System for stress level monitoring

Cenusa, Mihai; Poienar, Mihaela; Dan, Pata Sergiu

doi:10.1109/iseee.2017.8170706

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are instead in the literature interesting results of research projects focused on the detection and classification of stress and more in general emotions felt by a person subjected to stressful stimuli such as working under time-pressure conditions, continuous interruptions during activities, or viewing emotionally engaging images/videos during the experiment. These studies are mostly related to office-type environments or based on ad hoc laboratory setups that include video cameras, electromyographic helmets, multi-leads electrocardiogram devices and other devices for vital signs acquisition, which are difficult to apply during heavily dynamic activities typical of manufacturing companies [ 44 , 45 , 46 , 47 , 48 ]. Such types of working activities also impact the quality of signals measured by wearable devices, and the high level of noise with respect to (semi)stationary acquisitions needs to be considered in the detection of stress.…”

Section: State Of the Artmentioning

confidence: 99%

ECG-Based Stress Detection and Productivity Factors Monitoring: The Real-Time Production Factory System

Donati

Olivelli

Giovannini³

et al. 2023

Sensors

View full text Add to dashboard Cite

Productivity and production quality have become primary goals for the success of companies in all industrial and manufacturing sectors. Performance in terms of productivity is influenced by several factors including machinery efficiency, work environment and safety conditions, production processes organization, and aspects related to workers’ behavior (human factors). In particular, work-related stress is among the human factors that are most impactful and difficult to capture. Thus, optimizing productivity and quality in an effective way requires considering all these factors simultaneously. The proposed system aims to detect workers’ stress and fatigue in real time using wearable sensors and machine learning techniques and also integrate all data regarding the monitoring of production processes and the work environment into a single platform. This allows comprehensive multidimensional data analysis and correlation research, enabling organizations to improve productivity through appropriate work environments and sustainable processes for workers. The on-field trial demonstrated the technical and operational feasibility of the system, its high degree of usability, and the ability to detect stress from ECG signals exploiting a 1D Convolutional Neural Network (accuracy 88.4%, F1-score 0.90).

show abstract