Home

Pokemon Data Analysis in R Studio

This project studies features of Pokemons to determine the performance of a Pokemon in battle. It includes univariate and bivariate analysis
of each feature of the Pokemon. It also applies multiple linear regression model and linear prediction of Pokemon performance based on the
its features. In the end, it compared different models by applying statistical techniques including box-cox, backward selection,
forward selection, and cross-validation.

Tomato Leaf Disease CNN Project in Python

This is a real-life problem-based project that can be used for agricultural purposes. This project is based on the image classification technique.
It applies a convolutional neural network (CNN) as well as transfer technique Resnet 50. The model is trained based on different pictures of leaves
suffering from various diseases. After that, we will compare the model with normal leaf pictures and will check how much accuracy we are getting from it.
Tools we use are google colab and python.