Accuracy Assessment for Multi-Channel ECG Waveforms Using Soft Computing Methodologies

摘要

ECG waveform rhythmic analysis is very important. In recent trends, analysis processes of ECG waveform applications are available in smart devices. Still, existing methods are not able to accomplish the complete accuracy assessment while classify the multi-channel ECG waveforms. In this paper, proposed analysis of accuracy assessment of the classification of multi-channel ECG waveforms using most popular Soft Computing algorithms. In this research, main focus is on the better rule generation to analyze the multi-channel ECG waveforms. Analysis is mainly done inSoft Computing methods like the Decision Trees with different pruning analysis, Logistic Model Trees with different regression process and Support Vector Machine with Particle Swarm Optimization (SVM-PSO). All these analysis methods are trained and tested with MIT-BIH 12 channel ECG waveforms. Before trained these methods, MSO-FIR filter should be used as data preprocessing for removal of noise from original multi-channel ECG waveforms. MSO technique is used for automatically finding out the cutoff frequency of multichannel ECG waveforms which is used in low-pass filtering process. The classification performance is discussed using mean squared error, member function, classification accuracy, complexity of design, and area under curve on MIT-BIH data. Additionally, this research work is extended for the samples of multi-channel ECG waveforms from the Scope diagnostic center, Hyderabad. Our study assets the best process using the Soft Computing methods for analysis of multi-channel ECG waveforms.