Qualitative Activity Recognition using weight Lifting Exercise
Project Description
Machine learning and Pattern Recognition techniques to detect mistakes during weight lifting exercises. Goal is to use data from accelerometers on the belt, forearm, arm, and dumbbell of 6 participants. As they were asked to perform barbell lifts correctly and incorrectly in 5 different ways.
DataSet
Training set (19,622 entries) and testing set (20 entries) on 160 attributes. I have reduced the same to 40 attributes mainly by removing irrelevant attributes using PCA and zero or near to zero Covariance.
Algorithms Used
Random Forest, Decision Tree(C5), Support Vector Machine(Linear/Radial)