DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hwanjo Yu | - |
dc.contributor.author | Seongbo Jang | - |
dc.contributor.author | Ye-Eun Jang | - |
dc.contributor.author | Young-Jin Kim | - |
dc.date.accessioned | 2020-02-11T05:50:09Z | - |
dc.date.available | 2020-02-11T05:50:09Z | - |
dc.date.created | 2020-02-05 | - |
dc.date.issued | 2020-05 | - |
dc.identifier.issn | 0020-0255 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/100876 | - |
dc.description.abstract | Inversion of neural networks aims to find optimal input variables given a target output, and is widely applicable in an industrial field such as optimizing control variables of complex systems in manufacturing facilities. To achieve optimal inputs using a standard first-order optimization technique, proper initialization of input variables is essential. This paper presents a new initialization method for input variables of neural networks based on k-nearest neighbor (k-NN) approach. The proposed method finds inputs which resulted in an output close to a target output in a training dataset, and combine them to form initial input variables. Experiments on a toy dataset demonstrate that our method outperforms random initialization. Also, we introduce an exhaustive case study on power scheduling of a heating, ventilation, and air conditioning (HVAC) system in a building to support the effectiveness of the algorithm. (C) 2020 Elsevier Inc. All rights reserved. | - |
dc.language | English | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.relation.isPartOf | INFORMATION SCIENCES | - |
dc.subject | FREQUENCY REGULATION | - |
dc.title | Input initialization for inversion of neural networks using k-nearest neighbor approach | - |
dc.type | Article | - |
dc.identifier.doi | 10.1016/j.ins.2020.01.041 | - |
dc.type.rims | ART | - |
dc.identifier.bibliographicCitation | INFORMATION SCIENCES, v.519, pp.229 - 242 | - |
dc.identifier.wosid | 000522097600014 | - |
dc.citation.endPage | 242 | - |
dc.citation.startPage | 229 | - |
dc.citation.title | INFORMATION SCIENCES | - |
dc.citation.volume | 519 | - |
dc.contributor.affiliatedAuthor | Hwanjo Yu | - |
dc.contributor.affiliatedAuthor | Seongbo Jang | - |
dc.contributor.affiliatedAuthor | Ye-Eun Jang | - |
dc.contributor.affiliatedAuthor | Young-Jin Kim | - |
dc.identifier.scopusid | 2-s2.0-85078703175 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.type.docType | Article | - |
dc.subject.keywordPlus | FREQUENCY REGULATION | - |
dc.subject.keywordAuthor | Neural network inversion | - |
dc.subject.keywordAuthor | Input optimization | - |
dc.subject.keywordAuthor | Input initialization | - |
dc.subject.keywordAuthor | k-Nearest neighbor (k-NN) | - |
dc.subject.keywordAuthor | HVAC System | - |
dc.subject.keywordAuthor | Power scheduling | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.