Open AccessAn Expert System for Automatic Classification of Sound Signals
Author(s) -
Krzysztof Tyburek,
Piotr Kotlarz
Publication year - 2020
Publication title -
journal of telecommunications and information technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.151
H-Index - 12
eISSN - 1899-8852
pISSN - 1509-4553
DOI - 10.26636/jtit.2020.143220
Subject(s) - computer science , artificial neural network , fuzzy logic , artificial intelligence , expert system , machine learning , basis (linear algebra) , data mining , pattern recognition (psychology) , speech recognition , mathematics , geometry
In this paper, we present the results of research focusing on methods for recognition/classication of audio signals. We consider the results of the research project to serve as a basis for the main module of a hybrid expert system currently under development. In our earlier studies, we conducted research on the eectiveness of three classiers: fuzzy classier, neural classier and WEKA system for reference data. In this project, a particular emphasis was placed on ne-tuning the fuzzy classier model and on identifying neural classier applications, taking into account new neural networks that we have not studied so far in connection with sounds classication methods