Posture Classification Using a Hybrid Deep Learning Model

Title

Posture Classification Using a Hybrid Deep Learning Model

Creator

George, Geniets M.; Ummesalma, M.; Parihar, Ruchi Singh

Description

Automated posture detection is a critical task in ergonomics and healthcare, yet it presents significant challenges for standard computer vision models, particularly in handling class imbalance and understanding geometric constraints. This paper proposes an enhanced hybrid deep learning model that synergizes the feature extraction power of a pre-trained ResNet50 architecture with engineered geometric features derived from the Radon Transform and pre-calculated joint angles. Our approach utilizes a dual-balancing strategy, combining data upsampling with a custom weighted loss function, to effectively address the problem of underrepresented classes. By processing visual and geometric data streams in parallel and fusing them within a deep architecture, our model achieves a holistic understanding of the subject's posture. The fine-tuned model demonstrates strong performance on an unseen test set, achieving a final accuracy of 92% for wrist posture and 92% for neck posture. Crucially, it attains a robust F1-score of 0.74 for the challenging 'Bad Wrist Posture' minority class, a significant improvement compared to the ResNet50-only baseline (F1=0.24) and achieves excellent ROC-AUC scores of 0.9859 for wrist and 0.9838 for neck, proving the efficacy of our hybrid, dual-balancing methodology for realworld application. 2026 IEEE.

Source

Proceedings of the 4th IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2026;

Date

01-01-2026

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

Class Imbalance; Deep Learning; Feature Engineering; Hybrid Model; Posture Detection; Radon Transform; ResNet50; Transfer Learning

Coverage

George G.M., Christ (Deemed to be University), Dept. of Statistics and Data Science, Bangalore, India; Ummesalma M., Christ (Deemed to be University), Dept. of Statistics and Data Science, Bangalore, India; Parihar R.S., Christ (Deemed to be University), Dept. of Statistics and Data Science, Bangalore, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833154970-1;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/IATMSI68868.2026.11465994

https://www.scopus.com/pages/publications/105036962349?origin=resultslist