Matches in SemOpenAlex for { <https://semopenalex.org/work/W191574178> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W191574178 abstract "Neural networks are found to be attractive trainable machines for pattern recognition.The capability of these models to accommodate wide variety and variability ofconditions, and the ability to imitate brain functions, make them popular researcharea.This research focuses on developing hybrid rough neural networks. These novelapproaches are assumed to provide superior performance with respect to detectionand automatic target recognition.In this thesis, hybrid architectures of rough set theory and neural networks have beeninvestigated, developed, and implemented. The first hybrid approach provides novelneural network referred to as Rough Shared weight Neural Networks (RSNN). It usesthe concept of approximation based on rough neurons to feature extraction, andexperiences the methodology of weight sharing. The network stages are a featureextraction network, and a classification network. The extraction network iscomposed of rough neurons that accounts for the upper and lower approximationsand embeds a membership function to replace ordinary activation functions. Theneural network learns the rough set’s upper and lower approximations as featureextractors simultaneously with classification. The RSNN implements a novelapproximation transform. The basic design for the network is provided together withthe learning rules. The architecture provides a novel method to pattern recognitionand is expected to be robust to any pattern recognition problem.The second hybrid approach is a two stand alone subsystems, referred to as RoughNeural Networks (RNN). The extraction network extracts detectors that representpattern’s classes to be supplied to the classification network. It works as a filter fororiginal distilled features based on equivalence relations and rough set reduction,while the second is responsible for classification of the outputs from the first system.The two approaches were applied to image pattern recognition problems. The RSNNwas applied to automatic target recognition problem. The data is Synthetic ApertureRadar (SAR) image scenes of tanks, and background. The RSNN provides a novelmethodology for designing nonlinear filters without prior knowledge of the problem domain. The RNN was used to detect patterns present in satellite image. A novelfeature extraction algorithm was developed to extract the feature vectors. Thealgorithm enhances the recognition ability of the system compared to manualextraction and labeling of pattern classes. The performance of the roughbackpropagation network is improved compared to backpropagation of the samearchitecture. The network has been designed to produce detection plane for thedesired pattern.The hybrid approaches developed in this thesis provide novel techniques torecognition static and dynamic representation of patterns. In both domains the roughset theory improved generalization of the neural networks paradigms. Themethodologies are theoretically robust to any pattern recognition problem, and areproved practically for image environments." @default.
- W191574178 created "2016-06-24" @default.
- W191574178 creator A5019393379 @default.
- W191574178 creator A5065897746 @default.
- W191574178 date "2004-01-01" @default.
- W191574178 modified "2023-09-24" @default.
- W191574178 title "Rough Neural Networks Architecture For Improving Generalization In Pattern Recognition" @default.
- W191574178 hasPublicationYear "2004" @default.
- W191574178 type Work @default.
- W191574178 sameAs 191574178 @default.
- W191574178 citedByCount "0" @default.
- W191574178 crossrefType "dissertation" @default.
- W191574178 hasAuthorship W191574178A5019393379 @default.
- W191574178 hasAuthorship W191574178A5065897746 @default.
- W191574178 hasConcept C111012933 @default.
- W191574178 hasConcept C119857082 @default.
- W191574178 hasConcept C134306372 @default.
- W191574178 hasConcept C138885662 @default.
- W191574178 hasConcept C153180895 @default.
- W191574178 hasConcept C154945302 @default.
- W191574178 hasConcept C175202392 @default.
- W191574178 hasConcept C177148314 @default.
- W191574178 hasConcept C177264268 @default.
- W191574178 hasConcept C199360897 @default.
- W191574178 hasConcept C2776401178 @default.
- W191574178 hasConcept C33923547 @default.
- W191574178 hasConcept C41008148 @default.
- W191574178 hasConcept C41895202 @default.
- W191574178 hasConcept C50644808 @default.
- W191574178 hasConcept C52622490 @default.
- W191574178 hasConceptScore W191574178C111012933 @default.
- W191574178 hasConceptScore W191574178C119857082 @default.
- W191574178 hasConceptScore W191574178C134306372 @default.
- W191574178 hasConceptScore W191574178C138885662 @default.
- W191574178 hasConceptScore W191574178C153180895 @default.
- W191574178 hasConceptScore W191574178C154945302 @default.
- W191574178 hasConceptScore W191574178C175202392 @default.
- W191574178 hasConceptScore W191574178C177148314 @default.
- W191574178 hasConceptScore W191574178C177264268 @default.
- W191574178 hasConceptScore W191574178C199360897 @default.
- W191574178 hasConceptScore W191574178C2776401178 @default.
- W191574178 hasConceptScore W191574178C33923547 @default.
- W191574178 hasConceptScore W191574178C41008148 @default.
- W191574178 hasConceptScore W191574178C41895202 @default.
- W191574178 hasConceptScore W191574178C50644808 @default.
- W191574178 hasConceptScore W191574178C52622490 @default.
- W191574178 hasLocation W1915741781 @default.
- W191574178 hasOpenAccess W191574178 @default.
- W191574178 hasPrimaryLocation W1915741781 @default.
- W191574178 hasRelatedWork W1552673525 @default.
- W191574178 hasRelatedWork W1561137260 @default.
- W191574178 hasRelatedWork W1678838833 @default.
- W191574178 hasRelatedWork W1968147630 @default.
- W191574178 hasRelatedWork W2037622502 @default.
- W191574178 hasRelatedWork W2038770572 @default.
- W191574178 hasRelatedWork W2057137808 @default.
- W191574178 hasRelatedWork W2074897874 @default.
- W191574178 hasRelatedWork W2137248893 @default.
- W191574178 hasRelatedWork W2337922385 @default.
- W191574178 hasRelatedWork W2347307338 @default.
- W191574178 hasRelatedWork W2366946672 @default.
- W191574178 hasRelatedWork W2370957686 @default.
- W191574178 hasRelatedWork W2372277729 @default.
- W191574178 hasRelatedWork W2536558328 @default.
- W191574178 hasRelatedWork W2763479401 @default.
- W191574178 hasRelatedWork W3016866710 @default.
- W191574178 hasRelatedWork W84607321 @default.
- W191574178 hasRelatedWork W2001491853 @default.
- W191574178 hasRelatedWork W2028016548 @default.
- W191574178 isParatext "false" @default.
- W191574178 isRetracted "false" @default.
- W191574178 magId "191574178" @default.
- W191574178 workType "dissertation" @default.