Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386821068> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4386821068 endingPage "105442" @default.
- W4386821068 startingPage "105442" @default.
- W4386821068 abstract "The progressive neurodegenerative disease in the human brain causes Alzheimer's disease (AD).The earlier detection helps to slowdown the progression of AD using continuous medical support system. The research work aims in the detection of Alzheimer’s disease (AD) using brain images. The AD images are detected using fusion-based deep learning method. This works also adopts Pipelined LeNet (PLN) architecture. The brain Magnetic Resonance Imaging (MRI) images obtained are resized in the preprocessing stage and the internal regions are enhanced using the image fusion method. Therefore, the proposed AD detection system produces high classification rate even using low resolution brain MRI images. The ternary features are computed from the fused image and these features are classified by the proposed PLN architecture for identification of Alzheimer’s brain image. High efficient and high speed novel PLN architecture is proposed in this AD detection system using brain MRI images due to the consumption time of classification and requirement of brain image dataset by conventional methods. Evaluation of the work is carried out using Kaggle Alzheimer’s Classification Dataset (KACD). Performance of the AD image detection system in terms of sensitivity (Se), specificity (Sp), precision (Pr), and accuracy (Acc) are evaluated. The proposed AD image detection system obtains 99.9% Se, 99.8% Sp, 99.8% Pr and 99.5% Acc using PLN architecture. The proposed AD detection system using PLN architecture consumed 0.65 ms as an average execution span. By comparing the execution span of all other similar methods, the proposed system consumes less execution span due to its Pipelined architecture. The experimental results of the image detection system are compared with similar works in the literatures." @default.
- W4386821068 created "2023-09-19" @default.
- W4386821068 creator A5021177462 @default.
- W4386821068 creator A5070980655 @default.
- W4386821068 date "2024-01-01" @default.
- W4386821068 modified "2023-09-27" @default.
- W4386821068 title "Pipelined deep learning architecture for the detection of Alzheimer’s disease" @default.
- W4386821068 cites W2770927588 @default.
- W4386821068 cites W2800561544 @default.
- W4386821068 cites W2894834586 @default.
- W4386821068 cites W2896115045 @default.
- W4386821068 cites W2901050968 @default.
- W4386821068 cites W2906155095 @default.
- W4386821068 cites W2947823562 @default.
- W4386821068 cites W2948256550 @default.
- W4386821068 cites W2960357609 @default.
- W4386821068 cites W2999209878 @default.
- W4386821068 cites W3115324042 @default.
- W4386821068 cites W3197857423 @default.
- W4386821068 cites W4206730042 @default.
- W4386821068 cites W4289545164 @default.
- W4386821068 cites W4291149459 @default.
- W4386821068 cites W4312125929 @default.
- W4386821068 cites W4323315257 @default.
- W4386821068 cites W4328108216 @default.
- W4386821068 doi "https://doi.org/10.1016/j.bspc.2023.105442" @default.
- W4386821068 hasPublicationYear "2024" @default.
- W4386821068 type Work @default.
- W4386821068 citedByCount "0" @default.
- W4386821068 crossrefType "journal-article" @default.
- W4386821068 hasAuthorship W4386821068A5021177462 @default.
- W4386821068 hasAuthorship W4386821068A5070980655 @default.
- W4386821068 hasConcept C108583219 @default.
- W4386821068 hasConcept C153180895 @default.
- W4386821068 hasConcept C154945302 @default.
- W4386821068 hasConcept C31972630 @default.
- W4386821068 hasConcept C34736171 @default.
- W4386821068 hasConcept C41008148 @default.
- W4386821068 hasConceptScore W4386821068C108583219 @default.
- W4386821068 hasConceptScore W4386821068C153180895 @default.
- W4386821068 hasConceptScore W4386821068C154945302 @default.
- W4386821068 hasConceptScore W4386821068C31972630 @default.
- W4386821068 hasConceptScore W4386821068C34736171 @default.
- W4386821068 hasConceptScore W4386821068C41008148 @default.
- W4386821068 hasLocation W43868210681 @default.
- W4386821068 hasOpenAccess W4386821068 @default.
- W4386821068 hasPrimaryLocation W43868210681 @default.
- W4386821068 hasRelatedWork W2066259560 @default.
- W4386821068 hasRelatedWork W2148258325 @default.
- W4386821068 hasRelatedWork W2353388427 @default.
- W4386821068 hasRelatedWork W2380927352 @default.
- W4386821068 hasRelatedWork W2391959412 @default.
- W4386821068 hasRelatedWork W2899307613 @default.
- W4386821068 hasRelatedWork W2997394683 @default.
- W4386821068 hasRelatedWork W4313289316 @default.
- W4386821068 hasRelatedWork W4377967120 @default.
- W4386821068 hasRelatedWork W1966592431 @default.
- W4386821068 hasVolume "87" @default.
- W4386821068 isParatext "false" @default.
- W4386821068 isRetracted "false" @default.
- W4386821068 workType "article" @default.