A Survey on Next-Generation Internet of Military Things Wearable for Autonomous Soldier Monitoring

Abstract

This project presents an advanced Internet of Military Things (IoMT)-based system designed for real-time soldier health monitoring and battlefield threat detection. It addresses the limitations of traditional systems such as manual surveillance, delayed communication, and lack of intelligent analysis in high-risk environments. The proposed solution integrates wearable sensor nodes with a distributed battlefield monitoring network to continuously track vital parameters like heart rate, body temperature, SpO? levels, motion, gas exposure, and location. The system utilizes ESP32-based embedded devices combined with multiple sensors to collect and transmit real-time data using MQTT and long-range communication technologies such as LoRa. To ensure reliability, the architecture incorporates both edge computing and cloud-based processing, enabling continuous monitoring even in communication-constrained scenarios. A key feature of the project is the integration of machine learning models, including TinyML for on-device inference and LSTM-based deep learning models in the cloud for accurate anomaly detection. The system detects critical conditions such as fatigue, heat stroke, falls, toxic gas exposure, and geofence violations, ensuring timely alerts to the command center. A mobile-based interface provides real-time visualization, enabling faster decision-making and improved coordination. Secure data transmission is ensured through encryption techniques, enhancing system reliability in military applications. Additionally, the project evaluates performance metrics such as latency, power consumption, and communication efficiency, demonstrating a balance between accuracy and resource utilization. Overall, the proposed IoMT framework offers a scalable, cost-effective, and intelligent solution for enhancing soldier safety, situational awareness, and operational efficiency in modern warfare environments.

Introduction

The rapid advancement of connected technologies has led to the development of the Internet of Military Things (IoMT), which enhances military operations through intelligent communication among soldiers, sensors, and battlefield devices. Traditional soldier monitoring systems rely on manual methods, radio communication, and isolated sensors, resulting in limited situational awareness, delayed responses, and inefficient coordination. Modern IoMT systems address these issues by integrating wearable sensors, communication networks, and artificial intelligence to monitor soldier health, environmental conditions, and location in real time.

Recent developments have introduced wearable devices capable of tracking vital signs such as heart rate, body temperature, oxygen saturation (SpO?), and environmental hazards. However, many existing systems depend heavily on centralized cloud infrastructure, making them vulnerable to communication failures and latency issues in hostile environments. To overcome these challenges, researchers have proposed hybrid edge-cloud architectures, where edge devices perform local processing for faster responses, while cloud platforms provide advanced analytics. Communication technologies such as MQTT, LoRa, GSM/LTE, and mesh networking enhance connectivity, while encryption and secure protocols protect sensitive military data.

The literature survey highlights key advancements in IoMT-based soldier monitoring. Recent studies have explored AI-driven health monitoring, deep learning-based anomaly detection, TinyML for low-power edge intelligence, federated learning for privacy-preserving data analysis, and Internet of Battlefield Things (IoBT) frameworks. While these approaches improve accuracy, efficiency, and security, challenges remain in areas such as computational requirements, internet dependency, scalability, interoperability, and real-world battlefield deployment.

The proposed methodology presents a wearable IoMT framework centered on an ESP32 microcontroller connected to sensors for monitoring heart rate, temperature, SpO? levels, toxic gas exposure, and GPS location. The system performs local data processing at the edge to filter noise, detect abnormalities, generate emergency alerts, and store data during connectivity disruptions. Processed information is transmitted through Wi-Fi, GSM/LTE, or mesh networks to a central monitoring platform that provides real-time health tracking, location monitoring, data storage, and visualization for commanders.

The system includes an intelligent alert mechanism that detects abnormal physiological conditions, falls, inactivity, and hazardous environmental exposure. In emergencies, it automatically sends alerts and SOS messages with location details to command centers. Experimental results demonstrate accurate health and location monitoring, successful anomaly detection, rapid emergency response, and reliable communication between wearable devices and monitoring stations.

Conclusion

This project presents a comprehensive IoMT-based solution for real-time soldier health and threat monitoring in challenging battlefield environments. The system successfully integrates multiple sensors, embedded hardware, and intelligent data processing to ensure continuous monitoring of critical parameters. By combining biometric and environmental sensing, the proposed model enhances situational awareness and improves decision-making capabilities. The use of ESP32-based wearable nodes ensures a compact, cost-effective, and energy-efficient implementation. The adoption of MQTT protocol enables reliable and low-latency communication between devices and the command center. A key contribution of this project is the integration of both edge-based TinyML and cloud-based deep learning models. This hybrid approach ensures system functionality even in communication-constrained scenarios. The TinyML model provides fast, real-time inference at the device level, supporting offline operations. The cloud-based LSTM and autoencoder model improves detection accuracy through advanced temporal analysis. The developed Flutter application offers an intuitive interface for real-time monitoring and alert management. This enhances the ability of commanding officers to respond quickly to emergency situations. The system also demonstrates the effectiveness of multi-sensor data fusion in identifying complex health conditions. Experimental results indicate improvements in latency, reliability, and detection efficiency compared to traditional systems. The project successfully addresses major limitations of existing approaches, such as high false positives and lack of real- time intelligence. Additionally, the prototype remains economically feasible, making it suitable for scalable deployment. Despite these advantages, further improvements can be made in terms of large-scale testing and rugged hardware design. Future work can explore federated learning and enhanced security mechanisms for better data privacy and system robustness. Integration with advanced communication technologies like LoRa can further improve range and reliability. Overall, the proposed system demonstrates a significant step toward intelligent and resilient military IoMT solutions

References

[1] HEAL System Researchers, “AI-based IoMT system using LoRa for soldier health monitoring and predictive analysis,” 2026 [2] S. Mishra and R. Pande, “Deep learning-based anomaly detection using LSTM autoencoders in IoMT,” 2025,. [3] H. Li, W. Zhang, and Y. Chen, “A survey on TinyML applications for biometric recognition in embedded systems,” 2025 [4] A. Patel, M. Singh, and K. Reddy, “AI-integrated IoT wearable system for soldier health and situational awareness,” 2025 [5] F. Sattler, S. Wiedemann, K. Müller, and W. Samek, “Federated learning for distributed IoT systems,” 2024 [6] D. Verma, N. Shah, and S. Agrawal, “TinyML techniques for low-power IoT edge devices,” 2024 [7] DARPA IoBT Collaborative Research, “Internet of Battlefield Things (IoBT): Vision and challenges for modern warfare,” 2023 [8] P. Nair and B. Sharma, “Design of wearable multi-sensor systems for military applications,” 2022 [9] T. Ramesh and V. Krishnamurthy, “Real-time soldier monitoring system using IoT and MQTT-based GPS tracking,” 2022. [10] R. Kumar, S. Sharma, and P. Gupta, “IoT-based soldier health monitoring system using wearable sensors and GSM communication,” 2018

Copyright

Copyright © 2026 Nagarathna C, Sameeksha Patel, Reha Srikanta, Nadeem , Rishab N. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.