FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285307997> ?p ?o ?g. }

• W4285307997 endingPage "721" @default.
• W4285307997 startingPage "707" @default.
• W4285307997 abstract "A novel structure of reinforced two-stream fuzzy neural networks (TSFNNs) realized with the aid of fuzzy logic and transfer learning method is presented. This architecture consists of a TSFNN and a fusion strategy. TSFNN architecture consists of two combined networks of both fuzzy rules-based radial basis function neural networks (FRBFNN) and convolutional neural networks (CNNs). In the TSFNN architecture, one stream employs the deep CNN to extract the spatial information of images and effectively learn the high-level features and another stream uses the FRBFNN to analyze the distribution of data points over the input space and learn to capture complex relationships in data. In the fusion strategy, the outputs of two streams are concatenated by a softmax function, which normalizes the output to a probability distribution. A transfer learning method is considered to reconstruct new data representation as the inputs of CNN to mine potential spatial features of data. Moreover, L <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sub> -norm regularization is used to alleviate the possible overfitting and enhance the generalization ability. The proposed method not only inherits the advantages of FRBFNN and CNN such as global feature extraction ability, good local approximating performance, ability of handling uncertainty by fuzzy logic but also improves the classification performance under the synergy between two-stream architecture and the fusion strategy. Experimental results obtained for a diversity of datasets as well as partial discharge datasets be using in the real life of fault diagnosis and black plastic wastes datasets for recycling confirm the effectiveness of the proposed TSFNN. A comprehensive comparative analysis is covered. This design can simultaneously capture different level information of inputs and easing the insufficient problem of extracting features from a single steam. Especially, we show that the synergistic effect of FRBFNN, CNN, enabling deep learning for generic classification tasks and multipoint crossover, and L <sub xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>2</sub> -norm regularization can effectively improve the performance of the TSFNNs." @default.
• W4285307997 created "2022-07-14" @default.
• W4285307997 creator A5003799782 @default.
• W4285307997 creator A5033254809 @default.
• W4285307997 creator A5035932097 @default.
• W4285307997 creator A5075875574 @default.
• W4285307997 creator A5083193684 @default.
• W4285307997 date "2023-03-01" @default.
• W4285307997 modified "2023-10-15" @default.
• W4285307997 title "Reinforced Two-Stream Fuzzy Neural Networks Architecture Realized With the Aid of One-Dimensional/Two-Dimensional Data Features" @default.
• W4285307997 cites W1498436455 @default.
• W4285307997 cites W1541170979 @default.
• W4285307997 cites W1932847118 @default.
• W4285307997 cites W1964494592 @default.
• W4285307997 cites W1965217418 @default.
• W4285307997 cites W1975470076 @default.
• W4285307997 cites W1989130143 @default.
• W4285307997 cites W2019619214 @default.
• W4285307997 cites W2064535070 @default.
• W4285307997 cites W2075282432 @default.
• W4285307997 cites W2078094465 @default.
• W4285307997 cites W2107001311 @default.
• W4285307997 cites W2112796928 @default.
• W4285307997 cites W2113242816 @default.
• W4285307997 cites W2115403315 @default.
• W4285307997 cites W2129624644 @default.
• W4285307997 cites W2146096861 @default.
• W4285307997 cites W2155951042 @default.
• W4285307997 cites W2158247472 @default.
• W4285307997 cites W2164554122 @default.
• W4285307997 cites W2165698076 @default.
• W4285307997 cites W2166814474 @default.
• W4285307997 cites W2177019876 @default.
• W4285307997 cites W2520774990 @default.
• W4285307997 cites W2586564970 @default.
• W4285307997 cites W2767702821 @default.
• W4285307997 cites W2776378542 @default.
• W4285307997 cites W2899015155 @default.
• W4285307997 cites W2904043173 @default.
• W4285307997 cites W2911964244 @default.
• W4285307997 cites W2914580252 @default.
• W4285307997 cites W2941752771 @default.
• W4285307997 cites W2945754504 @default.
• W4285307997 cites W2949699261 @default.
• W4285307997 cites W2962895364 @default.
• W4285307997 cites W2964805495 @default.
• W4285307997 cites W2966040026 @default.
• W4285307997 cites W3000384844 @default.
• W4285307997 cites W3021972511 @default.
• W4285307997 cites W3044797745 @default.
• W4285307997 cites W3087890894 @default.
• W4285307997 cites W3101217327 @default.
• W4285307997 cites W3121335749 @default.
• W4285307997 cites W3154745533 @default.
• W4285307997 cites W3160306726 @default.
• W4285307997 cites W3213588331 @default.
• W4285307997 doi "https://doi.org/10.1109/tfuzz.2022.3186181" @default.
• W4285307997 hasPublicationYear "2023" @default.
• W4285307997 type Work @default.
• W4285307997 citedByCount "0" @default.
• W4285307997 crossrefType "journal-article" @default.
• W4285307997 hasAuthorship W4285307997A5003799782 @default.
• W4285307997 hasAuthorship W4285307997A5033254809 @default.
• W4285307997 hasAuthorship W4285307997A5035932097 @default.
• W4285307997 hasAuthorship W4285307997A5075875574 @default.
• W4285307997 hasAuthorship W4285307997A5083193684 @default.
• W4285307997 hasConcept C124101348 @default.
• W4285307997 hasConcept C150899416 @default.
• W4285307997 hasConcept C153180895 @default.
• W4285307997 hasConcept C154945302 @default.
• W4285307997 hasConcept C188441871 @default.
• W4285307997 hasConcept C22019652 @default.
• W4285307997 hasConcept C41008148 @default.
• W4285307997 hasConcept C50644808 @default.
• W4285307997 hasConcept C58166 @default.
• W4285307997 hasConcept C81363708 @default.
• W4285307997 hasConceptScore W4285307997C124101348 @default.
• W4285307997 hasConceptScore W4285307997C150899416 @default.
• W4285307997 hasConceptScore W4285307997C153180895 @default.
• W4285307997 hasConceptScore W4285307997C154945302 @default.
• W4285307997 hasConceptScore W4285307997C188441871 @default.
• W4285307997 hasConceptScore W4285307997C22019652 @default.
• W4285307997 hasConceptScore W4285307997C41008148 @default.
• W4285307997 hasConceptScore W4285307997C50644808 @default.
• W4285307997 hasConceptScore W4285307997C58166 @default.
• W4285307997 hasConceptScore W4285307997C81363708 @default.
• W4285307997 hasFunder F4320321001 @default.
• W4285307997 hasFunder F4320322120 @default.
• W4285307997 hasFunder F4320328359 @default.
• W4285307997 hasIssue "3" @default.
• W4285307997 hasLocation W42853079971 @default.
• W4285307997 hasOpenAccess W4285307997 @default.
• W4285307997 hasPrimaryLocation W42853079971 @default.
• W4285307997 hasRelatedWork W2758063741 @default.
• W4285307997 hasRelatedWork W2767651786 @default.
• W4285307997 hasRelatedWork W2977314777 @default.
• W4285307997 hasRelatedWork W2994590618 @default.
• W4285307997 hasRelatedWork W2997709384 @default.

• next