Physiological Demands of Basic Fire Management Tasks in Members of the Canadian Armed Forces: A Pilot Study

ABSTRACT Introduction Members of the Canadian Armed Forces (CAF) are required to meet the minimum standards of the Fitness for Operational Requirements of CAF Employment (FORCE) job-based simulation test (JBST) and must possess the capacity to perform other common essential tasks. One of those tasks is to perform basic fire management tasks during fire emergencies to mitigate damage and reduce the risk of injuries and/or death until professional firefighters arrive at the scene. To date however, the physiological demands of common firefighting tasks have mostly been performed on professional firefighters, thus rendering the transferability of the demands to the general military population unclear. This pilot study aimed to quantify, for the first time, the physiological demands of basic fire management tasks in the military, to determine if they are reflected in the FORCE JBST minimum standard. We hypothesized that the physiological demands of basic fire management tasks within the CAF are below the physiological demands of the FORCE JBST minimum standard, and as such, be lower than the demands of professional firefighting. Materials and methods To achieve this, 21 CAF members (8 females; 13 males; mean [SD] age: 33 [10] years; height: 174.5 [10.5] cm; weight: 85.4 [22.1] kg, estimated maximal oxygen uptake [$\dot V$O2peak]: 44.4 (7.4) mL kg−1 min−1) participated in a realistic, but physically demanding, JBST developed by CAF professional firefighting subject matter experts. The actions included lifting, carrying, and manipulating a 13-kg powder fire extinguisher and connecting, coupling, and dragging a 38-mm fire hose over 30 m. The rate of oxygen uptake ($\dot V$O2), heart rate, and percentage of heart rate reserve were measured continuously during two task simulation trials, which were interspersed by a recovery period. Rating of perceived exertion (6-no exertion; 20-maximal exertion) was measured upon completion of both task simulations. Peak $\dot V$O2 ($\dot V$O2peak) was estimated based on the results of the FORCE JBST. Results The mean (SD) duration of both task simulation trials was 3:39 (0:19) min:s, whereas the rest period in between both trials was 62 (19) minutes. The mean O2 was 21.1 (4.7) mL kg−1 min−1 across trials, which represented 52.1 (12.2) %$\dot V$O2peak and ∼81% of the FORCE JBST. This was paralleled by a mean heart rate of 136 (18) beats min−1, mean percentage of heart rate reserve of 61.2 (10.8), and mean rating of perceived exertion of 11 ± 2. Other physical components of the JBST consisted of lifting, carrying, and manipulating a 13-kg load for ∼59 seconds, which represents 65% of the load of the FORCE JBST. The external resistance of the fire hose drag portion increased up to 316 N, translating to a total of 6205 N over 30 m, which represents 96% of the drag force measured during the FORCE JBST. Conclusions Our findings demonstrate that the physiological demands of basic fire management tasks in the CAF are of moderate intensity, which are reflected in the CAF physical fitness standard. As such, CAF members who achieve the minimum standard on the FORCE JBST are deemed capable of physically performing basic fire management tasks during fire emergencies.

Designing Human-Autonomy Teaming Experiments Through Reinforcement Learning

This paper creates and defines a framework for building and implementing human-autonomy teaming experiments that enable the utilization of modern reinforcement learning models. These models are used to train artificial agents to then interact alongside humans in a human-autonomy team. The framework was synthesized from experience gained redesigning a previously known and validated team task simulation environment known as NeoCITIES. Through this redesign, several important high-level distinctions were made that regarded both the artificial agent and the task simulation itself. The distinctions within the framework include gamification, access to high-performance computing, a proper reward function, an appropriate team task simulation, and customizability. This framework enables researchers to create experiments that are more usable for the human and more closely resemble real-world human-autonomy interactions. The framework also allows researchers to create veritable and robust experimental platforms meant to study human-autonomy teaming for years to come.

An Unknown Radar Emitter Identification Method Based on Semi-Supervised and Transfer Learning

Aiming at the current problem that it is difficult to deal with an unknown radar emitter in the radar emitter identification process, we propose an unknown radar emitter identification method based on semi-supervised and transfer learning. Firstly, we construct the support vector machine (SVM) model based on transfer learning, using the information of labeled samples in the source domain to train in the target domain, which can solve the problem that the training data and the testing data do not satisfy the same-distribution hypothesis. Then, we design a semi-supervised co-training algorithm using the information of unlabeled samples to enhance the training effect, which can solve the problem that insufficient labeled data results in inadequate training of the classifier. Finally, we combine the transfer learning method with the semi-supervised learning method for the unknown radar emitter identification task. Simulation experiments show that the proposed method can effectively identify an unknown radar emitter and still maintain high identification accuracy within a certain measurement error range.

Experimental investigation of artificial intelligence applied in MPPT techniques

Nano-satellites are key features for sharing the space data and scientific researches. They embed subsystems that are fed from solar panels and batteries. Power generated from these panels is subject to environmental conditions, most important of them are irradiance and temperature. Optimizing the usage of this power versus environmental variations is a primary task. Synchronous DC-DC buck converter is used to control the power transferred from PV panels to the subsystems while maintaining operation at maximal power. <br />In this paper, artificial intelligence techniques: neural networks and adaptive neural fuzzy inference systems (ANFIS) are used to accomplish the tracking task. Simulation and experimental results demonstrate their efficiency, robustness and tracking quality. <br /><br />

Lyapunov Theory-Based Fusion Neural Networks for the Identification of Dynamic Nonlinear Systems

This paper introduces a novel fusion neural architecture and the use of a novel Lyapunov theory-based algorithm, for the online approximation of the dynamics of nonlinear systems. The proposed neural system, in combination with the proposed update rule of the neural weights, achieves fast convergence of the identification process, ensuring at the same time stability of the error system in the sense of Lyapunov theory. The fusion neural system combines the features that are extracted from two-independent neural streams, a feedforward and a diagonal recurrent one, satisfying different design criteria of the identification task. Simulation results for five cases reveal the approximation strength of both proposed fusion neural architecture and proposed learning algorithm. Also, additional experiments demonstrate the effectiveness in cases of parameter variations and additive noise.