Similarity measure models and algorithms for hierarchical cases

  • Authors:

  • Dianshuang Wu;Jie Lu;Guangquan Zhang

  • Affiliations:

  • Decision Systems & e-Service Intelligence (DeSI) Lab, Centre for Quantum Computation & Intelligent Systems (QCIS), Faculty of Engineering and Information Technology, University of Technology, Sydn ...;Decision Systems & e-Service Intelligence (DeSI) Lab, Centre for Quantum Computation & Intelligent Systems (QCIS), Faculty of Engineering and Information Technology, University of Technology, Sydn ...;Decision Systems & e-Service Intelligence (DeSI) Lab, Centre for Quantum Computation & Intelligent Systems (QCIS), Faculty of Engineering and Information Technology, University of Technology, Sydn ...

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2011

Quantified Score

Hi-index 12.05

Visualization

Abstract

Many business situations such as events, products and services, are often described in a hierarchical structure. When we use case-based reasoning (CBR) techniques to support business decision-making, we require a hierarchical-CBR technique which can effectively compare and measure similarity between two hierarchical cases. This study first defines hierarchical case trees (HC-trees) and discusses related features. It then develops a similarity evaluation model which takes into account all the information on nodes' structures, concepts, weights, and values in order to comprehensively compare two hierarchical case trees. A similarity measure algorithm is proposed which includes a node concept correspondence degree computation algorithm and a maximum correspondence tree mapping construction algorithm, for HC-trees. We provide two illustrative examples to demonstrate the effectiveness of the proposed hierarchical case similarity evaluation model and algorithms, and possible applications in CBR systems.