International Journal of Hybrid Intelligent Systems

This paper presents an application study of exploiting fuzzy-rough feature selection (FRFS) techniques in aid of efficient and accurate Mars terrain image classification. The employment of FRFS allows the induction of low-dimensionality feature sets from sample descriptions of feature vectors of a much higher dimensionality. Supported with comparative studies, the work demonstrates that FRFS helps to enhance both the effectiveness and the efficiency of conventional classification systems such as multi-layer perceptrons and K-nearest neighbors, by minimizing redundant and noisy features. This is of particular significance for on-board image classification in future Mars rover missions.

There are several papers in the literature in which generalized fuzzy numbers are used for solving real life problems but to the best of our knowledge, till now no one has used generalized fuzzy numbers for solving the maximal flow problems. In this paper, the existing algorithm is modified to find fuzzy maximal flow between source and sink by representing all the parameters as generalized triangular fuzzy numbers. To illustrate the modified algorithm a numerical example is solved and the obtained results are compared with the existing results. If there is no uncertainty about the flow between source and sink then the proposed algorithm gives the same result as in crisp maximal flow problems.

Colour quantisation algorithms are essential for displaying true colour images using a limited palette of distinct colours. The choice of a good colour palette is crucial as it directly determines the quality of the resulting image. Colour quantisation can also be seen as a clustering problem where the task is to identify those clusters that best represent the colours in an image. In this paper, we use a rough c-means clustering algorithm for colour quantisation of images. Experimental results on a standard set of images show that this rough colour quantisation approach performs significantly better than other, purpose built colour reduction algorithms.

The clusters tend to have vague or imprecise boundaries in some fields such as web mining, since clustering has been widely used. Fuzzy clustering is sensitive to noises and possibilistic clustering is sensitive to the initialization of cluster centers and generates coincident clusters. Based on combination of fuzzy clustering and possibilistic clustering, a novel possibilistic fuzzy leader (PFL) clustering algorithm is proposed in this paper to overcome these shortcomings. Considering the advantages of the leader algorithm in time efficiency and the initialization of cluster, the framework of the leader algorithm is used. In addition, a λ-cut set is defined to produce the overlapping clusters autonomously. The comparative experiments with synthetic and standard data sets show that the proposed algorithm is valid, efficient, and has better accuracy. The experiments with the web users access paths data set show that the proposed algorithm is capable of clustering access paths at an acceptable computational expense.

Rough Non-deterministic Information Analysis (RNIA) is a rough set-based data analysis framework for Non-deterministic Information Systems (NISs). RNIA-related algorithms and software tools developed so far for rule generation provide good characteristics of NISs and can be successfully applied to decision making based on non-deterministic data. In this paper, we extend RNIA by introducing stability factor that enables to evaluate rules in a more flexible way and by developing a question-answering functionality that enables decision makers to analyze data gathered in NISs in case there are no pre-extracted rules that may address specified conditions.