PhD Call: Conveying Predictive Intelligence to the Edge

Research Fields: Distributed Statistical Learning, Predictive Models, (Future) Internet of Things

Description: We are looking for an excellent candidate who will pursue a PhD on the development of energy-efficient distributed learning methods and algorithms in the context of the Internet of Things (IoT). We focus on an Internet of Things (IoT) environment where a network of sensing and computing devices are responsible to locally process contextual data, reason and collaboratively infer knolwedge. Pushing processing and inference to the edge of the IoT network allows the complexity of the reasoning process to be distributed into many smaller and more manageable pieces and to be physically located at the source of the contextual information it needs to work on. This enables a huge amount of rich contextual data to be processed in real time that would be prohibitively complex and costly to deliver on a traditional centralized cloud/back-end processing system. Emerging Future IoT applications based on knowledge derived from streaming contextual information include emergency situations awareness, smart city applications, remote sensing and environmental monitoring.

Challenges: We envisage a IoT environment, where things at the edge of the IoT network convey locally inferred knowledge to the IoT applications. We focus on a setting that involves networks of distributed wireless devices (e.g., sensor nodes and actuators, smart meters) capable of sensing and locally processing & reasoning about events. Each node perform measurements and locally extracts and infers knowledge over these measurements in light of predictive models reasoning. The fundamental requirement to materialize predictive intelligence at the edge of the IoT network is the autonomous nature of nodes to locally perform data sensing & inference, and disseminate only inferred knowledge (e.g., minimal sufficient statistics) to their neighbors and concentrators. Nodes convey intelligence to concentrators for inference.

Enrolment & Opportunity

The successful candidate will enrol as a PhD student at the School of Computing Science, University of Glasgow, under the supervision of Dr Christos Anagnostopoulos and will join the Information, Data, Event, and Analytics at Scale (IDEAS) and Networked Systems Research Laboratory (NETLAB) of the University of Glasgow. Our labs explore a number of different issues such as: machine and statistical learning in high dimensional settings, dimensionality reduction, scalable, distributed machine learning techniques, networked systems security, Network Function Virtualisation. For a more detailed description the interested candidates may visit:

http://www.gla.ac.uk/schools/computing/staff/christosanagnostopoulos/ and the list of publications within there.

The University of Glasgow is a world-renowned education and research hub, offering considerable opportunities for training and exposure to machine learning, large-scale analytics, and distributed computing with a number of research teams in the School of Computing Science being active on these and related fields. In addition the selected candidate will have ample opportunities to participate in the top conferences of distributed computing, mobile computing, large-scale learning and mining, and data engineering.

Skills

The ideal candidate will have a background in computer science and some background in either mathematics or statistics and distributed algorithms. Special areas of interest include: statistical learning, basics on statistics, and/or mathematical modelling/optimization. A good understanding of the basic machine learning methods/algorithms and distributed computing as well as an MSc in one of the above areas will be a considerable plus. Programming skills, good command of English and team work capacity are required.

Further Information

Questions regarding academic and research aspects of the position should be directed to Dr Christos Anagnostopoulos by e-mail: christos.anagnostopoulos@glasgow.ac.uk

For general enquiries about the application process visit our How to Apply page.

References

Anagnostopoulos, C., and Kolomvatsos, K. (2016) A delay-resilient and quality-aware mechanism over incomplete contextual data streams.Information Sciences, 355-56, pp. 90-109.

Kolomvatsos, K., Anagnostopoulos, C., and Hadjiefthymiades, S. (2016) Data fusion and type-2 fuzzy inference in contextual data stream monitoring. IEEE Transactions on Systems, Man, and Cybernetics: Systems, (doi:10.1109/TSMC.2016.2560533)

Anagnostopoulos, C. (2016) Quality-optimized predictive analytics. Applied Intelligence

Anagnostopoulos, C., Hadjiefthymiades, S., and Kolomvatsos, K. (2016) Accurate, dynamic, & distributed localization of phenomena for mobile sensor networks. ACM Transactions on Sensor Networks, 12(2), 9. (doi:10.1145/2882966)

Anagnostopoulos, C., and Hadjiefthymiades, S. (2014) Advanced principal component-based compression schemes for wireless sensor networks. ACM Transactions on Sensor Networks, 11(1), 7.

Advertisements