Lost Student Tracking in an Incomplete and Imprecise Information Environment Using Soft Computing Paradigm

Due to the growing variety and quantity of information available on the Web, there is urgent need for developing Web-based applications capable of adapting their services to the needs of the users. This is the main rationale behind the flourishing area of Web personalization that finds in soft computing (SC) techniques a valid tool to handle uncertainty in Web usage data and develop Web-based applications tailored to user preferences. The main reason for this success seems to be the synergy resulting from SC paradigms, such as fuzzy logic, neural networks, and genetic algorithms. Each of these computing paradigms provides complementary reasoning and searching methods that allow the use of domain knowledge and empirical data to solve complex problems. In this chapter, we emphasize the suitability of hybrid schemes combining different SC techniques for the development of effective Web personalization systems. In particular, we present a neuro-fuzzy approach for Web personalization that combines techniques from the fuzzy and the neural paradigms to derive knowledge from Web usage data and represent the knowledge in the comprehensible form of fuzzy rules. The derived knowledge is ultimately used to dynamically suggest interesting links to the user of a Web site.

In distributed wireless networks, nodes often do not have access to complete network information (e.g. network topology, channel gains, etc.). As a result, they have to execute their transmission and reception strategies with partial information about the network, in a distributed fashion. Thus, the key question is how good are the distributed decisions in comparison to the optimal decisions based on full network knowledge. In this paper, we formalize the concept of partial-information sum-capacity by defining normalized sum-capacity, which is defined as the maximum achievable fraction of full-information sum-capacity with a given amount of partial information. We then examine four deterministic networks, multiple access, multiuser Z-channel chain, one-to-many and many-to-one interference channel, and characterize the normalized sum-capacity. For each network, two cases of partial network information are analyzed: (a) each transmitter only knows the channel gains to its receiver, and (b) transmitters knows the channel gains of all links which are no more than two hops away. Quite interestingly, we show that in all eight cases (4 networks × 2 forms of partial information), the normalized sum-capacity is achieved by scheduling subnetworks for which there exist a universally optimal distributed strategy with the available partial information. Furthermore, we show that while actual sum-capacity is not known in all cases, normalized sum-capacity can be in fact be exactly characterized.

In order to provide approximate reasoning capabilities, in Gerla G, Sessa MI (1999) Chen G, Ying M, Cai K-Y (Eds) Fuzzy Logic and Soft computing, 19–31, Kluwer Academic Publishers, Boston an extension of Logic Programming has been proposed. Logic programs on function-free languages are considered, and approximate and imprecise information are represented by introducing a similarity relation ? in the set of predicate names and object names of the language. The inference system exploits the classical resolution rule of the Logic Programming paradigm. Moreover, the notion of fuzzy least Herbrand model is also provided. In this paper, by introducing the general notion of structural translation of languages, we generalize these results to the case of logic programs with function symbols. Some properties of the similarity relations are also proven.

This study proposes a structural model for defaultable options in a fuzzy environment. The proposed model is capable of dealing with market state variables, including firm value and fractional recovery rate, which are uncertain factors that differ from probabilistic essence and exhibit difficulty in determining precise price values exactly, namely they are market variables about which investors have only imprecise information. Since the unavailability of reliable accounting data makes the true value of firm assets unobservable, this study takes the advantage of fuzzy logic and adds a source of uncertainty to the classical stochastic default model, such as that of Klein (1996), to improve model performance. To show the robustness of the proposed model, some daily data of call options price are used to investigate its reliability. The empirical results demonstrate that the proposed fuzzy logic model has significantly better performance than previous structural form models and is indeed a useful means to manage prices risk for both option buyers and writers. This study is provided with the aim of offering insights into future research on defaultable options pricing under imprecise market information.

We describe in this book, new methods for building intelligent systems using type-2 fuzzy logic and soft computing techniques. Soft Computing (SC) consists of several computing paradigms, including type-1 fuzzy logic, neural networks, and genetic algorithms, which can be used to create powerful hybrid intelligent systems. In this book, we are extending the use of fuzzy logic to a higher order, which is called type-2 fuzzy logic. Combining type-2 fuzzy logic with traditional SC techniques, we can build powerful hybrid intelligent systems that can use the advantages that each technique offers. We consider in this book the use of type-2 fuzzy logic and traditional SC techniques to solve pattern recognition problems in real-world applications. We consider in particular the problems of face, fingerprint and voice recognition. We also consider the problem of recognizing a person by integrating the information given by the face, fingerprint and voice of the person. Other types of applications solved with type-2 fuzzy logic and SC techniques, include intelligent control, intelligent manufacturing, and adaptive noise cancellation.

In this paper we consider the evaluation of intervention countermeasures for the restoration of a radionuclide contaminated aquatic ecosystem, simultaneously taking into account several conflicting objectives, like environmental, social and economic impacts. We propose an extension of the additive multi-attribute utility model to incorporate the concept of veto to deal with this group decision-making problem. Moreover, we consider what is known as decision-making with partial, imprecise or incomplete information, which accounts for uncertainty about the alternative performances and imprecision concerning DM preferences by means of intervals or ordinal information. Veto values for the most important DMs are used to define veto ranges, whereas veto values corresponding to the other less important DMs are partially taken into account, leading to the construction of adjust ranges. We then build the veto and adjust functions into the additive model, and a dominance matrix accounting for incomplete information is computed. A dominance measuring method is then used to derive a ranking of alternatives for each DM, which are then aggregated taking into account their relative importance.

Given a set of collected evidence and a knowledge base, fuzzy compositional modelling (FCM) begins by retrieving model fragments which are the most likely to be relevant to the available data. Since FCM often involves imprecise and uncertain information, a match between the available data and the knowledge base cannot in general be done precisely, partial matching may suffice. This paper proposes a more flexible fuzzy model fragment retrieval mechanism to match data items with broader, including possibly subjective information in the knowledge base. It is capable of retrieving those model fragments that can approximately match the collected evidence, when no exact match occurs. The retrieval process and its capability is illustrated by means of an application example.

We consider an incomplete market with two information structures, complete and partial information and , respectively. The dynamics of the market are given by a risky asset driven by a m-dimensional Brownian motion W = (W1, …, Wm)′ as well as an integer-valued random measure μ(du, dy). To study the values with respect to the different information filtrations, we introduce the concept of dynamic < ![CDATA[exp]] >-utility indifference value (UIV) of with respect to denoted by Ct and the concept of dynamic < ![CDATA[exp]] >-UIV of the contingent claim H denoted by Ct(H), and we describe the dynamics of Ct and Ct(H) by BSDEs.

We study a mechanism design problem under the assumption that renegotiation cannot be prevented. We investigate what kind of equilibria of which mechanisms are renegotiation-proof under a variety of renegotiation procedures, and which social choice functions can be implemented in a way that is renegotiation-proof. In complete information environments, we show that the set of ex post renegotiation-proof implementable social choice functions contains all ex post efficient allocations when there at least three agents, but only budget balanced Groves allocations when there are two agents. In incomplete information environments with correlated beliefs and at least three agents, every ex post efficient social choice function can be implemented in the presence of ex post renegotiation, but with independent private values only social choice functions that are given by budget balanced “Groves in expectations” mechanisms are implementable in such a way. We further show that the requirement of interim renegotiation-proofness does not impose additional restrictions on implementable social choice functions under complete information, but is likely to impose additional restrictions under incomplete information.

Applications of Soft Computing to Human-centered Information Systems

How to quickly and cheaply construct Web ontologies has become a key technology to enable the Semantic Web. Classical ontologies are not sufficient for handling imprecise and uncertain information that is commonly found in many application domains. In this paper, we propose an approach for constructing fuzzy ontologies from fuzzy UML models, in which the fuzzy ontology consists of fuzzy ontology structure and instances. Firstly, the fuzzy UML model is investigated in detail, and a kind of formal definition of fuzzy UML models is proposed. Then, a kind of fuzzy ontology called fuzzy OWL DL ontology is introduced. Furthermore, we consider the fuzzy UML model and the corresponding fuzzy UML instantiations (i.e., object diagrams) simultaneously, and translate them into the fuzzy ontology structure and the fuzzy ontology instances, respectively. In addition, since a fuzzy OWL DL ontology is equivalent to a fuzzy Description Logic f-SHOIN(D) knowledge base, how the reasoning problems of fuzzy UML models (e.g., consistency, subsumption, equivalence, and redundancy) may be reasoned through reasoning mechanism of f-SHOIN(D) is investigated, which can help to construct fuzzy ontologies more exactly.

Information imprecision and uncertainty exist in many real-world applications, and for this reason fuzzy data modeling has been extensively investigated in various database models. In particular, Zadeh’s fuzzy set theory has been identified as a successful technique for modeling imprecise and uncertain information in various database models. This has resulted in numerous contributions, mainly with respect to the popular fuzzy conceptual data models (fuzzy ER/EER model, fuzzy UML data model, and etc.) and fuzzy logical database models (fuzzy relational database model, fuzzy object-oriented database model, and etc.). Also, it is shown that fuzzy set theory is very useful in Web-based business intelligence. Therefore, topics related to the modeling of fuzzy data are considered very interesting in XML since it is the current standard data representation and exchange format over the Web. In particular, to manage fuzzy XML data, it is necessary to integrate fuzzy XML and various fuzzy databases, and various fuzzy database models (fuzzy relational database model and fuzzy object-oriented database model) need to be used for mapping to and from the fuzzy XML models. Therefore, in this chapter, we mainly introduce several fuzzy database models, including fuzzy UML data model, fuzzy relational database model, and fuzzy object-oriented database model. Before that, we briefly introduce some notions of fuzzy set theory.

Segmentation of regions of interest plays important role in computer aided brain medical image diagnosis. Fuzzy techniques are widely used for this purpose as they can handle with imprecise or vague image information. The major achievement of this research is the introduction of a new region growing segmentation technique for which any fuzzy control model is possible to be applied. This enables the combination of physician knowledge, easily represented by fuzzy rules and therefore generalized, with the main concept of fuzzy control. Our approach is capable to segment cerebrospinal fluid in the cortical and subcortical areas of the brain. The study was performed by applying the segmentation method proposed on a dataset of 228 computed tomography scans of patients with diagnosed Alzheimer disease.

Nowadays practical solutions of engineering problems involve model integrated computing. Model based approaches offer a very challenging way to integrate a priori knowledge into the procedure. Due to their flexibility, robustness, and easy interpretability, the application of soft computing (SC), in particular fuzzy models, may have an exceptional role at many fields, especially in cases where the problem to be solved is highly nonlinear or when only partial, uncertain and/or inaccurate data is available. Nevertheless, ever so advantageous their usage can be, it is still limited by their exponentially increasing computational complexity. At the same time, there are other soft computing approaches which can counteract the nonadvantageous aspects of fuzzy (in general SC) techniques.

Rough set theory depending upon deterministic information systems or knowledge bases is now becoming a mathematical foundation of soft computing. In this paper, we pick up nondeterministic knowledge bases with incomplete and selective information. The both information are given as a set of attribute values, whose difference comes from the temporal concept. If the information is referring the past information then we see it incomplete information. On the other hand, selective information means that the real attribute value is not decided in a set, i.e., we can select the most proper value from this set. By introducing these two information into knowledge bases, we develop another framework for nondeterministic knowledge bases. Namely, we discuss question-answering, approximation, rough set concept and dependencies of attributes on this nondeterministic knowledge bases.