Online ISSN: 2515-8260

Author : ANANTHI, N.


Detection and Identification of Potato Plant Leaf Diseases using Convolution Neural Networks

N. ANANTHI; K. KUMARAN; MADHUSHALINI. V; GANESH MOORTHI. S; HARISH. P

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2753-2762

Crops suffering from various diseases can be a big turndown for crop yield. This can affect effective crop production, if left unnoticed. Hence, it is extremely important to examine the plant diseases in its initial stages so that felicitous actions can be taken by the farmers at the nick of time, to avoid further losses. It focuses on the method which is based on image processing way for identification of diseases of leaf in a plant .so let’s introduce a system which uses convolutional neural networks that helps farmers to identify any possible plant disease by loading a leaf image in to the system. The system consists of a collection of algorithms which identifies the type of disease with which the leaf is affected by a disease. Input image given by the user goes through many pre-processing steps to identify the disease and results are returned back to the user on a user interface.

IMPROVING THE ACCURACY IN THE PREDICTION OF HEART DISEASE USING MACHINE LEARNING ALGORITHM

KUMARAN. K; N. ANANTHI; G. SARANYA; P.M. LAVANYA; A. SRIDEVI; S.RESHMI SHREE

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 4, Pages 2792-2799

Heart disease is one of the most huge sickness disease in the world. Expectation of cardiovascular sickness is a major test in the clinical information investigation. Machine learning (ML) is utilized in settling on choices and forecasts from the enormous amount of information created by the human services industry. Different investigations offer coronary illness with ML methods. This paper is target discovering highlights by applying ML strategies for improving the accuracy level in heart disease. Various techniques have been presented to predict the heart disease. We produce the presentation level of about 88.7% through the forecast model for heart disease with the hybrid random forest techniques