A Machine Learning Approach to Automatic Fall Detection of Soldiers

TL;DR

This work addresses automatic fall detection for soldiers in combat using inertial data from wearable devices as part of the Brazilian Navy's Soldier of the Future program. It develops a Casualty Detection System with 1D CNN models trained on the IPqM-Fall dataset, collected from a chest-mounted smartphone and wrist wearables, and optimizes hyperparameters via Bayesian search. The chest-time-domain CNN1D with x, y, z components of linear and angular acceleration achieves MCC 0.9952, sensitivity 1.0, and specificity 0.9914, outperforming wrist-mounted and frequency-domain configurations. The study provides publicly released data and code, demonstrates the value of chest-mounted sensors for reliable fall detection in military contexts, and outlines future directions to extend applicability to real exercises and additional modalities such as gunfire detection.

Abstract

Military personnel and security agents often face significant physical risks during conflict and engagement situations, particularly in urban operations. Ensuring the rapid and accurate communication of incidents involving injuries is crucial for the timely execution of rescue operations. This article presents research conducted under the scope of the Brazilian Navy's ``Soldier of the Future'' project, focusing on the development of a Casualty Detection System to identify injuries that could incapacitate a soldier and lead to severe blood loss. The study specifically addresses the detection of soldier falls, which may indicate critical injuries such as hypovolemic hemorrhagic shock. To generate the publicly available dataset, we used smartwatches and smartphones as wearable devices to collect inertial data from soldiers during various activities, including simulated falls. The data were used to train 1D Convolutional Neural Networks (CNN1D) with the objective of accurately classifying falls that could result from life-threatening injuries. We explored different sensor placements (on the wrists and near the center of mass) and various approaches to using inertial variables, including linear and angular accelerations. The neural network models were optimized using Bayesian techniques to enhance their performance. The best-performing model and its results, discussed in this article, contribute to the advancement of automated systems for monitoring soldier safety and improving response times in engagement scenarios.

Figures (9)

• Figure 1: Outline of the Casualty Detection System.
• Figure 2: Fall Detection Algorithm Operation.
• Figure 3: Positions of the devices used in the simulated activities.
• Figure 4: Uniforms OP1, AD, and OP2, respectively.
• Figure 5: Rifles airsoft M4 4003MG and Colt M4 Carbine, respectively.