Loading...

ECG classification algorithm based on STDP and R-STDP neural networks for real-time monitoring on ultra low-power personal wearable devices

Amirshahi, A ; Sharif University of Technology | 2021

524 Viewed
  1. Type of Document: Article
  2. DOI: 10.1109/TBCAS.2019.2948920
  3. Publisher: Institute of Electrical and Electronics Engineers Inc , 2021
  4. Abstract:
  5. This paper presents a novel ECG classification algorithm for inclusion as part of real-time cardiac monitoring systems in ultra low-power wearable devices. The proposed solution is based on spiking neural networks which are the third generation of neural networks. In specific, we employ spike-timing dependent plasticity (STDP), and reward-modulated STDP (R-STDP), in which the model weights are trained according to the timings of spike signals, and reward or punishment signals. Experiments show that the proposed solution is suitable for real-time operation, achieves comparable accuracy with respect to previous methods, and more importantly, its energy consumption in real-time classification of ECG signals is significantly smaller. In specific, energy consumption is 1.78 µJ per beat, which is 2 to 9 orders of magnitude smaller than previous neural network based ECG classification methods. © 2019 IEEE
  6. Keywords:
  7. Embedded systems ; Energy utilization ; Interactive computer systems ; Learning algorithms ; Low power electronics ; Real time systems ; Supervised learning ; Wearable technology ; Cardiac monitoring ; Classification algorithm ; Electrocardiogram classification ; Embedded real time systems ; Lower-power consumption ; Neural-networks ; Spike timing dependent plasticities ; Spiking neural network ; Wearable devices ; Neural networks ; Algorithm ; Biological model ; Computer system ; Devices ; Electronic device ; Human ; Nerve cell plasticity ; Algorithms ; Computer Systems ; Electrocardiography ; Humans ; Models, Neurological ; Neural Networks, Computer ; Neuronal Plasticity ; Wearable Electronic Devices
  8. Source: IEEE Transactions on Biomedical Circuits and Systems ; Volume 13, Issue 6 , 2021 , Pages 1483-1493 ; 19324545 (ISSN)
  9. URL: https://ieeexplore.ieee.org/document/8879613