1-4hit |
Hang ZHOU Qing LI Hai ZHU Jian WANG
Large-scale virtualized data centers are increasingly becoming the norm in our data-intensive society. One pressing challenge is to reduce the energy consumption of servers while maintaining a high level of service agreement fulfillment. Due to the convenience of virtualization, virtual machine migration is an effective way to optimize the trade-off between energy and performance. However, there are obvious drawbacks in the current static threshold strategy for migration. This paper proposes a new decision strategy based on decision-theoretic rough sets. In the new strategy, the status of a server is determined by the Bayesian rough set model. The space is divided into positive, negative and boundary regions. According to this information, a migration decision with minimum risk will be made. This three-way decision framework in our strategy can reduce over-migration and delayed migration. The experiments in this paper show that this new strategy outperforms the benchmark examined. It is an efficient and flexible approach to the energy and performance trade-off in the cloud.
Sombut FOITONG Ouen PINNGERN Boonwat ATTACHOO
Feature selection (FS) plays an important role in pattern recognition and machine learning. FS is applied to dimensionality reduction and its purpose is to select a subset of the original features of a data set which is rich in the most useful information. Most existing FS methods based on rough set theory focus on dependency function, which is based on lower approximation as for evaluating the goodness of a feature subset. However, by determining only information from a positive region but neglecting a boundary region, most relevant information could be invisible. This paper, the maximal lower approximation (Max-Certainty) – minimal boundary region (Min-Uncertainty) criterion, focuses on feature selection methods based on rough set and mutual information which use different values among the lower approximation information and the information contained in the boundary region. The use of this idea can result in higher predictive accuracy than those obtained using the measure based on the positive region (certainty region) alone. This demonstrates that much valuable information can be extracted by using this idea. Experimental results are illustrated for discrete, continuous, and microarray data and compared with other FS methods in terms of subset size and classification accuracy.
Fan LI Shijin DAI Qihe LIU Guowei YANG
This letter presents a new inter-cluster proximity index for fuzzy partitions obtained from the fuzzy c-means algorithm. It is defined as the average proximity of all possible pairs of clusters. The proximity of each pair of clusters is determined by the overlap and the separation of the two clusters. The former is quantified by using concepts of Fuzzy Rough sets theory and the latter by computing the distance between cluster centroids. Experimental results indicate the efficiency of the proposed index.
The purpose of this paper is to offer a modal logic which enables us symbolic reasoning about data, especially, fuzzy relations. For such a purpose, the present author provided some systems of modal fuzzy logic. As a continuous one of those previous works, a logic based on the graded modalities is proposed. After showing some properties of this logic, the decision procedure for this logic is given in the rectangle method.