Search

Abstract: Data mining is the process of extracting desirable knowledge or interesting patterns from existing databases for specific purposes. Recently, the fuzzy and the object concepts have been very popular and used in a variety of applications, especially for complex data description. This paper thus proposes a new fuzzy data-mining algorithm for extracting interesting knowledge from quantitative transactions stored as object data. Each item itself is thought of as a class, and each item purchased in a transaction is thought of as an instance. Instances with the same class (item name) may have different quantitative attribute values since they may appear in different transactions. The proposed fuzzy algorithm can be divided into two main phases. The first phase is called the fuzzy intra-object mining phase, in which the linguistic large itemsets associated with the same classes (items) but with different attributes are derived. Each linguistic large itemset found in this phase is thought of as a composite item used in phase 2. The second phase is called the fuzzy inter-object mining phase, in which the large itemsets are derived and used to represent the relationship among different kinds of objects. An example is used to illustrate the algorithm. Experimental results are also given to show the effects of the proposed algorithm. [Copyright &y& Elsevier]

Abstract: The index C pmk is a well-known loss-based process capability index. It can reveal more information about the location of the process mean compared with other classic process capability indices. This index is also more sensitive than other capability indices to any deviations from process mean. When there are some uncertainties in observations, fuzzy logic can be employed to manage these uncertainties. There is some research on different fuzzy process capability indices and this paper is an extension of for the process capability index C pmk of fuzzy numbers. In order to find the membership function of process capability index C pmk , the α-cuts of the fuzzy observation were employed. An example of fuzzy process capability C pmk calculator was illustrated and compared with other classic fuzzy process capability indices and . Results showed that fuzzy has the advantages of both and . Since the index C pmk is a more sensitive index compared with other classic indices, the fuzzy process capability index can be a more sensitive fuzzy index compared with and . [Copyright &y& Elsevier]

Abstract: This paper proposes a genetic algorithm-based heuristic for the capacitated lotsizing problem in flow shops with sequence-dependent setups. The proposed heuristic combines genetic algorithm with rolling horizon approach. To evaluate the effectiveness of the proposed heuristic, some numerical experiments are conducted and corresponding results are compared with those of previously developed heuristics by authors. The comparative results indicate the superiority of genetic algorithm-based heuristic specially in solving the large-sized problem instances. [Copyright &y& Elsevier]

Abstract: The differential evolution (DE) is a global optimization algorithm to solve numerical optimization problems. Recently the quantum-inquired differential evolution (QDE) has been proposed for binary optimization. This paper proposes DE/QDE to learn the Takagi–Sugeno (T–S) fuzzy model. DE/QDE can simultaneously optimize the structure and the parameters of the model. Moreover a new encoding scheme is given to allow DE/QDE to be easily performed. The two benchmark problems are used to validate the performance of DE/QDE. Compared to some existing methods, DE/QDE shows the competitive performance in terms of accuracy. [Copyright &y& Elsevier]

Abstract: In this paper, we present a new method for analyzing fuzzy risk based on a new method for ranking generalized fuzzy numbers. First, we present a new method for ranking generalized fuzzy numbers. It considers the areas on the positive side, the areas on the negative side and the heights of the generalized fuzzy numbers to evaluate ranking scores of the generalized fuzzy numbers. The proposed method can overcome the drawbacks of some existing methods for ranking generalized fuzzy numbers. Then, we apply the proposed method for ranking generalized fuzzy numbers to develop a new method for dealing with fuzzy risk analysis problems. The proposed method provides us with a useful way to deal with fuzzy risk analysis problems based on generalized fuzzy numbers. [ABSTRACT FROM AUTHOR]

Abstract: Segmenting center of interests (COIs) from pictures is an important but highly challenging problem for researchers in computer vision and image processing. The capability of understanding the meanings of pictures by computers can lead to breakthroughs in a wide range of applications including Web image search and online picture-sharing communities. In this paper, a two-level strategy is presented, which consists of a rough segmentation stage and a fine segmentation stage. In the first level, a picture is partitioned into four regions by using a block clustering method based on color and texture features, and the COI within the picture is distinguished from the background according to the principles of photographic composition. This stage aims to determine the approximate region of the target. In the second level, a novel active contour model is established based on shape information and vector method, where the image energy is defined by a hue gradient and the external energy is generated from either a triangular inner force or a supplementary force. This stage tries to extract the boundary of the target accurately. Experimental results on photos downloaded from the Internet show the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Abstract: Tags are user-generated keywords for entities. Recently tags have been used as a popular way to allow users to contribute metadata to large corpora on the web. However, tagging style websites lack the function of guaranteeing the quality of tags for other usages, like collaboration/community, clustering, and search, etc. Thus, as a remedy function, automatic tag recommendation which recommends a set of candidate tags for user to choice while tagging a certain document has recently drawn many attentions. In this paper, we introduce the statistical language model theory into tag recommendation problem named as language model for tag recommendation (LMTR), by converting the tag recommendation problem into a ranking problem and then modeling the correlation between tag and document with the language model framework. Furthermore, we leverage two different methods based on both keywords extraction and keywords expansion to collect candidate tag before ranking with LMTR to improve the performance of LMTR. Experiments on large-scale tagging datasets of both scientific and web documents indicate that our proposals are capable of making tag recommendation efficiently and effectively. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a gradient-based adaptive error diffusion method with edge enhancement effect while preserving the smoothness effect. The proposed method not only can modulate the threshold in halftoning dynamically but also can determine the weights of the error diffusion filter adaptively to diffuse the quantization error to neighboring pixels properly. Under six testing images, experimental results demonstrate that our proposed new error diffusion method has a good compromise between the edge enhancement effect in the halftone image and the image quality effect in the corresponding inverse halftone image when compared to the methods by Floyd–Steinberg, Eschbach and Knox, Hwang et al., Li, and Feng et al., but it has some execution-time degradation. [ABSTRACT FROM AUTHOR]

Abstract: Text steam analysis is now of great importance and practical value today. It has several applications such as news group filtering, topic detection & tracking (TDT), user characterized recommendation etc. Clustering is one of the most important methods of analyzing text stream. However, most text stream clustering algorithms rarely consider the possible change of features during a long-time of clustering, which is usually the case, leading to unsatisfactory results of the clustering system. The paper mainly focuses on the problem of adaptive feature selection for clustering text stream. A validity index based method of adaptive feature selection is proposed, incorporating with which a new text stream clustering algorithm is developed. During the clustering process, threshold of cluster valid index is used to automatically trigger feature re-selection in order to ensure the validity of clustering. The experiment using Reuters-21578 text set as the text source shows that the clustering algorithm reaches reasonable results of high quality. [ABSTRACT FROM AUTHOR]

Abstract: In many domains today there are very limited explicit ontologies established for implementing information systems. Traditional ontology-driven semantic integration approaches cannot be directly applied in integrating these information systems. Usually, the information systems have schemas, a type of formal information model, for their information repositories which to some extent imply the semantics of the information. Each schema actually reflects a specific view of the domain conceptualization. This paper investigates the theoretical foundation of ontologies and extends the traditional ontology concept to the ontological view concept. It proposes to use ontological views to address the challenge of semantic integration. The proposed approach adopts the schemas to create local ontological views, uses data instances of the information systems to discover semantic relationships between the concepts within the ontological views, and builds a domain ontological view based on the discovered equivalence mappings. It applies the hierarchical clustering technique on the data instances and, in the further analysis, uses the clusters to reduce the cost of processing a large amount of data. The matching of concept properties is based on the probability distribution of the data instances. The experimental results have demonstrated the effectiveness of this approach. [ABSTRACT FROM AUTHOR]

In the last decades, several tools and various methodologies have been proposed by the researchers for developing effective medical decision support systems. Moreover, new methodologies and new tools are continued to develop and represent day by day. Diagnosing of the heart disease is one of the important issue and many researchers investigated to develop intelligent medical decision support systems to improve the ability of the physicians. In this paper, we introduce a methodology which uses SAS base software 9.1.3 for diagnosing of the heart disease. A neural networks ensemble method is in the centre of the proposed system. This ensemble based methods creates new models by combining the posterior probabilities or the predicted values from multiple predecessor models. So, more effective models can be created. We performed experiments with the proposed tool. We obtained 89.01% classification accuracy from the experiments made on the data taken from Cleveland heart disease database. We also obtained 80.95% and 95.91% sensitivity and specificity values, respectively, in heart disease diagnosis. [Copyright &y& Elsevier]

Abstract: Predicting the preferences of users and providing the personalized services or products based on their preferences are the important issues. However, the research considering users’ preferences on context-aware computing is a relatively insufficient research field. Hence, this paper aims to propose an agent-based framework for providing the personalized services using context history on context-aware computing. Based on the proposed framework, we implement a prototype system to show the feasibility of the framework. Previous researches require that the users input their preference manually, but this research provides the personalized services extracting the relationship between users’ profile and services under the same context automatically. [Copyright &y& Elsevier]

This paper proposes an image interpolation model based on probabilistic neural network (PNN). The method adjusts automatically the smoothing parameters for varied smooth/edge image region, and takes into consideration both smoothness (flat region) and sharpness (edge region) characteristics at the same model. A single neuron, combined with PSO training, is used for sharpness/smoothness adaptation. Finally, we report the performance of these newly proposed methods in other image interpolation method. [Copyright &y& Elsevier]

For continuous systems with polytopic uncertainties, the mixed H 2/H ∞ robust output control problem is considered in this paper. The design objective is to seek a static output feedback controller that is able to stabilize the uncertain system and to minimize the mixed H 2/H ∞ norm. To this end, a hybrid algorithm mixed by the technique of Hurwitz testing matrix of family of polynomial, average performance constraint and genetic algorithm (GA) is proposed. Due to the fact that the algorithm is based on GAs, we use a hierarchical structure to merge the conditions of Hurwitz testing matrix technique and average performance constraint into a fitness function which is called Hierarchical Fitness Function Structure (HFFS). By replacing fitness function with HFFS, any GAs can be applied to constitute the algorithm. Also, the proposed approach does not need any assumptions, so it is much more relaxed than that of Lyapunov-based design methods. [Copyright &y& Elsevier]

As an important preprocessing technology in text classification, feature selection can improve the scalability, efficiency and accuracy of a text classifier. In general, a good feature selection method should consider domain and algorithm characteristics. As the Naïve Bayesian classifier is very simple and efficient and highly sensitive to feature selection, so the research of feature selection specially for it is significant. This paper presents two feature evaluation metrics for the Naïve Bayesian classifier applied on multi-class text datasets: Multi-class Odds Ratio (MOR), and Class Discriminating Measure (CDM). Experiments of text classification with Naïve Bayesian classifiers were carried out on two multi-class texts collections. As the results indicate, CDM and MOR gain obviously better selecting effect than other feature selection approaches. [Copyright &y& Elsevier]

Abstract: In this paper, we present a generalized model for handling prioritized multicriteria decision making systems. First, we present a new method for handling prioritized multicriteria decision making problems, where the weights of the lower priority criteria of each alternative depend on whether each alternative satisfies the requirements of all the higher priority criteria or not. Then, we also present a generalized prioritized multicriteria decision making method for handling multicriteria decision making problems, where some criteria may have equal priority which can be aggregated by the ordered weighted averaging (OWA) operator or the weighted averaging method. The proposed methods can overcome the drawbacks of the methods presented in [Yager, R. R. (2004a). Modeling prioritized multicriteria decision making. IEEE Transactions on Systems, Man, and Cybernetics-Part B: Cybernetics, 34(6), 2396–2404]. The proposed methods can handle multicriteria decision making problems in a more intelligent and more flexible manner. [Copyright &y& Elsevier]

Effective and efficient development of product configuration systems, including the modeling of product configuration knowledge and the development of inference systems, is a key successful factor to implement mass customization paradigm. Ontology-based method for knowledge representation offers a means for the reuse and sharing of knowledge unambiguously. In this paper, we present a way of representing product configuration knowledge using semantic web technology, namely OWL and SWRL, and developing actual configuration engines based on derived configuration knowledge. Firstly, a general configuration ontology model defining vocabularies, terminologies and relationships that are common to the product configuration domain is constructed to act as a general semantic foundation for product configuration. With this general model, domain specific configuration models can be derived by inheriting or subclassing the ontologies within this general model. Both general ontology-based model and domain specific configuration model are formalized using OWL, an ontology language for encoding knowledge over the Web. Furthermore, constraint knowledge, such as require constraints and resource constraints, is represented with SWRL, a rule language based on OWL. Finally, actual configuration system is implemented using JESS by mapping OWL-based configuration knowledge and SWRL-based constraints into Jess facts and Jess, respectively. The presented ontology-based method for representing configuration knowledge enables the reuse of product configuration knowledge and thus facilitates the processes of modeling product configuration knowledge. In addition, the implementation of actual configuration system with existing rule engine, namely JESS, makes it possible the rapid development of product configuration systems. [Copyright &y& Elsevier]

Online mining of path traversal patterns from Web click-streams is one of the most important problems of Web usage mining. In this paper, we propose a sliding window-based Web data mining algorithm, called Top-SW (Top-k path traversal patterns of Stream sliding Window), to discover the set of top-k path traversal patterns from streaming maximal forward references, where k is the desired number of path traversal patterns to be mined. A new summary data structure, called Top-list (a list of Top-k path traversal patterns) is developed to maintain the essential information about the top-k path traversal patterns from the current maximal forward references stream. Experimental studies show that the proposed Top-SW algorithm is an efficient, single-pass algorithm for mining the set of top-k path traversal patterns from a continuous stream of maximal forward references. [Copyright &y& Elsevier]

Abstract: This paper experimentally examines the effects of domain complexity on the quality of knowledge acquired and the efficiency with which knowledge acquisition (KA) is accomplished. The experiment is performed using two of the most prominent KA methods: unstructured interviews and protocol analysis. One contribution of the research is that it employs an experimental strategy that pays particular attention to addressing problematic issues of measurement and control. The experimental results indicate that domain complexity strongly influences the quality of knowledge acquired when protocol analysis is used for KA. While finding the other hypotheses to be inconclusive, some interesting trends were also identified regarding the quality and efficiency of knowledge acquisition methods. [Copyright &y& Elsevier]

Abstract: A data stream is a massive, open-ended sequence of data elements continuously generated at a rapid rate. Mining data streams is more difficult than mining static databases because the huge, high-speed and continuous characteristics of streaming data. In this paper, we propose a new one-pass algorithm called DSM-MFI (stands for Data Stream Mining for Maximal Frequent Itemsets), which mines the set of all maximal frequent itemsets in landmark windows over data streams. A new summary data structure called summary frequent itemset forest (abbreviated as SFI-forest) is developed for incremental maintaining the essential information about maximal frequent itemsets embedded in the stream so far. Theoretical analysis and experimental studies show that the proposed algorithm is efficient and scalable for mining the set of all maximal frequent itemsets over the entire history of the data streams. [Copyright &y& Elsevier]

Abstract: The aim of this paper is to estimate the fault location on transmission lines quickly and accurately. The faulty current and voltage signals obtained from a simulation are decomposed by wavelet packet transform (WPT). The extracted features are applied to artificial neural network (ANN) for estimating fault location. As data sets increase in size, their analysis become more complicated and time consuming. The energy and entropy criterion are applied to wavelet packet coefficients to decrease the size of feature vectors. The test results of ANN demonstrate that the applying of energy criterion to current signals after WPT is a very powerful and reliable method for reducing data sets in size and hence estimating fault locations on transmission lines quickly and accurately. [Copyright &y& Elsevier]

Abstract: Following tremendous advancement in information technology, the speed of information development has become increasingly fast-paced. Yet the overabundance of information has forced users to spend more time and resources in searching for information relevant to their needs. Today, recommendation systems already exist that provide services like filtering, customization, and others to assist users in searching for the right information. This study proposes to use ontology and the spreading activation model for research paper recommendation, hoping that it can elevate the performance of the recommendation system and also improve the shortcomings of today’s recommendation systems. This study utilizes ontology to construct user profiles and makes use of user profile ontology as the basis to reason about the interests of users. Furthermore, this study takes advantage of the spreading activation model to search for other influential users in the community network environment, making a study on their interests in order to provide recommendation on related information. Based on actual experiment results, the method of ontology network analysis that combines ontology and the spreading activation model is effective in knowing the research interests of users. Hence, using the mechanism proposed in this study can make up for the insufficiencies or shortcomings of other recommendation systems. Moreover, the precision rate can be up to 93% showing that our recommendation system has a positive effect on the effectiveness of the recommendation. [Copyright &y& Elsevier]

There are some problems that need expertise in order to get a satisfactory solution. Ferryboat carries goods, fresh water, diesel oil, luggage and storing rooms up to its permissible draft in order to maintain safety according to the international safety regulations. The best weight distribution on ferryboat needs human expertise to handle many variables, such as the amount of the bunker and fresh water that allow us to use more rooms for charging in order to maximize the profit. This sort of problems can be classified under Configuration Problem. In this paper, we address the development of a ferryboat expert systems (WDFB) using CommonKADS knowledge engineering methodology. We propose a reusable problem-solving approach, which is an enhancement of the structure-oriented approach, capable of solving the ferryboat configuration problem. The proposed model includes heuristics that make the search of suitable configuration more efficient, taking into consideration the transformation knowledge and the optimality criteria. The results of testing the system on a real-world data from National Navigation Company, Suez, Egypt, were satisfactory. [Copyright &y& Elsevier]

This paper presents a new approach for integrating case-based reasoning (CBR) with an ART-Kohonen neural network (ART-KNN) to enhance fault diagnosis. When solving a new problem, the neural network is used to make hypotheses and to guide the CBR module in the search for a similar previous case that supports one of the hypotheses. The knowledge acquired by the network is interpreted and mapped into symbolic diagnosis descriptors, which are kept and used by the system to determine whether a final answer is credible, and to build explanations for the reasoning carried out. ART-KNN, synthesizing the theory of adaptive resonance theory and the learning strategy of Kohonen neural network, can solve the plasticity-stability dilemma of conventional neural networks. It can carry out ‘on-line’ training without forgetting previously trained patterns (stable training), and recode previously trained categories adaptive to changes in the environment and is self-organizing, which differs from most of networks that only can be carried out off-line. The proposed system has been used in the faults diagnosis of electric motor to verify the system performance. The result shows the proposed system performs better than self-organizing feature map (SOFM) based system with respect to classification rate. [Copyright &y& Elsevier]

This paper investigates the asymmetric costs of false positive and negative errors to enhance the IDS performance. The proposed method utilizes the neural network model to consider the cost ratio of false negative errors to false positive errors. Compared with false positive errors, false negative errors incur a greater loss to organizations which are connected to the systems by networks. This method is designed to accomplish both security and system performance objectives. The results of our empirical experiment show that the neural network model provides high accuracy in intrusion detection. In addition, the simulation results show that the effectiveness of intrusion detection can be enhanced by considering the asymmetric costs of false negative and false positive errors. [Copyright &y& Elsevier]