26 results

A topological insight into restricted Boltzmann machines

Journal Article
Mocanu, D. C., Mocanu, E., Nguyen, P. H., Gibescu, M., & Liotta, A. (2016)
A topological insight into restricted Boltzmann machines. Machine Learning, 104(2-3), 243-270. https://doi.org/10.1007/s10994-016-5570-z
Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep artificial neural networks for automatic feature...

Decentralized dynamic understanding of hidden relations in complex networks

Journal Article
Mocanu, D. C., Exarchakos, G., & Liotta, A. (2018)
Decentralized dynamic understanding of hidden relations in complex networks. Scientific Reports, 8(1), https://doi.org/10.1038/s41598-018-19356-4
Almost all the natural or human made systems can be understood and controlled using complex networks. This is a difficult problem due to the very large number of elements in s...

The challenge of visualising multiple overlapping classification.

Conference Proceeding
Graham, M., Kennedy, J., & Hand, C. (1999)
The challenge of visualising multiple overlapping classification. In N. W. Paton, & T. Griffiths (Eds.), Proceedings [of] IEEE User Interfaces to Data Intensive Systems (UIDIS) 1999, 42-51. https://doi.org/10.1109/UIDIS.1999.791461
Techniques for visualising hierarchies have concentrated on displaying static structures or, in the case of dynamic hierarchies, adding or deleting nodes from the hierarchy. H...

Lightweight Reinforcement Learning for Energy Efficient Communications in Wireless Sensor Networks

Journal Article
Savaglio, C., Pace, P., Aloi, G., Liotta, A., & Fortino, G. (2019)
Lightweight Reinforcement Learning for Energy Efficient Communications in Wireless Sensor Networks. IEEE Access, 7, 29355-29364. https://doi.org/10.1109/access.2019.2902371
High-density communications in wireless sensor networks (WSNs) demand for new approaches to meet stringent energy and spectrum requirements. We turn to reinforcement learning,...

A framework for information visualisation

Journal Article
Kennedy, J., Mitchell, K., & Barclay, P. J. (1996)
A framework for information visualisation. SIGMOD record, 25, 30-34
In this paper we examine the issues involved in developing information visualisation systems and present a framework for their construction. The framework addresses the compon...

Visual comparison and exploration of natural history collections

Conference Proceeding
Graham, M., Kennedy, J., & Downey, L. (2006)
Visual comparison and exploration of natural history collections. In A. Celentano, & P. Mussio (Eds.), Advanced Visual Interfaces (AVI) 2006, Proceedings of the International Working Conference, 310-313. doi:10.1145/1133265.1133329
Natural history museum collections contain a wealth of specimen level data that is now opening up for digital access. However, current interfaces to access and manipulate this...

Resilience of Video Streaming Services to Network Impairments

Journal Article
Torres Vega, M., Perra, C., & Liotta, A. (2018)
Resilience of Video Streaming Services to Network Impairments. IEEE Transactions on Broadcasting, 64(2), 220-234. https://doi.org/10.1109/tbc.2017.2781125
When dealing with networks, performance management through conventional quality of service (QoS)-based methods becomes difficult and is often ineffective. In fact, quality eme...

A standard data model representation for taxonomic information.

Journal Article
Kennedy, J., Hyam, R., Kukla, R., & Paterson, T. (2006)
A standard data model representation for taxonomic information. OMICS, 10, 220-230. doi:10.1089/omi.2006.10.220
The names used by biologists to label the observations they make are imprecise. This is an issue as workers increasingly seek to exploit data gathered from multiple, unrelated...

Analyzing Objective and Subjective Data in Social Sciences: Implications for Smart Cities

Journal Article
Erhan, L., Ndubuaku, M., Ferrara, E., Richardson, M., Sheffield, D., Ferguson, F. J., …Liotta, A. (2019)
Analyzing Objective and Subjective Data in Social Sciences: Implications for Smart Cities. IEEE Access, 7, 19890-19906. https://doi.org/10.1109/access.2019.2897217
The ease of deployment of digital technologies and the Internet of Things gives us the opportunity to carry out large-scale social studies and to collect vast amounts of data ...

On-Line Building Energy Optimization Using Deep Reinforcement Learning

Journal Article
Mocanu, E., Mocanu, D. C., Nguyen, P. H., Liotta, A., Webber, M. E., Gibescu, M., & Slootweg, J. G. (2019)
On-Line Building Energy Optimization Using Deep Reinforcement Learning. IEEE Transactions on Smart Grid, 10(4), 3698-3708. https://doi.org/10.1109/tsg.2018.2834219
Unprecedented high volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the ...