arbiter
JournalsAccount

Machine learning-based approach to identify human push recovery using GAIT analysis

S. Niranjani et al.

International Journal of Enterprise Network Management2025https://doi.org/10.1504/ijenm.2025.146312article
AJG 1ABDC B
Weight
0.50

Abstract

The authors have performed empirical mode decomposition for a process to arrive at the human push recovery data using features that are obtained from intrinsic mode functions (IMFs). For the above purpose data related to leg joint angles (hip, knee and ankle) are collected. Three kinds of pushes were applied to analyse the recovery mechanism, in the field of robotics. The classification was performed using deep neural network (DNN) and other classification methods like KNN, naive Bayes, decision tree, random forest and support vector machine. The results have been compared to find the best method for further analysis. Use of five different classification technique and extraction of two additional features which improved the accuracy of the system are some of the unique features of this article.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.1504/ijenm.2025.146312

Or copy a formatted citation

@article{s.2025,
  title        = {{Machine learning-based approach to identify human push recovery using GAIT analysis}},
  author       = {S. Niranjani et al.},
  journal      = {International Journal of Enterprise Network Management},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1504/ijenm.2025.146312},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Machine learning-based approach to identify human push recovery using GAIT analysis

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.