ABSTRACT
The traditional k Nearest Neighbor (KNN)1 algorithm does not consider the relative relationship between the sample features. The classification speed is slow and the computational complexity is high. The distance between the test sample and all the training samples needs to be calculated to determine the k nearest neighbors. Therefore, this paper proposes a fuzzy k nearest neighbor (FKNN) algorithm based on weighted chi-square distance. First, the fuzzy normalization process is performed, and the similarity is taken as the fuzzy membership degree. The closeness of features is used to determine the weight of each feature, and the weighted chi-square distance is used as the distance measure. Finally, the sample class to be classified is determined by the class membership of k neighbors. The classification results show that the evaluation indexes of the algorithm are better than the existing ones.
- Cover T and Hart P. 1967. Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1967), 21--27. Google ScholarDigital Library
- Jiyu Liu, Qiang Wang, Zhao-hui Luo, Hao Song, and Lv-yun Zhang. 2015. Weighted KNN Data Classification Algorithm Based on Rough Sets. Computer Science, 10(2015), 281--286.Google Scholar
- Yijuan Su and Zhenyun Deng. 2016. Fast KNN Classification Algorithm under Big Data. Application Research of Computers, 4(2016), 1003--1006.Google Scholar
- Jinping Zhang and Guangbin Bai. 2017. Method of Rotating Machinery Fault Pattern Recognition Based on PCA and KNN Algorithm. Machinery Design & Manufacture, 6(2017), 23--29.Google Scholar
- Fafa Chen and Mian Li. 2016. Fault Diagnosis of Roller Bearing based on Hybrid Feature Set and Weighted KNN. Mechanical Drive, 8(2016), 138--143.Google Scholar
- Zhengbiao Ji, Jilin Wang, and Li Zhao. 2015. Speech Emotion Recognition Based on FKNN. MICROELECTRONICS & COMPUTER, 3(2015), 59--62.Google Scholar
- Ming Yang. 2007. Study on the Pattern Recognition of Pueraria DC.based on Fuzzy k-nearest Neighbor Algorithm. Journal of Mathematical Medicine, 20(2007), 839--841.Google Scholar
- Mingjuan Song and Siyu Zhu. 2016. The New FKNN Algorithm and Its Application. Fuzzy Systems and Mathematics, 8(2016), 89--93.Google Scholar
- Wenqian Shang, Youli Qu, Houkuan Huang, and Hongbin Dong. 2006. Fuzzy knn text classifier based on gini index. Journal of Guang xi Normal University: Natural Science Edition, 24(2006), 87--90.Google Scholar
- Keller J M, Gray M R, and Givens J A. 1985. A fuzzy k-nearest neighbour algorithm. IEEE Transactions on System, Man and Cybernetics, 15(1985), 580--585.Google ScholarCross Ref
- Hui-Ling Chen Bo Yang, Gang Wang, Jie Liu, Xin Xu, Su-Jing Wang, and Da You Liu. 2011. A novel bankruptcy prediction model based on an adaptive fuzzy k-nearest neighbor method, Knowledge-Based Systems, 24(2011), 1348--1359. Google ScholarDigital Library
- Hong Xie and Hongye Zhao. 2015. An improved KNN algorithm based on Chi-square distance measure. Applied Science and Technology, 2(2015), 10--14.Google Scholar
- Feng Lv, Ni Du, and Chenglin Wen. 2012. A Fuzzy-Evidential k Nearest Neighbor Classification Algorithm. ACTA ELECTRONICA, 12(2012), 2390--2395.Google Scholar
- Xiaolong Huang and Weiting Liu. 2012. Fault Diagnosis Based on Fuzzy Nearness. Science Technology and Engineering, 10(2012), 8111--8115.Google Scholar
- Zheng Tao and Hongyu Wang. 2016. Improved WLAN Localization Algorithm Based on Chi-square Distance. COMPUTER TECHNOLOGY AND DEVELOPMENT, 9(2016), 50--55.Google Scholar
- Zhiwei Shi, Tao Liu, and Gongyi Wu. 2005. A Efficient and Efficient Algorithm for Text Classification. Computer Engineering and Applications, 10(2005), 180--183.Google Scholar
- Frak A and Asuncion A. 2010. UCI machine learning repository. DOI: http://archive.ics.uci.edu/ml/.Google Scholar
Index Terms
- A Fuzzy KNN Algorithm Based on Weighted Chi-square Distance
Recommendations
Improvement of Fuzzy KNN Classification Algorithm Based on Fuzzy C-means
CSAE '18: Proceedings of the 2nd International Conference on Computer Science and Application EngineeringK-nearest-neighbor (KNN)1 algorithm is a kind of classification algorithm, which is simple and easy to implement. However, when there is a large number of training sets or numerous attributes, it has the disadvantage of inefficient and time consuming. ...
Condensed fuzzy nearest neighbor methods based on fuzzy rough set technique
As a generalization of K-nearest neighbor K-NN algorithm, the fuzzy K-nearest neighbor fuzzy K-NN algorithm was originally developed by Keller in 1985 to overcome one of the drawbacks of K-NN i.e. all of instances are considered equally important in K-...
An instance selection algorithm for fuzzy K-nearest neighbor
The condensed nearest neighbor (CNN) is a pioneering instance selection algorithm for 1-nearest neighbor. Many variants of CNN for K-nearest neighbor have been proposed by different researchers. However, few studies were conducted on condensed fuzzy K-...
Comments