Abstract | ||
---|---|---|
Due to its strong performance in handling uncertain and ambiguous data, the fuzzy
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
-nearest-neighbor method (FKNN) has realized substantial success in a wide variety of applications. However, its classification performance would be heavily deteriorated if the number
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i>
of nearest neighbors was unsuitably fixed for each testing sample. This study examines the feasibility of using only one fixed
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i>
value for FKNN on each testing sample. A novel FKNN-based classification method, namely, fuzzy KNN method with adaptive nearest neighbors (A-FKNN), is devised for learning a distinct optimal
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i>
value for each testing sample. In the training stage, after applying a sparse representation method on all training samples for reconstruction, A-FKNN learns the optimal
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
value for each training sample and builds a decision tree (namely, A-FKNN tree) from all training samples with new labels (the learned optimal
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
values instead of the original labels), in which each leaf node stores the corresponding optimal
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
value. In the testing stage, A-FKNN identifies the optimal
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
value for each testing sample by searching the A-FKNN tree and runs FKNN with the optimal
<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${k}$ </tex-math></inline-formula>
value for each testing sample. Moreover, a fast version of A-FKNN, namely, FA-FKNN, is designed by building the FA-FKNN decision tree, which stores the optimal
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</i>
value with only a subset of training samples in each leaf node. Experimental results on 32 UCI datasets demonstrate that both A-FKNN and FA-FKNN outperform the compared methods in terms of classification accuracy, and FA-FKNN has a shorter running time. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/TCYB.2020.3031610 | IEEE Transactions on Cybernetics |
Keywords | DocType | Volume |
Algorithms,Cluster Analysis | Journal | 52 |
Issue | ISSN | Citations |
6 | 2168-2267 | 2 |
PageRank | References | Authors |
0.36 | 33 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zekang Bian | 1 | 6 | 2.10 |
Chi-Man Vong | 2 | 557 | 41.41 |
Pak-kin Wong | 3 | 282 | 28.33 |
Shitong Wang | 4 | 1485 | 109.13 |