ItemConference Paper

Hybrid Machine Learning Approach for Gait Type Classification Using Pose-Based Feature Extraction

Title
Hybrid Machine Learning Approach for Gait Type Classification Using Pose-Based Feature Extraction
Creator
Srivastava, Pulkit; Singhal, Prateek; Singh, Madan
Description
Gait analysis is essential for the diagnosis of neuromuscular and musculoskeletal disorders. Traditional methods are vulnerable and lead to inconsistency as they rely on subjective assessments. An angle-based approach which uses advanced machine learning techniques have been used address this. Extracted joint angle measurements have been extracted from the video data using computer vision methods. The characteristics used in this research were used to train a hybrid model of a Random Forest classifier and a Fuzzy C-Means clustering algorithm. Random Forest model was used as it is stable and capable of dealing with intricate nonlinear relationships and Fuzzy C-Means was used as it can manage ambiguity in the data as well as overlapping class distributions. The results showed that the Random Forest classifier has a classification accuracy of 94.62%, which is better than the other models in distinguishing between normal and abnormal gait patterns. Fuzzy C-Means also shows high accuracy is capable of clustering various forms of gait and extracting detailed features in gait dynamics. Results suggest that integrating joint angle analysis with machine learning methods provides a credible tool for gait analysis, which can aid clinicians in the early detection and treatment of gait related disorders. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
Source
Lecture Notes in Networks and Systems;Volume;1601 LNNS;pp.522-534
Date
01-01-2026
Publisher
Springer Science and Business Media Deutschland GmbH
Subject
Fuzzy C Means; Gait Analysis; Random Forest; Rehabilitation; Scissor Gait; Support Vector Machine; Waddling Gait
Coverage
Srivastava P., Department of Computer Science, School of Sciences, Christ (Deemed to be University) Delhi-NCR, Uttar Pradesh, Ghaziabad, India; Singhal P., Department of Computer Science, School of Sciences, Christ (Deemed to be University) Delhi-NCR, Uttar Pradesh, Ghaziabad, India; Singh M., Department of Computer Science, School of Sciences, Christ (Deemed to be University) Delhi-NCR, Uttar Pradesh, Ghaziabad, India
Rights
Restricted Access; Hardcopy may be available in the library
Relation
ISSN: 23673370; ISBN: 978-303203526-4;
Format
online
Language
English
Type
Conference paper

Citation

Srivastava, Pulkit; Singhal, Prateek; Singh, Madan, “Hybrid Machine Learning Approach for Gait Type Classification Using Pose-Based Feature Extraction,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/25340.

Output Formats