QRS detection using adaptive filters: A comparative study. (January 2017)

• Record Type: Journal Article
• Authors: Jain, Shweta; Ahirwal, M.K.; Kumar, Anil; Bajaj, V.; Singh, G.K.
• Is Part Of: ISA transactions. Volume 66(2017:Jan.)
• Page Start: 362
• Page End: 375
• Publication Date: 2017-01
• Subjects: Adaptive filtering -- Adaptive thresholding -- ECG -- Leaky-LMS -- QRS complex detection; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2016.09.023
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Electrocardiogram (ECG) is one of the most important physiological signals of human body, which contains important clinical information about the heart. Monitoring of ECG signal is done through QRS detection. In this paper, an improved QRS detection algorithm, based on adaptive filtering principle, has been designed. Enumeration of the effectiveness of various LMS variants used in adaptive filtering based QRS detection algorithm has been done through fidelity parameters like sensitivity and positive predictivity. Whole family of LMS algorithm has been implemented for comparison. Sign-sign LMS, sign error LMS, basic LMS and normalized LMS are re-implemented, while variable leaky LMS, variable step-size LMS, leaky LMS, recursive least squares (RLS), and fractional LMS are novel combination presented in this paper. After analysis of the obtained results, performance of leaky-LMS algorithm is found to be the best with sensitivity, positive predictivity, and processing time of 99.68%, 99.84%, and 0.45 s respectively. Reported results are tested and evaluated over MIT/BIH arrhythmia database. Presented study also concludes that the performance of most of the variants gets affected due to low SNR but the Leaky LMS performs better even under heavy noise conditions. Highlights: This paper presents an improved QRS detection algorithm which is based on adaptive filtering principle. In comparative study, Variable-Leaky LMS, Variable Step-size LMS, Leaky-LMS, RLS and Fractional-LMS are novel combinations. The leaky-LMS algorithm gives the best performance with sensitivity of 99.68% and positive predictivity of 99.84%. According to study, performance of other LMS-variants gets affected due to low SNR, but Leaky-LMS still gives better results.