M. De Cock

Fuzzy versus quantitative association rules: a fair data-driven comparison

As opposed to quantitative association rule mining, fuzzy association rule mining is said to prevent the overestimation of boundary cases, as can be shown by small examples. Rule mining, however, becomes interesting in large databases, where the problem of boundary cases is less apparent and can be further suppressed by using sensible partitioning methods. A data-driven approach is used to investigate if there is a significant difference between quantitative and fuzzy association rules in large databases. The influence of the choice of a particular triangular norm in this respect is also examined.

Fuzzifying Allen's Temporal Interval Relations

When the time span of an event is imprecise, it can be represented by a fuzzy set, called a fuzzy time interval. In this paper, we propose a framework to represent, compute, and reason about temporal relationships between such events. Since our model is based on fuzzy orderings of time points, it is not only suitable to express precise relationships between imprecise events (ldquoRoosevelt died before the beginning of the Cold Warrdquo) but also imprecise relationships (ldquoRoosevelt died just before the beginning of the Cold Warrdquo). We show that, unlike previous models, our model is a generalization that preserves many of the properties of the 13 relations Allen introduced for crisp time intervals. Furthermore, we show how our model can be used for efficient fuzzy temporal reasoning by means of a transitivity table. Finally, we illustrate its use in the context of question answering systems.

Fuzzy rough sets: beyond the obvious

Rough set theory was introduced in 1982. Soon it was combined with fuzzy set theory, giving rise to a hybrid model, involving fuzzy sets and fuzzy relations, which appears to be a natural, elegant generalization. In this paper we reveal that in the fuzzification process an important step seems to be overlooked. The most fascinating part is that this forgotten step arises from the true essence of fuzzy set theory: namely, that an element can belong to a given degree to more than one fuzzy set at the same time.

Influence of pores on the quality of a silicon polyester coated galvanised steel system

Silicon polyester coated steel plate is frequently used because of its good corrosion resistance under various conditions. However, if the application of the coating and/or the curing process is carried out too fast, evaporating solvent is enclosed in the coating, forming pores. The aim of this study is to investigate the influence of different types of pores on the corrosion resistance of the above-mentioned coating system by means of electrochemical impedance spectroscopy (EIS). Three different phases in the degradation process could be observed. An almost intact coating area is investigated as reference coating. By simultaneous interpretation of the measured corrosion potential, the evolution of the coating capacitance and its resistance, it can be concluded that this system provides a very good corrosion resistance in a saline environment. A coating containing only small macro-pores (2 μm 100 μm) can even reach the underlying zinc surface. They will strongly decrease the corrosion protection behaviour of the coating.

Location approximation for local search services using natural language hints

Local search services allow a user to search for businesses that satisfy a given geographical constraint. In contrast to traditional web search engines, current local search services rely heavily on static, structured data. Although this yields very accurate systems, it also implies a limited coverage, and limited support for using landmarks and neighborhood names in queries. To overcome these limitations, we propose to augment the structured information available to a local search service, based on the vast amount of unstructured and semi‐structured data available on the web. This requires a computational framework to represent vague natural language information about the nearness of places, as well as the spatial extent of vague neighborhoods. In this paper, we propose such a framework based on fuzzy set theory, and show how natural language information can be translated into this framework. We provide experimental results that show the effectiveness of the proposed techniques, and demonstrate that local search based on natural language hints about the location of places with an unknown address, is feasible.

A new class of fuzzy modifiers

In this paper we introduce a new class of fuzzy modifiers based on fuzzy relations. We apply them in the framework of linguistic variables, which plays a key role in fuzzy control. More precisely we will use the new class of fuzzy modifiers for the representation of weakening, intensifying and ordering-based linguistic modifiers. Furthermore we will also show how these fuzzy modifiers can be applied in image processing.

Getting Cold Start Users Connected in a Recommender System's Trust Network

Generating personalized recommendations for new users is particularly challenging, because in this case, the recommender system has little or no user record of previously rated items. Connecting the newcomer to an underlying trust network among the users of the recommender system alleviates this socalled cold start problem. In this paper, we study the effect of guiding the new user through the connection process, and in particular the influence this has on the amount of generated recommendations. Experiments on a dataset from Epinions.com support the claim that it is more beneficial for a newcomer to connect to an identified key figure instead of to a random user.

Modelling nearness and cardinal directions between fuzzy regions

A significant part of real-world spatial information is affected by vagueness. For example, boundaries of non-administrative geographical regions tend to be ill-defined, while information about the nearness and relative orientation of two places is typically expressed through vague linguistic descriptions. In this paper, we propose a general framework to represent such information, using the concept of relatedness measures for fuzzy sets. Regions are represented as fuzzy sets in a two-dimensional Euclidean space, and nearness and relative orientation are expressed as fuzzy relations. To support fuzzy spatial reasoning, we derive transitivity rules and provide efficient techniques to deal with the complex interactions between nearness and cardinal directions.

The representation of linguistic hedges using fuzzy relational calculus

Traditionally in fuzzy set theoretical frameworks linguistic hedges are modelled by technical operators lacking inherent meaning. We elaborate on a representation of modified linguistic expressions that takes into account mutual relationships between objects of the universe. Formally this is accomplished by modelling hedges by means of taking images under fuzzy relations: for ordering-based hedges orderings and strict orderings are used, while for weakening and intensifying hedges we propose to use fuzzy relations modelling approximate equality. Since fuzzy T-equivalence relations prove to be unsuitable for this purpose, resemblance relations are chosen instead. The resulting framework not only allows for a unified approach to the modelling of hedges but also endows them with an inherent semantics, thereby overcoming important shortcomings of the traditional approaches, as we will illustrate by means of several examples in numerical as well as non-numerical universes.

Acquiring Vague Temporal Information from the Web

Many real-world information needs are naturally formulated as queries with temporal constraints. However, the structured temporal background information needed to support such constraints is usually not available to information retrieval systems. As an alternative, we automatically compile temporal knowledge bases from Web documents, combining whatever quantitative and qualitative temporal information we can find about events of interest. By using simple heuristic techniques for temporal information extraction, we initially focus more on recall than on precision, relying on the subsequent application of a fuzzy temporal reasoner to improve the reliability of the extracted information.