C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

Recent developments in brain-machine interface technology have rendered seizure prediction possible. However, the transmission of a large volume of electrophysiological signals between sensors and processing apparatuses and the related computation become two major bottlenecks for seizure prediction...

Full description

Saved in:
Bibliographic Details
Main Authors: Di Wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Transactions on Neural Systems and Rehabilitation Engineering
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10012381/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849736535036919808
author Di Wu
Yi Shi
Ziyu Wang
Jie Yang
Mohamad Sawan
author_facet Di Wu
Yi Shi
Ziyu Wang
Jie Yang
Mohamad Sawan
author_sort Di Wu
collection DOAJ
description Recent developments in brain-machine interface technology have rendered seizure prediction possible. However, the transmission of a large volume of electrophysiological signals between sensors and processing apparatuses and the related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computational resources, especially for power-critical wearable and implantable medical devices. Although many data compression methods can be adopted to compress the signals to reduce communication bandwidth requirement, they require complex compression and reconstruction procedures before the signal can be used for seizure prediction. In this paper, we propose <inline-formula> <tex-math notation="LaTeX">$\text{C}^{{2}}$ </tex-math></inline-formula>SP-Net, a framework to jointly solve compression, prediction, and reconstruction without extra computation overhead. The framework consists of a plug-and-play in-sensor compression matrix to reduce transmission bandwidth requirements. The compressed signal can be utilized for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Compression and classification overhead from the energy consumption perspective, prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated using various compression ratios. The experimental results illustrate that our proposed framework is energy efficient and outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.6&#x0025; in prediction accuracy with a compression ratio ranging from 1/2 to 1/16.
format Article
id doaj-art-6afd900879d84256aa2aedc0a284c785
institution DOAJ
issn 1534-4320
1558-0210
language English
publishDate 2023-01-01
publisher IEEE
record_format Article
series IEEE Transactions on Neural Systems and Rehabilitation Engineering
spelling doaj-art-6afd900879d84256aa2aedc0a284c7852025-08-20T03:07:14ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102023-01-013184185010.1109/TNSRE.2023.323539010012381C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure PredictionDi Wu0https://orcid.org/0000-0001-6589-7136Yi Shi1Ziyu Wang2Jie Yang3https://orcid.org/0000-0002-4148-0042Mohamad Sawan4https://orcid.org/0000-0002-4137-7272College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, ChinaCenter of Excellence in Biomedical Research on Advanced Integrated-on-Chips Neurotechnologies (CenBRAIN Neurotech), School of Engineering, Westlake University, Hangzhou, ChinaCenter of Excellence in Biomedical Research on Advanced Integrated-on-Chips Neurotechnologies (CenBRAIN Neurotech), School of Engineering, Westlake University, Hangzhou, ChinaCenter of Excellence in Biomedical Research on Advanced Integrated-on-Chips Neurotechnologies (CenBRAIN Neurotech), School of Engineering, Westlake University, Hangzhou, ChinaCenter of Excellence in Biomedical Research on Advanced Integrated-on-Chips Neurotechnologies (CenBRAIN Neurotech), School of Engineering, Westlake University, Hangzhou, ChinaRecent developments in brain-machine interface technology have rendered seizure prediction possible. However, the transmission of a large volume of electrophysiological signals between sensors and processing apparatuses and the related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computational resources, especially for power-critical wearable and implantable medical devices. Although many data compression methods can be adopted to compress the signals to reduce communication bandwidth requirement, they require complex compression and reconstruction procedures before the signal can be used for seizure prediction. In this paper, we propose <inline-formula> <tex-math notation="LaTeX">$\text{C}^{{2}}$ </tex-math></inline-formula>SP-Net, a framework to jointly solve compression, prediction, and reconstruction without extra computation overhead. The framework consists of a plug-and-play in-sensor compression matrix to reduce transmission bandwidth requirements. The compressed signal can be utilized for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Compression and classification overhead from the energy consumption perspective, prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated using various compression ratios. The experimental results illustrate that our proposed framework is energy efficient and outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.6&#x0025; in prediction accuracy with a compression ratio ranging from 1/2 to 1/16.https://ieeexplore.ieee.org/document/10012381/Seizure predictionEEGconvolutional neural networkcompressive sensing (CS)hardware-friendly
spellingShingle Di Wu
Yi Shi
Ziyu Wang
Jie Yang
Mohamad Sawan
C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
IEEE Transactions on Neural Systems and Rehabilitation Engineering
Seizure prediction
EEG
convolutional neural network
compressive sensing (CS)
hardware-friendly
title C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
title_full C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
title_fullStr C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
title_full_unstemmed C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
title_short C<sup>2</sup>SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction
title_sort c sup 2 sup sp net joint compression and classification network for epilepsy seizure prediction
topic Seizure prediction
EEG
convolutional neural network
compressive sensing (CS)
hardware-friendly
url https://ieeexplore.ieee.org/document/10012381/
work_keys_str_mv AT diwu csup2supspnetjointcompressionandclassificationnetworkforepilepsyseizureprediction
AT yishi csup2supspnetjointcompressionandclassificationnetworkforepilepsyseizureprediction
AT ziyuwang csup2supspnetjointcompressionandclassificationnetworkforepilepsyseizureprediction
AT jieyang csup2supspnetjointcompressionandclassificationnetworkforepilepsyseizureprediction
AT mohamadsawan csup2supspnetjointcompressionandclassificationnetworkforepilepsyseizureprediction