School of
Information Technology and Electrical Engineering

Through a dedicated laboratory space, Data Science researchers have access to a one terabyte SAP HANA in-memory database.

The SAP HANA technology provides researchers with invaluable computing power to analyse large experimental datasets. This lab infrastructure supports indexing and query processing, data quality management, information extraction, linkage and integration, data mining and pattern recognition, as well as clustering, ranking and recommendation. 

The group has access to a diversity of real world datasets including spatiotemporal, multimedia, business, heath, social, text and graphic data.

Computing Infrastructure:

  • 8 high-end servers + 4 GPUs
  • In-memory computing including SAP HANA (1TB Memory) + a HANA-free mirror
  • FlashLite: 70 compute nodes (`2400 cores): Dual socket Intel E5-2680v3 2.5GHz (Haswell), 512 GB DDR-2, 4.8 TB NVMe SSD
  • 16-node Cluster/Hadoop/Spark platforms