Enabling technologies for Human-centered Industry 4.0 and Healthcare 4.0

Industry 4.0 has transformed the manufacturing industry into a new paradigm causing numerous changes in the models of business and process automation. The profound change in the context of production has brought the issue of efficiency. Some of the key technologies that emerged to tackle this issue are Big Data, Internet of Things (IoT), Digital Twins, Artificial Intelligence, Machine Learning, Augmented Reality and Additive Manufacturing. This revolution has not remained within the borders of the manufacturing field but it pushes changes in a lot of fields; in particular, it has introduced health care delivery to the dawn of a foundational change into the new era of smart and connected health care, referred to as Healthcare 4.0. Although automation and assistance technologies are becoming more prevalent in production and logistics, there is consensus that humans remain an essential part of operations systems bringing to the definition of Human-centered Industry 4.0. Nevertheless, human factors are still underrepresented in the research stream resulting in an important research and application gap. This Ph.D. thesis proposes a set of innovative work-flows for real systems based on enabling technologies of Industry 4.0 and Healthcare 4.0 that can enhance and complement the human in manufacturing and healthcare. The work is trying to fill a portion of the gap between research and application concerning the Human factor in Industry 4.0 and propose new solutions that increase efficacy, flexibility and cost-effectiveness of healthcare services focusing especially on movement disorders rehabilitation. This thesis is composed of four chapters. The first Chapter provides an introduction to the reference context. Chapter 2 describes the state of the art of Industry 4.0, its challenges and technologies with a focus on the Human factor and reports the contribution of the usage of Industry 4.0 enabling technologies to provide new solutions for maintenance training, process quality assessment and bio-mechanical risk detection. Chapter 3 introduces the Healthcare 4.0 going into detail about new rehabilitation protocols for movement disorders; it shows work for signal processing, focusing on the application of undercomplete autoencoders for surface electromyography analysis and evaluation of cueing technique efficacy for Parkinson's Disease rehabilitation. The study cases and the contributions reported in this thesis were always compared with standard techniques. Finally, the conclusions about the research works and future research propose.