According to the World Health Organization, 12 million people die each year as a result of heart disease. Because heart attacks and stroke are the primary causes of morbidity and mortality in the global population, recent research has focused on the prediction of cardiovascular disease. Many studies have been undertaken in an attempt to identify the most relevant risk factors for heart disease and to accurately assess the overall risk. Early detection of cardiac disease is critical in making lifestyle adjustments decisions in high-risk patients, reducing consequences.This research study presents a Machine Learning-based Innovative Heart Disease Assessment System (ML-IHDAS) that employs the Forward Sequential Feature Selection (FSFS) approach. In this investigation, the FSFS technique assesses subsets of features and selects the subset that gets the maximum performance on a certain criterion after making that determination. The proposed ML-IHDAS builds the classification models using Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosted decision trees (XGBoost) with selected features. Several performance indicators, including accuracy, precision, recall, and F1-measure, are utilized by the authors in order to assess the effectiveness of these models. The experimental results indicate that the XGBoost classifier outperforms the other three classifiers with highest accuracy. This method has the potential to assist medical professionals in accurately and successfully identifying heart disease.
Recently, COVID-19 is spreading rapidly and fast detection of COVID-19 can save millions of lives. Further, the COVID-19 can be detected easily from computed tomography (CT) images using artificial intelligence methods. However, the performance of these application and methods are reduced due to noises presented in the CT images, which degrading the performance of overall systems. Therefore, this article is focused on implementation of an innovative method for quickly processing CT images of low quality, which enhances the contrast using fuzzy logic. This method makes use of tuned fuzzy intensification operators and is intended to speed up the processing time. Extensive experiments were carried out to test the processing capacity of the method that was proposed, and the results obtained demonstrated that it was capable of filtering a variety of images that had become degraded.
Recently, people are suffering with variety of skin cancers due to radiation problems, atmospheric effects and change in environmental conditions. So, early detection of skin cancers can save the millions of people. The conventional image processing methods were failed to localize disease effected region accurately, which caused improper prediction of skin cancer types. Therefore, this article is implemented the preprocessing-based skin lesion segmentation network (SLS-Net). Initially, fast nonlocal mean (FNLM) filter is applied to remove the different types of noises from skin lesions, which also enhances the skin lesion image. Further, skip connection-based U-Net (SCU-Net) model is applied for accurate segmentation of skin lesions. The simulations performed on ISIC-2019 and PH 2 datasets discloses the superiority of proposed SLS-Net in terms of precision, recall, sensitivity, specificity, and f1-score as compared to conventional segmentation models.
28 July 2022 in International Journal of Image and Graphics
The smart classroom attendance monitoring system is designed based on the Convolutional Neural Network. In this way it looks like a human entrance and exit to l