Combining ε-similar Fuzzy Rules for Efficient Classification of Cardiotocographic Signals
Autor: | Michal Jezewski, Jacek M. Leski, Robert Czabanski, Radek Martinek, Adam Matonia |
---|---|
Rok vydání: | 2020 |
Předmět: |
010302 applied physics
010308 nuclear & particles physics Computer science business.industry Fuzzy set Pattern recognition 01 natural sciences Condition assessment Fuzzy logic Fuzzy classifier Support vector machine Fetal heart rate 0103 physical sciences Benchmark (computing) Artificial intelligence business |
Zdroj: | MIXDES |
Popis: | CardioTocoGraphic (CTG) monitoring is the primary method of fetal condition assessment. Due to the inter- and intra-observer disagreement between experts when evaluating signals visually, a well established solution supporting the diagnostic decision is automated classification of CTG signals. The goal of this paper is to propose a method of simplifying the fuzzy classifier rule base by combining e-similar rules, to achieve high quality of CTG signals classification, but with fewer conditional rules. The results of experiments performed using the benchmark CTG database confirm the efficiency of the introduced method. |
Databáze: | OpenAIRE |
Externí odkaz: |