Search: onr:"swepub:oai:DiVA.org:mdh-55485" >
ELC-ECG :
ELC-ECG : Efficient LSTM cell for ECG classification based on quantized architecture
-
- Sinaei, Sima (author)
- Mälardalens universitet,Inbyggda system
-
- Nazari, N. (author)
- School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
-
- Ansarmohammadi, S. A. (author)
- School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
-
show more...
-
- Sinaei, Sima (author)
- Mälardalens universitet,Inbyggda system
-
- Salehi, M. E. (author)
- School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran
-
- Daneshtalab, Masoud (author)
- Mälardalens högskola, Inbyggda system,Mälardalen University, Sweden; Tallinn University of Technology, Estonia
-
show less...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers Inc. 2021
- 2021
- English.
-
In: Proceedings - IEEE International Symposium on Circuits and Systems. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728192017 ; May
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- Long Short-Term Memory (LSTM) is one of the most popular and effective Recurrent Neural Network (RNN) models used for sequence learning in applications such as ECG signal classification. Complex LSTMs could hardly be deployed on resource-limited bio-medical wearable devices due to the huge amount of computations and memory requirements. Binary LSTMs are introduced to cope with this problem. However, naive binarization leads to significant accuracy loss in ECG classification. In this paper, we propose an efficient LSTM cell along with a novel hardware architecture for ECG classification. By deploying 5-level binarized inputs and just 1-level binarization for weights, output, and in-memory cell activations, the delay of one LSTM cell operation is reduced 50x with about 0.004% accuracy loss in comparison with full precision design of ECG classification.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Keyword
- Electrocardiogram (ECG) Signal Classification
- Long Short -Term Memory (LSTM)
- Wearable Devices
- Cells
- Cytology
- Electrocardiography
- Memory architecture
- Network architecture
- Cell operation
- Ecg classifications
- Memory requirements
- Novel hardware
- Precision design
- Recurrent neural network (RNN)
- Sequence learning
- Long short-term memory
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database