FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4368358709> ?p ?o ?g. }

• W4368358709 endingPage "285" @default.
• W4368358709 startingPage "280" @default.
• W4368358709 abstract "The method of using deep learning technology to realize automatic sleep staging needs a lot of data support, and its computational complexity is also high. In this paper, an automatic sleep staging method based on power spectral density (PSD) and random forest is proposed. Firstly, the PSDs of six characteristic waves (K complex wave, δ wave, θ wave, α wave, spindle wave, β wave) in electroencephalogram (EEG) signals were extracted as the classification features, and then five sleep states (W, N1, N2, N3, REM) were automatically classified by random forest classifier. The whole night sleep EEG data of healthy subjects in the Sleep-EDF database were used as experimental data. The effects of using different EEG signals (Fpz-Cz single channel, Pz-Oz single channel, Fpz-Cz + Pz-Oz dual channel), different classifiers (random forest, adaptive boost, gradient boost, Gaussian naïve Bayes, decision tree, K-nearest neighbor), and different training and test set divisions (2-fold cross-validation, 5-fold cross-validation, 10-fold cross-validation, single subject) on the classification effect were compared. The experimental results showed that the effect was the best when the input was Pz-Oz single-channel EEG signal and the random forest classifier was used, no matter how the training set and test set were transformed, the classification accuracy was above 90.79%. The overall classification accuracy, macro average F1 value, and Kappa coefficient could reach 91.94%, 73.2% and 0.845 respectively at the highest, which proved that this method was effective and not susceptible to data volume, and had good stability. Compared with the existing research, our method is more accurate and simpler, and is suitable for automation.采用深度学习技术实现睡眠自动分期计算复杂度较高，且需大量数据支撑。本文提出一种基于功率谱密度和随机森林的自动睡眠分期方法，先提取脑电信号6种特征波（K复合波、δ波、θ波、α波、纺锤波、β波）的功率谱密度作为特征，然后利用随机森林分类器实现5种睡眠状态（W、N1、N2、N3、REM）自动分类。采用Sleep-EDF数据库中健康受试者整晚睡眠脑电数据作为实验数据，对比了使用不同输入通道脑电信号（Fpz-Cz单通道、Pz-Oz单通道、Fpz-Cz + Pz-Oz双通道）、不同分类器（随机森林、自适应增强、梯度提升、高斯朴素贝叶斯、决策树、K近邻）、不同训练集与测试集划分方法（2折、5折、10折交叉验证及单个受试者）对分类效果的影响。实验结果表明，当采用Pz-Oz单通道脑电信号和随机森林分类器时效果最好，无论怎样变换训练集与测试集，分类准确率都达到90.79%以上，总体分类准确率、宏观平均F1值、Kappa系数最高分别可达到91.94%、73.2%、0.845，证明该方法是有效的，且不易受数据量影响，具有较好的稳定性。与已有研究相比，该方法分类准确率更高、实现更简单，适用于自动化。." @default.
• W4368358709 created "2023-05-05" @default.
• W4368358709 creator A5019258983 @default.
• W4368358709 creator A5064930617 @default.
• W4368358709 date "2023-04-25" @default.
• W4368358709 modified "2023-09-29" @default.
• W4368358709 title "[Automatic sleep staging based on power spectral density and random forest]." @default.
• W4368358709 cites W1545241942 @default.
• W4368358709 cites W1577987636 @default.
• W4368358709 cites W2144691514 @default.
• W4368358709 cites W2162800060 @default.
• W4368358709 cites W2396351021 @default.
• W4368358709 cites W2604096629 @default.
• W4368358709 cites W2805033630 @default.
• W4368358709 cites W2920016582 @default.
• W4368358709 cites W3143029809 @default.
• W4368358709 doi "https://doi.org/10.7507/1001-5515.202207047" @default.
• W4368358709 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37139759" @default.
• W4368358709 hasPublicationYear "2023" @default.
• W4368358709 type Work @default.
• W4368358709 citedByCount "1" @default.
• W4368358709 countsByYear W43683587092023 @default.
• W4368358709 crossrefType "journal-article" @default.
• W4368358709 hasAuthorship W4368358709A5019258983 @default.
• W4368358709 hasAuthorship W4368358709A5064930617 @default.
• W4368358709 hasConcept C105795698 @default.
• W4368358709 hasConcept C118552586 @default.
• W4368358709 hasConcept C12267149 @default.
• W4368358709 hasConcept C153180895 @default.
• W4368358709 hasConcept C154945302 @default.
• W4368358709 hasConcept C15744967 @default.
• W4368358709 hasConcept C168110828 @default.
• W4368358709 hasConcept C169258074 @default.
• W4368358709 hasConcept C169903167 @default.
• W4368358709 hasConcept C27181475 @default.
• W4368358709 hasConcept C28490314 @default.
• W4368358709 hasConcept C33923547 @default.
• W4368358709 hasConcept C41008148 @default.
• W4368358709 hasConcept C52001869 @default.
• W4368358709 hasConcept C522805319 @default.
• W4368358709 hasConcept C84525736 @default.
• W4368358709 hasConcept C95623464 @default.
• W4368358709 hasConceptScore W4368358709C105795698 @default.
• W4368358709 hasConceptScore W4368358709C118552586 @default.
• W4368358709 hasConceptScore W4368358709C12267149 @default.
• W4368358709 hasConceptScore W4368358709C153180895 @default.
• W4368358709 hasConceptScore W4368358709C154945302 @default.
• W4368358709 hasConceptScore W4368358709C15744967 @default.
• W4368358709 hasConceptScore W4368358709C168110828 @default.
• W4368358709 hasConceptScore W4368358709C169258074 @default.
• W4368358709 hasConceptScore W4368358709C169903167 @default.
• W4368358709 hasConceptScore W4368358709C27181475 @default.
• W4368358709 hasConceptScore W4368358709C28490314 @default.
• W4368358709 hasConceptScore W4368358709C33923547 @default.
• W4368358709 hasConceptScore W4368358709C41008148 @default.
• W4368358709 hasConceptScore W4368358709C52001869 @default.
• W4368358709 hasConceptScore W4368358709C522805319 @default.
• W4368358709 hasConceptScore W4368358709C84525736 @default.
• W4368358709 hasConceptScore W4368358709C95623464 @default.
• W4368358709 hasIssue "2" @default.
• W4368358709 hasLocation W43683587091 @default.
• W4368358709 hasOpenAccess W4368358709 @default.
• W4368358709 hasPrimaryLocation W43683587091 @default.
• W4368358709 hasRelatedWork W2275058042 @default.
• W4368358709 hasRelatedWork W2508925980 @default.
• W4368358709 hasRelatedWork W2964383635 @default.
• W4368358709 hasRelatedWork W3093525770 @default.
• W4368358709 hasRelatedWork W3130989307 @default.
• W4368358709 hasRelatedWork W3133324635 @default.
• W4368358709 hasRelatedWork W3204641204 @default.
• W4368358709 hasRelatedWork W3205756533 @default.
• W4368358709 hasRelatedWork W4280583453 @default.
• W4368358709 hasRelatedWork W4313241900 @default.
• W4368358709 hasVolume "40" @default.
• W4368358709 isParatext "false" @default.
• W4368358709 isRetracted "false" @default.
• W4368358709 workType "article" @default.