A Novel Technique to Investigation of Infectious Diseases

Abstract

To carry out this research, a systematic review methodology will be used along with three different investigations for viral disease. As the viral disease has various forms of occurrence as they have less infected or highly invested. The recent scenario also very aware about the covid. A systematic review is a well-planned examination to answer research questions using a systematic and clear technique to locate, select, and critically assess the outcomes of prior research studies. When doing a systematic review, it is important to use strict methodological procedures in order to ensure that the results are unique. This thesis investigates two illnesses, one for the purpose of analytical data analysis using machine learning, and the other for the purpose of contaminated area identification using artificial intelligence. There is one additional inquiry that has been initiated for covid Exploration. Data has been gathered constantly from the 10th of March, 2020, and will continue to be collected until the 6th of May, 2021, according to the schedule. The total number of occurrences of the covid case has been represented. For this we used the chaste images (Infected) on which the SVM has been apply with the to detect the affected area. For this we have train the affected area and test on the chaste image. This thesis tries to detect the pattern of the affected area within the images. The detection started with an image-based identification algorithm from the UCI library. The data sets were run via the MATLAB simulator to determine the prediction accuracy using the UCI image data base. Data augmentation is all about adding data points. It refers to the growing dataset. We need to extend the dataset to prevent overfitting. Applying Pneumonia treatment, filtering data conditions, and constructing data may accomplish this. Our models would perform better with additional data. Now we look at the AI work for infected area detection. We utilized virgin photos (Infected) and used SVM to identify the impacted region. Then we test on a chaste picture. The work for the detection of contaminated regions applying artificial intelligence was also studied further in this thesis, according to the results. A clean picture (Infected) was used to train the SVM, which was then utilized to detect the affected area on the image. For this, we trained the affected area and tested it on a chaste image in order to get the desired results. It is the goal of this thesis to identify patterns in the pictures that represent the affected area as shown in the GUI-based Layout by searching for patterns in the images.