传感技术学报2017,Vol.30Issue(7):1050-1056,7.DOI:10.3969/j.issn.1004-1699.2017.07.014
基于时空稀疏模型的穿戴式心电信号压缩感知方法
Compressive Sensing Method of Wearable ElectrocardiosignalBased on Spatio-Temporal Sparse Model
摘要
Abstract
A spatio-temporal sparse model-based method is proposed for the compressive sensing of electrocardiosignal.The electrocardiosignal is reconstruted by exploiting the temporal and spatial correlation of signal.In addition,a"split-merge"dictionary learning approach is developed.It determines a dictionary by using its inherent clustered structure,and the electrocardiosignal is sparse represented on this dictionary.Thus,the reconstruction performance of electrocardiosignal is further improved.The proposed compressive sensing method of electrocardiosignal is compared with other two benchmarking methods to illustrate its effectiveness.The simulation results show the proposed method can improve the quality of electrocardiosignal reconstruction.关键词
心电信号/压缩感知/时空稀疏/"分-合"式字典学习Key words
electrocardiosignal/compressive sensing/spatio-temporal sparse/"split-merge"dictionary learning分类
信息技术与安全科学引用本文复制引用
华晶,张华,刘继忠,徐亦璐..基于时空稀疏模型的穿戴式心电信号压缩感知方法[J].传感技术学报,2017,30(7):1050-1056,7.基金项目
江西省教育厅科技项目(GJJ150424) (GJJ150424)
江西省高校科技落地计划项目(KJLD13002) (KJLD13002)
国家自然科学基金项目(61363041) (61363041)