In response to the escalating complexity and frequency of wildland fires, this study investigates the feasibility of using wearable devices for real-time monitoring of cardiac, respiratory, physical, and environmental parameters during live wildfire suppression tasks. Data were collected from twelve male firefighters (FFs) from the Italian National Fire Corp during a simulated protocol, including rest, running, and active fire suppression phases. Physiological and physical metrics such as heart rate (HR), heart rate variability (HRV), respiratory frequency (fR) and physical activity levels were extracted using chest straps. The protocol designed to mimic real-world firefighting scenarios revealed significant cardiovascular and respiratory strain, with HR often exceeding 85% of age-predicted maxima and sustained elevations in high-stress roles. Recovery phases highlighted variability in physiological responses, with reduced HRV indicating heightened autonomic stress. Additionally, physical activity analysis showed task-dependent intensity variations, with debris management roles exhibiting consistently high exertion levels. These findings demonstrate the relevance of wearable technology for real-time monitoring, providing an accurate analysis of key metrics to offer a comprehensive overview of work-rest cycles, informing role-specific training and operational strategies.
This study focuses on the integration and validation of a filtering face piece 3 (FFP3) facemask module for monitoring breathing activity in industrial environments. The key objective is to ensure accurate, real-time respiratory rate (RR) monitoring while maintaining workers’ comfort. RR monitoring is conducted through temperature variations detected using temperature sensors tested in two configurations: sensor t1, integrated inside the exhalation valve and necessitating structural mask modifications, and sensor t2, mounted externally in a 3D-printed structure, thus preserving its certification as a piece of personal protective equipment (PPE). Ten healthy volunteers participated in static and dynamic tests, simulating typical daily life and industrial occupational activities while wearing the breathing activity monitoring module and a chest strap as a reference instrument. These tests were carried out in both indoor and outdoor settings. The results demonstrate comparable mean absolute error (MAE) for t1 and t2 in both indoor (i.e., 0.31 bpm and 0.34 bpm) and outdoor conditions (i.e., 0.43 bpm and 0.83 bpm). During simulated working activities, both sensors showed consistency with MAE values in static tests and were not influenced by motion artifacts, with more than 97% of RR estimated errors within ±2 bpm. These findings demonstrate the effectiveness of integrating a smart module into protective masks, enhancing occupational health monitoring by providing continuous and precise RR data without requiring additional wearable devices.
Human activity recognition (HAR) is gaining importance in the development of smart personal protective equipment (PPE). Yet, most solutions rely on body-worn devices or invasive helmet modifications, limiting adoption in industrial settings. We propose a non-invasive smart helmet with embedded motion and environmental sensors, fully integrated into a certification-compliant shell. To explore its applicability in realistic industrial conditions, we focused on constrained acquisition scenarios—characterized by low sampling rates, limited storage, and processing capacity. A multimodal dataset was collected using embedded tri-axial accelerometers and barometric pressure sensors during operational tasks. Four classification pipelines were evaluated: Random Forest (RF), Extreme Gradient Boosting (XGBoost), a wavelet-based RF (using Horizontal Concatenation of Continuous Wavelet Transforms, HC-CWT), and a deep learning pipeline combining a Convolutional Autoencoder with LSTM (ConvAE-LSTM). Among these, XGBoost achieved the highest accuracy (up to 87.4%) and the most favorable balance between latency and computational efficiency, particularly with 8–15 s windows. This best-performing model was then deployed on the resource-constrained helmet system, confirming its suitability for on-board HAR in scalable occupational safety applications.
Despite its critical role in assessing physiological strain and mitigating heat- and smoke-related risks, real-time respiratory monitoring is still largely absent in wildland firefighting. This study evaluates two wearable systems for estimating respiratory rate (RR) under operational field conditions (i.e., a multistage fire suppression protocol): a face-mounted system based on a thermistor integrated into a FFP3 facemask (Mask) and a chest-worn commercial strap (Bioharness, BH) with an integrated strain sensor. RR was estimated from raw signals using frequency–domain analysis considering both 25 s and 50 s windows lengths. Pairwise comparisons were performed between RR values estimated from Mask and BH, and, respectively, between each of them and the manufacturer–generated “Summary RR” provided by the BH's onboard processor. Results underscore the influence of signal processing over sensor placement and demonstrate the feasibility of unobtrusive RR tracking using both wearable systems in dynamic, high-risk environments.
This study evaluates the performance of a 32-marker motion capture (MoCap) system in estimating respiratory frequency () and tidal volume () during cycling exercise. Fourteen well-trained cyclists performed an incremental step test on a cycle ergometer, while simultaneously recording a raw flow signal with a reference metabolic cart (COSMED) and respiratory-induced torso movements with twelve optoelectronic cameras registering the position of 32 markers affixed to the torso. and were calculated from both systems on a breath-by-breath basis. The MoCap system showed a strong correlation with the COSMED system when measuring and ( = 0.99, = 0.87, respectively) during exercise. For , the mean absolute error (MAE) and mean absolute percentage error (MAPE) were 0.79 breaths/min and 2.1%, respectively. For , MoCap consistently underestimated values compared to COSMED, showing a bias (MOD ± LOA) of −0.11 ± 0.42 L and MAPE values of 8%. These findings highlight the system’s capabilities for real-time respiratory monitoring in athletic environments.
This paper presents a mobile application designed to support emergency operators during indoor missions, where Global Positioning System (GPS) often fails. The system combines a wearable waist-mounted Inertial Measurement Unit (IMU) with a network of pre-installed Radio Frequency Identification (RFID) tags, enabling robust, real-time geo-referenced tracking of both personnel and critical Points of Interest (PoIs), such as resources and threats. Development was guided by interviews and surveys with emergency professionals, ensuring the tool addresses real operational needs. Key features include dynamic updates of operator positions and nearby hazards, enabled by an Indoor Positioning System (IPS) that fuses IMU and RFID data to improve accuracy in position and heading estimation. The application also offers a user-friendly Human–Environment Interface (HEI) displaying information on a spatially referenced map. By merging advanced technology with expert feedback, this system enhances safety and coordination in critical scenarios, offering a promising solution for indoor navigation and Situational Awareness (SA) in emergency response.