International Journal of Neutrosophic Science IJNS 2690-6805 2692-6148 10.54216/IJNS https://www.americaspg.com/journals/show/4006 2020 2020 Department of Computer Science and Engineering, University of Colorado Denver, Denver, Colorado, USA Majed Majed Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia Reda Salama Department of Information Technology, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia Mahmoud Ragab Department of Computer Science and Engineering, University of Colorado Denver, Denver, Colorado, USA Ashis Kumer Biswas The neutrosophic set (NS) concept from the philosophical perspective extends and simplifies the principles of fuzzy set (FS) and intuitionistic FS (IFS). A NS is defined by truth, indeterminacy, and falsity membership functions, with each value belonging to the non-standard intervals (−0, 1+). In contrast to IFSs, there is no limitation in the membership function in NS, and the hesitancy degree is incorporated in NS. Arrhythmia is a medical illness wherein the regular pumping mechanism of the human heart becomes abnormal. The arrhythmia detection is one of the most essential steps to identify the disorder that can play a significant role in helping cardiologist with their decision. The initial identification of abnormal heart disease is critical for patients with heart disorders. Computer-aided diagnosis (CAD) has gained popularity in the arrhythmia domain recently, as artificial intelligence (AI) technology has matured. Still, the AI-based deep learning (DL) techniques are applied frequently to classify and detect arrhythmia. This paper presents an Enhanced Diagnostic Model for Cardiac Arrhythmia using Principal Component Analysis and Pythagorean Neutrosophic Bonferroni Mean (DMCA-PCAPNBM) technique in Cardiovascular Signal Processing. The objective is in the automated arrhythmia detection using advanced techniques. Initially, the DMCA-PCAPNBM model applies the min-max scaler-based data pre-processing technique for transforming input data into an appropriate format. In addition, the principal component analysis (PCA) method is applied for the feature subset selection model to pick out the optimal attributes from the dataset. For the procedure of arrhythmia detection, the PNBM model is utilized. Finally, the improved dung beetle optimization (IDBO) approach is applied for parameter tuning, resulting in enhanced classification performance. A comprehensive experimentation is implemented to verify the superior outcome of the DMCA-PCAPNBM model on the ECG arrhythmia classification dataset. The experimental validation of the DMCA-PCAPNBM approach illustrated an improved accuracy value of 99.06% over recent techniques. 2026 2026 79 94 10.54216/IJNS.270208 https://www.americaspg.com/articleinfo/21/show/4006