A Machine Learning Approach To Disease Prediction Using Human Aura Images

Abstract

The human body vibrates at varied rates because of several reasons. That magnetic field is the result of pulsating energy. Electrochemical processes are the basis of every biological process in the human body, from breathing and feeding to the nervous and circulatory systems. The "Bio-Energetic Field" is the result of a synthesis of magnetic and electrical energy fields. This line of inquiry has helped to shed light on a wide range of fascinating issues and characteristics that may be used to human bio-field research. The research in this field enables to comprehend more about the individual's mental condition, health difficulties, and other pertinent factors. There have been a number of advancements in this area that make it easier to analyze the human bio-field and bring attention to the fact that we as a species exist. In the proposed method, AURA pictures are used to detect the shifts.  Preprocessing is the initial step in the Gas Discharge Visualisation (GDV) images; subsequently, Machine Learning (ML) techniques such as Support Vector Machine, Random Forest (RF), and Ensembled AdaBoost (Eada) are employed to identify, train, and classify characteristics. By utilizing the Ensembled AdaBoost method, the average accuracy of classification is enhanced.