Donisi, Leandro (2022) Design and development of an E-textile device and a methodology for personalized and non-invasive assessment of biomechanical risk associated to manual handling. [Tesi di dottorato]

Preview

Text Donisi_Leandro_34.pdf Download (8MB) | Preview

Collection description

Recently, wearable sensors, including electronic textiles, have been developed in order to allow the assessment of human motion in several medical fields, ranging from rehabilitation medicine to ergonomics. About the latter, many activities may elicit a biomechanical overload. Among these, lifting loads can cause work-related musculoskeletal disorders. Aspiring to improve risk prevention, the National Institute for Occupational Safety and Health (NIOSH) established a methodology for assessing lifting actions by means of a quantitative method based on intensity, duration, frequency and other geometrical characteristics of lifting. Therefore these approaches are time consuming, operator dependent and costly in terms of resources. To overcome these limits, recent advances in pervasive sensing, mobile, communication technology, wearable and e-textiles have led to the deployment of new smart sensors that can be worn without affecting a person’s daily activities. These sensors are able to measure several kinematics quantities, such as acceleration, magnetic field and angular rate and biosignals such as electrocardiography and electromyography. In this thesis, a new e-textile-based system for the remote monitoring of biomedical signals is presented. The system includes a textile sensing shirt, an electronic unit for data transmission, a custom-made Android application for real-time signal visualization and a software desktop for advanced digital signal processing. The device allows for the acquisition of electrocardiographic, bicep electromyographic and trunk acceleration signals. The sensors, electrodes, and bus structures are all integrated within the textile garment, without any discomfort for users. A wide-ranging set of algorithms for signal processing were also developed for use within the system, allowing to rapidly obtain a complete and schematic overview of a worker’s status. Moreover in this thesis, the machine learning feasibility to classify biomechanical risk according to the revised NIOSH lifting equation was explored. Acceleration and EMG signals from the biceps were collected using the e-textile shirt proposed during lifting tasks performed by five subjects and further segmented to extract time-domain and frequency-domain features. The features were fed to several machine learning algorithms. Interesting results were obtained in terms of evaluation metrics for a binary risk/no risk classification. In conclusion, this study indicates the proposed combination of features and algorithms represents a valuable approach to automatically classify work activities in two NIOSH risk groups. These data confirm the potential of this methodology to assess the biomechanical risk to which subjects are exposed during their work activity. Future investigation on enriched study population will be able to confirm the potentiality of this methodology in the biomechanical risk assessment.

Downloads

Actions (login required)

View Item