Abstract
The Internet of Medical Things (IoMT) paradigm is becoming mainstream in multiple clinical trials and healthcare procedures. Thanks to innovative technologies, latest-generation communication networks, and state-of-the-art portable devices, IoTM opens up new scenarios for data collection and continuous patient monitoring. Two very important aspects should be considered to make the most of this paradigm. For the first aspect, moving the processing task from the cloud to the edge leads to several advantages, such as responsiveness, portability, scalability, and reliability of the sensor node. For the second aspect, in order to increase the accuracy of the system, state-of-the-art cognitive algorithms based on artificial intelligence and deep learning must be integrated. Sensory nodes often need to be battery powered and need to remain active for a long time without a different power source. Therefore, one of the challenges to be addressed during the design and development of IoMT devices concerns energy optimization. Our work proposes an implementation of cognitive data analysis based on deep learning techniques on resource-constrained computing platform. To handle power efficiency, we introduced a component called Adaptive runtime Manager (ADAM). This component takes care of reconfiguring the hardware and software of the device dynamically during the execution, in order to better adapt it to the workload and the required operating mode. To test the high computational load on a multi-core system, the Orlando prototype board by STMicroelectronics, cognitive analysis of Electrocardiogram (ECG) traces have been adopted, considering single-channel and six-channel simultaneous cases. Experimental results show that by managing the sensory node configuration at runtime, energy savings of at least 15% can be achieved.
Highlights
The generation of biomedical devices is making great strides in the scientific community
We have used them to manage communication and synchronization between the Digital Signal Processors (DSPs) in the platform and to manage the operating state of the processing elements, setting to sleep mode those that are stalled on input, or output channels, or that are not assigned with a task
We show the results obtained with the proposed extension of Adaptive runtime Manager (ADAM) for multi-core platforms, and in particular, considering the Orlando board from STMicroelectronics [20]
Summary
The generation of biomedical devices is making great strides in the scientific community. If applied in a domestic environment, in addition to greatly improving communication between the patient and the healthcare provider, it is possible to significantly reduce public medical costs. In the literature, some critical points are being widely questioned, and alternative solutions are being proposed to improve aspects concerning: responsiveness, scalability, privacy, and security. In Reference [2], it is shown how proprietary IoT device solutions can be weak from a privacy and security standpoint. It is demonstrated how a collaborative IoT network can lead to greater resistance to malicious attacks or how the use of end-to-end encryption methods prevents man-in-the-middle attacks. Reference [2] discusses how the fusion of on-edge cognitive processing and the potentialities related to IoT networks brings numerous benefits in terms of robustness in contrasting environmental changes, responsiveness, human intervention reduction, and lower energy consumption
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
