Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380590372> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4380590372 abstract "<p>The paper explores how deep LSTM and deep spiking neural networks (SNN) can be used to extract meaningful features from spatio-temporal EEG brain data for early, on-line diagnosis. It introduces a new online spike encoding algorithm for Izhikevich neural networks and new methods for learning and diagnostic biomarker discovery for each of the three most popular deep learning neural network models, namely: deep BiLSTM; reservoir SNN; and NeuCube. The methods reveal that hidden neurons in a BiLSTM can capture biological meaning, while a reservoir SNN neuron activities and the spiking activities in a NeuCube model can be used to discover EEG channels that can be utilized as brain biomarkers. The study used EEG data from three datasets related to epileptic-, migraine- and healthy subjects. The problem of discriminating epilepsy from migraine using EEG data is a well known hard problem. LSTM and a reservoir SNN achieved 90% and 85% classification accuracy correspondingly and indicated that channels F8, T3,T’6 and F7,T6 correspondingly can be explored as potential biomarkers, while a NeuCube model achieved 97% with T6, F7 and also C4 and F8 as potential biomarkers for a better classification. In addition, a 2 class NeuCube model discriminated perfectly well epilepsy from migraine and pointing to two channels C4 and F8 as potential biomarkers for the task. While all models resulted in a good classification and feature selected, the main reason for the superior performance of NeuCube is its brain-inspired architecture, where a brain map is used to structure a 3D SNN model to capture deep spatio-temporal dynamics from EEG data. This research has important implications for the development of more effective algorithms for on-line EEG classification, analysis and early brain state diagnosis, adding new features of <em>explainability</em> and <em>discovery</em> to otherwise effective AI models. The proposed methods and findings can be used for the development of more efficient brain-computer interfaces and for clinical practice. </p>" @default.
- W4380590372 created "2023-06-15" @default.
- W4380590372 creator A5024893012 @default.
- W4380590372 date "2023-06-14" @default.
- W4380590372 modified "2023-09-28" @default.
- W4380590372 title "Diagnostic biomarker discovery from brain EEG data with LSTM, reservoir-SNN and NeuCube: Methods and a pilot study on epilepsy vs migraine" @default.
- W4380590372 doi "https://doi.org/10.36227/techrxiv.23514486" @default.
- W4380590372 hasPublicationYear "2023" @default.
- W4380590372 type Work @default.
- W4380590372 citedByCount "0" @default.
- W4380590372 crossrefType "posted-content" @default.
- W4380590372 hasAuthorship W4380590372A5024893012 @default.
- W4380590372 hasBestOaLocation W43805903721 @default.
- W4380590372 hasConcept C108583219 @default.
- W4380590372 hasConcept C11731999 @default.
- W4380590372 hasConcept C118552586 @default.
- W4380590372 hasConcept C119857082 @default.
- W4380590372 hasConcept C138885662 @default.
- W4380590372 hasConcept C153180895 @default.
- W4380590372 hasConcept C154945302 @default.
- W4380590372 hasConcept C15744967 @default.
- W4380590372 hasConcept C169760540 @default.
- W4380590372 hasConcept C2776401178 @default.
- W4380590372 hasConcept C2778186239 @default.
- W4380590372 hasConcept C2778541695 @default.
- W4380590372 hasConcept C2781197716 @default.
- W4380590372 hasConcept C41008148 @default.
- W4380590372 hasConcept C41895202 @default.
- W4380590372 hasConcept C50644808 @default.
- W4380590372 hasConcept C522805319 @default.
- W4380590372 hasConcept C55493867 @default.
- W4380590372 hasConcept C86803240 @default.
- W4380590372 hasConceptScore W4380590372C108583219 @default.
- W4380590372 hasConceptScore W4380590372C11731999 @default.
- W4380590372 hasConceptScore W4380590372C118552586 @default.
- W4380590372 hasConceptScore W4380590372C119857082 @default.
- W4380590372 hasConceptScore W4380590372C138885662 @default.
- W4380590372 hasConceptScore W4380590372C153180895 @default.
- W4380590372 hasConceptScore W4380590372C154945302 @default.
- W4380590372 hasConceptScore W4380590372C15744967 @default.
- W4380590372 hasConceptScore W4380590372C169760540 @default.
- W4380590372 hasConceptScore W4380590372C2776401178 @default.
- W4380590372 hasConceptScore W4380590372C2778186239 @default.
- W4380590372 hasConceptScore W4380590372C2778541695 @default.
- W4380590372 hasConceptScore W4380590372C2781197716 @default.
- W4380590372 hasConceptScore W4380590372C41008148 @default.
- W4380590372 hasConceptScore W4380590372C41895202 @default.
- W4380590372 hasConceptScore W4380590372C50644808 @default.
- W4380590372 hasConceptScore W4380590372C522805319 @default.
- W4380590372 hasConceptScore W4380590372C55493867 @default.
- W4380590372 hasConceptScore W4380590372C86803240 @default.
- W4380590372 hasLocation W43805903721 @default.
- W4380590372 hasOpenAccess W4380590372 @default.
- W4380590372 hasPrimaryLocation W43805903721 @default.
- W4380590372 hasRelatedWork W2011213191 @default.
- W4380590372 hasRelatedWork W2152120467 @default.
- W4380590372 hasRelatedWork W2390479791 @default.
- W4380590372 hasRelatedWork W4223943233 @default.
- W4380590372 hasRelatedWork W4309045103 @default.
- W4380590372 hasRelatedWork W4311472507 @default.
- W4380590372 hasRelatedWork W4312200629 @default.
- W4380590372 hasRelatedWork W4360585206 @default.
- W4380590372 hasRelatedWork W4364306694 @default.
- W4380590372 hasRelatedWork W4380086463 @default.
- W4380590372 isParatext "false" @default.
- W4380590372 isRetracted "false" @default.
- W4380590372 workType "article" @default.