Ambient and wearable system for workers' stress evaluation

The paradigm of Industry 4.0 involves fully automated and interconnected industrial production processes demanding a great deal of human-machine interaction. This implies the emergence of new problems related to the stress assessment of workers operating in new and more complex work contexts. To address this need, it may be important to implement automated stress detection platform designed to be effective in a real-world work setting. Many works in the literature deal with the stress evaluation topic, they use above all wearable systems that are often intrusive and subject to noise and artifacts that degrade performance. Moreover, most of them integrate supervised machine learning algorithms, which achieve high levels of detection accuracy, but require a complicated training phase, which might not be suitable in a real-world context. To reduce these limitations, a stress detection platform combining data from a wearable and an environmental system is presented in this paper. It analyses heart rate, galvanic skin response and camera RGB signals. The wearable device was designed to be minimally invasive with good signal stability and low noise, while a commercial camera was added to improve the performance of the whole hardware architecture. From the software perspective, the presented solution was first tested and validated using a supervised approach. Subsequently, attention was focused on the analysis and development of an unsupervised solution, implementing three unsupervised algorithms. The best performance was obtained with the Gaussian Mixture Model having an accuracy of 77.4% considering one level of stress and 75.1% with two levels of stress.