FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317183365> ?p ?o ?g. }

• W4317183365 endingPage "13" @default.
• W4317183365 startingPage "3" @default.
• W4317183365 abstract "Diseases related to human cardiac system are very common now-days. Activities within the patient’s cardiac system can be captured using an electrical conduction system and mapped on a waveform named an electrocardiogram (ECG). The abnormal heartbeats, or arrhythmias, can be seen in the ECG data. ECG signal data is vast and calls for many qualified medical professionals and resources. Machine learning has become a vast field of study to uncover the properties of ECG signals. Traditional approaches need additional efforts in feature extraction to support designing a more optimal system. Patients’ acute and chronic heart problems must be accurately diagnosed using deep machine learning. A deep learning model can be evaluated on the MIT-BIH dataset, it has available ECG data for medical research and practices. In spite of the fact that CNN accomplishes well enough to improve computer-based diagnosis. Computer automatic diagnosis in the medical field along with present-day ML techniques may be accurate and efficient in this area. An optimal deep model design & procedures for classification of electrocardiogram waveform would be helpful to bring off medical resources and brush-up research trials. In this paper, a cascade model of LSTM and RNN is proposed and compared with the existing single model on the necessary parameters to judge. Experimental evaluation is to classify irregularities in ECG signal 12 lead data collected from MIT-BIH and classified through a proposed cascading model. The proposed cascaded model archived 89.9% accuracy with 93.46% sensitivity and 84.36% specificity. The comparison results show that LSTM with RNN suits real-time generated data sequences like ECG." @default.
• W4317183365 created "2023-01-18" @default.
• W4317183365 creator A5048125366 @default.
• W4317183365 creator A5062899257 @default.
• W4317183365 creator A5088999117 @default.
• W4317183365 date "2022-01-01" @default.
• W4317183365 modified "2023-10-02" @default.
• W4317183365 title "Cardiac Arrhythmia Classification Using Cascaded Deep Learning Approach (LSTM & RNN)" @default.
• W4317183365 cites W2109255472 @default.
• W4317183365 cites W2140668360 @default.
• W4317183365 cites W2605056515 @default.
• W4317183365 cites W2702116941 @default.
• W4317183365 cites W2745699887 @default.
• W4317183365 cites W2748902594 @default.
• W4317183365 cites W2762718731 @default.
• W4317183365 cites W2771170013 @default.
• W4317183365 cites W2771532190 @default.
• W4317183365 cites W2790971290 @default.
• W4317183365 cites W2791025763 @default.
• W4317183365 cites W2794869652 @default.
• W4317183365 cites W2795115089 @default.
• W4317183365 cites W2795157542 @default.
• W4317183365 cites W2796767721 @default.
• W4317183365 cites W2802832784 @default.
• W4317183365 cites W2804642894 @default.
• W4317183365 cites W2810921282 @default.
• W4317183365 cites W2884754815 @default.
• W4317183365 cites W2884795774 @default.
• W4317183365 cites W2886982273 @default.
• W4317183365 cites W2887119478 @default.
• W4317183365 cites W2898682710 @default.
• W4317183365 cites W2898853290 @default.
• W4317183365 cites W2915804162 @default.
• W4317183365 cites W2962835126 @default.
• W4317183365 cites W2972401431 @default.
• W4317183365 cites W2999552082 @default.
• W4317183365 cites W3033966907 @default.
• W4317183365 cites W3090787545 @default.
• W4317183365 cites W3098971646 @default.
• W4317183365 cites W3101844402 @default.
• W4317183365 cites W3156640576 @default.
• W4317183365 doi "https://doi.org/10.1007/978-3-031-24352-3_1" @default.
• W4317183365 hasPublicationYear "2022" @default.
• W4317183365 type Work @default.
• W4317183365 citedByCount "1" @default.
• W4317183365 countsByYear W43171833652023 @default.
• W4317183365 crossrefType "book-chapter" @default.
• W4317183365 hasAuthorship W4317183365A5048125366 @default.
• W4317183365 hasAuthorship W4317183365A5062899257 @default.
• W4317183365 hasAuthorship W4317183365A5088999117 @default.
• W4317183365 hasConcept C108583219 @default.
• W4317183365 hasConcept C119857082 @default.
• W4317183365 hasConcept C127413603 @default.
• W4317183365 hasConcept C147168706 @default.
• W4317183365 hasConcept C153180895 @default.
• W4317183365 hasConcept C154945302 @default.
• W4317183365 hasConcept C164705383 @default.
• W4317183365 hasConcept C202444582 @default.
• W4317183365 hasConcept C2779161974 @default.
• W4317183365 hasConcept C2988455589 @default.
• W4317183365 hasConcept C33923547 @default.
• W4317183365 hasConcept C34146451 @default.
• W4317183365 hasConcept C41008148 @default.
• W4317183365 hasConcept C42360764 @default.
• W4317183365 hasConcept C50644808 @default.
• W4317183365 hasConcept C71924100 @default.
• W4317183365 hasConcept C9652623 @default.
• W4317183365 hasConceptScore W4317183365C108583219 @default.
• W4317183365 hasConceptScore W4317183365C119857082 @default.
• W4317183365 hasConceptScore W4317183365C127413603 @default.
• W4317183365 hasConceptScore W4317183365C147168706 @default.
• W4317183365 hasConceptScore W4317183365C153180895 @default.
• W4317183365 hasConceptScore W4317183365C154945302 @default.
• W4317183365 hasConceptScore W4317183365C164705383 @default.
• W4317183365 hasConceptScore W4317183365C202444582 @default.
• W4317183365 hasConceptScore W4317183365C2779161974 @default.
• W4317183365 hasConceptScore W4317183365C2988455589 @default.
• W4317183365 hasConceptScore W4317183365C33923547 @default.
• W4317183365 hasConceptScore W4317183365C34146451 @default.
• W4317183365 hasConceptScore W4317183365C41008148 @default.
• W4317183365 hasConceptScore W4317183365C42360764 @default.
• W4317183365 hasConceptScore W4317183365C50644808 @default.
• W4317183365 hasConceptScore W4317183365C71924100 @default.
• W4317183365 hasConceptScore W4317183365C9652623 @default.
• W4317183365 hasLocation W43171833651 @default.
• W4317183365 hasOpenAccess W4317183365 @default.
• W4317183365 hasPrimaryLocation W43171833651 @default.
• W4317183365 hasRelatedWork W3014300295 @default.
• W4317183365 hasRelatedWork W3164822677 @default.
• W4317183365 hasRelatedWork W4223943233 @default.
• W4317183365 hasRelatedWork W4225161397 @default.
• W4317183365 hasRelatedWork W4250304930 @default.
• W4317183365 hasRelatedWork W4312200629 @default.
• W4317183365 hasRelatedWork W4360585206 @default.
• W4317183365 hasRelatedWork W4364306694 @default.
• W4317183365 hasRelatedWork W4380075502 @default.
• W4317183365 hasRelatedWork W4380086463 @default.
• W4317183365 isParatext "false" @default.

• next