Selection and Classification of Statistical Data Using Fuzzy Logic

Linguistic expressions like: high rate of unemployment, or high migration level etc., are very often used in life and in statistics. The goal of this research is to capture these expressions and make them suitable for database queries and classification tasks. This paper shows differences between usual and fuzzy approaches in database queries and classification and points out advantages of the fuzzy approach. The fuzzy logic deals with reasoning that is approximate rather than precise to solve problems in a way that more resembles human logic. For querying process the generalised logical condition in the WHERE part of the SQL was developed. In order to classify data, fuzzy queries are generated from fuzzy rules. The objective of integration is to use the same generalised logical condition in data selection and data classification. The proposed fuzzy approach provides flexibility when users cannot unambiguously set the boundaries between data. The fuzzy approach also extracts additional valuable hidden information in comparison with the usual, crisp approaches. In this way, queries based on linguistic expressions on client’s side are supported and are accessing relational databases in the same way as the classical SQL enables.