Key result
Machine-learning edge monitoring cuts energy use ~70% vs maximum settings for ECG and EEG.
Why the study?
Previous works on task offloading for generic edge computing and machine learning did not consider application-specific parameters such as sampling rate, measurement duration, and number of input channels or leads for wearable sensor continuous monitoring.
Effect estimate: up to 70% energy savings
The proposed energy-efficient machine learning approach for continuous edge monitoring can significantly reduce energy consumption for wearable ECG and EEG sensors.
May extend continuous wearable ECG/EEG monitoring; leaves open prospective clinical validation.
In this paper, we propose an energy-efficient approach for machine-learning based continuous testing and monitoring of long-term patients at the wireless edge. The approach is applicable for any wearable sensors that generate time-series data. Our scheme simultaneously performs sensor-server clustering while ensuring the delay requirements of every user are met. In contrast to previous works on task offloading for generic edge computing/machine learning, our proposed model considers application specific parameters including the sampling rate, measurement duration and number of input channels/leads. We formulate the problem as a mixed integer nonlinear program (MINLP) and propose a heuristic solution. Two applications, cardiac event prediction from a wearable electrocardiograms (ECG), and epileptic seizure prediction from wearable scalp electroencephalography (EEG) are used to demonstrate the superiority of the proposed approach. Results indicate that our proposed algorithm can provide up-to 70% energy savings compared to the case when maximum settings are used.
No takes yet. Share an insight, caveat, or question.
Mohammad et al. (2023) studied Cardiac events and epileptic seizures. Energy-efficient machine-learning based continuous monitoring algorithm vs. Maximum settings was evaluated on Energy savings (up to 70% energy savings). An energy-efficient machine-learning algorithm for continuous edge monitoring provided up to 70% energy savings compared to maximum settings for ECG and EEG applications.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: