Knowledge Management System of Institue of Mechanics, CAS
| Pattern Recognition With Weighted Complex Networks | |
| Cheh J; Zhao H; Cheh, J (reprint author), Xiamen Univ, Dept Phys, Inst Theoret Phys & Astrophys, Xiamen 361005, Peoples R China. | |
| Source Publication | Physical Review E
 |
| 2008 | |
| ISSN | 1539-3755 |
| Abstract | In this paper we introduce a weighted complex networks model to investigate and recognize structures of patterns. The regular treating in pattern recognition models is to describe each pattern as a high-dimensional vector which however is insufficient to express the structural information. Thus, a number of methods are developed to extract the structural information, such as different feature extraction algorithms used in pre-processing steps, or the local receptive fields in convolutional networks. In our model, each pattern is attributed to a weighted complex network, whose topology represents the structure of that pattern. Based upon the training samples, we get several prototypal complex networks which could stand for the general structural characteristics of patterns in different categories. We use these prototypal networks to recognize the unknown patterns. It is an attempt to use complex networks in pattern recognition, and our result shows the potential for real-world pattern recognition. A spatial parameter is introduced to get the optimal recognition accuracy, and it remains constant insensitive to the amount of training samples. We have discussed the interesting properties of the prototypal networks. An approximate linear relation is found between the strength and color of vertexes, in which we could compare the structural difference between each category. We have visualized these prototypal networks to show that their topology indeed represents the common characteristics of patterns. We have also shown that the asymmetric strength distribution in these prototypal networks brings high robustness for recognition. Our study may cast a light on understanding the mechanism of the biologic neuronal systems in object recognition as well. |
| Keyword | Neural-networks Associative Memory Performance Components Topology |
| DOI | 10.1103/PhysRevE.78.056107 |
| Indexed By | SCI |
| Language | 英语 |
| WOS ID | WOS:000261213800015 |
| WOS Keyword | NEURAL-NETWORKS ; ASSOCIATIVE MEMORY ; PERFORMANCE ; COMPONENTS ; TOPOLOGY |
| WOS Research Area | Physics |
| WOS Subject | Physics, Fluids & Plasmas ; Physics, Mathematical |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://dspace.imech.ac.cn/handle/311007/25822 |
| Collection | 力学所知识产出(1956-2008) |
| Corresponding Author | Cheh, J (reprint author), Xiamen Univ, Dept Phys, Inst Theoret Phys & Astrophys, Xiamen 361005, Peoples R China. |
| Recommended Citation GB/T 7714 | Cheh J,Zhao H,Cheh, J . Pattern Recognition With Weighted Complex Networks[J]. Physical Review E,2008. |
| APA | Cheh J,Zhao H,&Cheh, J .(2008).Pattern Recognition With Weighted Complex Networks.Physical Review E. |
| MLA | Cheh J,et al."Pattern Recognition With Weighted Complex Networks".Physical Review E (2008). |
| Files in This Item: | Download All | |||||
| File Name/Size | DocType | Version | Access | License | ||
| Jp121.pdf（567KB） | 开放获取 | -- | View Download | |||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment