Research


Multimedia Analytics Multimedia analytics is a new and exciting research area that combines techniques from multimedia analysis, visual analytics, and data management, with a focus on creating systems for analysing large-scale multimedia collections. The size and complexity of media collections is ever increasing, as is the desire to harvest useful information from these collections, with expected impacts ranging from the advancement of science to increased company profits. Indeed, multimedia analytics sees potential applications in diverse fields, including data journalism, urban computing, lifelogging, digital heritage, healthcare, digital forensics, natural sciences, and social media.

Tags

Buildings as Cyber-Physical Systems Denmark aims to become a fossil free society in 2050. Shaping electricity demand so that it matches the variable nature of renewable supply will lead us a long way towards achieving these climate and energy targets. Digital technologies are expected to play an enabling key role in supporting flexible electricity consumption. Buildings are the main consumer of primary energy in Europe and the US. Non-residential buildings, like the one of the IT University, are particularly challenging because they are public spaces where economic incentives are not linked to electricity consumption.

Tags

Buildings as Cyber-Physical Systems The Copernicus program provides a large amount of satellite data in a way that allows IT people to integrate them into their applications. Satellite data gives us new opportunities to create improvements within domains like sustainable energy, agriculture and transportation. At PiTLab, we explore how satellite data can be combined with IoT-based systems that provide in-situ sensing capabilities to provide new insights for air- or water-quality monitoring.

Tags

Decentralized Cloud IoT systems rely on gateways that interface devices embedded in the physical world and cloud-based services. When latency is of the essence, when the volume of data is important or when personal data is concerned, it is necessary to process data at the edges of the network, on the IoT gateways. The new generation of decentralised storage systems based on distributed ledgers (such as IPFS, StorJ or MaidSafe) offer technical options, but there are socio-technical challenges at the edge of the Internet, which cannot be addressed by a single technology.

Tags

Near-Data Processing When network and hosts are bottlenecks, it is necessary to minimize data movement. Processing data where it resides (in situ) or as it moves through the network (in-transit) is an efficient means to avoid data movement. We consider a tiered storage architecture at rack-scale, where multi-core hosts are connected to a collection of open-channel SSDs via a SoC that offloads the hosts and processes data in order to minimize data movement.

Tags