Abstract
Entropy profiling is a recently introduced approach that reduces parametric dependence in traditional Kolmogorov-Sinai (KS) entropy measurement algorithms. The choice of the threshold parameter r of vector distances in traditional entropy computations is crucial in deciding the accuracy of signal irregularity information retrieved by these methods. In addition to making parametric choices completely data-driven, entropy profiling generates a complete profile of entropy information as against a single entropy estimate (seen in traditional algorithms). The benefits of using “profiling” instead of “estimation” are: (a) precursory methods such as approximate and sample entropy that have had the limitation of handling short-term signals (less than 1000 samples) are now made capable of the same; (b) the entropy measure can capture complexity information from short and long-term signals without multi-scaling; and (c) this new approach facilitates enhanced information retrieval from short-term HRV signals. The novel concept of entropy profiling has greatly equipped traditional algorithms to overcome existing limitations and broaden applicability in the field of short-term signal analysis. In this work, we present a review of KS-entropy methods and their limitations in the context of short-term heart rate variability analysis and elucidate the benefits of using entropy profiling as an alternative for the same.
Highlights
Heart rate variability (HRV), a variation in the time interval between successive heart beats, is a prognostic indicator of various physiological conditions, such as disease, stress, aging, fitness and gender [1,2,3]
Having introduced a novel solution to address the same, we find the time and opportunity suitable to present a detailed review on KS-entropy methods, their limitations, research progress and our novel idea of entropy profiling
Extend the method to use on any physiological signal
Summary
Heart rate variability (HRV), a variation in the time interval between successive heart beats, is a prognostic indicator of various physiological conditions, such as disease, stress, aging, fitness and gender [1,2,3]. The physiological process of HRV being highly non-linear in nature cannot be contained fully by linear approaches This necessitates the use of non-linear dynamic methods to carry out HRV analysis. Non-linear KS-entropy algorithms, such as approximate entropy (ApEn) and sample entropy (SampEn), are efficient in dealing with short-term data, but their dependence on input parameters affects the quality of information retrieval to a great extent. Elimination of the parametric dependence of such methods will prove beneficial in the context of information retrieval from short-term heart rate data. This generates a profile of entropy values, in contrast to a single estimate of entropy This certainly means enhanced information retrieval from the signal. How entropy profiling can be done efficiently and how the profiling can be used to improve short-length HRV signal analysis have been the main contributions of our research. The content could be seen as divided into four main branches: (1) an introduction and necessary background information; (2) case studies and results; (3) a detailed discussion of the results and impacts; (4) conclusive comments and future research directions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
