1. Identification of Heterogeneous Identifiers of Objects Based on Support Vector Machin
- Author
-
Zhengkun Wu, Lingyun Jiang, and Yanru Mu
- Subjects
Information retrieval ,business.industry ,Computer science ,010401 analytical chemistry ,Feature extraction ,02 engineering and technology ,01 natural sciences ,0104 chemical sciences ,Support vector machine ,Identifier ,Software ,Software deployment ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Object identifier ,business ,MATLAB ,Classifier (UML) ,computer ,computer.programming_language - Abstract
In the applications of the Internet of things, the identifiers of objects are beneficial for authentication and management of objects, and are effective to query the status or data of the object, which greatly accelerate the development and deployment of the Internet of things. At the same time, more and more identification systems, which are supported by an organization or an industry, are gradually formed. With the increasing demand for cross-industry applications, the heterogeneous identifiers of objects bring some problems about research and development. For example, the repeated identifiers of an object will increase the redundant information in the database. Aiming at the heterogeneity of the identification systems, this paper describes the related features of the object identifier through the subset search and subset evaluation methods, and then trains the support vector machine multi-class classifier to identify the heterogeneous identifiers of object. Finally, the simulation experiment is carried out by using the LIBSVM software combined with MATLAB. The experimental results show that the method can effectively identify the heterogeneous identifiers of object.
- Published
- 2019