面向焦虑改善的睡眠脑电信号深度学习分析模型研究

黄辰; 马耀龙; 张龑; 王时绘; 杨超; 宋建华; 陈侃松; 杨伟平

doi:10.11999/JEIT241123

面向焦虑改善的睡眠脑电信号深度学习分析模型研究

doi: 10.11999/JEIT241123 cstr: 32379.14.JEIT241123

黄辰^{1, 2, 3, 4},
马耀龙^{1, 2, 3, 4},
张龑^{1, 2, 3, 4, ,},
王时绘^{1, 2, 3, 4},
杨超^{1, 2, 3, 4},
宋建华^{2, 3, 4, 5},
陈侃松^{1, 2, 3, 4},
杨伟平⁶

1.
湖北大学计算机与信息工程学院武汉 430062
2.
智能感知系统与安全教育部重点实验室武汉 430062
3.
大数据智能分析与行业应用湖北省重点实验室武汉 430062
4.
湖北省高校人文社科重点研究基地-绩效评价信息管理研究中心武汉 430062
5.
湖北大学网络空间安全学院武汉 430062
6.
湖北大学教育学院武汉 430062

基金项目: 武汉市知识创新专项项目(202311901251001)，湖北省科技计划重大科技专项(2024BAA008)，湖北省重大攻关项目(2023BAA018)，深圳市科技攻关重点项目(2020N061)

详细信息

作者简介:
黄辰：男，教授，研究方向为计算机科学

马耀龙：男，硕士生，研究方向为计算机科学

张龑：男，教授，研究方向为计算机科学

王时绘：男，教授，研究方向为计算机科学

杨超：男，教授，研究方向为计算机科学

宋建华：女，教授，研究方向为软件工程

陈侃松：男，教授，研究方向为软件工程

杨伟平：女，教授，研究方向为脑与认知

通讯作者:
张龑　zhangyan@hubu.edu.cn

中图分类号: TN911.7; TP391
计量
- 文章访问数: 131
- HTML全文浏览量: 86
- PDF下载量: 26
- 被引次数: 0
出版历程
- 收稿日期: 2024-12-23
- 修回日期: 2025-07-02
- 网络出版日期: 2025-07-25
- 刊出日期: 2025-08-27

Research on Deep Learning Analysis Model of Sleep ElectroEncephalography Signals for Anxiety Improvement

HUANG Chen^{1, 2, 3, 4},
MA Yaolong^{1, 2, 3, 4},
ZHANG Yan^{1, 2, 3, 4
, ,},
WANG Shihui^{1, 2, 3, 4},
YANG Chao^{1, 2, 3, 4},
SONG Jianhua^{2, 3, 4, 5},
CHEN Kansong^{1, 2, 3, 4},
YANG Weiping⁶

1.
School of Computer Science and Information Engineering, Hubei University, Wuhan 430062, China
2.
Key Laboratory of Intelligent Sensing System and Security, Ministry of Education, Wuhan 430062, China
3.
Hubei Key Laboratory of Big Data Intelligent Analysis and Application, Wuhan 430062, China
4.
Hubei Province Project of Key Research Institute of Humanities and Social Sciences at Universities, Wuhan 430062, China
5.
School of Cyber Science and Technology, Hubei University, Wuhan 430062, China
6.
Faculty of Education, Hubei University, Wuhan 430062, China

Funds: Wuhan Knowledge Innovation Special Project(202311901251001), Hubei Province Science and Technology Plan Major Science and Technology Project (2024BAA008), The Major Research Projects in Hubei Province(2023BAA018), The Key Projects of Science and Technology in Shenzhen (2020N061)

摘要

摘要: 焦虑是一种常见的情绪障碍，其严重时会显著影响个体的身心健康。已有研究表明，睡眠与焦虑存在双向调控关系，高质量睡眠有助于缓解焦虑情绪。为提高在睡眠环境下对焦虑患者脑电信号的分析准确率，该文提出一种改进型特征金字塔网络(IFPN)模型。在IFPN模型中，首先，对焦虑患者睡眠前后脑电信号进行预处理，采用脑电信号标准化和特征金字塔网络去噪，以统一脑电信号尺度并去除噪声。然后，将预处理后焦虑患者的睡眠脑电数据转换为脑熵地形图，以强化在睡眠环境下对焦虑改善的脑电信号分析能力，接着，利用改进型特征金字塔网络对脑熵地形图进行特征提取，生成特征脑地形图。最后，将特征脑地形图输入到ResNet-50进行脑电信号分析。本文在开源数据集上验证了IFPN模型的有效性。实验结果表明，在睡眠环境下，采用所提模型能够进一步提升针对焦虑脑电信号的分析能力和准确率，从而为分析睡眠对于焦虑的改善作用提供深入的理论和实验支撑。
- 睡眠 /
- 焦虑 /
- 脑电图 /
- 改进型特征金字塔网络 /
- 奇异谱熵
Abstract: Objective Anxiety is a common emotional disorder, characterized by excessive worry and fear, which negatively affects mental, physical, and social well-being. A bidirectional relationship exists between anxiety and sleep, poor sleep quality worsens anxiety symptoms, and anxiety disrupts normal sleep patterns. ElectroEncephaloGraphy (EEG) signals provide a non-invasive and informative means to investigate brain activity, making them useful for studying the neurophysiological underlying this association. However, conventional EEG analysis methods often fail to capture the complex, multiscale features needed to assess anxiety modulation during sleep. This study proposes an Improved Feature Pyramid Network (IFPN) model to enhance EEG analysis in sleep settings, with the aim of improving the detection and interpretation of anxiety-related brain activity. Methods The IFPN model comprises a preprocessing module, feature extraction module, and classification module, each being optimized for analyzing EEG signals related to anxiety during sleep. The preprocessing module applies Z-score normalization to EEG signals from individuals with anxiety to standardize signal amplitude across channels. Noise artifacts are reduced using a denoising process based on a feature pyramid network. Preprocessed signals are then converted into brain entropy topographies using Singular Spectral Entropy (SSE), which quantifies signal complexity. These entropy maps are processed by the IFPN backbone, which incorporates convolutional layers, SSE-guided upsampling, and lateral connections to enable multiscale feature fusion. The resulting features are input to a modified ResNet-50 network for classification, with SSE-based regularization applied to enhance model robustness and accuracy. The model is evaluated using two independent EEG datasets: a sleep deprivation dataset and a cognitive-state EEG dataset, both comprising participants with levels of anxiety. Results and Discussions The experimental results demonstrate that the IFPN model improves the detection of anxiety-related features in EEG signals during sleep. Spectral power analysis shows a significant reduction in β-band power after sleep, reflecting decreased hyperarousal commonly associated with anxiety. In Dataset 1, β-band power declines from 16% to 13% (p < 0.01), and in Dataset 2, from 19.5% to 15% (p < 0.05). This is accompanied by an increase in the θ/β power ratio, suggesting a shift toward a more relaxed neural state post-sleep. The IFPN model achieves 85% accuracy in identifying severe anxiety, outperforming baseline methods, which reach 78%. This improvement results from the model’s capacity to integrate multiscale features and selectively emphasize anxiety-related patterns, supporting more accurate classification of elevated anxiety states. Conclusions This study proposes an IFPN model for EEG analysis during sleep, with a focus on detecting anxiety-related neural activity. Unlike traditional approaches that rely on shallow architectures or frequency- limited metrics, the IFPN model addresses the multiscale and spatially heterogeneous nature of brain activity associated with anxiety. By incorporating SSE as a nonlinear dynamic feature, the model captures subtle regional and frequency-specific variations in EEG complexity. SSE functions as both a signal complexity metric and a functional biomarker of neural disorganization linked to anxiety. Integrated with the multiscale fusion capability of the feature pyramid network, SSE enhances the model’s ability to extract salient spatiotemporal features relevant to anxiety states. Experimental results show that the IFPN model outperforms existing methods in both accuracy and robustness, particularly in identifying severe anxiety, where conventional models often struggle due to noise and reduced discriminative performance. These findings highlight the model’s potential utility in clinical assessment of anxiety during sleep.
- Sleep /
- Anxiety /
- ElectroEncephaloGraphy (EEG) /
- Improve Feature Pyramid Network (IFPN) /
- Singular Spectral Entropy(SSE)

HTML全文

图 1 改进型特征金字塔网络模型图

下载: 全尺寸图片幻灯片

图 2 特征提取模块步骤图

下载: 全尺寸图片幻灯片

图 3 分类预测模块流程图

下载: 全尺寸图片幻灯片

图 4 睡眠前后脑电功率变化

下载: 全尺寸图片幻灯片

图 5 STFN-BRPS模型准确率

下载: 全尺寸图片幻灯片

图 6 IFPN模型准确率

下载: 全尺寸图片幻灯片

参考文献(22)

[1]	VAZARD J. Feeling the unknown: Emotions of uncertainty and their valence[J]. Erkenntnis, 2024, 89(4): 1275–1294. doi: 10.1007/s10670-022-00583-1.
[2]	LABRAGUE L J. Pandemic fatigue and clinical nurses’ mental health, sleep quality and job contentment during the COVID‐19 pandemic: The mediating role of resilience[J]. Journal of Nursing Management, 2021, 29(7): 1992–2001. doi: 10.1111/jonm.13383.
[3]	ASTUTI R D, SUHARDI B, LAKSONO P W, et al. Investigating the relationship between noise exposure and human cognitive performance: attention, stress, and mental workload based on EEG signals using power spectrum density[J]. Applied Sciences, 2024, 14(7): 2699. doi: 10.3390/app14072699.
[4]	ZHANG Bingtao, WANG Chonghui, YAN Guanghui, et al. Functional brain network based on improved ensemble empirical mode decomposition of EEG for anxiety analysis and detection[J]. Biomedical Signal Processing and Control, 2024, 91: 106030. doi: 10.1016/j.bspc.2024.106030.
[5]	RAJWAL S and AGGARWAL S. Convolutional neural network-based EEG signal analysis: A systematic review[J]. Archives of Computational Methods in Engineering, 2023, 30(6): 3585–3615. doi: 10.1007/s11831-023-09920-1.
[6]	LI Kuan, AO Bin, WU Xin, et al. Parkinson’s disease detection and classification using EEG based on deep CNN-LSTM model[J]. Biotechnology and Genetic Engineering Reviews, 2024, 40(3): 2577–2596. doi: 10.1080/02648725.2023.2200333.
[7]	MAHMOUD A, AMIN K, AL RAHHAL M M, et al. A CNN approach for emotion recognition via EEG[J]. Symmetry, 2023, 15(10): 1822. doi: 10.3390/sym15101822.
[8]	PALANISAMY K K and RENGARAJ A. Detection of anxiety-based epileptic seizures in EEG signals using fuzzy features and parrot optimization-tuned LSTM[J]. Brain Sciences, 2024, 14(8): 848. doi: 10.3390/brainsci14080848.
[9]	PONOMAREVA N, HAZIMEH H, KURAKIN A, et al. How to DP-fy ML: A practical guide to machine learning with differential privacy[J]. Journal of Artificial Intelligence Research, 2023, 77: 1113–1201. doi: 10.1613/jair.1.14649.
[10]	NIU Zhaoyang, ZHONG Guoqiang, and YU Hui. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48–62. doi: 10.1016/j.neucom.2021.03.091.
[11]	CHEN Guijun, LIU Yue, and ZHANG Xueying. EEG–fNIRS-based emotion recognition using graph convolution and capsule attention network[J]. Brain Sciences, 2024, 14(8): 820. doi: 10.3390/brainsci14080820.
[12]	GAO Zhongke, LI Yanli, YANG Yuxuan, et al. A GPSO-optimized convolutional neural networks for EEG-based emotion recognition[J]. Neurocomputing, 2020, 380: 225–235. doi: 10.1016/j.neucom.2019.10.096.
[13]	LI Xiang, ZHANG Yazhou, TIWARI P, et al. EEG based emotion recognition: A tutorial and review[J]. ACM Computing Surveys, 2023, 55(4): 79. doi: 10.1145/3524499.
[14]	SUN Haitao, YANG Shuai, CHEN Lijuan, et al. Brain tumor image segmentation based on improved FPN[J]. BMC Medical Imaging, 2023, 23(1): 172. doi: 10.1186/s12880-023-01131-1.
[15]	YU Muyao, DONG Shengbo, DUAN Xiangyu, et al. A novel interference suppression method for interrupted sampling repeater jamming based on singular spectrum entropy function[J]. Sensors, 2019, 19(1): 136. doi: 10.3390/s19010136.
[16]	周涛, 刘赟璨, 陆惠玲, 等. ResNet及其在医学图像处理领域的应用: 研究进展与挑战[J]. 电子与信息学报, 2022, 44(1): 149–167. doi: 10.11999/JEIT210914. ZHOU Tao, LIU Yuncan, LU Huiling, et al. ResNet and its application to medical image processing: Research progress and challenges[J]. Journal of Electronics & Information Technology, 2022, 44(1): 149–167. doi: 10.11999/JEIT210914.
[17]	DONG Li, ZHAO Lingling, ZHANG Yufan, et al. Reference electrode standardization interpolation technique (RESIT): A novel interpolation method for scalp EEG[J]. Brain Topography, 2021, 34(4): 403–414. doi: 10.1007/s10548-021-00844-2.
[18]	KOU Yiwen, CHEN Zixiang, and GU Quanquan. Implicit bias of gradient descent for two-layer reLU and leaky reLU networks on nearly-orthogonal data[C]. The 37th Annual Conference on Neural Information Processing Systems, New Orleans, USA, 2024: 36.
[19]	GHOJOGH B and CROWLEY M. The theory behind overfitting, cross validation, regularization, bagging, and boosting: Tutorial[EB/OL]. https://arxiv.org/abs/1905.12787, 2019.
[20]	XIANG Chuqin, FAN Xinrui, BAI Duo, et al. A resting-state EEG dataset for sleep deprivation[J]. Scientific Data, 2024, 11(1): 427. doi: 10.1038/s41597-024-03268-2.
[21]	WANG Yulin, DUAN Wei, DONG Debo, et al. A test-retest resting, and cognitive state EEG dataset during multiple subject-driven states[J]. Scientific Data, 2022, 9(1): 566. doi: 10.1038/s41597-022-01607-9.
[22]	HU Fo, ZHANG Lekai, YANG Xusheng, et al. EEG-based driver fatigue detection using spatio-temporal fusion network with brain region partitioning strategy[J]. IEEE Transactions on Intelligent Transportation Systems, 2024, 25(8): 9618–9630. doi: 10.1109/TITS.2023.3348517.