Integration of WEKA in a Science Gateway
Integration of the Waikato Environment for Knowledge Analysis (WEKA) collection of machine learning algorithms for data mining tasks in a Science Gateway. WEKA will be trained with the Wisconsin Breast Cancer datasets from the UCI Machine Learning Repository to help doctors in Tanzania to distinguish breast cancer from benign samples.
The main outcome of the use case is a JSR 168/286 standard-based “portlet”, which will be integrated in the Africa Grid Science Gateway.
For running WEKA, the Africa Grid Science Gateway is connected to a FutureGateway API Server – developed in the context of the INDIGO-DataCloud project – which seamlessly executes jobs on local, Grid and Cloud resources belonging to the Africa & Arabia Regional Operation Centre.