Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387514095> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4387514095 endingPage "139" @default.
- W4387514095 startingPage "132" @default.
- W4387514095 abstract "Bio-electrical time signals play a significant role in assisting non-invasive observational procedures in healthcare. These bioelectrical signals are weak signals with inherently low voltage and low frequency, hidden mostly under relatively large high-voltage noise signals. Hence it is extra challenging to analyze them. In modern clinical data analysis, these signals could be further analyzed using conventional machine learning (ML) methods. Also, in the recent past, two-dimensional spectrum-based classification, predominantly with Convolutional Neural Networks (CNN), has been tried with time-series data. One of the objectives of this study is to find which approach would suit better for biomedical signal analysis when data are scarce and signals are weak. Also, in bio-medical signal analysis data is scarce. Yet, to effectively train either an ML or a deep learning (DL) model, a sample clinical dataset of a significant size is required. Hence, the second objective of this research is to present a novel data synthesis method to address data scarcity. With these objectives, the study compares the performance of the time-series-based classification with traditional ML approaches, against the 2D spectrum-based classification for bio-electrical signal classification. For this purpose the study utilizes learning models; Multi-layer Perceptron (MLP), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Long Short-Term Memory Networks (LSTMs), Auto Encoder (AE), and Convolutions Neural Network (CNN). Also, the authors propose a novel data synthesis method based on LSTMs to improve the sample size of the standard CHB-MIT Scalp EEG dataset. The results show that with the expanded dataset, the two-dimensional spectrum-based classification architecture was able to achieve a precision level of 85% at the classification. The conventional ML-based methods showed on average a precision level of 82%. In conclusion with the proposed virtual sample generation approach, 2D spectrum-based classification with Convolutional Neural Networks showed promising performances." @default.
- W4387514095 created "2023-10-11" @default.
- W4387514095 creator A5017191477 @default.
- W4387514095 creator A5093039997 @default.
- W4387514095 date "2023-10-10" @default.
- W4387514095 modified "2023-10-12" @default.
- W4387514095 title "A Novel LSTM-based Data Synthesis Approach for Performance Improvement in Detecting Epileptic Seizures" @default.
- W4387514095 cites W1566689562 @default.
- W4387514095 cites W2026241496 @default.
- W4387514095 cites W2097245460 @default.
- W4387514095 cites W2116016394 @default.
- W4387514095 cites W2162800060 @default.
- W4387514095 cites W2518153892 @default.
- W4387514095 cites W2765856398 @default.
- W4387514095 cites W2770913396 @default.
- W4387514095 cites W2774240538 @default.
- W4387514095 cites W2899042961 @default.
- W4387514095 cites W3091321442 @default.
- W4387514095 cites W3096426711 @default.
- W4387514095 cites W3207901562 @default.
- W4387514095 doi "https://doi.org/10.37394/23208.2023.20.13" @default.
- W4387514095 hasPublicationYear "2023" @default.
- W4387514095 type Work @default.
- W4387514095 citedByCount "0" @default.
- W4387514095 crossrefType "journal-article" @default.
- W4387514095 hasAuthorship W4387514095A5017191477 @default.
- W4387514095 hasAuthorship W4387514095A5093039997 @default.
- W4387514095 hasBestOaLocation W43875140951 @default.
- W4387514095 hasConcept C108583219 @default.
- W4387514095 hasConcept C115961682 @default.
- W4387514095 hasConcept C119857082 @default.
- W4387514095 hasConcept C147168706 @default.
- W4387514095 hasConcept C153180895 @default.
- W4387514095 hasConcept C154945302 @default.
- W4387514095 hasConcept C199360897 @default.
- W4387514095 hasConcept C2779843651 @default.
- W4387514095 hasConcept C41008148 @default.
- W4387514095 hasConcept C50644808 @default.
- W4387514095 hasConcept C60908668 @default.
- W4387514095 hasConcept C81363708 @default.
- W4387514095 hasConcept C99498987 @default.
- W4387514095 hasConceptScore W4387514095C108583219 @default.
- W4387514095 hasConceptScore W4387514095C115961682 @default.
- W4387514095 hasConceptScore W4387514095C119857082 @default.
- W4387514095 hasConceptScore W4387514095C147168706 @default.
- W4387514095 hasConceptScore W4387514095C153180895 @default.
- W4387514095 hasConceptScore W4387514095C154945302 @default.
- W4387514095 hasConceptScore W4387514095C199360897 @default.
- W4387514095 hasConceptScore W4387514095C2779843651 @default.
- W4387514095 hasConceptScore W4387514095C41008148 @default.
- W4387514095 hasConceptScore W4387514095C50644808 @default.
- W4387514095 hasConceptScore W4387514095C60908668 @default.
- W4387514095 hasConceptScore W4387514095C81363708 @default.
- W4387514095 hasConceptScore W4387514095C99498987 @default.
- W4387514095 hasLocation W43875140951 @default.
- W4387514095 hasOpenAccess W4387514095 @default.
- W4387514095 hasPrimaryLocation W43875140951 @default.
- W4387514095 hasRelatedWork W2953061907 @default.
- W4387514095 hasRelatedWork W3029198973 @default.
- W4387514095 hasRelatedWork W3032952384 @default.
- W4387514095 hasRelatedWork W3133861977 @default.
- W4387514095 hasRelatedWork W3167935049 @default.
- W4387514095 hasRelatedWork W3193565141 @default.
- W4387514095 hasRelatedWork W4225394202 @default.
- W4387514095 hasRelatedWork W4226493464 @default.
- W4387514095 hasRelatedWork W4298287631 @default.
- W4387514095 hasRelatedWork W4312417841 @default.
- W4387514095 hasVolume "20" @default.
- W4387514095 isParatext "false" @default.
- W4387514095 isRetracted "false" @default.
- W4387514095 workType "article" @default.