Pattern Classifications in Cognitive Informatics - Computational Intelligence Paradigms in Advanced Pattern Classification - page 39

Chapter 4
Pattern Classifications in Cognitive Informatics
Lidia Ogiela
AGH University of Science and Technology
Al. Mickiewicza 30, PL-30-059 Krakow, Poland
[e-mail]
Abstract. This chapter presents problems to which cognitive data analysis
algorithms are applied. The cognitive data analysis approach presented here will be
used to build cognitive systems for classifying patterns, which in turn will form the
basis for discussing and characterising Understanding Based Image Analysis
Systems (UBIAS). The purpose of these systems is image analysis, while their
design and operation follow cognitive/reasoning processes characteristic for human
cognition. Such processes represent not just simple data analysis, but their main
function is to interpret, understand and reason about analysed data sets, employing
the automatic data understanding process carried out by the system. A characteristic
feature of cognitive analysis processes is the use of linguistic algorithms - which are
to extract the meaning from data sets - to describe the analysed sets. It is those
algorithms that serve to describe the data, interpret it and to reason.
Keywords: Cognitive informatics, pattern classifications, pattern understanding,
cognitive analysis, computational intelligence, natural intelligence, intelligent
systems.
1 Introduction
Data understanding by interpreting the meaning of analysed data is based on a
semantic analysis of patterns defined in the system. Such analysis and reasoning
processes are conducted by cognitive systems, understood as systems that carry
out semantic analysis processes. Semantic analysis processes make use of
cognitive resonance, described in the author's publications [17]-[42], [44], [45],
[48]-[51], which forms the main stage in the correct operation of the system. The
development of cognitive information systems was sparked by moves to combine
systems which recognised data (most often data in the form of images) with
automatic data understanding processes (an implementation of semantic analysis
solutions understood as the cognitive analysis). These processes have been
described in publications [17]-[45], [48]-[57] and are still successfully developed.