Pixel based classification of satellite imagery - feature generation using Orfeo Toolbox, feature selection using Learning Vector Quantization, CLassification using Decision Tree, Neural Networks, Random Forests, KNN and Naive Bayes Classifier

Assess various ML algorithms on KDD99 network dataset then apply the best algorithm (Random Forest) using R.

Identifying 15 facial key points on a human greyscale image.

R/Auto-WEKA interface

Four practical applications: 50% of the overall grade, all weigh equal (12.50% out of 100%). The mark in each has to be greater or equal to 4 (out of 10) to pass this compulsory part.

Work I did for a group project that built machine learning models for heart disease datasets.