Name
Title | ||
|---|---|---|
Discovering useful concept prototypes for classification based on filtering and abstraction |
Abstract | ||
|---|---|---|
The nearest-neighbor algorithm and its derivatives have been shown to perform well for pattern classification. Despite their high classification accuracy, they suffer from high storage requirement, computational cost, and sensitivity to noise. We develop anew framework, called ICPL (Integrated Concept Prototype Learner), which integrates instance-filtering and instance-abstraction techniques by maintaining a balance of different kinds of concept prototypes according to instance locality. The abstraction component, based on typicality, employed in our ICPL framework is specially designed for concept integration. We have conducted experiments on a total of 50 real-world benchmark data sets. We find that our ICPL framework maintains or achieves better classification accuracy and gains a significant improvement in data reduction compared with existing filtering and abstraction techniques as well as some existing techniques. |
Year | DOI | Venue |
|---|---|---|
2002 | 10.1109/TPAMI.2002.1023804 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
abstraction,sensitivity,data reduction,better classification accuracy,existing technique,computational cost,concept prototype discovery,noise,integrated concept prototype learner,pattern classification,abstraction technique,nearest-neighbor algorithm,icpl framework,abstraction component,computational complexity,icpl,instance-filtering,high classification accuracy,filtering theory,concept integration,filtering,noise sensitivity,instance-abstraction techniques,new framework,discovering useful concept prototypes,instance locality,storage requirement,machine learning,neural networks,nearest neighbor,nearest neighbor algorithm,data mining,classification,prototypes,helium | Data mining,Data set,Locality,Abstraction,Computer science,Artificial intelligence,Pattern recognition,Prototype learning,Filter (signal processing),Filtering theory,Machine learning,Computational complexity theory,Data reduction | Journal |
Volume | Issue | ISSN |
24 | 8 | 0162-8828 |
Citations | PageRank | References |
52 | 1.93 | 36 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wai Lam | 1 | 1498 | 145.11 |
| Chi-Kin Keung | 2 | 91 | 6.27 |
| Danyu Liu | 3 | 298 | 19.96 |