{"title":"Short-time Heart Rate Estimation Based on 60-GHz FMCW Radar","authors":"Zhenhao Yang, Zengdi Bao","doi":"10.1109/IWS58240.2023.10222194","DOIUrl":null,"url":null,"abstract":"A short-time non-contact heart rate estimation method based on a commercial 60GHz frequency-modulated continuous-wave (FMCW) millimeter-wave radar is proposed in this work. The proposed approach involves the use of the average elimination method to suppress background noise and the median filtering to eliminate impulse noise interference. More importantly, the improved complete ensemble empirical mode decomposition with adaptive noise analysis (ICEEMDAN) and the fast independent component analysis (Fast-ICA) are jointly used to suppress respiratory harmonics so that the signal-to-noise ratio of heartbeat signal is increased; meanwhile, the estimation is also speeded up since the numbers of pseudo modes and iterations are reduced. Experiments show that the proposed method can achieve fast heart rate estimation with mean absolute errors less than 4 beats per minute (BPM) over short durations of 5-second.","PeriodicalId":219295,"journal":{"name":"2023 IEEE MTT-S International Wireless Symposium (IWS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE MTT-S International Wireless Symposium (IWS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWS58240.2023.10222194","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
A short-time non-contact heart rate estimation method based on a commercial 60GHz frequency-modulated continuous-wave (FMCW) millimeter-wave radar is proposed in this work. The proposed approach involves the use of the average elimination method to suppress background noise and the median filtering to eliminate impulse noise interference. More importantly, the improved complete ensemble empirical mode decomposition with adaptive noise analysis (ICEEMDAN) and the fast independent component analysis (Fast-ICA) are jointly used to suppress respiratory harmonics so that the signal-to-noise ratio of heartbeat signal is increased; meanwhile, the estimation is also speeded up since the numbers of pseudo modes and iterations are reduced. Experiments show that the proposed method can achieve fast heart rate estimation with mean absolute errors less than 4 beats per minute (BPM) over short durations of 5-second.