A new locally adaptive K-nearest centroid neighbor classification based on the average distance
The classification performance of a k-nearest neighbour (KNN) method is dependent on the choice of the k neighbours of a query. However, it is difficult to optimise the performance of KNN by choosing appropriate neighbours and an appropriate value of k. Moreover, the performance of KNN suffers from...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | Connection Science |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/09540091.2022.2088695 |
| _version_ | 1797684063660670976 |
|---|---|
| author | Benqiang Wang Shunxiang Zhang |
| author_facet | Benqiang Wang Shunxiang Zhang |
| author_sort | Benqiang Wang |
| collection | DOAJ |
| description | The classification performance of a k-nearest neighbour (KNN) method is dependent on the choice of the k neighbours of a query. However, it is difficult to optimise the performance of KNN by choosing appropriate neighbours and an appropriate value of k. Moreover, the performance of KNN suffers from the use of a simple majority voting method. To address these three issues, we propose a new locally adaptive k-nearest centroid neighbour classification based on the average distance (AD-LAKNCN) in this paper. First, the k neighbours of the query based on the nearest centroid neighbour (NCN) are found, and the discrimination classes with different k values are derived from the number and distribution of each class of neighbours considered in the query. Then, based on the distribution information in the discrimination class for each k, the adaptive k and the final classification result are obtained. The experimental results based on 24 real-world datasets show that the new method achieves better classification performance than nine other state-of-the-art KNN algorithms. |
| first_indexed | 2024-03-12T00:23:58Z |
| format | Article |
| id | doaj.art-4a701bb95eb943c381d2fe6673ed6064 |
| institution | Directory Open Access Journal |
| issn | 0954-0091 1360-0494 |
| language | English |
| last_indexed | 2024-03-12T00:23:58Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Connection Science |
| spelling | doaj.art-4a701bb95eb943c381d2fe6673ed60642023-09-15T10:48:00ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013412084210710.1080/09540091.2022.20886952088695A new locally adaptive K-nearest centroid neighbor classification based on the average distanceBenqiang Wang0Shunxiang Zhang1Anhui University of Science and Technology, Huainan, People’s Republic of ChinaAnhui University of Science and Technology, Huainan, People’s Republic of ChinaThe classification performance of a k-nearest neighbour (KNN) method is dependent on the choice of the k neighbours of a query. However, it is difficult to optimise the performance of KNN by choosing appropriate neighbours and an appropriate value of k. Moreover, the performance of KNN suffers from the use of a simple majority voting method. To address these three issues, we propose a new locally adaptive k-nearest centroid neighbour classification based on the average distance (AD-LAKNCN) in this paper. First, the k neighbours of the query based on the nearest centroid neighbour (NCN) are found, and the discrimination classes with different k values are derived from the number and distribution of each class of neighbours considered in the query. Then, based on the distribution information in the discrimination class for each k, the adaptive k and the final classification result are obtained. The experimental results based on 24 real-world datasets show that the new method achieves better classification performance than nine other state-of-the-art KNN algorithms.http://dx.doi.org/10.1080/09540091.2022.2088695k-nearest neighbork-nearest centroid neighboraverage distanceadaptive k value |
| spellingShingle | Benqiang Wang Shunxiang Zhang A new locally adaptive K-nearest centroid neighbor classification based on the average distance Connection Science k-nearest neighbor k-nearest centroid neighbor average distance adaptive k value |
| title | A new locally adaptive K-nearest centroid neighbor classification based on the average distance |
| title_full | A new locally adaptive K-nearest centroid neighbor classification based on the average distance |
| title_fullStr | A new locally adaptive K-nearest centroid neighbor classification based on the average distance |
| title_full_unstemmed | A new locally adaptive K-nearest centroid neighbor classification based on the average distance |
| title_short | A new locally adaptive K-nearest centroid neighbor classification based on the average distance |
| title_sort | new locally adaptive k nearest centroid neighbor classification based on the average distance |
| topic | k-nearest neighbor k-nearest centroid neighbor average distance adaptive k value |
| url | http://dx.doi.org/10.1080/09540091.2022.2088695 |
| work_keys_str_mv | AT benqiangwang anewlocallyadaptiveknearestcentroidneighborclassificationbasedontheaveragedistance AT shunxiangzhang anewlocallyadaptiveknearestcentroidneighborclassificationbasedontheaveragedistance AT benqiangwang newlocallyadaptiveknearestcentroidneighborclassificationbasedontheaveragedistance AT shunxiangzhang newlocallyadaptiveknearestcentroidneighborclassificationbasedontheaveragedistance |