Display options
Cite
Peng J, Heisterkamp DR, Dai HK. LDA/SVM driven nearest neighbor classification. IEEE Trans Neural Netw. 2003;14(4):940-2doi: 10.1109/TNN.2003.813835.
Peng, J., Heisterkamp, D. R., & Dai, H. K. (2003). LDA/SVM driven nearest neighbor classification. IEEE transactions on neural networks, 14(4), 940-2. https://doi.org/10.1109/TNN.2003.813835
Peng, Jing, et al. "LDA/SVM driven nearest neighbor classification." IEEE transactions on neural networks vol. 14,4 (2003): 940-2. doi: https://doi.org/10.1109/TNN.2003.813835
Peng J, Heisterkamp DR, Dai HK. LDA/SVM driven nearest neighbor classification. IEEE Trans Neural Netw. 2003;14(4):940-2. doi: 10.1109/TNN.2003.813835. PMID: 18238072.
Copy Download .nbib Format: NLM
Share it on

IEEE Trans Neural Netw. 2003;14(4):940-2. doi: 10.1109/TNN.2003.813835.

LDA/SVM driven nearest neighbor classification.

IEEE transactions on neural networks

Jing Peng, D R Heisterkamp, H K Dai

Affiliations

  1. Electr. Eng. and Comput. Sci. Dept., Tulane Univ., New Orleans, LA, USA.

PMID: 18238072 DOI: 10.1109/TNN.2003.813835

Abstract

Nearest neighbor (NN) classification relies on the assumption that class conditional probabilities are locally constant. This assumption becomes false in high dimensions with finite samples due to the curse of dimensionality. The NN rule introduces severe bias under these conditions. We propose a locally adaptive neighborhood morphing classification method to try to minimize bias. We use local support vector machine learning to estimate an effective metric for producing neighborhoods that are elongated along less discriminant feature dimensions and constricted along most discriminant ones. As a result, the class conditional probabilities can be expected to be approximately constant in the modified neighborhoods, whereby better classification performance can be achieved. The efficacy of our method is validated and compared against other competing techniques using a number of datasets.

Publication Types