An Efficient Approach to enhance the clustering and classification ensembles technique based on RBF and SOM Network [ READ ]
Kirit Singh, Prof. Sitendra Tamrakar
In this paper we proposed a novel method for mixed data classification based on clustering and classification ensemble. Ensemble learning is a commonly used tool for building prediction models from data classification, due to its intrinsic merits of handling large volumes data. Despite of its extraordinary successes in stream data mining, existing ensemble models, in stream data environments, mainly fall into the ensemble classifiers category, without realizing that building classifiers requires labor intensive labeling process, and it is often the case that we may have a small number of labeled samples to train a few classifiers, but a large number of unlabeled samples are available to build clusters from mixed data. Ensemble clustering-classification aims to combine multiple clusters together for prediction. For a given test set, each cluster will derive a label vector. Noticing that some label vectors may conflict with each other, most state-of-theart ensemble clusters models employ a equiledian distance metric to minimize the discrepancy between each pair of label vectors. Although such a label vector based consensus method performs well on mixed dataset. Our novel approached divide into three sections first on ECC method second one is ECC with SOM network and finally ECC –RBF.
Kirit Singh, Prof. Sitendra Tamrakar
In this paper we proposed a novel method for mixed data classification based on clustering and classification ensemble. Ensemble learning is a commonly used tool for building prediction models from data classification, due to its intrinsic merits of handling large volumes data. Despite of its extraordinary successes in stream data mining, existing ensemble models, in stream data environments, mainly fall into the ensemble classifiers category, without realizing that building classifiers requires labor intensive labeling process, and it is often the case that we may have a small number of labeled samples to train a few classifiers, but a large number of unlabeled samples are available to build clusters from mixed data. Ensemble clustering-classification aims to combine multiple clusters together for prediction. For a given test set, each cluster will derive a label vector. Noticing that some label vectors may conflict with each other, most state-of-theart ensemble clusters models employ a equiledian distance metric to minimize the discrepancy between each pair of label vectors. Although such a label vector based consensus method performs well on mixed dataset. Our novel approached divide into three sections first on ECC method second one is ECC with SOM network and finally ECC –RBF.
