Journal of Northeastern University Natural Science ›› 2019, Vol. 40 ›› Issue (7): 932-936.DOI: 10.12068/j.issn.1005-3026.2019.07.004

• Information & Control • Previous Articles     Next Articles

A Modified KNN Classifier for Unbalanced Dataset

LIU Peng1,2, DU Jia-zhi3, LYU Wei-gang2,4, DOU Ming-wu1   

  1. 1. Computing Center, Ocean University of China, Qingdao 266100, China; 2. School of Information, Ocean University of China, Qingdao 266100, China; 3. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China; 4. Department of Educational Technology, Ocean University of China, Qingdao 266100, China.
  • Received:2018-07-13 Revised:2018-07-13 Online:2019-07-15 Published:2019-07-16
  • Contact: DOU Ming-wu
  • About author:-
  • Supported by:
    -

Abstract: The existing arrhythmia datasets are suffering from the unbalanced number of training sample for electrocardiogram(ECG) data due to the obvious difference among the sample number of different types. A novel KNN-based classification algorithm, i.e., a modified kernel difference-weighted KNN classifier(MKDF-WKNN) was proposed, by introducing a correction factor to restrain the weights of the categories with more samples and increase the weights of the categories with fewer samples. The experiment was carried on the UCI arrhythmia dataset to classify the ECG data. The results show that, for unbalanced datasets the proposed algorithm is better than some other KNN-based algorithms such as KNN, DS-WKNN, DF-WKNN and KDF-WKNN, in terms of classification accuracy.

Key words: cardiac arrhythmias, electrocardiogram, pattern classification, KNN algorithm, unbalanced dataset

CLC Number: