The work in this thesis describes some properties of common neural networks methods and the Multichannel Adaptive Resonance Theory (MART), which is an Adaptive Resonance Theory (ART)-based neural network for adaptive classification of Multichannel signal patterns without prior supervised learning. The mechanical aspect and the electrical aspect that include (ECG wave generation, sensors leads of the body and all type of noises) are shown in the present work. Also the Premature Ventricular Contraction disease (PVC) was dealt with in details. The operation of MART was analyzed for diagnosing a set of real patterns (QRS interval of PVC disease) that were taken from many patients of Holter ECG system with the help Al-Kadmia Teaching Hospital. Then an off line method was used for learning the MART by using MATLAB 6.5 program. Because the ability of truly two-channels to quantify and take into account the different changing reliabilities of the individual signal channels and using the credibility parameter in the algorithm, during PVC pattern classification, this will reduce the creation of spurious or duplicate categories (major problem for ART-based classification of noisy channels ) and reduce the processing time to 0.124 sec. Where the Accuracy and Sensitivity of MART in the present work are 93.4