Adaptive cognitive sensor nodes for the internet of medical things

The Internet of Medical Things (IoMT) paradigm is becoming mainstream in multiple clinical trials and healthcare procedures. It relies on novel, very accurate and compact sensing devices, network and communication infrastructures, opening previously unmatched possibilities of implementing data collection and continuous patient monitoring. Nevertheless, to fully exploit the potential of IoMT, some steps forward are needed. First, the edge-computing paradigm must be added to the picture. A certain level of near-sensor processing has to be enabled, to improve the scalability, portability, reliability and responsiveness of the IoMT nodes. Second, novel, increasingly accurate data analysis algorithms, such as those based on artificial intelligence and deep learning, must be exploited. To reach these objectives, designers, and programmers of IoMT nodes, have to face challenging optimization tasks, in order to execute fairly complex computing processes on low-power wearable and portable processing systems, with tight power and battery lifetime budgets. In this thesis, the implementation on resource-constrained computing platforms of a cognitive data analysis algorithm based on a convolutional neural network was explored. The treatment of cardiovascular disease and fitness tracking were chosen as use cases within the IoMT context to validate our approach. To minimize power consumption, an adaptivity layer has been added, the latter dynamically manages the hardware and software configuration of the device to adapt it at runtime to the required operating mode. The experimental results show that adapting the node setup to the workload at runtime can save up to 60% power consumption. The optimized and quantized neural network reaches an accuracy value higher than 97% for arrhythmia disorders detection and more than 97% for detecting some specific physical exercises on a wobble board.