Real-Time Anomaly Detection over ECG Data Stream Based on Component Spectrum

摘要：

　　Anomaly detection is a popular research in the age of Big Data.As a typical application scenario,anomaly detection over ECG data stream is confronted with particular difficulties including high realtime requirement and poor data quality.In this article,a novel method based on component spectrum is presented to provide a practicable solution for the problem.Experiments on real data show that the proposed method achieves high sensitivity,high specificity and low false alarm rate.

关键词： Anomaly detection Component spectrum ECG data stream

作者: Meng Wu Zhen Qiu Shenda Hong Hongyan Li

作者单位: Key Laboratory of Machine Perception,Peking University,Ministry of Education,Beijing 100871,China;School of Electronics Engineering and Computer Science,Peking University,Beijing 100871,China

会议类型: 国际会议

会议名称: International Asia-Pacific Web Conference(第18届国际亚太互联网大会)

会议地点: 苏州

会议语种:英文

页码: 56-67

在线出版日期: 2016-09-23（万方平台首次上网日期，不代表论文的发表时间）