FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310332690> ?p ?o ?g. }

• W4310332690 endingPage "1856" @default.
• W4310332690 startingPage "1845" @default.
• W4310332690 abstract "The monitoring of epilepsy patients in non-hospital environment is highly desirable, where ultra-low power wearable seizure detection devices are essential in such a system. The state-of-the-art epileptic seizure detection algorithms targeting such devices either rely on manual feature extractions, which can be biased due to the experience of experts, or deep neural networks, which suffer from high computation complexity. In this paper, we propose a lightweight deep learning model, LightSeizureNet (LSN), for real-time epileptic seizure detection based on raw EEG data in ultra-low power wearable seizure detection devices. The proposed LSN model includes a patient-independent version and a patient-specific version, both of which avoids manual feature extractions and high computation complexity, while maintaining good classification accuracy. Dilated one-dimensional (1D) convolution, global average pooling, and kernel-wise pruning are adopted to compress the LSN model. The proposed models are evaluated on the CHB-MIT scalp EEG database. The patient-independent LSN model achieves 97.09% accuracy with 6.2M MACs, while the patient-specific LSN model achieves 99.77% accuracy with 3.7 M MACs, which are competitive compared to the state of the art in terms of accuracy and complexity. Furthermore, the proposed model is highly interpretable, which is missing in many previous works. By using a uniform approach to explore the interpretability of the proposed model, fine-grained information such as the activated brain region and the frequency of brainwave during seizures is obtained for clinical diagnosis." @default.
• W4310332690 created "2022-12-08" @default.
• W4310332690 creator A5018393711 @default.
• W4310332690 creator A5022639653 @default.
• W4310332690 creator A5042636120 @default.
• W4310332690 date "2023-04-01" @default.
• W4310332690 modified "2023-10-17" @default.
• W4310332690 title "LightSeizureNet: A Lightweight Deep Learning Model for Real-Time Epileptic Seizure Detection" @default.
• W4310332690 cites W2001922685 @default.
• W4310332690 cites W2005791255 @default.
• W4310332690 cites W2012383929 @default.
• W4310332690 cites W2021970732 @default.
• W4310332690 cites W2050637571 @default.
• W4310332690 cites W2088432928 @default.
• W4310332690 cites W2102244548 @default.
• W4310332690 cites W2119234283 @default.
• W4310332690 cites W2142181855 @default.
• W4310332690 cites W2158468574 @default.
• W4310332690 cites W2276892413 @default.
• W4310332690 cites W2295107390 @default.
• W4310332690 cites W2329051445 @default.
• W4310332690 cites W2418090813 @default.
• W4310332690 cites W2568407436 @default.
• W4310332690 cites W2592285721 @default.
• W4310332690 cites W2593873339 @default.
• W4310332690 cites W2776446922 @default.
• W4310332690 cites W2789800602 @default.
• W4310332690 cites W2790567680 @default.
• W4310332690 cites W2790950056 @default.
• W4310332690 cites W2795691199 @default.
• W4310332690 cites W2890956351 @default.
• W4310332690 cites W2903709507 @default.
• W4310332690 cites W2907284364 @default.
• W4310332690 cites W2917354916 @default.
• W4310332690 cites W2932763761 @default.
• W4310332690 cites W2965277555 @default.
• W4310332690 cites W2973010960 @default.
• W4310332690 cites W2980823296 @default.
• W4310332690 cites W2997300524 @default.
• W4310332690 cites W3005778357 @default.
• W4310332690 cites W3007289630 @default.
• W4310332690 cites W3020080361 @default.
• W4310332690 cites W3023066741 @default.
• W4310332690 cites W3036629615 @default.
• W4310332690 cites W3080378203 @default.
• W4310332690 cites W3119307757 @default.
• W4310332690 cites W3119640139 @default.
• W4310332690 cites W3129434311 @default.
• W4310332690 cites W3135997330 @default.
• W4310332690 cites W3153903265 @default.
• W4310332690 cites W3156889579 @default.
• W4310332690 cites W3177432079 @default.
• W4310332690 cites W4210753840 @default.
• W4310332690 cites W4214850322 @default.
• W4310332690 cites W4248307879 @default.
• W4310332690 cites W2108087301 @default.
• W4310332690 cites W2136030102 @default.
• W4310332690 doi "https://doi.org/10.1109/jbhi.2022.3223970" @default.
• W4310332690 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36417737" @default.
• W4310332690 hasPublicationYear "2023" @default.
• W4310332690 type Work @default.
• W4310332690 citedByCount "2" @default.
• W4310332690 countsByYear W43103326902023 @default.
• W4310332690 crossrefType "journal-article" @default.
• W4310332690 hasAuthorship W4310332690A5018393711 @default.
• W4310332690 hasAuthorship W4310332690A5022639653 @default.
• W4310332690 hasAuthorship W4310332690A5042636120 @default.
• W4310332690 hasConcept C108010975 @default.
• W4310332690 hasConcept C108583219 @default.
• W4310332690 hasConcept C114614502 @default.
• W4310332690 hasConcept C119857082 @default.
• W4310332690 hasConcept C138885662 @default.
• W4310332690 hasConcept C149635348 @default.
• W4310332690 hasConcept C150594956 @default.
• W4310332690 hasConcept C153180895 @default.
• W4310332690 hasConcept C154945302 @default.
• W4310332690 hasConcept C169760540 @default.
• W4310332690 hasConcept C2776401178 @default.
• W4310332690 hasConcept C2778186239 @default.
• W4310332690 hasConcept C2779334592 @default.
• W4310332690 hasConcept C2781067378 @default.
• W4310332690 hasConcept C33923547 @default.
• W4310332690 hasConcept C41008148 @default.
• W4310332690 hasConcept C41895202 @default.
• W4310332690 hasConcept C45347329 @default.
• W4310332690 hasConcept C50644808 @default.
• W4310332690 hasConcept C52622490 @default.
• W4310332690 hasConcept C6557445 @default.
• W4310332690 hasConcept C74193536 @default.
• W4310332690 hasConcept C81363708 @default.
• W4310332690 hasConcept C86803240 @default.
• W4310332690 hasConceptScore W4310332690C108010975 @default.
• W4310332690 hasConceptScore W4310332690C108583219 @default.
• W4310332690 hasConceptScore W4310332690C114614502 @default.
• W4310332690 hasConceptScore W4310332690C119857082 @default.
• W4310332690 hasConceptScore W4310332690C138885662 @default.
• W4310332690 hasConceptScore W4310332690C149635348 @default.
• W4310332690 hasConceptScore W4310332690C150594956 @default.

• next