IoT device for Athlete's movements recognition using inertial measurement unit (IMU)

This paper proposes a novel approach to tackle the human activity recognition (HAR) problem. Four classes of body movement datasets, namely stand-up, sit-down, run, and walk, are applied to perform HAR. Instead of using vision-based solutions, we address the HAR challenge by implementing a real-time HAR system architecture with a wearable inertial measurement unit (IMU) sensor, which aims to achieve networked sensing and data sampling of human activity, data pre-processing and feature analysis, data generation and correction, and activity classification using hybrid learning models. Referring to the experimental results, the proposed system selects the pre-trained eXtreme Gradient Boosting (XGBoost) model and the Convolutional Variational Autoencoder (CVAE) model as the classifier and generator, respectively, with 96.03% classification accuracy.

Section: Related Workmentioning

confidence: 99%

Hybrid Learning Models for IMU-Based HAR with Feature Analysis and Data Correction

Tseng,

Wen

2023

“…Many studies have focused on the analysis of athletes’ movement. For instance, by having athletes wear a Wi-Fi-based inertial sensing module on their wrist, Abdallah et al presented a new wearable IoT device capable of monitoring athletes’ movements in real-time [ 24 ]. Ivanov et al presented a wearable electronic system that includes a microcontroller, accelerometers, microsensors, and a heart-rate module for recognizing and controlling the accuracy of athletes’ movements [ 25 ].…”

Section: Related Workmentioning

confidence: 99%

Analysis on the Subdivision of Skilled Mowing Movements on Slopes

Nishimura

et al. 2022

Owing to the aging of the rural population in the hilly and mountainous areas of Japan, mowing on narrow ridges and steep slopes is done manually by the elderly—individuals over 65 years of age. Studies have shown that many accidents that occurred during mowing were caused by workers’ unstable posture, especially when mowing on steep surfaces where there is a high risk of falling. It is necessary to analyze the body movements of mowing workers to elucidate the elements related to the risk of falls. Therefore, in this study, based on a high-precision motion-capture device and a series of experiments with elderly, skilled mowing workers, we focused on the movements of mowing. We sought to identify effective and safe mowing patterns and the factors that lead to the risk of falls. In various mowing styles, compared to the stride (S) and downward (D) mowing patterns, the basic (B) and moving (M) patterns were the most efficient; however, the risk of falls was also the highest among these patterns. While mowing, workers need to pay more attention to their arm strength and take appropriate measures to reduce the risk of falls according to their age and physique. The results can be used as data for the development of fall-detection systems and offer useful insights for the training of new mowing workers.

“…Human movement monitoring plays a key role in various applications: human–machine interfaces for virtual reality applications [ 18 ], monitoring of diseases affecting movements [ 19 ], training of athletes [ 20 , 21 , 22 ], treatment and monitoring of posture problems [ 23 , 24 ], etc.…”

Section: Introductionmentioning

confidence: 99%

Movement Recognition through Inductive Wireless Links: Investigation of Different Fabrication Techniques

Monti,

Tarricone

2023

In this paper, an inductive wireless link for motion recognition is investigated. In order to validate the feasibility of a wearable implementation, the use of three different materials is analyzed: a thin copper wire, a conductive yarn, and a conductive non-woven fabric. Results from the application of the developed devices on an arm are reported and discussed. It is demonstrated that the proposed textile inductive resonant wireless links are well suited for developing a compact wearable system for joint flexion recognition.