SPECTRE: a deep learning network for posture recognition in manufacturing

Work-related musculoskeletal disorders are a very impactful problem, both socially and economically, in the manufacturing sector. To control their effect, standardised methods and technologies for ergonomic assessment have been developed. The main technologies used are inertial sensors and vision-based systems. The former are accurate and reliable, but invasive and not affordable for many companies. The latter use machine learning algorithms to detect human pose and assess ergonomic risks. In this paper, using data collecting by reproducing the working environment in LUBE, the major Italian kitchen manufacturer, we propose SPECTRE (Sensor-independent Parallel dEep ConvoluTional leaRning nEtwork): a fully sensor-independent learning model based on convolutional networks to classify postures in the workplace. This system assesses ergonomic risks in major body segments through Deep Learning with a minimal impact. SPECTRE's performance is evaluated using established metrics for imbalanced data (precision, recall, F1-score and area under the precision-recall curve). Overall, SPECTRE shows good performance and, thanks to an agnostic explainable machine learning method, is able to extrapolate which patterns are significant in the input.