Cell Phone based Activity Detection using Markov Logic Network

Project report

The goal of the project is to design and implement of an experiment and signal processing algorithm to classify the activities performed by a set of people based on the and Iphone’s sensor (accelerometer, gyroscope, etc.). The data set was modeled as a Markov Logic Network. Different algorithms present in the Alchemy system was tried to train and test the data. Also different machine learning classification algorithms were used to compare the results obtained from the Alchemy system.