Intelli-Helmet: An IoT, Edge-AI, and TinyML-Based Real-Time Soldier Health and Threat Monitoring System with Novel Panic Tactile Switch Mechanism

DOI

10.2991/978-94-6239-664-7_80How to use a DOI?

Keywords

TinyML; IoT; Edge-AI; Soldier Safety; Fall Detection; Acoustic Classification; Real-time Monitoring; Finite State Machine; ESP32; Wearable Systems

Abstract

Modern battlefield environments demand intelligent systems for real-time soldier monitoring and rapid casualty response. This paper presents Intelli-Helmet, an integrated IoT and TinyML-based wearable system addressing critical gaps in military safety infrastructure. We introduce three key algorithmic innovations: (1) an optimized TensorFlow Lite fall detection model achieving 98.5% accuracy with sub-200ms inference latency on resource-constrained ESP32 hardware, (2) a convolutional neural network (CNN) for acoustic threat classification (gunshot, explosion) with 98.56% accuracy using mel-spectrogram preprocessing, and (3) a novel two-stage finite state machine (FSM) panic mechanism with 185ms secure data erase capability and 98.7% successful trigger rate. The system integrates multimodal sensors (MPU6050, MAX30102, INMP441, Neo-6M GPS) with dual-communication fallback (Wi-Fi/GSM) transmitting to a Flask-based command dashboard. While trained on synthetic fall data and public acoustic datasets (UrbanSound8K, ESC-50), the system provides a foundation for battlefieldready soldier monitoring, with future validation planned using Bangladesh Army training scenarios.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Fatima Ashraf
AU  - Iftiak Ahmed
AU  - M. Akhtaruzzaman
AU  - Md Rashid Ul Islam
AU  - Tasnim Ullah Shakib
AU  - Abdus Sattar
PY  - 2026
DA  - 2026/06/08
TI  - Intelli-Helmet: An IoT, Edge-AI, and TinyML-Based Real-Time Soldier Health and Threat Monitoring System with Novel Panic Tactile Switch Mechanism
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 1175
EP  - 1196
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_80
DO  - 10.2991/978-94-6239-664-7_80
ID  - Ashraf2026
ER  -