A Domain Knowledge as a Tool For Improving Classifiers

Abstract

This paper investigates the approaches to an improvement of classifiers quality through the application of a domain knowledge. The expertise may be utilizable on several levels of decision algorithms such as: feature extraction, feature selection, a definition of temporal patterns used in an approximation of the concepts, especially of the complex spatio-temporal ones, an assignment of an object to the concept and a measurement of the objects similarity. The domain knowledge incorporation results then in the reduction of the size of searched spaces. The work constitutes an overview of classifier building methods efficiently utilizing the expertise, worked out latterly by Professor Andrzej Skowron research group. The methods using domain knowledge intended to enhance the quality of classic classifiers, to identify the behavioral patterns and for automatic planning are discussed. Finally it answers a question whether the methods satisfy the hopes vested in them and indicates the directions for future development.

The temporal inference with the use of ant-based clustering algorithm and flow graphs in the problem of prognosing complications of medical surgical procedures

“…Creation of fuzzy flow graphs and extraction of episodes using the ant-based clustering algorithm have been also implemented in our software tool (CLAPSS), see (Pancerz, Lewicki & Sarzynski, 2019). Moreover, an important issue is to use a domain knowledge to improve solving decision problems (see for example (Bazan, Buregwa-Czuma & Jankowski, 2013)). The domain knowledge can have different forms.…”

Ant-based clustering for flow graph mining

“…Firstly, in the case of fuzzy flow graphs, we can test a variety of shapes of membership functions used to model linguistic values as well as a variety of triangular norms used to determine certainties of sequences found. Secondly, a challenging thing is to use approaches in which the domain knowledge is taken into consideration in graph mining (Bazan et al, 2013;Pancerz, 2016).…”

Interval modelling in optimization of k‐NN classifiers for large number of attributes in data sets on an example of DNA microarrays

“…Classifying algorithms are applied to solve problems in machine learning, pattern recognition, expert systems, knowledge discovery, and data mining 1 . There are several ways to construct classifiers, which rely on decision rules, decision trees, neural networks, inductive logic programming, and classical or modern statistical methods 1–5 . Data sets used in classifiers may be presented by data tables where objects correspond to rows and attributes correspond to columns of the given data table.…”

“…1 There are several ways to construct classifiers, which rely on decision rules, decision trees, neural networks, inductive logic programming, and classical or modern statistical methods. [1][2][3][4][5] Data sets used in classifiers may be presented by data tables where objects correspond to rows and attributes correspond to columns of the given data table . In this contribution we consider decision tables of the form U A d T = ( , , ), 6 where A is the set of attributes, U is the set of objects, and d is a decision attribute (distinguished from the set A).…”