Improve Adaptive k-Nearest Neighbor Algorithm using Multi-threading

  Krupali A. Hansaliya,  Kamal Sutaria

The traditional k-nearest neighbor (kNN) algorithm is one of the oldest method for classification. It benefits from distances among examples to classify the data. The traditional kNN algorithm usually identifies the same number of nearest neighbors for each test examples. This is one of the limitations of traditional kNN algorithm which is overcome by an adaptive k-nearest neighbor (AdaNN) algorithm. The AdaNN algorithm finds out the optimal k, the number of the fewest nearest neighbor to classify each test example correctly. For classifying test examples, AdaNN set k to be the same as the optimal k of its nearest neighbor in the training data. AdaNN algorithm gives better performance than the traditional kNN. In this paper we improved the performance of adaptive kNN algorithm using multi-threading technique. The performance of the proposed algorithm is tested on several medical datasets. Experimental results indicate that our algorithm performs better than the traditional kNN algorithm and adaptive kNN algorithm.

Keywords- k-nearest neighbor algorithm (kNN), Adaptive k-nearest neighbor algorithm (AdaNN), nearest neighbors, Multi-threading

Unique Identification Number - IJEDR1602275
Page Number(s) - 1536-1541
Pubished in - Volume 4 | Issue 2 | June 2016
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Krupali A. Hansaliya,  Kamal Sutaria,   "Improve Adaptive k-Nearest Neighbor Algorithm using Multi-threading", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.4, Issue 2, pp.1536-1541, June 2016, Available at :http://www.ijedr.org/papers/IJEDR1602275.pdf