Intelligent Posture Training - Machine-Learning-Powered Human Sitting Posture Recognition Based on a Pressure-Sensing IoT Cushion

Aug 3, 2026

Upload by Skyler

A machine-learning solution supports intelligent posture training through accurate, real-time sitting posture monitoring using the LifeChair IoT pressure-sensing cushion and supervised learning with user body data. Experiments demonstrate high recognition performance for 15 sitting postures (98.82% accuracy) and six seated stretches (97.94% accuracy). Results show that BMI divergence significantly influences recognition accuracy. Validation across five workplace environments compares outcomes and informs model training strategies, and the work introduces a smart, data-driven stretch recommendation system aligned with physiotherapy standards.

LanguageEnglish

CategoryTechnology

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

1. Introduction

2. Related Work

3. System and Data Collection

4. Machine Learning Approach

5. Experimental Evaluation

6. Workplace Validation and Training Strategies

7. Smart Stretch Recommendation System

8. Conclusions

sensors Article Intelligent Posture Training: Machine-Learning-Powered Human Sitting Posture Recognition Based on a Pressure-Sensing IoT Cushion Katia Bourahmoune 1, *, Karlos Ishac 2 and Toshiyuki Amagasa 3 􀀁􀀂􀀃􀀁􀀄 􀀆􀀇􀀈 􀀁􀀂􀀃􀀄􀀅􀀆􀀇 Citation: Bourahmoune, K.; Ishac, K.; Amagasa, T. Intelligent Posture Training: Machine-Learning-Powered Human Sitting Posture Recognition Based on a Pressure-Sensing IoT Cushion. Sensors 2022, 22, 5337 . [https://doi.org/10.3390/s22145337](https://doi.org/10.3390/s22145337)[ ](https://doi.org/10.3390/s22145337)Academic Editor: Isabel De la Torre Díez Received: 28 May 2022 Accepted: 11 July 2022 Published: 17 July 2022 Publisher's Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional afﬁliations. Copyright: © 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba 305-8577, Japan 2 Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia; [karlos.ishac@uts.edu.au](karlos.ishac@uts.edu.au) 3 Center for Computational Sciences, University of Tsukuba, Tsukuba 305-8577, Japan; [amagasa@cs.tsukuba.ac.jp](amagasa@cs.tsukuba.ac.jp) * Correspondence: [katia.bmn@kde.cs.tsukuba.ac.jp](katia.bmn@kde.cs.tsukuba.ac.jp) Abstract: We present a solution for intelligent posture training based on accurate, real-time sitting posture monitoring using the LifeChair IoT cushion and supervised machine learning from pressure sensing and user body data. We demonstrate our system's performance in sitting posture and seated stretch recognition tasks with over 98.82% accuracy in recognizing 15 different sitting postures and 97.94% in recognizing six seated stretches. We also show that user BMI divergence signiﬁcantly affects posture recognition accuracy using machine learning. We validate our method's performance in ﬁve different real-world workplace environments and discuss training strategies for the machine learning models. Finally, we propose the ﬁrst smart posture data-driven stretch recommendation system in alignment with physiotherapy standards. Keywords: posture recognition; applied machine learning; IoT; pressure sensing; human well-being 1. Introduction With recent advances in medical and health sciences and the accessibility of information about healthy living, the awareness of the importance of well-being at work is rising. However, the stresses and commitments associated with modern living can hinder efforts towards achieving better health and well-being on a daily basis. In particular, the increase in desk-bound work and the use of computers and hand-held devices such as smartphones and tablets has exacerbated the problems of sedentary lifestyles and poor sitting posture [1] . A systematic review based on accelerometry measurement of 11 large-scale population studies found that adults spend approximately 10 h a day or approximately 65–80% of the day performing sedentary behaviors [2] . Common sedentary behaviors that most people engage in daily occur while working, commuting, and many leisure activities that require prolonged sitting. Slouching in particular has been termed “the new smoking” [3] . Slouching while sitting is a state where the person's posture is imbalanced forward or to the sides in addition to any combination of rounded shoulders, forward head posture, and angled neck or lumbar. A vast body of research has shown that poor sitting posture and prolonged sitting lead to a wide range of physical and mental health issues such as lower back pain, neck pain, headaches, respiratory and cardiovascular

FAQs

How does the proposed system recognize human sitting postures and stretches?

It uses the LifeChair IoT cushion to capture pressure-sensing signals and applies supervised machine learning with pressure and user body data to classify sitting postures and seated stretches.

What recognition accuracy does the system achieve?

The system reports over 98.82% accuracy for 15 sitting postures and 97.94% accuracy for recognizing six seated stretches.

How does BMI divergence affect posture recognition accuracy?

The document states that user BMI divergence significantly affects posture recognition accuracy, indicating the models’ performance varies across body characteristics.

Aug 3, 2026

Upload by Skyler