Data mining is commonly used method for processing large amount of data in heart disease prediction. Many heart disease prediction researches are carried out by different authors. But the accuracy level was not improved. In order to address these issues, Kushner-Stratonovich Dice Segmented Haar Wavelet (KSDSC) Deep Convolutional Neural Learning Model is introduced. The main aim of KSDSC Model is to perform efficient heart disease prediction with five layers, namely one input layer, three hidden layers and one output layer. Initially, ultrasound images are collected as an input at input layer. An image pre-processing is carried out using Kushner-Stratonovich Filter to eliminate the noisy pixels from US image and transmitted to hidden layer 2. Sørensen–Dice Image Segmentation Process partitions the preprocessed image into number of divisions in hidden layer 2. After that in hidden layer 3, the multiple features are extracted using Curvelet transform from segmented image and sent to the output layer. The output layer uses softmax yolov4 darknet53 activation function to match extracted features for heart disease prediction. Experimental analysis is performed on parameters such as prediction accuracy, false positive rate, and prediction time with respect to a number of US images.

No abstract

Nowadays people are taking more care of their health and lifestyle. At the same time, diseases affected probability also increased even at most one of the deadly diseases is cardiovascular disease. Earlier prediction and diagnosis are the only solution for resolving the issues. To identify deep language models will be used to predict issues efficiently in the earliest stage in the affected location. In this paper, we recommend an Enhanced DCNN model to classify and segment the issue in affected areas using ultrasonic Images. The model has three layers for the primary layer will train the input and passed the hidden layer. The secondary layer will classify the image based on the model and dataset using the convolution layer and finally the affected area presented by the bound box. This model shows the more accurate result on both training and testing data. And this method shows better results with 94% of accuracy are provides while compared to the existing method.

No abstract

No abstract