This work presents a novel technique for ECG signal classification by integrating the Fractional Fourier Transform (FrFT), Particle Swarm Optimization (PSO), and Principal Component Analysis (PCA). Initially, FrFT is used to convert ECG signals from the time domain to the frequency domain, enabling the extraction of vital spectral features. PSO is then applied to optimize feature selection, ensuring that only the most relevant characteristics are retained to enhance classification accuracy. Subsequently, PCA reduces the dimensionality of the selected features, leading to faster computation and improved model efficiency. The proposed method effectively identifies cardiac abnormalities while maintaining critical diagnostic information.