Ultra Low Power Programmable Wireless ExG SoC Design for IoT Healthcare System

Adimulam, Mahesh Kumar; Srinivas, M.B.

doi:10.1007/978-3-319-98551-0_5

Cited by 6 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In some works proposed in the literature dealing with ECG signal monitoring, local processing is used only for implementing easy checks on raw data and/or marshaling tasks for wrapping the sensed data inside standard communication protocols [26]- [29]. On the other hand, there are numerous works in the literature that exploit cognitive computing for CVD detection, even at the edge.…”

Section: Related Workmentioning

confidence: 99%

An Adaptive Cognitive Sensor Node for ECG Monitoring in the Internet of Medical Things

et al. 2022

View full text Add to dashboard Cite

The Internet of Medical Things (IoMT) paradigm is becoming mainstream in multiple clinical trials and healthcare procedures. Cardiovascular diseases monitoring, usually involving electrocardiogram (ECG) traces analysis, is one of the most promising and high-impact applications. Nevertheless, to fully exploit the potential of IoMT in this domain, some steps forward are needed. First, the edgecomputing 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 tasks on low-power wearable and portable processing systems, with tight power and battery lifetime budgets. In this work, we explore the implementation of a cognitive data analysis algorithm, based on a convolutional neural network trained to classify ECG waveforms, on a resource-constrained microcontroller-based computing platform. To minimize power consumption, we add an adaptivity layer that dynamically manages the hardware and software configuration of the device to adapt it at runtime to the required operating mode. Our experimental results show that adapting the node setup to the workload at runtime can save up to 50% power consumption. Our optimized and quantized neural network reaches an accuracy value higher than 97% for arrhythmia disorders detection on MIT-BIH Arrhythmia dataset. INDEX TERMSAdaptive system, health information management, Internet of Things, low power electronics, neural network, remote sensing, runtime, wearable sensors.

show abstract

Section: Related Workmentioning

confidence: 99%

An Adaptive Cognitive Sensor Node for ECG Monitoring in the Internet of Medical Things

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Local processing is frequently used only for implementing simple checks on raw data and/or marshaling tasks for wrapping sensed data inside standard communication protocols, and the edge-computing paradigm is only marginally exploited [3,4,5]. More complex and accurate algorithms, such as those based on artificial intelligence or deep learning, must be targeted in order to properly use cognitive computing at the edge.…”

Section: Related Workmentioning

confidence: 99%

An adaptable cognitive microcontroller node for fitness activity recognition

Scrugli¹,

Blažica²,

Meloni³

2022

Preprint

View full text Add to dashboard Cite

The new generation of wireless technologies, fitness trackers, and devices with embedded sensors can have a big impact on healthcare systems and quality of life. Among the most crucial aspects to consider in these devices are the accuracy of the data produced and power consumption. Many of the events that can be monitored, while apparently simple, may not be easily detectable and recognizable by devices equipped with embedded sensors, especially on devices with low computing capabilities. It is well known that deep learning reduces the study of features that contribute to the recognition of the different target classes. In this work, we present a portable and battery-powered microcontroller-based device applicable to a wobble board. Wobble boards are low-cost equipment that can be used for sensorimotor training to avoid ankle injuries or as part of the rehabilitation process after an injury. The exercise recognition process was implemented through the use of cognitive techniques based on deep learning. To reduce power consumption, we add an adaptivity layer that dynamically manages the device's hardware and software configuration to adapt it to the required operating mode at runtime. Our experimental results show that adjusting the node configuration to the workload at runtime can save up to 60% of the power consumed. On a custom dataset, our optimized and quantized neural network achieves an accuracy value greater than 97% for detecting some specific physical exercises on a wobble board.

show abstract

“…Many of these IoMT devices, whether commercial or not, provide days or weeks of autonomy [8,9]. However, few systems propose to move the processing task directly to the node, which is used only for the transmission of the raw signals sampled by the sensor [10][11][12][13]. The use of artificial intelligence is gaining momentum in many areas, often used because of the simplicity of implementation and the high accuracy potentially offered by these techniques.…”

Section: Related Workmentioning

confidence: 99%

Runtime Adaptive IoMT Node on Multi-Core Processor Platform

Scrugli

Meloni

et al. 2021

Electronics

View full text Add to dashboard Cite

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.

show abstract

Ultra Low Power Programmable Wireless ExG SoC Design for IoT Healthcare System

Cited by 6 publications

References 11 publications

An Adaptive Cognitive Sensor Node for ECG Monitoring in the Internet of Medical Things

An Adaptive Cognitive Sensor Node for ECG Monitoring in the Internet of Medical Things

An adaptable cognitive microcontroller node for fitness activity recognition

Runtime Adaptive IoMT Node on Multi-Core Processor Platform

Contact Info

Product

Resources

About