GRADIENT DESCENT OPTIMIZATION FOR INTELLIGENT CORONARY DISEASE DIAGNOSIS USING FOG

Abstract

The leading cause of death in the modern world is heart disease. Early diagnosis of heart failure is crucial for improving the healthcare sector. Depending on preexisting information and statistics from comparable medical settings, the consistent and actual incidence of heart failure varies. Several solutions are capable of learning, adapting, and changing functional dependencies in response to new observations or due to changing interaction.There is gradient descent optimization in all of these abilities (GDO).People have incredible models that are easily generalised, entail little human interaction, and need just a little amount of computation during training. The cardiovascular disease prognosis, which has a significant impact on the lives of millions of people, is among the most significant prognoses constructed using algorithms for machine learning.Heart disease patients have a wide range of independent characteristics that can be utilised to diagnose them extremely successfully. The suggested model employs the gradient descent optimization approach to model variables using fog for security of data. The suggested SDCD-GDO system can take the place of costly medical tests because to its sophisticated detection of individuals who are likely to develop heart disease. Researchers from all across the world are now closely monitoring how medical databases are used. The suggested SDCD-GDO model is built using real data acquired from various sources, and during the validation phase, The recommended model's accuracy in detecting cardiovascular disease was 94.4 %.