Design and Experimental Verification of a Posture Correction System: Development of an Artificial Neural Network to Predict the Effectiveness of the Developed System to Correct Poor Posture
[ X ]
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Taylor & Francis Inc
Access Rights
info:eu-repo/semantics/closedAccess
Abstract
This research aims to address designing an experiment to evaluate the impact of a developed posture correction system. Also, the correct posture learning habits of users can be estimated with an artificial neural network (ANN) structure that predicts the poor posture count (PPC) in the last session of the experiment using the information received from the users and the developed system. The developed system aims to collect data from different individuals about their sitting posture information. An ANN analysis tool is developed to predict the individuals' habits of learning the correct posture. This setup is based on a flex sensor and has the capability of collecting posture information data and warning the user when the posture is not correct. A three-session experiment was conducted on 12 healthy participants to investigate his/her posture habits. The data was analyzed to determine the average PPC value. It was observed that PPC decreased by 56.27% from session one to session three, and the average improvement evaluation (IE) value after each session was found to be positive. In addition to experimental analysis, the collected posture data was used to train and validate an ANN architecture capable of predicting PPC values. The developed device is effective in improving posture habits and has the potential to predict PPC values with the ANN architecture.
Description
Keywords
Artificial neural networks; haptic feedback; posture; prediction; wearable devices
Journal or Series
International Journal of Human-Computer Interaction
WoS Q Value
N/A
Scopus Q Value
Q1
