K-NN based interpolation to handle artifacts for heart rate variability analysis

Authors:
S. Begum;M. S. Islam;M. U. Ahmed;P. Funk
Affiliations:
School of innovation, design and engineering, Mälardalen University, SE-72123 Västerås, Sweden;School of innovation, design and engineering, Mälardalen University, SE-72123 Västerås, Sweden;School of innovation, design and engineering, Mälardalen University, SE-72123 Västerås, Sweden;School of innovation, design and engineering, Mälardalen University, SE-72123 Västerås, Sweden
Venue:
ISSPIT '11 Proceedings of the 2011 IEEE International Symposium on Signal Processing and Information Technology
Year:
2011

Citing 0
Cited 1

Classification of physiological signals for wheel loader operators using Multi-scale Entropy analysis and case-based reasoning

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Heart rate variability (HRV) is a popular parameter for depicting activities of autonomous nervous system and helps to explain various physiological activities of the body. A small amount of artifacts can produce significant changes especially, for time domain HRV features. Manual correction of artifacts performed by visual inspection of the signal by experts is tedious and time consuming and often leads to incorrect result especially for long term recordings. Therefore, an automatic artifact removing approach that helps to provide clinically useful HRV analysis is valuable. This paper proposes an algorithm that detects and replaces artifacts from inter-beat interval (IBI) signal for HRV analysis. The detection is mainly based on windowing technique and interpolation is performed using the k-nearest neighbour (K-NN) algorithm. The experimental work shows a promising performance in handling artifacts for HRV analysis using electrocardiogram (ECG) sensor signal.