DOI: 10.14704/nq.2022.20.11.NQ66257

ANALYSIS OF MEDICAL IMAGE DATA BY DEEP CONVOLUTION TECHNIQUES AND KERNEL DENSITY ESTIMATION

Dr.M. SubbaRao, Kethireddy Anusha, Dr.N. Penchalaiah

Abstract

Consider the data/datasets are everywhere to define. Time aware search using queries results the best understanding of temporal data. Time aware kernel Estimation describes about the word temporal predictor to characterize the word-level temporal relevance by fine-grained time-aware kernel density estimation over the datasets and to capture the temporal relevance of query word that was made. The Kernel density defines as it results the predicted data in the form of histograms that was a form of analysis which shows the predicted data of the EHR data search. It mainly consists the word level temporal prediction of past experiences with an incompletely known system to predict future behavior. The effectiveness and robustness proposed by the temporal predictors as time aware to analyze chronic diseases using EHR data. As the growth of chronic diseases, The health care growing parallel. This can elevate visualization, accuracy and effectiveness by considering the chronic disease data analysis time to time. It can be defined as word-level temporal relevance of data from the information and to make kernel density estimation for better effective and the accurate results.

Keywords

Medical image classication, pre-trained DCNN, convolution neural network, big data, image analysis, image enhancement, biomedical image processing, deep learning

Full Text

References