RT

R. Tebbens

info

Please Note

2 records found

Improving and testing football activity recognition based on signal data using deep learning

There is a raising demand for player statistics in the world of football. With the developments over the last years in wearable sensors, Human Activity Recognition (HAR) based on wearable IMU sensors can be used to tackle this problem. This thesis builds upon an earlier research done for this topic, where an end-to-end pipeline based on deep learning was created that is able to be trained and used for football activity recognition. The goal is to test and improve said pipeline. This was done by adding change of directions (COD’s) to the classifiable activities. Furthermore, run velocities were build as a spectrum with several categories depending on the speed. A combination of convolutional and recurrent layers resulted in test accuracies up to 88.9%.
Afterwards, the pipeline was used to evaluate larger datasets containing football drill and a football physiotherapy training. For this a sliding window evaluation procedure was proposed. These evaluations gave promising results. Many actions and football related activities could be recognized, however many smaller, shorter actions were missed. This can be seen as lack in trainingdata. In this data, little activities with the ball were present. Hence the deep learning models could not be trained accordingly. Later, it was researched
if additional training of activities with ball increased the evaluation. This was indeed confirmed, since the evaluations showed more detailed and realistic results. Including even more additional trainingdata, could result in the pipeline performing reliably in real-life football scenario’s. ...
Bachelor thesis (2018) - Ricardo Tebbens, Mathijs Joosten, Mark Veraar, Bart van den Dries
When is a deck of cards shuffled good enough? We have to perform seven Riffle Shuffles to randomize a deck of 52 cards. The mathematics used to calculate this, has some strong connections with permutations, rising sequences and the L1 metric: the variation distance. If we combine these factors, we can get an expression of how good a way of shuffling is in randomizing a deck. We say a deck is randomized, when every possible order of the cards is equally likely. This gives us the cut-off result of seven shuffles. Furthermore, this gives us a window to look at other ways of shuffling, some even used in casinos. It turns out that some of these methods are not randomizing a deck enough. We can also use Markov chains in order to see how we randomize cards by ”washing” them over a table. ...