FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220912912> ?p ?o ?g. }

• W4220912912 endingPage "109557" @default.
• W4220912912 startingPage "109557" @default.
• W4220912912 abstract "Early prediction of epilepsy seizures can warn the patients to take precautions and improve their lives significantly. In recent years, deep learning has become increasingly predominant in seizure prediction for its outstanding performance. With the aim of predicting unseen seizures, it is essential to guarantee the generalization ability of the model, especially considering the non-stationary nature of EEG and the scarcity of seizure events in EEG recordings. Stability training against extra perturbations is an intuitive and effective way to improve the model's ability to generalize. Though a great number of deep learning methods have been developed for seizure prediction, their strategies to increase generalization performance focus on improving the model's architecture itself, and few of them pay attention to the stability of the model against small perturbations.In this study, we propose a novel consistency-based training strategy to address this issue. The proposed strategy underlines that a robust model should maintain consistent results for the same input under extra perturbations. Specifically, during training, we use stochastic augmentations to make the input vary from iteration to iteration and consider the output as a stochastic variable. Then a consistency constraint is constructed to penalize the difference between the current output and previous outputs. In this way, the generalization ability of the model will be fully enhanced.To better verify the effectiveness of our proposed strategy, we implement it in two state-of-the-art models with public-available codes, including STFT CNN and Multi-view CNN. Notably, we compare with the first baseline on a scalp EEG dataset and the other on an intracranial EEG dataset. The results show that our strategy could improve the performance significantly for both of them.Our strategy has increased the sensitivity by 7.1% and reduced the false prediction rate by 0.12/h on the first baseline while improving the AUC by 0.020 on the second baseline.This study is easy to implement, providing a new solution to enhance the performance of seizure prediction." @default.
• W4220912912 created "2022-04-03" @default.
• W4220912912 creator A5017511779 @default.
• W4220912912 creator A5027835055 @default.
• W4220912912 creator A5069334991 @default.
• W4220912912 creator A5077155065 @default.
• W4220912912 creator A5083857025 @default.
• W4220912912 date "2022-04-01" @default.
• W4220912912 modified "2023-09-25" @default.
• W4220912912 title "A novel consistency-based training strategy for seizure prediction" @default.
• W4220912912 cites W1989915444 @default.
• W4220912912 cites W2004685246 @default.
• W4220912912 cites W2025668297 @default.
• W4220912912 cites W2088222765 @default.
• W4220912912 cites W2119705365 @default.
• W4220912912 cites W2162800060 @default.
• W4220912912 cites W2317674142 @default.
• W4220912912 cites W2342045095 @default.
• W4220912912 cites W2465455179 @default.
• W4220912912 cites W2758802379 @default.
• W4220912912 cites W2780723646 @default.
• W4220912912 cites W2799610518 @default.
• W4220912912 cites W2888598199 @default.
• W4220912912 cites W2896164972 @default.
• W4220912912 cites W2967087414 @default.
• W4220912912 cites W2976267777 @default.
• W4220912912 cites W2980065969 @default.
• W4220912912 cites W2992904850 @default.
• W4220912912 cites W2998508940 @default.
• W4220912912 cites W3002954434 @default.
• W4220912912 cites W3042619474 @default.
• W4220912912 cites W3109672150 @default.
• W4220912912 cites W3138797496 @default.
• W4220912912 cites W3160746195 @default.
• W4220912912 cites W3166792421 @default.
• W4220912912 cites W877297219 @default.
• W4220912912 doi "https://doi.org/10.1016/j.jneumeth.2022.109557" @default.
• W4220912912 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35276242" @default.
• W4220912912 hasPublicationYear "2022" @default.
• W4220912912 type Work @default.
• W4220912912 citedByCount "3" @default.
• W4220912912 countsByYear W42209129122022 @default.
• W4220912912 countsByYear W42209129122023 @default.
• W4220912912 crossrefType "journal-article" @default.
• W4220912912 hasAuthorship W4220912912A5017511779 @default.
• W4220912912 hasAuthorship W4220912912A5027835055 @default.
• W4220912912 hasAuthorship W4220912912A5069334991 @default.
• W4220912912 hasAuthorship W4220912912A5077155065 @default.
• W4220912912 hasAuthorship W4220912912A5083857025 @default.
• W4220912912 hasConcept C108583219 @default.
• W4220912912 hasConcept C112972136 @default.
• W4220912912 hasConcept C118552586 @default.
• W4220912912 hasConcept C119857082 @default.
• W4220912912 hasConcept C134306372 @default.
• W4220912912 hasConcept C154945302 @default.
• W4220912912 hasConcept C15744967 @default.
• W4220912912 hasConcept C169760540 @default.
• W4220912912 hasConcept C177148314 @default.
• W4220912912 hasConcept C2524010 @default.
• W4220912912 hasConcept C2776036281 @default.
• W4220912912 hasConcept C2776436953 @default.
• W4220912912 hasConcept C2778186239 @default.
• W4220912912 hasConcept C2779334592 @default.
• W4220912912 hasConcept C33923547 @default.
• W4220912912 hasConcept C41008148 @default.
• W4220912912 hasConcept C50644808 @default.
• W4220912912 hasConcept C522805319 @default.
• W4220912912 hasConcept C5465570 @default.
• W4220912912 hasConceptScore W4220912912C108583219 @default.
• W4220912912 hasConceptScore W4220912912C112972136 @default.
• W4220912912 hasConceptScore W4220912912C118552586 @default.
• W4220912912 hasConceptScore W4220912912C119857082 @default.
• W4220912912 hasConceptScore W4220912912C134306372 @default.
• W4220912912 hasConceptScore W4220912912C154945302 @default.
• W4220912912 hasConceptScore W4220912912C15744967 @default.
• W4220912912 hasConceptScore W4220912912C169760540 @default.
• W4220912912 hasConceptScore W4220912912C177148314 @default.
• W4220912912 hasConceptScore W4220912912C2524010 @default.
• W4220912912 hasConceptScore W4220912912C2776036281 @default.
• W4220912912 hasConceptScore W4220912912C2776436953 @default.
• W4220912912 hasConceptScore W4220912912C2778186239 @default.
• W4220912912 hasConceptScore W4220912912C2779334592 @default.
• W4220912912 hasConceptScore W4220912912C33923547 @default.
• W4220912912 hasConceptScore W4220912912C41008148 @default.
• W4220912912 hasConceptScore W4220912912C50644808 @default.
• W4220912912 hasConceptScore W4220912912C522805319 @default.
• W4220912912 hasConceptScore W4220912912C5465570 @default.
• W4220912912 hasLocation W42209129121 @default.
• W4220912912 hasLocation W42209129122 @default.
• W4220912912 hasOpenAccess W4220912912 @default.
• W4220912912 hasPrimaryLocation W42209129121 @default.
• W4220912912 hasRelatedWork W3014300295 @default.
• W4220912912 hasRelatedWork W3099765033 @default.
• W4220912912 hasRelatedWork W3164822677 @default.
• W4220912912 hasRelatedWork W4223943233 @default.
• W4220912912 hasRelatedWork W4225161397 @default.
• W4220912912 hasRelatedWork W4250304930 @default.
• W4220912912 hasRelatedWork W4299487748 @default.

• next