Key points are not available for this paper at this time.
Cardiomyopathy is a disease category that describes the diseases of the heart muscle. It can infect all ages with different serious complications, such as heart failure and sudden cardiac arrest. Usually, signs and symptoms of cardiomyopathy include abnormal heart rhythms, dizziness, lightheadedness, and fainting. Smart devices have blown up a nonclinical revolution to heart patients' monitoring. In particular, motion sensors can concurrently monitor patients' abnormal movements. Smart wearables can efficiently track abnormal heart rhythms. These intelligent wearables emitted data must be adequately processed to make the right decisions for heart patients. In this article, a comprehensive, optimized model is introduced for smart monitoring of cardiomyopathy patients via sensors and wearable devices. The proposed model includes two new proposed algorithms. First, a fuzzy Harris hawks optimizer (FHHO) is introduced to increase the coverage of monitored patients by redistributing sensors in the observed area via the hybridization of artificial intelligence (AI) and fuzzy logic (FL). Second, we introduced wearable sensing data optimization (WSDO), which is a novel algorithm for the accurate and reliable handling of cardiomyopathy sensing data. After testing and verification, FHHO proves to enhance patient coverage and reduce the number of needed sensors. Meanwhile, WSDO is employed for the detection of heart rate and failure in large simulations. These experimental results indicate that WSDO can efficiently refine the sensing data with high accuracy rates and low time cost.
Ding et al. (Wed,) studied this question.