Proceedings of the 1st International Conference on Management, Business, Applied Science, Engineering and Sustainability Development, ICMASES 2019, 9-10 February 2019, Malang, Indonesia

Research Article

Performance Analysis of Distance Measures in K-Nearest Neighbor

Download2004 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.4108/eai.3-8-2019.2290748,
    author={A F Pulungan and M Zarlis and S Suwilo},
    title={Performance Analysis of Distance Measures in  K-Nearest Neighbor},
    proceedings={Proceedings of the 1st International Conference on Management, Business, Applied Science, Engineering and Sustainability Development, ICMASES 2019, 9-10 February 2019, Malang, Indonesia},
    publisher={EAI},
    proceedings_a={ICMASES},
    year={2020},
    month={1},
    keywords={classification k-nearest neighbor braycurtis distance canberra distance euclidean distance confusion matrix},
    doi={10.4108/eai.3-8-2019.2290748}
}
  • A F Pulungan
    M Zarlis
    S Suwilo
    Year: 2020
    Performance Analysis of Distance Measures in K-Nearest Neighbor
    ICMASES
    EAI
    DOI: 10.4108/eai.3-8-2019.2290748
A F Pulungan1,*, M Zarlis2, S Suwilo3
  • 1: The students in Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Medan, Indonesia
  • 2: Department of Computer Science, Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Medan, Indonesia
  • 3: Department of Mathematics, Universitas Sumatera Utara, Medan, Indonesia
*Contact email: annisa.pulungan93@gmail.com

Abstract

K-Nearest Neighbor (KNN) has important parameters that affect the performance of the KNN. The parameter is the k value and distance matrix. In KNN, the distance between two points is determined by the calculation of the distance matrix. In this paper, we will analyze and compare the performance KNN using the distance function. The distance is Braycurtis, Canberra and Euclidean Distance. This study uses Confusion Matrix for evaluation of accuracy, sensitivity, and specificity. The results showed that the Braycurtis distance had better performance than Canberra Distance and Euclidean Distance with accuracy values of 96%, sensitivity of 96.8% and specificity of 98.2%.

Keywords
classification k-nearest neighbor braycurtis distance canberra distance euclidean distance confusion matrix
Published
2020-01-08
Publisher
EAI
http://dx.doi.org/10.4108/eai.3-8-2019.2290748
Copyright © 2019–2024 EAI