At TRACKTICS we are constantly trying to come up with new ways to visualize the data that our customers acquire with their GPS Performance Trackers. Recently, I created a small prototype, visualizing locations and orientation (yaw angle) time series data in the form of three-dimensional animations using the Unity 3D engine. Here’s a small example:
The visualization has been featured in a Report by Stuttgarter Zeitung and might be turned into a new feature for TRACKTIC’s Web App feature - not decided yet, though ;-).
Age-dependency of sprint top speeds TRACKTICS is having a long-term partnership with Fundación Real Madrid Clinics (FRMC) where we equip hundreds of football schools under the Real Madrid Brand Umbrella with our GPS performance trackers. In the scope of this partnership we have collected performance data of tens of thousands of youth players, which amounts to what we think is probably the largest data set of its kind.
Based on the Real Madrid dataset we have devised a new model of sprint top speed age-dependency, using simple restricted cubic spline regression (see the figure above).
CloudQuake is a university project where I tried to apply real-time sentiment analysis on Twitter streams. Our approach was to first collect data via Amazon Kinesis (which allows for a convenient way to combine data from different sources) and then use Apache Spark Realtime and its MLlib to classify tweets using a simple Naive Bayes classifier trained with publicly available annotations. While the initial idea was to first filter the data for earthquake related tweets and then combine the inferred tweet sentiments with a Long/Short term moving average indicator with the goal to detect whether the mentions of Quake-related tweets allow to detect earthquakes.