Information Sciences - Applications最新文献

Fuzzy sets and fuzzy state modeling require modifications of fundamental principles of statistical estimation and inference. These modifications trade increased computational effort for greater generality of data representation. For example, multivariate discrete response data of high (but finite) dimensionality present the problem of analyzing large numbers of cells with low event counts due to finite sample size. It would be useful to have a model based on an invariant metric to represent such data parsimoniously with a latent “smoothed” or low dimensional parametric structure. Determining the parameterization of such a model is difficult since multivariate normality (i.e., that all significant information is represented in the second order moments matrix), an assumption often used in fitting the most common types of latent variable models, is not appropriate. We present a fuzzy set model to analyze high dimensional categorical data where a metric for grades of membership in fuzzy sets is determined by latent convex sets, within which moments up to order J of a discrete distribution can be represented. The model, based on a fuzzy set parameterization, can be shown, using theorems on convex polytopes [1], to be dependent on only the enclosing linear space of the convex set. It is otherwise measure invariant. We discuss the geometry of the model's parameter space, the relation of the convex structure of model parameters to the dual nature of the case and variable spaces, how that duality relates to describing fuzzy set spaces, and modified principles of estimation.

In this paper, two-phase horizontal partitioning of distributed databases is addressed. First, primary horizontal fragmentation is carried out on each relation based on the predicate affinity matrix and the bond energy algorithm. This is an application of a vertical partitioning algorithm to the horizontal fragmentation problem. Second, the derived horizontal fragmentation is further performed by considering information related to the global relational database schema and its transactions. A necessary and sufficient condition for the correctness of derived fragmentations is also proved.

This paper presents a technique of selecting an optimal number of features from the original set of features. Due to the large number of features considered, it is computationally more efficient to select a subset of features that can discriminate as well as the original set. The subset of features is determined using stepwise discriminant analysis. The results of using such a scheme to classify scaled, rotated, and translated binary images and also images that have been perturbed with random noise are reported. The features used in this study are Zernike moments, which are the mapping of the image onto a set of complex orthogonal polynomials. The performance of using a subset is examined through its comparison to the original set.

The classifiers used in this study are neural network and a statistical nearest neighbor classifier. The back-propagation learning algorithm is used in training the neural network. The classifers are trained with some noiseless images and are tested with the remaining data set. When an optimal subset of features is used, the classifers performed almost as well as when trained with the original set of features.

A major cause of freeway congestion before the traffic density becomes critical is the shock wave due to the speed differences between consecutive vehicles. Such disturbance can be reduced if we can impose homogeneous speed control on the vehicles. In this paper, a two-level model-free control scheme using neural-network-based fuzzy logic controllers is proposed which regulates the speed of the freeway through speed advisory boards. Using information from both measurement data and expert knowledge (e.g., environmental information and psychological factors), it is expected that this controller will outperform the conventional ones.

The classification of each pixel in a Landsat image to one of the land cover types by conventional clustering techniques is highly inappropriate due to the low resolution of Landsat images and the multiplicity of terrain. The concept of fuzzy logic provides a flexible solution to this problem. This paper presents a new two-pass unsupervised clustering algorithm incorporated the fuzzy theory. In the first pass the mean vectors of different land cover types representing their geographic attributes are derived. In the second pass the membership grade of a pixel belonging to different land cover types is computed based on the distance between its gray-value vector and the mean vector of each type. Experimental results show that the developed fuzzy clustering algorithm produces more reasonable phenomenon interpretation than the traditional hard partition techniques.

Rosenfeld proposed the concept of the 2D fuzzy subset and successfully applied it to the problem of image segmentation. However, the 2D fuzzy subset approach could be used only for gray scale image segmentation because it fails to handle higher-dimensional range images such as color images. To deal with higher-dimensional range images, we introduce a new concept—fuzzy subfiber—which can be viewed as an extension of the 2D fuzzy subset. In this paper, we give the definition of fuzzy subfiber and discuss one of its most important properties: connectivity on fuzzy subfibers. This property enables us to develop fast image segmentation algorithms for higher-dimensional range images. Finally, we discuss lithology determination (classification) as a real application of fuzzy subfiber.

This paper proposes an innovative approach for dynamically analyzing a user's dialog behavior and inferring a user's domain knowledge level simultaneously that combines neural networks, fuzzy cognitive maps, and fuzzy production rules. Further, this approach supports more cooperative human-computer interaction through dialog adaptation. Furthermore, when the user's knowledge level and problem-solving capability are inferred more accurately, there is more assurance that the system's interaction strategy can match more closely to the user's style. This research implements a neural network for classifying a user's performance pattern using UNIX file security commands. Input and output information that relate to a fuzzy cognitive map and fuzzy production rules are explained.

This paper first proposes a fuzzy neural network and the learning method using fuzzy teaching input. As an application, a fuzzy neural expert system (FNES) for diagnosing hepatobiliary disorders has been developed. We used a real medical database containing the results of nine biochemical tests of four hepatobiliary disorders. After learning by using training data (373 patients), the proposed system correctly diagnosed 77.3% of test (external) data from 163 previously unseen patients and correctly diagnosed 100% of the training data. Conversely, the diagnostic accuracy of the linear discriminant analysis was 63.2% of the test data and 67.0% of the training data.

The paper describes a general-purpose board-level fuzzy inference engine intended primarily for experimental and educational applications. The components are all standard TTL integrated circuits (7400 series) and CMOS RAMs (CY7C series). The engine processes 16 rules in parallel with two antecedents and one consequent per rule. The design may easily be scaled to accommodate more or fewer rules. Static RAMs are used to store membership functions of both antecedent and consequent variables. “Min-max” composition is used for inferencing, and for defuzzification, the mean of maxima strategy is used. Simulation on VALID CAE software predicts that the engine is capable of performing up to 1.56 million fuzzy logic inferences per second.

Application of fuzzy set theory [35] provides a conceptual framework for empirical development of fuzzy user classes for measurement of computer users. Fuzzy classes generalize discrete (fixed boundary) classes by assigning scores that relate each person to each class for representing within-class heterogeneity [13, 25]. Use of fuzzy classes permits individual heterogeneity to be represented by a relatively few analytically defined types [14]. Applying the properties of fuzzy set theory to user classification will result in the definition of a user's membership within a series of fuzzy user classes within the user space. These fuzzy classes can be considered an alternative method for defining stereotypes by empirically defining potential categories into which users can be assigned. The major difference between fuzzy user classes and stereotypes lies in the application of grades of membership to directly measure simultaneous membership in multiple categories. Thus, variability can be very accurately measured and represented using fuzzy sets and grades of membership. These fuzzy classes or user types represent archetypical users or fuzzy users. Application of fuzzy set theory provides an opportunity to extend the current classification methods to measure the differences between users more accurately. This increase in accuracy assists in developing effective adaptive human computer interfaces.