Special Issue on Wearable Computing and Machine Learning for Applications in Sports, Health, and Medical Engineering

Recent advancement in digital technologies is driving a remarkable transformation in sports, health, and medical engineering, aiming to achieve the accurate quantification of performance, well-being, and disease condition, and the optimization of sports, clinical, and therapeutic training and treatment programs. Traditionally, understanding and monitoring of functional performance and capacity has been performed in gait laboratories based on optoelectronic motion capture systems. However, gait laboratories in practical settings are often not readily available because the systems are costly and require trained experts to operate. Most importantly, when assessments are restricted to laboratory settings, they provide a narrow snapshot of function and do not capture functionality in natural free-living settings, thus representing a severely under-sampled view of an individual’s condition. The use of mobile and wearable technologies has been explored in many sports, health, and medical research studies examining individuals in “in-the-wild” settings. Among the most important drivers of this transformation are (1) wearable sensors and (2) signal processing and machine learning algorithms. Wearable sensors are capable of collecting physical and/or physiological data continuously and seamlessly outside of laboratory settings. Signal processing and machine learning algorithms allow data-driven approaches for analyzing considerable amounts of multidimensional sensory data and for extracting important information relevant to the mentioned application areas (e.g., validating the efficacy of sports training, health benefits, and chronic disease progression). These technologies together would support how sports and clinical professionals understand and interpret individuals’ performance more objectively, and enable proactive, evidence-based, and personalized management systems.