An IoT-Enabled Wearable Device for Fetal Movement Detection Using Accelerometer and Gyroscope Sensors DOI Creative Commons
Atcharawan Rattanasak, Talit Jumphoo,

Wongsathon Pathonsuwan

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1552 - 1552

Published: March 2, 2025

Counting fetal movements is essential for assessing health, but manually recording these can be challenging and inconvenient pregnant women. This study presents a wearable device designed to detect across various settings, both within outside medical facilities. The integrates accelerometer gyroscope sensors with Internet of Things (IoT) technology accurately differentiate between non-fetal movements. Data were collected from 35 women at Suranaree University Technology (SUT) Hospital. evaluated ten signal extraction methods, six machine learning algorithms, four feature selection techniques enhance classification performance. utilized Particle Swarm Optimization (PSO) Extreme Gradient Boosting (XGB) PSO hyper-tuning. It achieved sensitivity 90.00%, precision 87.46%, an F1-score 88.56%, reflecting commendable results. IoT-enabled facilitated continuous monitoring average latency 423.6 ms. ensured complete data integrity successful transmission, the capability operate continuously up 48 h on single charge. findings substantiate efficacy proposed approach in detecting movements, thereby demonstrating practical valuable movement detection applications.

Language: Английский

An IoT-Enabled Wearable Device for Fetal Movement Detection Using Accelerometer and Gyroscope Sensors DOI Creative Commons
Atcharawan Rattanasak, Talit Jumphoo,

Wongsathon Pathonsuwan

et al.

Sensors, Journal Year: 2025, Volume and Issue: 25(5), P. 1552 - 1552

Published: March 2, 2025

Counting fetal movements is essential for assessing health, but manually recording these can be challenging and inconvenient pregnant women. This study presents a wearable device designed to detect across various settings, both within outside medical facilities. The integrates accelerometer gyroscope sensors with Internet of Things (IoT) technology accurately differentiate between non-fetal movements. Data were collected from 35 women at Suranaree University Technology (SUT) Hospital. evaluated ten signal extraction methods, six machine learning algorithms, four feature selection techniques enhance classification performance. utilized Particle Swarm Optimization (PSO) Extreme Gradient Boosting (XGB) PSO hyper-tuning. It achieved sensitivity 90.00%, precision 87.46%, an F1-score 88.56%, reflecting commendable results. IoT-enabled facilitated continuous monitoring average latency 423.6 ms. ensured complete data integrity successful transmission, the capability operate continuously up 48 h on single charge. findings substantiate efficacy proposed approach in detecting movements, thereby demonstrating practical valuable movement detection applications.

Language: Английский

Citations

0