Wyniki wyszukiwania - BazTech

1

Interpolation Models for Spatiotemporal Association Mining

Li D., Deogun J.S.

Fundamenta Informaticae

|

2004

|

Vol. 59, nr 2,3

153--172

EN

In this paper, we investigate interpolation methods that are suitable for discovering spatiotemporal association rules for unsampled sites with a focus on drought risk management problem. For drought risk management, raw weather data is collected, converted to various indices, and then mined for association rules. To generate association rules for the unsampled sites, interpolation methods can be applied at any stage of this data mining process. We develop and integrate three interpolation models into our association rule mining algorithm. We call them pre-order, in-order and post-order interpolation models. The performance of these three models is experimentally evaluated comparing the interpolated association rules with the rules discovered from actual raw data based on two metrics, precision and recall. Our experiments show that the post-order interpolation model provides the highest precision among the three models, and the Kriging method in the pre-order interpolation model presents the highest recall.

2

Concept Approximations Based on Rough Sets and Similarity Measures

Saquer J., Deogun J. S.

International Journal of Applied Mathematics and Computer Science

|

2001

|

Vol. 11, no 3

655-674

EN

The formal concept analysis gives a mathematical definition of a formal concept. However, in many real-life applications, the problem under investigation cannot be described by formal concepts. Such concepts are called the non-definable concepts (Saquer and Deogun, 2000b). The process of finding formal concepts that best describe non-definable concepts is called the concept approximation. In this paper, we present two different approaches to the concept approximation. The first approach is based on rough set theory while the other is based on a similarity measure. We present algorithms for the two approaches.

3

Concept Based Retrieval Using Generalized Retrieval Functions

Kim M., Deogun J.S., Raghavan V.V.

Fundamenta Informaticae

|

2001

|

Vol. 47, nr 1,2

119-135

EN

One of the essential goals in information retrieval is to bridge the gap between the way users would prefer to specify their information needs and the way queries are required to be expressed. Rule Based Information Retrieval by Computer (RUBRIC) is one of the approaches proposed to achieve this goal. This approach involves the use of production rules to capture user-query concepts (or topics). In RUBRIC, a set of related production rules is represented as an AND/OR tree, or alternatively by a disjunction of Minimal Term Sets (MTSs). The retrieval output is determined by the evaluation of the weighted Boolean expressions of the AND/OR tree, and processing efficiency can be enhanced by employing MTSs. However, since the weighted Boolean expression ignores the term-term association unless it is explicitly represented in the tree, the terminological gap between users' queries and their information needs may still remain. To solve this problem, we adopt the generalized vector space model (GVSM) and the p-norm based extended Boolean model. Experiments are performed for two variations of the RUBRIC model, extended with GVSM, as well as for the integrated use of RUBRIC with the p-norm based extended Boolean model. The results are compared to the original RUBRIC model based on recall-precision