Wang Zhuozheng, Ma Zhuo, Liu Wei, An Zhefeng, Huang Fubiao
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
Advising Center for Student Development, Beijing University of Technology, Beijing 100124, China.
Brain Sci. 2022 Jun 26;12(7):834. doi: 10.3390/brainsci12070834.
Depression is a common but easily misdiagnosed disease when using a self-assessment scale. Electroencephalograms (EEGs) provide an important reference and objective basis for the identification and diagnosis of depression. In order to improve the accuracy of the diagnosis of depression by using mainstream algorithms, a high-performance hybrid neural network depression detection method is proposed in this paper combined with deep learning technology. Firstly, a concatenating one-dimensional convolutional neural network (1D-CNN) and gated recurrent unit (GRU) are employed to extract the local features and to determine the global features of the EEG signal. Secondly, the attention mechanism is introduced to form the hybrid neural network. The attention mechanism assigns different weights to the multi-dimensional features extracted by the network, so as to screen out more representative features, which can reduce the computational complexity of the network and save the training time of the model while ensuring high precision. Moreover, dropout is applied to accelerate network training and address the over-fitting problem. Experiments reveal that the 1D-CNN-GRU-ATTN model has more effectiveness and a better generalization ability compared with traditional algorithms. The accuracy of the proposed method in this paper reaches 99.33% in a public dataset and 97.98% in a private dataset, respectively.
抑郁症是一种常见但使用自评量表时容易误诊的疾病。脑电图（EEG）为抑郁症的识别和诊断提供了重要参考和客观依据。为了利用主流算法提高抑郁症诊断的准确性，本文结合深度学习技术提出了一种高性能混合神经网络抑郁症检测方法。首先，采用串联一维卷积神经网络（1D-CNN）和门控循环单元（GRU）来提取脑电信号的局部特征并确定全局特征。其次，引入注意力机制形成混合神经网络。注意力机制为网络提取的多维特征分配不同权重，从而筛选出更具代表性的特征，在保证高精度的同时可以降低网络的计算复杂度并节省模型的训练时间。此外，应用随机失活（dropout）来加速网络训练并解决过拟合问题。实验表明，与传统算法相比，1D-CNN-GRU-ATTN模型具有更高的有效性和更好的泛化能力。本文提出的方法在公开数据集和私有数据集中的准确率分别达到了99.33%和97.98%。
