Multiresoloution wavelet analysis based ischemic beat detection using fuzzy reasoning

In this study a new fuzzy expert system for ischemic beat detection based on interpretability is proposed. First, efficacious morphologic features which are useful in ischemia detection are extracted by wavelet analysis. Then, subtractive clustering is performed for clustering of normal patterns. Finally after creation of fuzzy system, rule reduction and optimization is employed in respect with accuracy and interpretability in order to achieve more optimized system. The fuzzy expert system is evaluated on the European Society of Cardiology (ESC) ST-T database. The results proof the medical rules that are common in detection of ischemia by physicians. Also some other rules those are not common for physicians gain medical interpretation ability is proposed.