Citation

Abbasi AQ, Abbasi MM, Nahml W. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2022; 2022: 3640-3644.

Copyright

(Copyright © 2022, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/EMBC48229.2022.9871100

PMID

36086565

Abstract

Human gait is a complex system affected by many other processes of human physiology. It has multiple inputs and multiple outputs. Due to its complex nature, signals obtained from this system also exhibit complexity and variability. It has been analyzed in many ways to extract the information inhabited by these signals. Entropy based methods showed a significant impact on analysis of gait signals. Threshold based symbolic entropy analysis is one of the entropy based method applied to human gait signals. In this method Normalized Corrected Shannon Entropy (NCSE) is calculated to compare the spontaneous output of the human locomotors system during different walking conditions. Selection of the threshold values is an important task and sometimes it depends upon the type and size of the data.

RESULTS are dependent on the proper selection of the threshold. In this paper, different threshold selection methods are discussed and their impact on the results are presented. It was observed that, variation in stride interval has performed better as a threshold value as compare to the other methods. It provided maximum separation among different groups of gait data used in this study. We concluded with the recommendations for the proper selection of the threshold values to apply symbolic entropy methods on human gait signals. Clinical relevance Various gait related problems are common in older adults that increase with age and are associated with reduced gait speed increased fall risk and other impairments. Consequently objective gait assessment in the clinics depending upon the size of the available data has become increasingly important for the classification of gait. It was found that while applying symbolic entropy method proper selection of threshold result into improved classification of different types of gait data which will help the clinician for better decision-making regarding treatment.

Language: en