English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent development in brain-machine interface technology has made seizureprediction possible. However, the communication of large volume ofelectrophysiological signals between sensors and processing apparatus andrelated computation become two major bottlenecks for seizure prediction systemsdue to the constrained bandwidth and limited computation resource, especiallyfor wearable and implantable medical devices. Although compressive sensing (CS)can be adopted to compress the signals to reduce communication bandwidthrequirement, it needs a complex reconstruction procedure before the signal canbe used for seizure prediction. In this paper, we propose C$^2$SP-Net, tojointly solve compression, prediction, and reconstruction with a single neuralnetwork. A plug-and-play in-sensor compression matrix is constructed to reducetransmission bandwidth requirement. The compressed signal can be used forseizure prediction without additional reconstruction steps. Reconstruction ofthe original signal can also be carried out in high fidelity. Predictionaccuracy, sensitivity, false prediction rate, and reconstruction quality of theproposed framework are evaluated under various compression ratios. Theexperimental results illustrate that our model outperforms the competitivestate-of-the-art baselines by a large margin in prediction accuracy. Inparticular, our proposed method produces an average loss of 0.35 % inprediction accuracy with a compression ratio ranging from 1/2 to 1/16.

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction