Data Science projects

SquashFlow Analytics

A semi-automated pipeline that can analyse videos of squash matches using machine learning techniques. It extracts movement and shot information from the video to generate dynamic match reports.

• Firstly, players poses are estimate using a deep neural network. The pose results are then cleaned with the help of visual filters and colour histogram classification in order to ensure the best data quality.

• Shot timing is predicted using a convolutional neural network (CNN)

• The position and shot timing data are combined to identify each players position during the shots and distinguish between different types of shots (i.e. service, drop, cross-court)

• Finally all position are used to generate insightful metrics that are presented in a dashboard.

Extraction LoggeR

Access the dashboard here.

A dashboard used to track the progress of high-throughput genomics experiments in the frame of a large collaborative project. Users can log new experiments as well as explore the archive previous experiments. Lastly, the dashboard indicates the next steps the project's workflow.

Developed in R, using the shiny package.