The proper functioning of the heart can be ascertained through ECG or Electro-Cardio-Gram. It is a form of signal that gives important information about the working of heart with respect to time and analysing ECG signals without manual intervention is an important application. Early detection of heart diseases or abnormalities is very important as it can help in prolonging life time and also to increase the quality of life. The ECG signals are captured by placing several electrode pads on the body at various positions. A better diagnosis of the heart disease can be achieved by using Multi-lead ECGs as it acquires signals simultaneously. This work focuses on the suggested Discrete Wavelet Transform (DWT) used in processing ECG recordings and also to extract certain attributes. The process of feature extraction and dimensionality reduction can be effectively performed using Principal Component Analysis (PCA). A population of knowledge structures is maintained in Genetic Algorithm (GA) called chromosomes. Each of these represents a candidate solution to the given problem. An algorithm having it basis on the governing laws of one dimensional collision between two bodies from physics was proposed and named as Colliding Bodies Optimization (CBO). This protocol is a modern populationbased stochastic optimization algorithm. Naïve Bayes, K-Nearest Neighbor (KNN) and Classification and Regression Tree (CART) classifiers are used. Through the outputs it is clear that the proposed method performs well when compared against other methods.