纺织工程学报2025，Vol.3Issue(6)：1-18,18.
基于多特征融合的PSO-SVM优化算法睡眠脑电方法
PSO-SVM optimization algorithm sleep EEG method based on multi feature fusion
摘要
Abstract
In response to the issues of single feature dimension and low efficiency in hyperparameter optimiza-tion in existing sleep staging methods,a multi-feature analysis approach that integrates time-frequency domain features with nonlinear dynamic parameters is proposed.The Support Vector Machine(SVM)classification model is improved by combining the Particle Swarm Optimization(PSO)algorithm to achieve the staging of sleep EEG signals.Through wavelet threshold denoising and Principal Component Analysis(PCA)for dimen-sionality reduction,the feature dimension is reduced from 15 to 6(with a cumulative contribution rate of 92.3%).A feature set including time-domain statistics,frequency band energy ratios,and nonlinear parameters is constructed.The kernel parameters and penalty factors of the SVM are optimized using PSO to enhance clas-sification performance.In the 5-fold cross-validation on the Sleep-EDF public dataset(10 subjects,4526 seg-ments),an overall accuracy of over 90%is achieved,which is an 8.2 percentage point improvement compared to the traditional grid search method.The experimental results demonstrate that the proposed method,through feature fusion and parameter optimization,provides a reliable technical solution for the development of clinical sleep monitoring devices.关键词
睡眠脑电信号/支持向量机/多特征融合/主成分分析/粒子群优化/睡眠分类Key words
sleep EEG signals/Support Vector Machines/multi-feature fusion/principal component analysis/Particle swarm optimization/sleep classification分类
轻工纺织引用本文复制引用
ZHANG Yaqian,LIU Hao..基于多特征融合的PSO-SVM优化算法睡眠脑电方法[J].纺织工程学报,2025,3(6):1-18,18.基金项目
国家重点研发计划"科技冬奥"重点专项(2019YFF0302105) （2019YFF0302105）
天津市自然科学基金资助项目(18JCYBJC18500) （18JCYBJC18500）
国家自然科学基金资助项目(52203276,82272204). （52203276,82272204）
