کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
530408 | 869765 | 2014 | 12 صفحه PDF | دانلود رایگان |
![عکس صفحه اول مقاله: Information theoretic clustering using a k-nearest neighbors approach Information theoretic clustering using a k-nearest neighbors approach](/preview/png/530408.png)
• Propose a new method of estimating Information Theoretic measures using KNN.
• Introduce a hierarchical clustering routine using this estimate.
• Use two different values for k depending on which information theoretic measure is being estimated.
• Avoid having to tune a critical parameter for each clustering task.
• Handles datasets of different scales well compared to traditional methods.
We develop a new non-parametric information theoretic clustering algorithm based on implicit estimation of cluster densities using the k-nearest neighbors (k-nn) approach. Compared to a kernel-based procedure, our hierarchical k-nn approach is very robust with respect to the parameter choices, with a key ability to detect clusters of vastly different scales. Of particular importance is the use of two different values of k, depending on the evaluation of within-cluster entropy or across-cluster cross-entropy, and the use of an ensemble clustering approach wherein different clustering solutions vote in order to obtain the final clustering. We conduct clustering experiments, and report promising results.
Journal: Pattern Recognition - Volume 47, Issue 9, September 2014, Pages 3070–3081