Abstract
In this paper, two different classifiers are software and hardware implemented for neural seizure detection. The two techniques are support vector machine(SVM) and artificial neural networks(ANN). The two techniques are pretrained on software and only the classifiers are hardware implemented and tested. A comparison of the two techniques is performed on the levels of performance, energy consumption and area. The SVM is pretrained using gradient ascent (GA) algorithm, while the neural network is implemented with single hidden layer. It is found that the ANN consumes more power than the SVM by a factor of 4 with almost the same performance. However, the ANN finishes classification in much less number of clock cycles than the SVM by a factor of 34.
Original language | English (US) |
---|---|
Title of host publication | 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS) |
Publisher | IEEE |
Pages | 646-649 |
Number of pages | 4 |
ISBN (Print) | 9781728127880 |
DOIs | |
State | Published - Oct 31 2019 |
Bibliographical note
KAUST Repository Item: Exported on 2020-10-01Acknowledgements: This work was partially funded by ONE Lab at Zewail City of Science and Technology and Cairo University, NTRA, ITIDA, ASRT, Mentor Graphics, NSERC.