Name
Abstract | ||
|---|---|---|
The need to deduce interesting and valuable information from large, complex, information-rich data sets is common to many research fields. Rule discovery or rule mining uses a set of IF-THEN rules to classify a class or category in a comprehensible way. Besides the classical approaches, many rule mining approaches use biologically-inspired algorithms such as evolutionary algorithms and swarm intelligence approaches. In this paper, a Particle Swarm Optimization based discrete classification implementation with a local search strategy (DPSO-LS) was devised and applied to discrete data. In addition, a fuzzy DPSO-LS (FDPSO-LS) classifier is proposed for both discrete and continuous data in order to manage imprecision and uncertainty. Experimental results reveal that DPSO-LS and FDPSO-LS outperform other classification methods in most cases based on rule size, True Positive Rate (TPR), False Positive Rate (FPR), and precision, showing slightly improved results for FDPSO-LS. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.3233/HIS-140190 | International Journal of Hybrid Intelligent Systems |
Keywords | Field | DocType |
fuzzy rule-based classification system,local strategy,particle swarm optimization,pittsburgh approach | False positive rate,Data mining,Evolutionary algorithm,Computer science,Swarm intelligence,Artificial intelligence,Classifier (linguistics),Particle swarm optimization,Pattern recognition,Fuzzy logic,Multi-swarm optimization,Local search (optimization),Machine learning | Journal |
Volume | Issue | Citations |
11 | 3 | 1 |
PageRank | References | Authors |
0.35 | 23 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Min Chen | 1 | 1 | 0.35 |
| Simone A Ludwig | 2 | 1309 | 179.41 |