论文信息 - KNN behavior with set-valued attributes

KNN behavior with set-valued attributes

This paper addresses the problem of dealing with set-valued attributes in the lazy learning context. This type of attribute is present in various domains, yet the instance-based learning tools do not provide a representation for them. To solve this problem, we present a proposal for the treatment of the sets in the context of the k-NN algorithm through an extension to HEOM distance. Experiments using various data sets show the feasibility of this option.

Carlos Morell | Yanet Rodríguez | Mabel González Castellanos

[1] T. Payne. Dimensionality Reduction for Agent-Based Learning , 1996 .

[2] Terry R. Payne. Dimensionality reduction and representation for nearest neighbour learning , 1999 .

[3] Blaz Zupan,et al. Orange: From Experimental Machine Learning to Interactive Data Mining , 2004, PKDD.

[4] Richard C. H. Connor,et al. The Joy of Sets , 1993, DBPL.

[5] Tony R. Martinez,et al. Improved Heterogeneous Distance Functions , 1996, J. Artif. Intell. Res..

[6] David L. Waltz,et al. Toward memory-based reasoning , 1986, CACM.

[7] William W. Cohen. Learning Trees and Rules with Set-Valued Features , 1996, AAAI/IAAI, Vol. 1.

[8] María José del Jesús,et al. KEEL: a software tool to assess evolutionary algorithms for data mining problems , 2008, Soft Comput..

[9] Ingo Mierswa,et al. YALE: rapid prototyping for complex data mining tasks , 2006, KDD '06.

[10] Ricardo del Corazón Grau-Ábalo,et al. Prediction of Pediatric Risk Using a Hybrid Model Based on Soft Computing Techniques , 2008, MICAI.

[11] D. Kibler,et al. Instance-based learning algorithms , 2004, Machine Learning.