Convolutional neural networks involve either 1D convolution or 2D convolution. In this work, both 2D and 1D convolution has been introduced in one network only. The concept of cross-attention has been a new one. Moreover, the property of self-attention has been applied for signals or one 2D matrix only, but we implemented it here for several 2D matrices. All these techniques are incorporated in the designed deep network to differentiate the patients suffering from conduction disorders from those having coronary artery malfunction. ECG and PPG signals were acquired simultaneously and converted to a fused signal using the proposed algorithm. Until now either ECG or PPG signal was targeted for identifyingonly one type of cardiac morbidity, but here we developed this new framework for distinguishing among the type of heart-related diseases. To make this framework more robust and efficient, the reinforcement learning scheme is utilized to design the adaptive model. With the addition of new ...

Clinicians refer to standard physiological signals (ECG and PPG) to diagnose conduction disorders and coronary arterial malfunctions. The exact disease is identified from the results of confirmatory medical tests. This procedure creates a time lag in treating patients and causes difficulty in attending emergency cases. In this study, a novel method is proposed to detect and classify diseases related to electrical impulses and coronary arteries from other cardiac abnormalities efficiently. The ECG and PPG signals are collected simultaneously from 300 cardiovascular diseased patients, following a predecided inclusion and exclusion criteria. A fused signal is generated using an algorithm from the PPG and ECG signals. The deep neural network is constructed involving self and cross attention properties, multidimensional convolution, and skip connections. Reinforcement learning is utilized to induce an adaptive property in the model. The model’s ability in distinguishing the targeted disease...