Alireza Amirshahi, Matin Hashemi, "ECG Classification Algorithm Based on STDP and R-STDP Neural Networks for Real-time Monitoring on Ultra Low-Power Personal Wearable Devices", IEEE Transactions on Biomedical Circuits and Systems (TBioCAS), Vol. 13, No. 6, December 2019.
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 uJ per beat, which is 2 to 9 orders of magnitude smaller than previous neural network based ECG classification methods.
The source code is available from this link.
Contact a.amirshahi37@gmail.com or matin@sharif.edu in case you have any questions regarding the source code.
Use the following entry to cite our work in your publications:
@article{amirshahi2019tbiocas,
author = {Alireza Amirshahi and Matin Hashemi},
title = {ECG Classification Algorithm Based on STDP and R-STDP Neural Networks for Real-time Monitoring on Ultra Low-Power Personal Wearable Devices},
journal = {IEEE Transactions on Biomedical Circuits and Systems (TBioCAS)},
year = {2019},
month = {December},
volume = {13},
number = {6},
pages = {1483-1493},
doi = {10.1109/TBCAS.2019.2948920}
}