An IoT-Enabled Wearable Device for Fetal Movement Detection Using Accelerometer and Gyroscope Sensors

Area of Science:

• Biomedical Engineering
• Maternal-Fetal Medicine
• Wearable Technology

Background:

• Manual fetal movement counting is crucial for fetal well-being but poses practical challenges for pregnant individuals.
• Existing methods for monitoring fetal activity can be inconvenient and limited to clinical environments.

Purpose of the Study:

• To develop and evaluate a wearable device for accurate and convenient detection of fetal movements.
• To differentiate fetal movements from other physical activities using advanced sensor and machine learning techniques.

Main Methods:

• Integration of accelerometer and gyroscope sensors with Internet of Things (IoT) technology in a wearable device.
• Evaluation of signal extraction, machine learning algorithms, and feature selection techniques, including Particle Swarm Optimization (PSO) and Extreme Gradient Boosting (XGB).
• Data collection from 35 pregnant women at Suranaree University of Technology (SUT) Hospital.

Main Results:

• The device achieved high classification performance with 90.00% sensitivity, 87.46% precision, and an 88.56% F1-score.
• IoT integration enabled continuous monitoring with low latency (423.6 ms) and ensured data integrity.
• The wearable device demonstrated a battery life of up to 48 hours on a single charge.

Conclusions:

• The proposed wearable device offers a practical and effective solution for fetal movement detection.
• The technology facilitates continuous, remote fetal monitoring, enhancing antenatal care accessibility.
• This innovation represents a significant advancement in non-invasive fetal health assessment tools.