Proceedings of the 2020 2nd Asia Pacific Information Technology Conference 2020
DOI: 10.1145/3379310.3379318
|View full text |Cite
|
Sign up to set email alerts
|

Multiscale Entropy for Physical Activity Recognition

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
2

Relationship

1
4

Authors

Journals

citations
Cited by 5 publications
(5 citation statements)
references
References 16 publications
0
5
0
Order By: Relevance
“…Entropy-based analysis has been widely applied to different fields, like medicine and biology because of its suitability in analyzing nonlinear data [ 7 , 8 , 10 , 11 , 12 ]. Multiscale entropy (MSE) was introduced to quantify the complexity of limited length time-series data [ 22 ].…”
Section: Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…Entropy-based analysis has been widely applied to different fields, like medicine and biology because of its suitability in analyzing nonlinear data [ 7 , 8 , 10 , 11 , 12 ]. Multiscale entropy (MSE) was introduced to quantify the complexity of limited length time-series data [ 22 ].…”
Section: Methodsmentioning
confidence: 99%
“…Past studies used various approaches to measure human postural stability evaluation, such as the center of pressure (COP) [ 5 , 6 , 7 , 8 , 9 ], entropy-based methods [ 7 , 8 , 10 , 11 , 12 ], and the Star Excursion Balance Test [ 13 ]. The COP measurement using a force platform is the most commonly used method to evaluate postural stability.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Secondly, the sliding window technique segments continuous data into several fragments. The window size and overlap percentage in the sliding window technique are important parameters, which may affect the feature extraction from sequences of data and the performance of classifiers [27][28][29][30]. However, there is no precise guideline for selecting the optimal window size.…”
Section: Gesture Recognitionmentioning
confidence: 99%
“…Based on Shannon's entropy, a number of entropy variants such as discrete entropy [29], spectral entropy [30] and sample entropy [31] have been proposed. Nurwulan et al compare features extracted by multi-scale entropy (MSE) and traditional features from 3-axis acceleration data, showing that the MSE performed better compared to the traditional features on the k-nearest neighbors (KNN) and random forest (RF) classification [32]. Bao et al extract frequency-domain entropy features from original acceleration data, which are used as the inputs with mean, energy, and correlation of the original data to build the model, and obtained ideal results [33].…”
Section: R Wmentioning
confidence: 99%