← Back to VOLUME 13, ISSUE 11, NOVEMBER 2026
This work is licensed under a Creative Commons Attribution 4.0 International License.
Privacy-Preserving Edge-Based Wearable System for Real-Time Detection of Hand Tremors and Seizure-Like Movement Events
Prof. Supriya Chougule, Tanishqa Hole, Sakshi Jagtap, Vaishnavi Kolhe, Nikita Jagtap
👁 3 views📥 1 download
Abstract: Epileptic seizures and pathological tremors can seriously affect a person’s safety and daily life, which is why wearable systems that monitor continuously and raise timely alerts are so valuable. Many existing wearables depend on cloud connectivity, rely on a single sensor, or stream data nonstop. This adds communication overhead, drains energy, and often leads to false alarms.
In this paper, we propose an edge-processed, multimodal wearable system for real-time monitoring of pathological tremors and seizure-related events, built into a low-cost smart glove. The glove combines surface electromyography (sEMG) and inertial measurement unit (IMU) sensors, so it can capture both muscle activity and movement patterns. All signals are processed locally on an ESP32 -based embedded platform, where signal-processing techniques and a lightweight, quantized machine-learning model are intended to classify movement patterns as they happen. An OLED display and a buzzer give immediate local alerts, while Bluetooth Low Energy (BLE) offers optional wireless communication, so the device never needs a constant internet connection.
Keywords: Epileptic seizure monitoring, pathological tremor, wearable system, multimodal sensors, edge computing, TinyML, ESP32, sEMG, IMU, Bluetooth Low Energy.
In this paper, we propose an edge-processed, multimodal wearable system for real-time monitoring of pathological tremors and seizure-related events, built into a low-cost smart glove. The glove combines surface electromyography (sEMG) and inertial measurement unit (IMU) sensors, so it can capture both muscle activity and movement patterns. All signals are processed locally on an ESP32 -based embedded platform, where signal-processing techniques and a lightweight, quantized machine-learning model are intended to classify movement patterns as they happen. An OLED display and a buzzer give immediate local alerts, while Bluetooth Low Energy (BLE) offers optional wireless communication, so the device never needs a constant internet connection.
Keywords: Epileptic seizure monitoring, pathological tremor, wearable system, multimodal sensors, edge computing, TinyML, ESP32, sEMG, IMU, Bluetooth Low Energy.
How to Cite:
[1] Prof. Supriya Chougule, Tanishqa Hole, Sakshi Jagtap, Vaishnavi Kolhe, Nikita Jagtap, “Privacy-Preserving Edge-Based Wearable System for Real-Time Detection of Hand Tremors and Seizure-Like Movement Events,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), DOI: 10.17148/IARJSET.2026.131107
