**1. Introduction**

Quantifying human movement characteristics can provide a significant foundation for enabling optimized rehabilitation therapy, for which the advent of wearable and wireless inertial sensor systems provides considerable opportunity [1–12]. The quantification of inertial sensor systems have been proposed for the measurement and quantification of human movement characteristics since approximately the mid-20th century. However, sufficient miniaturization and reliability regarding that timeframe had not been achieved for associated biomedical applications [11–15]. Motivating research, development, testing, and evaluation for the evolution of inertial sensors derived from industries extrinsic relative to the biomedical field, such as the automotive industry for regulation of airbag deployment [11–13, 15]. Upon the achievement of a sufficient threshold

for miniaturization and reliability these inertial sensors have been successfully applied to numerous human movement scenarios, such as the quantification of reflex, gait, and movement disorder. Furthermore, these inertial sensors were noted as functionally wearable with wireless in capability, which ushered the presence of wearable and wireless inertial sensor systems for quantifying human movement [1–12]. A historical and evolutionary perspective leading to the amalgamation of inertial sensors that are functionally wearable with wireless connectivity to Cloud computing resources in conjunction with machine learning classification as an advanced post-processing technique, which is known as Network Centric Therapy, for the biomedical domain is presented.
