through attention mechanisms to explore the complex correlation between EEG signals and demographic factors, and ultimately to generate more effective high-level representations for the detection of depression. Based on the premise that different bands of the voice spectrum contribute unevenly to the detection of depression, Niu et al (2021) proposed a time-frequency attention (TFA) component that highlights those distinct timestamps, bands, and channels that make the prediction of individual depression more effective than before.…”

Section: Attention Mechanismmentioning

confidence: 99%

Depression Speech Recognition With a Three-Dimensional Convolutional Network

Wang

Liu

Zhen

et al. 2021

Front. Hum. Neurosci.

View full text Add to dashboard Cite

Depression has become one of the main afflictions that threaten people's mental health. However, the current traditional diagnosis methods have certain limitations, so it is necessary to find a method of objective evaluation of depression based on intelligent technology to assist in the early diagnosis and treatment of patients. Because the abnormal speech features of patients with depression are related to their mental state to some extent, it is valuable to use speech acoustic features as objective indicators for the diagnosis of depression. In order to solve the problem of the complexity of speech in depression and the limited performance of traditional feature extraction methods for speech signals, this article suggests a Three-Dimensional Convolutional filter bank with Highway Networks and Bidirectional GRU (Gated Recurrent Unit) with an Attention mechanism (in short 3D-CBHGA), which includes two key strategies. (1) The three-dimensional feature extraction of the speech signal can timely realize the expression ability of those depression signals. (2) Based on the attention mechanism in the GRU network, the frame-level vector is weighted to get the hidden emotion vector by self-learning. Experiments show that the proposed 3D-CBHGA can well establish mapping from speech signals to depression-related features and improve the accuracy of depression detection in speech signals.

show abstract

EEG-based Depression Detection Using Convolutional Neural Network with Demographic Attention Mechanism

Cited by 23 publications

References 27 publications

Automated Diagnosis of Major Depressive Disorder Using Brain Effective Connectivity and 3D Convolutional Neural Network

Automated Diagnosis of Major Depressive Disorder Using Brain Effective Connectivity and 3D Convolutional Neural Network

Depression Diagnosis by Deep Learning Using EEG Signals: A Systematic Review

Depression Speech Recognition With a Three-Dimensional Convolutional Network

Contact Info

Product

Resources

About