The Application of Ant Colony Optimization in CBR
In the Case-Based Reasoning (CBR) System, the retrieval efficiency and system performance are reduced because of the unlimited increasing case base with the incremental learning. This paper proposes the method of ant colony optimization (ACO) in the CBR s
- PDF / 1,761,531 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 89 Downloads / 227 Views
Abstract In the Case-Based Reasoning (CBR) System, the retrieval efficiency and system performance are reduced because of the unlimited increasing case base with the incremental learning. This paper proposes the method of ant colony optimization (ACO) in the CBR system. This method combines the increased efficiency of case retrieval, the effective case base indexing, and the validity of maintenances by adding or reducing cases. Through the all processes we have used the clustering and classification algorithm based ACO. The implementation of the ACO algorithm into the CBR system is successful and the experimental results verify its effectiveness.
Keywords CBR ACO Clustering Classification Case retrieval Case-base maintenance
1 Introduction Case-Based Reasoning (CBR) solves new problems by reusing the old solutions in similar context. As an effective problem-solving method, CBR has been deployed in a wide variety of applications, such as planning, classification, diagnosis, decision supporting system and others [1]. CBR as an important complement to the rule-based reasoning (RBR), to some extent, has make up for the defects in the RBR. The knowledge acquisition J. Shu (&) School of Medicine Information Engineering, Anhui University of Traditional Chinese Medicine, Hefei, Anhui, China e-mail: [email protected] J. Shu School of Mathematics and Physics, Anhui University of Science and Technology, Huainan, Anhui, China
Z. Yin et al. (eds.), Proceedings of The Eighth International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA), 2013, Advances in Intelligent Systems and Computing 212, DOI: 10.1007/978-3-642-37502-6_143, Springer-Verlag Berlin Heidelberg 2013
1229
1230
J. Shu
bottleneck has received the attention of artificial intelligence researchers. CBR has many advantages which are discussed below: it has a strong learning ability; the realization is relatively simple; the maintenance of knowledge is simple. However, CBR, there are also some problems: (1) it is particularly sensitive to noise data, error data and redundant data which will affect the efficiency of the system retrieves and solution results easily; (2) when the number of cases in the case base is increasing, it may be retrieved low efficiency, redundant search results; (3) the knowledge acquisition bottlenecks still exist. Therefore, it is necessary to improve the search capabilities of the case base and strengthen the case base maintenance. Ant colony optimization (ACO) [2] is a population-based meta heuristic that can be used to find approximate solutions to difficult optimization problems. It is inspired by the foraging behavior of ant colonies. The first ant colony optimization algorithm was proposed in 1991 by Dorigo M for the approximate solution of the traveling salesman problem. Afterwards, the ACO algorithm has been applied successfully to many combinatorial optimization problems, such as the assignment problems, scheduling problems, vehicle routing problems. But, recently there exist new ACO a
Data Loading...
