| 孙诗晴,孙嘉琪,孙玉冰,蔡靖,刘光达.基于PLSTM-AttnNet的抑郁症识别研究[J].电子测量与仪器学报,2026,40(4):253-261 |
| 基于PLSTM-AttnNet的抑郁症识别研究 |
| Experimental design of depression diagnosis based on PLSTM-AttnNet |
| |
| DOI： |
| 中文关键词: 脑电信号 抑郁症识别 深度残差网络 长短时记忆网络 注意力机制 |
| 英文关键词:electroencephalogram (EEG) depression recognition deep residual networks (ResNet) long short term memory (LSTM) attention mechanism (AM) |
| 基金项目:吉林大学本科教学改革研究项目（2023XZD066）资助 |
|
|
| Author | Institution |
| Sun Shiqing | School of Instrument Science and Electrical Engineering, Jilin University, Changchun 130000, China |
| Sun Jiaqi | School of Instrument Science and Electrical Engineering, Jilin University, Changchun 130000, China |
| Sun Yubing | School of Instrument Science and Electrical Engineering, Jilin University, Changchun 130000, China |
| Cai Jing | School of Instrument Science and Electrical Engineering, Jilin University, Changchun 130000, China |
| Liu Guangda | School of Instrument Science and Electrical Engineering, Jilin University, Changchun 130000, China |
|
| 摘要点击次数: 340 |
| 全文下载次数: 125 |
| 中文摘要: |
| 为提高抑郁症的自动识别准确率，提出使用融合深度残差网络作为编码器，同时引入改进长短时记忆网络与自注意力机制以提升网络模型对数据时序性的感知能力，得到效果较好的PLSTM-AttnNet模型。首先对脑电信号进行滤波、去噪等预处理操作，提取6项典型时域数据以及涵盖涵盖δ、θ、α、β、γ 5个频段的微分熵与功率谱密度。将预处理的数据输入ResNet编码器提取空间维度信息，使用PLSTM模块和自注意力Attention模块处理ResNet编码器的输出特征以捕捉数据的时序维度信息，提高抑郁症的识别准确率。在公开EEG数据集上开展大量对比实验，量化结果显示，所提PLSTM-AttnNet模型分类准确率达97.3%，较于单一ResNet模型、ResNet-PLSTM模型，准确率分别提升10.1%、3.9%，且在F1分数等评价指标上均显著优于对比模型。结果表明，该模型通过ResNet与PLSTM-Attention的创新融合，有效强化了EEG信号时序 空间特征的协同表征能力，解决了传统模型特征捕捉片面的问题，为抑郁症的高效自动识别提供了可靠方案，具有重要的临床应用价值。 |
| 英文摘要: |
| To improve the accuracy of automatic recognition of depression, a fusion deep residual network is proposed as the encoder, and an improved long short-term memory network and self attention mechanism are introduced to enhance the network model’s perception ability of data temporality, resulting in a well performing PLSTM AttnNet model. Firstly, preprocessing operations such as filtering and denoising are performed on the EEG signal to extract six typical time-domain data and differential entropy and power spectral density covering five frequency bands: δ, θ, α, β, and γ. Input the preprocessed data into the ResNet encoder to extract spatial dimension information, use the PLSTM module and self attention module to process the output features of the ResNet encoder to capture the temporal dimension information of the data, and improve the recognition accuracy of depression. A large number of comparative experiments were conducted on the publicly available EEG dataset, and the quantitative results showed that the proposed PLSTM AttnNet model achieved a classification accuracy of 97.3%. Compared with the single ResNet model and ResNet PLSTM model, the accuracy was improved by 10.1% and 3.9% respectively, and it was significantly better than the comparative model in evaluation indicators such as F1 score. The results indicate that the innovative fusion of ResNet and PLSTM Attention effectively enhances the collaborative representation ability of EEG signal temporal spatial features, solves the problem of one-sided feature capture in traditional models, and provides a reliable solution for efficient automatic recognition of depression, which has important clinical application value. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
