FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3011928443> ?p ?o ?g. }

• W3011928443 endingPage "956" @default.
• W3011928443 startingPage "956" @default.
• W3011928443 abstract "Artificial Neural Networks (ANNs) have been used in a wide range of applications for complex datasets with their flexible mathematical architecture. The flexibility is favored by the introduction of a higher number of connections and variables, in general. However, over-parameterization of the ANN equations and the existence of redundant input variables usually result in poor test performance. This paper proposes a superstructure-based mixed-integer nonlinear programming method for optimal structural design including neuron number selection, pruning, and input selection for multilayer perceptron (MLP) ANNs. In addition, this method uses statistical measures such as the parameter covariance matrix in order to increase the test performance while permitting reduced training performance. The suggested approach was implemented on two public hyperspectral datasets (with 10% and 50% sampling ratios), namely Indian Pines and Pavia University, for the classification problem. The test results revealed promising performances compared to the standard fully connected neural networks in terms of the estimated overall and individual class accuracies. With the application of the proposed superstructural optimization, fully connected networks were pruned by over 60% in terms of the total number of connections, resulting in an increase of 4% for the 10% sampling ratio and a 1% decrease for the 50% sampling ratio. Moreover, over 20% of the spectral bands in the Indian Pines data and 30% in the Pavia University data were found statistically insignificant, and they were thus removed from the MLP networks. As a result, the proposed method was found effective in optimizing the architectural design with high generalization capabilities, particularly for fewer numbers of samples. The analysis of the eliminated spectral bands revealed that the proposed algorithm mostly removed the bands adjacent to the pre-eliminated noisy bands and highly correlated bands carrying similar information." @default.
• W3011928443 created "2020-03-23" @default.
• W3011928443 creator A5046223798 @default.
• W3011928443 creator A5054216311 @default.
• W3011928443 creator A5068481691 @default.
• W3011928443 date "2020-03-16" @default.
• W3011928443 modified "2023-10-13" @default.
• W3011928443 title "Design of Feedforward Neural Networks in the Classification of Hyperspectral Imagery Using Superstructural Optimization" @default.
• W3011928443 cites W1574682743 @default.
• W3011928443 cites W1968817565 @default.
• W3011928443 cites W1976878264 @default.
• W3011928443 cites W1984271318 @default.
• W3011928443 cites W1991359408 @default.
• W3011928443 cites W1991449819 @default.
• W3011928443 cites W1999933124 @default.
• W3011928443 cites W2001823726 @default.
• W3011928443 cites W2005404041 @default.
• W3011928443 cites W2013272253 @default.
• W3011928443 cites W2039972295 @default.
• W3011928443 cites W2040870580 @default.
• W3011928443 cites W2059174629 @default.
• W3011928443 cites W2061962896 @default.
• W3011928443 cites W2070188654 @default.
• W3011928443 cites W2071334094 @default.
• W3011928443 cites W2071556151 @default.
• W3011928443 cites W2076627662 @default.
• W3011928443 cites W2078840559 @default.
• W3011928443 cites W2079019836 @default.
• W3011928443 cites W2079454091 @default.
• W3011928443 cites W2091010379 @default.
• W3011928443 cites W2093678292 @default.
• W3011928443 cites W2098248868 @default.
• W3011928443 cites W2103263653 @default.
• W3011928443 cites W2105325887 @default.
• W3011928443 cites W2126333738 @default.
• W3011928443 cites W2130269771 @default.
• W3011928443 cites W2130794164 @default.
• W3011928443 cites W2131408733 @default.
• W3011928443 cites W2139318413 @default.
• W3011928443 cites W2144841545 @default.
• W3011928443 cites W2144931885 @default.
• W3011928443 cites W2145085734 @default.
• W3011928443 cites W2149518557 @default.
• W3011928443 cites W2168809519 @default.
• W3011928443 cites W2172009270 @default.
• W3011928443 cites W2789933240 @default.
• W3011928443 cites W2793927960 @default.
• W3011928443 cites W2884036810 @default.
• W3011928443 cites W2884821113 @default.
• W3011928443 doi "https://doi.org/10.3390/rs12060956" @default.
• W3011928443 hasPublicationYear "2020" @default.
• W3011928443 type Work @default.
• W3011928443 sameAs 3011928443 @default.
• W3011928443 citedByCount "17" @default.
• W3011928443 countsByYear W30119284432021 @default.
• W3011928443 countsByYear W30119284432022 @default.
• W3011928443 countsByYear W30119284432023 @default.
• W3011928443 crossrefType "journal-article" @default.
• W3011928443 hasAuthorship W3011928443A5046223798 @default.
• W3011928443 hasAuthorship W3011928443A5054216311 @default.
• W3011928443 hasAuthorship W3011928443A5068481691 @default.
• W3011928443 hasBestOaLocation W30119284431 @default.
• W3011928443 hasConcept C106131492 @default.
• W3011928443 hasConcept C108010975 @default.
• W3011928443 hasConcept C126255220 @default.
• W3011928443 hasConcept C134306372 @default.
• W3011928443 hasConcept C140779682 @default.
• W3011928443 hasConcept C153180895 @default.
• W3011928443 hasConcept C154945302 @default.
• W3011928443 hasConcept C159078339 @default.
• W3011928443 hasConcept C177148314 @default.
• W3011928443 hasConcept C179717631 @default.
• W3011928443 hasConcept C31972630 @default.
• W3011928443 hasConcept C33923547 @default.
• W3011928443 hasConcept C41008148 @default.
• W3011928443 hasConcept C50644808 @default.
• W3011928443 hasConcept C60908668 @default.
• W3011928443 hasConcept C6557445 @default.
• W3011928443 hasConcept C86803240 @default.
• W3011928443 hasConceptScore W3011928443C106131492 @default.
• W3011928443 hasConceptScore W3011928443C108010975 @default.
• W3011928443 hasConceptScore W3011928443C126255220 @default.
• W3011928443 hasConceptScore W3011928443C134306372 @default.
• W3011928443 hasConceptScore W3011928443C140779682 @default.
• W3011928443 hasConceptScore W3011928443C153180895 @default.
• W3011928443 hasConceptScore W3011928443C154945302 @default.
• W3011928443 hasConceptScore W3011928443C159078339 @default.
• W3011928443 hasConceptScore W3011928443C177148314 @default.
• W3011928443 hasConceptScore W3011928443C179717631 @default.
• W3011928443 hasConceptScore W3011928443C31972630 @default.
• W3011928443 hasConceptScore W3011928443C33923547 @default.
• W3011928443 hasConceptScore W3011928443C41008148 @default.
• W3011928443 hasConceptScore W3011928443C50644808 @default.
• W3011928443 hasConceptScore W3011928443C60908668 @default.
• W3011928443 hasConceptScore W3011928443C6557445 @default.
• W3011928443 hasConceptScore W3011928443C86803240 @default.
• W3011928443 hasIssue "6" @default.
• W3011928443 hasLocation W30119284431 @default.

• next