The naive Bayes classifier has proved to be very effective on many real data applications. Its performance usually benefits from an accurate estimation of univariate conditional probabilities and from variable selection. However, although variable selection is a desirable feature, it is prone to overfitting. In this paper, we introduce a Bayesian regularization technique to select the most probable subset of variables compliant with the naive Bayes assumption. We also study the limits of Bayesian model averaging in the case of the naive Bayes assumption and introduce a new weighting scheme based on the ability of the models to conditionally compress the class labels. The weighting scheme on the models reduces to a weighting scheme on the variables, and finally results in a naive Bayes classifier with “soft variable selection”. Extensive experiments show that the compressionbased averaged classifier outperforms the Bayesian model averaging scheme.

Abstract ⎯ Training systems based on virtual reality are used in several areas of human activities. The user is immersed into a virtual world to have realistic training and realistic interactions with that world. In some kinds of training it is important to know the user's skills. An online assessment system allows to the user improve his learning because it can identify, immediately after the training, where he committed mistakes or presented low efficiency. In this paper, it was used an another approach for Fuzzy Naive Bayes proposed by Störr, for online training assessment based on a for modeling and classification of simulation in N pre-defined classes. Fuzzy Naive Bayes is a generalization of probabilistic networks, specifically Bayesian Networks, which each variable takes linguistic values and they are defined as fuzzy sets. Over them, it is computed a fuzzy partition over continuous variables.

6.8 Conclusion............................... 157

Training systems based on virtual reality are used in several areas, as in the medical sciences. In these systems the user is immersed into a virtual world to have realistic training through realistic interactions. In such training is important to know the quality of user's training and by didactic reasons the user must receive his/her assessment immediately after of end of training. For this reason, an online assessment system allows the user to improve his/her learning because it can identify, where he committed mistakes or presented low efficiency. Several approaches to perform assessment in training simulators based on virtual reality have been proposed. In this paper, we present a new approach to online training assessment based on Gaussian Naive Bayes for modeling and classification of simulation in M pre-defined classes. Gaussian Naive Bayes is a generalization of Naive Bayes Networks, which are a special case of probabilistic networks that allows treating continuous variables.

In very large seaports, where many ships are entering and leaving the port, collision avoidance is of utmost importance. A system used to quickly identify ships and to provide additional information is the Automatic Identification System (AIS). Data Mining methods may be employed to mine AIS trajectory data for patterns to create a model capable of predicting future events, which can be used as an extra aid for situational awareness. Two classification methods are proposed and described to create such model. The final port of a ship entering a large sea port is chosen as future event to predict. Both presented classification methods significantly outperform the baseline method. 1

www.elsevier.com/locate/jvlc

Biclustering has become an important data mining technique for microarray gene expression analysis and profiling, as it provides a local view of the hidden relationships in data, unlike a global view provided by conventional clustering techniques. This technique, in contrast to the conventional clustering techniques, helps in identifying a subset of the genes and a subset of the experimental conditions that together exhibit co-related pattern. In this paper, a biclustering technique using weighted crossing minimization paradigm is proposed, which can mine significant patterns by employing a local search instead of a global search of the input data matrix. We present the novel idea of modelling the gene expression data as a weighted bipartite graph between genes and experimental conditions in order to rearrange the vertices in one layer of this graph. Using this model, an efficient biclustering technique is developed that can mine different types of biclusters and works well in practice for simulated and real world data. The experimental results demonstrate that, our method is scalable to practical gene expression data and has superiority over other similar algorithms in terms of accuracy and computational efficiency.