首页 | 本学科首页   官方微博 | 高级检索  
   检索      


Bidirectional cognitive computing method supported by cloud technology
Institution:1. Hubei Province Key Laboratory of Intelligent Robots, Wuhan Institute of Technology, Wuhan, PR China;2. School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, PR China;3. Wuhan inCarCloud Technologies Pte. Ltd, Wuhan, PR China;4. Wuhan Winphone Technology Co., Ltd, Wuhan, PR China;1. Laboratory of Neural Systems, Departament of Physics, School of Philosophy, Sciences and Letters of Ribeirão Preto, University of São Paulo, Ribeirão Preto, Brazil;2. Laboratório Nacional de Computação Científica, Av. Getúlio Vargas 333, Petrópolis, RJ, Brazil
Abstract:To realize the bidirectional cognitive computing supported by cloud technology, the cloud model is taken as a bidirectional cognitive computing model based on probability and statistics, a bidirectional cognitive calculation method is constructed, and the bidirectional cognitive conversion between concept connotation and extension is studied. In view of the defects in the existing backward cloud conversion algorithm, two stable multistep backward cloud conversion algorithms are proposed, which lays the foundation for the realization of a stable bidirectional cognitive calculation process. A bidirectional cognitive computing model is proposed, which combines the characteristics of human cognition and the bidirectional cognitive conversion algorithm to simulate bidirectional cognitive computing process based on concept by means of calculation. Moreover, the application of bidirectional cognitive transform algorithm in image segmentation is studied combined with the characteristics of human image cognition. It is also compared with the classical algorithm and methods based on cloud model. The results show that the proposed method has lower mean error and is obviously better than other algorithms, which fully proves the effectiveness of the method.
Keywords:Cloud model  Cognitive computing  Cloud transformation  Uncertainty
本文献已被 ScienceDirect 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号