Wearable Sensors and Artificial Intelligence for Physical Ergonomics: A Systematic Review of Literature

Abstract

Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, for example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown potential for improvement in experimental methods of ergonomic analysis, through the combined use of artificial intelligence, and wearable sensors. In this regard, this review intends to provide a first account of the investigations carried out using these combined methods, considering the period up to 2021. The method that combines the information obtained on the worker through physical sensors (IMU, accelerometer, gyroscope, etc.) or biopotential sensors (EMG, EEG, EKG/ECG), with the analysis through artificial intelligence systems (machine learning or deep learning), offers interesting perspectives from both diagnostic, prognostic, and preventive points of view. In particular, the signals, obtained from wearable sensors for the recognition and categorization of the postural and biomechanical load of the worker, can be processed to formulate interesting algorithms for applications in the preventive field (especially with respect to musculoskeletal disorders), and with high statistical power. For Ergonomics, but also for Occupational Medicine, these applications improve the knowledge of the limits of the human organism, helping in the definition of sustainability thresholds, and in the ergonomic design of environments, tools, and work organization. The growth prospects for this research area are the refinement of the procedures for the detection and processing of signals; the expansion of the study to assisted working methods (assistive robots, exoskeletons), and to categories of workers suffering from pathologies or disabilities; as well as the development of risk assessment systems that exceed those currently used in ergonomics in precision and agility.

Wearables for Monitoring and Postural Feedback in the Work Context: A Scoping Review

“…Based on this evidence, it seems reasonable to integrate IMUs into posture monitoring and feedback wearables in the workplace context. It is worth noting that IMUs, which allow for a more comprehensive assessment [ 7 ], are the most used type of sensor according to Ciccarelli et al [ 2 ]; Conforti et al [ 14 ]; Donisi et al [ 59 ], and Patel et al [ 18 ]. In contrast, this scoping review found that IMUs with accelerometers only (three-axis IMU-accelerometer) were the most frequently used resource for analysis and corrective feedback in the workplace.…”

“…According to Donisi et al [ 59 ], it is observed that the most common and frequent approach to monitor postural changes is the placement of sensors throughout the body. However, this contradicts the findings of this scoping review, where the authors predominantly placed the sensors on the upper trunk, cervical and thoracic spine, and upper limbs, alongside some studies that focused on the lumbar region or the entire body.…”

“…Wearables have emerged as a solution for the prevention of WRMSDs due to their versatility, particularly because of the real-time feedback they can provide [ 59 ]. This feedback should provide personalised information, and it is important to ensure that workers understand and adjust their posture based on the stimulus received [ 86 ].…”

Transparency as a Means to Analyse the Impact of Inertial Sensors on Users during the Occupational Ergonomic Assessment: A Systematic Review

“…It would thus be necessary to weigh the benefits of increasing user transparency (i.e., to affect their behaviour as little as possible) against the cost of receiving limited and/or reduced information [ 43 ]. On the other hand, some of the limitations of this technology could perhaps be solved thanks to promising advances in artificial intelligence, machine learning, and/or neural networks [ 72 ]. Finally, regardless of the associations exposed here between transparency and other factors, we cannot conclude whether transparency directly affects worker behaviour or the large-scale applicability of this technology.…”

Human Postures Recognition by Accelerometer Sensor and ML Architecture Integrated in Embedded Platforms: Benchmarking and Performance Evaluation

“…The data processed as described in the previous section are used to obtain the most suitable information for the identification of human postures. To this purpose, the main features in the literature developed in applications for monitoring the human posture were identified and analyzed [ 25 , 26 , 27 , 28 , 29 ]. The focus was on those achieved in the time domain in order to reduce computational cost and execution time.…”