Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ding, Weiping | en_US |
dc.contributor.author | Guan, Zhijin | en_US |
dc.contributor.author | Shi, Quan | en_US |
dc.contributor.author | Wang, Jiandong | en_US |
dc.date.accessioned | 2015-07-21T08:29:37Z | - |
dc.date.available | 2015-07-21T08:29:37Z | - |
dc.date.issued | 2015-02-01 | en_US |
dc.identifier.issn | 0020-0255 | en_US |
dc.identifier.uri | http://dx.doi.org/10.1016/j.ins.2014.09.010 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/123847 | - |
dc.description.abstract | In order to further improve the adaptability of attribute reduction and enhance its application performance in large-scale attribute reduction, a more efficient attribute self-adaptive co-evolutionary reduction algorithm by combining quantum elitist frogs and cloud model operators (QECMASCR) is proposed in this paper. Firstly, quantum chromosome is used to encode the evolutionary population, and a multilevel elitist pool of quantum frogs is constructed in which quantum elitist frogs can fast guide the evolutionary population into the optimal area. Secondly, a reversible cloud mode based on attribute entropy weight is designed to adjust the quantum cloud revolving angle, so that the scope of search space can be adaptively controlled under the guidance of qualitative knowledge. In addition, both the quantum cloud mutation operator and quantum cloud entanglement operator are used to make quantum frogs be adaptive to get the optimal set of attribute reduction fast. Thirdly, an improved decomposition framework of attribute self-adaptive co-evolution is adopted to capture interdependencies of decision variables. It can decompose the largescale attribute set into reasonable-scale subsets according to two kinds of the best performance fitness and assignment credit. Thus, some optimal elitists in different memeplexes of multilevel elitist pool are selected out to evolve their representing attribute subsets, which can increase the cooperation and efficiency of attribute reduction. So the global minimum attribute reduction can be achieved steadily and efficiently. Experimental results indicate the proposed QECMASCR algorithm achieves the better superior performance than existing representative algorithms. Moreover it is applied into MRI segmentation, and the effective and robust segmentation results further demonstrate its stronger applicability. (C) 2014 Elsevier Inc. All rights reserved. | en_US |
dc.language.iso | en_US | en_US |
dc.subject | Multilevel elitist pool | en_US |
dc.subject | Quantum elitist frog | en_US |
dc.subject | Cloud model operator | en_US |
dc.subject | Attribute self-adaptive co-evolution based | en_US |
dc.subject | decomposition framework | en_US |
dc.subject | Assignment credit | en_US |
dc.subject | MRI segmentation | en_US |
dc.title | A more efficient attribute self-adaptive co-evolutionary reduction algorithm by combining quantum elitist frogs and cloud model operators | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1016/j.ins.2014.09.010 | en_US |
dc.identifier.journal | INFORMATION SCIENCES | en_US |
dc.citation.volume | 293 | en_US |
dc.citation.spage | 214 | en_US |
dc.citation.epage | 234 | en_US |
dc.contributor.department | 腦科學研究中心 | zh_TW |
dc.contributor.department | Brain Research Center | en_US |
dc.identifier.wosnumber | WOS:000345480900013 | en_US |
dc.citation.woscount | 0 | en_US |
Appears in Collections: | Articles |