Combining algorithms in automatic detection of R-peaks in ECG signals
ABSTRACT R-peak detection is the crucial first step in every automatic ECG analysis. Much work has been carried out in this field, using various methods ranging from filtering and threshold methods, through wavelet methods, to neural networks, and others. Performance is generally good, but each method has situations where it fails. In this paper we suggest an approach to automatically combine different algorithms, here the Pan Tompkins and wavelet algorithms, for detection of R-peaks in ECG signals, in order to benefit from the strengths of both algorithms. Experimental results and analysis are provided on the MIT-BIH Arrhythmia Database. We obtained substantial improvements on the test data with respect to the best individual algorithm.
- SourceAvailable from: mirlabs.info
Conference Paper: Low Cost, Low Power QRS Detection Module Using PIC[Show abstract] [Hide abstract]
ABSTRACT: This paper presents an efficient, low cost, low power QRS complexes detection module for ECG analysis. In past lot of research on algorithms for QRS detection has been carried out. All such methods mostly rely on a priori knowledge of the shape of the QRS complexes and general aspects of the ECG. Most of approaches require more CPU time and involve complex mathematics which is difficult to implement for low cost, low power pacemaker design. Moreover, baseline shift, power line interference, muscle noise and other artifacts poses further bottleneck for accurate QRS detection. Detailed analysis of various approaches and their constraints for real time pacemaker application has been done in this paper. A simple, cost competitive smart design has also been proposed. Our solution has very low power requirement and achieves high QRS detection performance without compromising timing accuracy and reliability. To achieve improved QRS detection reliability, various noise components have been attenuated by clever implementation of optimized prefiltering in conjunction with a A/D conversion and Zero-crossing detection. Complete system proposed in this paper has been designed around a PIC microcontroller, Data Acquisition module and a display unit. Proposed design has been tested for extensive data collected from hospitals. Result achieved confirms the design approach illustrated.Communication Systems and Network Technologies (CSNT), 2011 International Conference on; 07/2011
- [Show abstract] [Hide abstract]
ABSTRACT: A computational cardiology based approach to find the number of ECG-waves responsible for generation and presentation of an ECG episode is proposed. The methodology adopted here is based on the comparison and study of diagnostic efficiency calculated from 12 lead ECG data. The diagnostic-efficiency is measured by using NN classifier whereas clustered points of most likely ECG-episode constitute the diagnostic feature. The result is also cross-validated using episodes transformed by existing signal transform technique, “Discrete Fourier Transform” and another transformation. “Velocity-Wave number Transform.” The result indicates the possible number of episode-clusters giving maximum diagnostic efficiency and also gives a new insight on ECG waves.Pattern Recognition and Image Analysis 01/2009; 19(1):30-34.
Article: Mining of an electrocardiogram[Show abstract] [Hide abstract]
ABSTRACT: Widespread use of medical information systems and explosive growth of medical databases re-quire methods for efficient computer assisted analysis. In the paper we focus on the QRS complex detection in electrocardiogram but, the idea of further recognition of anomalies in QRS complexes based on the im-munology approach is described, as well. In order to detect QRS complexes the neural network ensemble is proposed. It consists of three neural networks. The details referring to this solution are described. The results of the experimental study are also shown.