摘要
现有睡眠分期方法存在特征提取不充分、类别间存在数据不平衡等问题,导致睡眠分期的精度不高。基于残差收缩网络设计高效的特征提取网络,同时,在损失函数中基于重加权思想设计了类别加权损失函数,通过调整损失函数有效解决了数据不平衡对分类精度的影响。实验结果表明,改进算法在Sleep-EDF数据集中的Fpz-Cz、Pz-Oz通道上,准确率分别为85.4%和82.2%,MF_(1)分别为79.6%和75.4%,均高于基准算法和目前先进的对比算法,证明了算法的有效性和先进性。
For the exiting staging methods,the accuracy is limited by insufficient feature extraction and class imbalance.To solve the problem,the residual shrinkage network is applied to design a convolutional neural network to extract feature efficiently.Meanwhile,the idea of re-weighting is used to design the loss function to address the problem that N1 stage gets low accuracy due to less samples.Finally,experiments are designed based on data of the Fpz-Cz and Pz-Oz channel in the Sleep-EDF dataset.The accuracy rates are 85.4%and 82.2%,respectively.The MF;values are 79.6%and 75.4%,respectively.Results show that the method achieves higher accuracy and MF_(1)than the benchmark algorithm and current advanced comparison algorithms.It proves the effectiveness and advancement of the proposed algorithm.
作者
陈玲玲
毕晓君
Chen Lingling;Bi Xiaojun(College of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China;School of Information Engineering,Minzu University of China,Beijing 100081,China)
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2022年第2期148-155,共8页
Chinese Journal of Scientific Instrument
基金
国家社科基金重大项目(20&ZD279)资助
关键词
睡眠分期
残差收缩网络
类别加权损失函数
脑电信号
重加权思想
sleep stage
residual shrinkage network
class weighted loss function
electroencephalogram
re-weighting