An Online Method for Supporting and Monitoring Repetitive Physical Activities Based on Restricted Boltzmann Machines

Abstract

Human activity recognition has been widely used to monitor users during physical activities. By embedding a pre-trained model into wearable devices with an inertial measurement unit, it is possible to identify the activity being executed, count steps and activity duration time, and even predict when the user should hydrate himself. Despite these interesting applications, these approaches are limited by a set of pre-trained activities, making them unable to learn new human activities. In this paper, we introduce a novel approach for generating runtime models to give the users feedback that helps them to correctly perform repetitive physical activities. To perform a distributed analysis, the methodology focuses on applying the proposed method to each specific body segment. The method adopts the Restricted Boltzmann Machine to learn the patterns of repetitive physical activities and, at the same time, provides suggestions for adjustments if the repetition is not consistent with the model. The learning and the suggestions are both based on inertial measurement data mainly considering movement acceleration and amplitude. The results show that by applying the model’s suggestions to the evaluation data, the adjusted output was up to 3.68x more similar to the expected movement than the original data.

3D Convolutional Neural Networks based Movement Evaluation System for Gymnasts in Computer Vision Applications

“…In [15], a novel approach using runtime models in wearable devices for human activity recognition, offering feedback to improve performance in repetitive physical activities. The method utilizes Restricted Boltzmann Machines on inertial measurement data, resulting in adjustments up to 3.68 times more accurate compared to the original movement data, aiding in precise activity execution.…”