Software clustering algorithms are used to create high-level views of a system’s structure using source code-level artifacts. Software clustering is an active area of research that has produced many clustering algorithms. However, we have seen very little work that investigates how the results of these algorithms can be evaluated objectively in the absence of a benchmark decomposition, or witho...

Unsupervised sequence learning is important to many applications. A learner is presented with unlabeled sequential data, and must discover sequential patterns that characterize the data. Popular approaches to such learning include (and often combine) frequency-based approaches and statistical analysis. However, the quality of results is often far from satisfactory. Though most previous investig...

The paper proposes a technique based on a combined approach of data mining algorithms and linear programming methods for classifying organizational units, such as research centers. We exploit clustering algorithms for grouping information concerning the scientific activity of research centers. We also show that the replacement of an expensive efficiency measurement, based on the solution of lin...

To better meet users’ underlying navigational requirement, search engines like Baidu has developed general recommendation engine and provided related entities on the right side of the search engine results page(SERP). However, users’ behavior have not been well investigated after the association of individual queries in search engine. To better understand users’ navigational activities, we prop...

We study a multiscale discontinuous Galerkin method introduced in [10] that reduces the computational complexity of the discontinuous Galerkin method, seemingly without adversely affecting the quality of results. For a stabilized variant we are able to obtain the same error estimates for the advection-diffusion equation as for the usual discontinuous Galerkin method. We assess the stability of ...

The combination of multiple classifiers to generate a single classifier has been shown to be very useful in practice. Similarly, several efforts have shown that cluster ensembles can improve the quality of results as compared to a single clustering solution. These observations suggest that ensembles containing both classifiers and clusterers are potentially useful as well. Specifically, cluster...

While most knowledge engineers believe that the quality of results obtained by means of Bayesian networks is not too sensitive to imprecision in probabilities, this remains a conjecture with only modest empirical support. We summarize the results of several previously presented experiments involving Hepar II model, in which we manipulated the quality of the model’s numerical parameters and chec...

Web link analysis has been proven to provide significant enhancement to the precision of web search in practice. The PageRank algorithm, used in the Google Search Engine, plays an important role in improving the quality of results by employing an explicit hyperlink structure among the Web pages. The prestige of Web pages defined by PageRank is derived solely from surfers’ random walk on the Web...

The quality of results for partitioning clustering algorithms depends on the assumption made on the number of clusters presented in the data set. Applying clustering methods on real data missing values turn out to be an additional challenging problem for clustering algorithms. Fuzzy clustering approaches adapted to incomplete data perform well for a given number of clusters. In this study, we a...

The network community structure detection problem has been recently approached with several variants of an extremal optimization algorithm. An extremal optimization algorithm is a stochastic local search method that evolves pairs of individuals that can be represented as having several components by randomly replacing components having worst fitnesses. The number of components to be replaced in...