In the summer of 2014, I worked on a project about the Classification of Accelerometer Data under the supervision
of Professor Doina Precup
of the Reasoning and Learning Lab at McGill.
Professor Precup and her colleagues acquired accelerometer data that was retrieved from mobile phones carried by students
that recorded the phone's movements.
My objective of the project was to determine the best set of parameters for a classifier that determines
the identity of the students carrying the phones.
Specifically, I focused on the tuning of parameters for Weka's built-in J48 and IBk classifiers.
I programmed in Java to preprocess raw mobile phone accelerometer data to be formatted for Weka software.
Moreoever, I ran scripts through Weka on both Windows and Linux while tuning classifiers.
In addition to working on my project, I attended weekly lab meeting and listened to graduate student thesis defences.
On the final week of the summer, I presented my project in front of the other Reasoning and Learning Lab students.