In order to classify data with noises or outliers, Fuzzy support vector machine (FSVM) improve the generalization power of traditional SVM by assigning a fuzzy membership to each input data point. In this paper, an improved FSVM based on vague sets is proposed by assigning a truthmembership and a false-membership to each data point. And we reformulate the improved FSVM so that different input p...

Image sequence stabilization aims to remove unwanted fluctuations from an image sequence. This paper proposes a novel stabilization system making use of a fuzzy filter constructed by dynamic system based estimator definition with a fuzzy corrector. The stabilization system selectively switches between a pre-defined set of membership functions so as to improve gross movement tracking and stabili...

Results from a set o f questionnaires designed to compare methods of obtaining membership functions were analyzed to identify general trends in fuzziness. It was found that fuzziness in comprehension is ahvays reflected in the answer; concepts such as difficulty, imprecision, and shape of membership functions are clearly interrelated; and the transition between crisp extremes through fuzziness ...

An approach to analyzing human walking states based on multiviewing-angle was proposed in this paper. Firstly, the moving person was detected using self-adaptive background updating algorithm. Then, the moving period of the centroid in the upper part of the human body was extracted by 4direction chain code and the next motion of person was predicted. Finally, fuzzy set of walking states was obt...

This paper describes a learning system, OMLET, which helps to automate the construction of function-based object recognition systems. OMLET is designed to learn fuzzy membership functions which approximate the allowable ranges of physical dimensions such as width, area, relative orientation, etc. The learning is done by iterative error reduction on a set of labeled training examples. Results fr...

A set A is symmetric enumeration (se-) reducible to a set B (A≤seB) if A is enumeration reducible to B and A is enumeration reducible to B. This reducibility gives rise to a degree structure (Dse) whose least element is the class of computable sets. We give a classification of ≤se in terms of other standard reducibilities and we show that the natural embedding of the Turing degrees (DT) into th...

Soft segmentation takes an important role in partial volume segmentation for MRI brain image. Soft segmentation is also more flexible than hard segmentation. But the membership functions are usually sensitive to noise. In this paper, we proposed a multiphase soft segmentation model for nearly piecewise constant images based on stochastic principle, where intensities of the image are modeled as ...

Nowadays, the demand for high product quality focuses extensive attention to the quality of machined surface. The (CNC) milling machine facilities provides a wide variety of parameters set-up, making the machining process on the glass excellent in manufacturing complicated special products compared to other machining processes. However, the application of grinding process on the CNC milling mac...

In this paper, new non-quadratic stability conditions are derived based on the parallel distributed compensation scheme to stabilize Takagi-Sugeno (T-S) fuzzy systems. We use a non-quadratic Lyapunov function as a fuzzy mixture of multiple quadratic Lyapunov functions. The quadratic Lyapunov functions share the same membership functions with the T-S fuzzy model. The stability conditions we prop...