Work

Deep Learning-Based Sitting Posture Recognition from Pressure Distribution Across Hard and Soft Seat Environment

Year: 2025

Type: article

Abstract: This study investigates the classification of nine sitting postures using pressure distribution data from hard and soft seat surfaces. Three neural network architectures (FNN, CNN, ResNet) were evaluated under single-surface and mixed-domain training regimes. While all models achieved high accuracy (>96%) when trained on mixed-domain dataset, significant performance degradation occurred in cross-domain testing. CNN demonstrated superior capability in leveraging spatial pressure features under mixed training conditions, while FNN exhibited relatively better cross-domain robustness. Results indicate model performance highly depends on architectural inductive biases and training data diversity. These findings underscore the importance of employing representative multi-surface datasets for ensuring generalization in practical sitting posture recognition systems.

Source: Applied Sciences

DOI: 10.3390/app152312744

Authors: Boren Wang, Lili Tu, Qiuqiong Shi, Shiwei Mo

Institutions: Shenzhen University, Hong Kong Polytechnic University

Language: English

Topic: Context-Aware Activity Recognition Systems

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,896

Funder: National Key Research and Development Program of China