Wearable-sensors Based Activity Recognition for Smart Human Healthcare Using Internet of Things

With the growing of chronic diseases, strain on public healthcare systems becomes a critical problem of our society. Internet of Things (IoT) technology [1]-[3], as a hot topic, has attracted more and more attention recently due to its potential ability to reduce the strain on public healthcare systems. In IoT based healthcare system, the information of patients can be automatically obtained via various sensors and the physical condition of patients can be analyzed via those obtained data. In this work, we present a IoT and blockchain based healthcare system for human activity recognition via monitoring vital/non-vital signals collected from wearable-sensors remotely. On the one hand, the IoT technology is used for data acquisition and transmission [4]. On the other hand, the blockchain technology is used for data encryption. An incremental learning strategy based on covariance matrix is designed to recognize the activity done by a patient under care and determine whether there is an emergency for the patient under care. In such a manner, necessary feedback or programmable alarms can be made during or after the activity.