CNSD-Net: joint brain–heart disorders identification using remora optimization algorithm-based deep Q neural network.

People around the globe are suffering from different types of brain–heart disorders. Early detection of these disorders may increase the lifespan of humans. Numerous inherited and non-hereditary central nervous system disorders (CNSDs) may have an effect on brain–heart diseases either directly or indirectly. However, the clinical predictions of these CNSDs are time-consuming. So, a computer-aided detection-based artificial intelligence model can be used to predict and classify CNSDs with high accuracy. This article is focused on the implementation of CNSD-Network (CNSD-Net) for joint brain–heart disorders identification through collective analysis of EEG and ECG signals to trace the problems related to epilepsy, stroke, Alzheimer's and sleep disorders. Initially, minimum mean-square-error short-time spectral amplitude is performed as a preprocessing operation, which removes different types of noise from the dataset. Then, disease-specific features and disease-dependent features are extracted using a transfer learning-based AlexNet model from the denoised signal. In addition, a nature-inspired remora optimization algorithm is used to extract the optimal features. In addition, a deep Q neural network is used to classify various central nervous system diseases from optimal trained features. The simulations proved that the proposed CNSD-Net resulted in superior performance when compared to conventional approaches in terms of accuracy, sensitivity, specificity, and F1-score. [ABSTRACT FROM AUTHOR]