FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384408522> ?p ?o ?g. }

• W4384408522 endingPage "107721" @default.
• W4384408522 startingPage "107721" @default.
• W4384408522 abstract "Background and Objective:Medical hyperspectral images (MHSIs) are used for a contact-free examination of patients without harmful radiation. However, high-dimensionality images contain large amounts of data that are sparsely distributed in a high-dimensional space, which leads to the “curse of dimensionality” (called Hughes’ phenomenon) and increases the complexity and cost of data processing and storage. Hence, there is a need for spectral dimensionality reduction before the clinical application of MHSIs. Some dimensionality-reducing strategies have been proposed; however, they distort the data within MHSIs. Methods: To compress dimensionality without destroying the original data structure, we propose a method that involves data gravitation and weak correlation-based ranking (DGWCR) for removing bands of noise from MHSIs while clustering signal-containing bands. Band clustering is done by using the connection centre evolution (CCE) algorithm and selecting the most representative bands in each cluster based on the composite force. The bands within the clusters are ranked using the new entropy-containing matrix, and a global ranking of bands is obtained by applying an S-shaped strategy. The source code is available at https://www.github.com/zhangchenglong1116/DGWCR. Results: Upon feeding the reduced-dimensional images into various classifiers, the experimental results demonstrated that the small number of bands selected by the proposed DGWCR consistently achieved higher classification accuracy than the original data. Unlike other reference methods (e.g. the latest deep-learning-based strategies), DGWCR chooses the spectral bands with the least redundancy and greatest discrimination. Conclusions: In this study, we present a method for efficient band selection for MHSIs that alleviates the “curse of dimensionality”. Experiments were validated with three MHSIs in the human brain, and they outperformed several other band selection methods, demonstrating the clinical potential of DGWCR." @default.
• W4384408522 created "2023-07-16" @default.
• W4384408522 creator A5015577975 @default.
• W4384408522 creator A5020913004 @default.
• W4384408522 creator A5021019273 @default.
• W4384408522 creator A5024379450 @default.
• W4384408522 creator A5039420381 @default.
• W4384408522 creator A5048407616 @default.
• W4384408522 creator A5063565684 @default.
• W4384408522 creator A5073157317 @default.
• W4384408522 creator A5076035971 @default.
• W4384408522 date "2023-10-01" @default.
• W4384408522 modified "2023-10-14" @default.
• W4384408522 title "Unsupervised band selection of medical hyperspectral images guided by data gravitation and weak correlation" @default.
• W4384408522 cites W1504710628 @default.
• W4384408522 cites W1910604087 @default.
• W4384408522 cites W1932531222 @default.
• W4384408522 cites W1964940342 @default.
• W4384408522 cites W1988386267 @default.
• W4384408522 cites W2005871861 @default.
• W4384408522 cites W2006676204 @default.
• W4384408522 cites W2021373288 @default.
• W4384408522 cites W2047029347 @default.
• W4384408522 cites W2071185414 @default.
• W4384408522 cites W2082468369 @default.
• W4384408522 cites W2089527220 @default.
• W4384408522 cites W2096003572 @default.
• W4384408522 cites W2103094532 @default.
• W4384408522 cites W2119456790 @default.
• W4384408522 cites W2138038253 @default.
• W4384408522 cites W2150566919 @default.
• W4384408522 cites W2150990614 @default.
• W4384408522 cites W2153635508 @default.
• W4384408522 cites W2156932943 @default.
• W4384408522 cites W2162698522 @default.
• W4384408522 cites W2165835468 @default.
• W4384408522 cites W2168481151 @default.
• W4384408522 cites W2261059368 @default.
• W4384408522 cites W2406483574 @default.
• W4384408522 cites W2464122548 @default.
• W4384408522 cites W2547680145 @default.
• W4384408522 cites W2570459851 @default.
• W4384408522 cites W2603834682 @default.
• W4384408522 cites W2608819578 @default.
• W4384408522 cites W2611477785 @default.
• W4384408522 cites W2620489131 @default.
• W4384408522 cites W2746763695 @default.
• W4384408522 cites W2750827587 @default.
• W4384408522 cites W2793848630 @default.
• W4384408522 cites W2901326905 @default.
• W4384408522 cites W2919868964 @default.
• W4384408522 cites W2921862546 @default.
• W4384408522 cites W2937638900 @default.
• W4384408522 cites W2941617643 @default.
• W4384408522 cites W2950325582 @default.
• W4384408522 cites W2952532836 @default.
• W4384408522 cites W2967209214 @default.
• W4384408522 cites W2972435376 @default.
• W4384408522 cites W2976114323 @default.
• W4384408522 cites W2978620371 @default.
• W4384408522 cites W2981959903 @default.
• W4384408522 cites W2997272341 @default.
• W4384408522 cites W2998656915 @default.
• W4384408522 cites W3001645721 @default.
• W4384408522 cites W3010420609 @default.
• W4384408522 cites W3023065102 @default.
• W4384408522 cites W3046819794 @default.
• W4384408522 cites W3120077038 @default.
• W4384408522 cites W3134985592 @default.
• W4384408522 cites W3171243408 @default.
• W4384408522 cites W3173675588 @default.
• W4384408522 cites W3211275894 @default.
• W4384408522 cites W3214085799 @default.
• W4384408522 cites W4210330613 @default.
• W4384408522 cites W4220694613 @default.
• W4384408522 cites W4224879968 @default.
• W4384408522 cites W4225487062 @default.
• W4384408522 cites W4280588196 @default.
• W4384408522 cites W4281557545 @default.
• W4384408522 cites W4291474829 @default.
• W4384408522 cites W4319027477 @default.
• W4384408522 cites W4361270996 @default.
• W4384408522 cites W964460774 @default.
• W4384408522 doi "https://doi.org/10.1016/j.cmpb.2023.107721" @default.
• W4384408522 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37506601" @default.
• W4384408522 hasPublicationYear "2023" @default.
• W4384408522 type Work @default.
• W4384408522 citedByCount "0" @default.
• W4384408522 crossrefType "journal-article" @default.
• W4384408522 hasAuthorship W4384408522A5015577975 @default.
• W4384408522 hasAuthorship W4384408522A5020913004 @default.
• W4384408522 hasAuthorship W4384408522A5021019273 @default.
• W4384408522 hasAuthorship W4384408522A5024379450 @default.
• W4384408522 hasAuthorship W4384408522A5039420381 @default.
• W4384408522 hasAuthorship W4384408522A5048407616 @default.
• W4384408522 hasAuthorship W4384408522A5063565684 @default.
• W4384408522 hasAuthorship W4384408522A5073157317 @default.
• W4384408522 hasAuthorship W4384408522A5076035971 @default.

• next