Edge-Centric Adaptive Inferential Analytics

Research Fields: wireless sensor networks, pervasive computing, edge computing, network-centric information processing systems.

Description: We are looking for an excellent candidate who will pursue a PhD on the development of energy-efficient distributed inferential analytics methods and algorithms at the network edge. We focus on distributed and mobile computing environments where a network of sensing and computing devices are responsible to locally process contextual data, reason and collaboratively infer knowledge. Pushing processing and inference to the network edge 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 intelligent and adaptive 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 mobile computing environment, where things at the edge of the network convey locally inferred knowledge to the applications. We focus on a setting that involves networks of adaptive distributed wireless devices (e.g., sensor nodes and actuators) capable of sensing and locally processing & reasoning about events. Each node performs measurements and locally extracts and infers knowledge over these measurements considering predictive models reasoning. The fundamental requirement to materialize predictive intelligence at the network edge is the autonomous nature of nodes to locally perform data sensing & inference, and disseminate only inferred knowledge (e.g., minimal sufficient statistics) to their neighbours for further processing.

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 Dr Dimitrios Pezaros and will join the Pervasive & Distributed Intelligence (Essence) Research Team and Networked Systems Research Laboratory (NETLAB) of the University of Glasgow. Our labs explore several different issues such as: distributed sensor networks, mobile computing, statistical learning, scalable & adaptive information processing, intelligent systems, bio-mimetic and bio-inspired data processing algorithms.

Skills: The ideal candidate will have a background in Computer Science and some background in either Mathematics and/or Statistics. Special areas of interest include: in-network processing, basics on statistics, and/or mathematical modelling/optimization. A good understanding of the basic Machine Learning and Adaptation algorithms 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.

Bio-Inspired In-Network Pervasive Systems

Research Fields: In-network processing, mobile computing, computational and swarm intelligence, bio-inspired information processing, pervasive computing.

Description: We are looking for an excellent candidate who will pursue a PhD on the development of new large-scale, in-network processing methods for distributed, streaming/contextual data and/or time-series generated in the context of the Internet of Things (IoT). Such methods will become the basis for building intelligent and adaptive applications over IoT data. IoT is a part of future Internet and comprises many billions of devices (‘things’) that sense, compute, communicate, share knowledge, and actuate. Such devices incorporate machine intelligence, physical/virtual identities, contextual sensors, RFIDs, social media, etc. The vision of IoT is to allow ‘things’ to be connected any-time, any-place, with anything and anyone. Some emerging Big Data applications based on knowledge derived from streaming contextual information include emergency situations awareness, smart city applications, remote sensing and environmental monitoring.

Challenges: In-network processing of contextual data and bio-inspired adaptation to changes in the context of IoT sets forth several challenges that have to do with the nature of the contextual data and the processes that generate them. Contextual information including time-series coming from IoT devices has a strong spatio-temporal dimension, which needs to be considered during the data modelling and learning process heading for reliable knowledge inference/reasoning and context awareness in pervasive computing environments. Moreover, research challenges relate to in-network contextual data and knowledge fusion, and localized adaptive bio-inspired decision making, which deals with the redundancies and interactions that exist among the distributed contextual data sources. In addition, IoT devices regularly fail, e.g. limited battery life-time and loss of connectivity, thus, resulting to incomplete contextual data availability. It is challenging for in-network context prediction and adaptation algorithm to cope with incomplete and missing contextual information, concept drift and changing data distributions.

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 Dr Dimitrios Pezaros and will join the Pervasive & Distributed Intelligence (Essence) Research Team and Networked Systems Research Laboratory (NETLAB) of the University of Glasgow. Our labs explore several different issues such as: distributed sensor networks, mobile computing, statistical learning, scalable & adaptive information processing, intelligent systems, bio-mimetic and bio-inspired data processing algorithms.

Skills: The ideal candidate will have a background in Computer Science and some background in either Mathematics/Statistics or Computational/Swarm Intelligence. Special areas of interest include: in-network processing, basics on statistics, and/or swarm intelligence. A good understanding of the basic adaptation and swarm intelligence algorithms (e.g., PSO, ACO, etc) 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.

Intelligence over Distributed Time Series: Learn to Adapt

Research Fields: multidimensional data streams, time-series, sensor networks, pervasive computing.

Description: The main aim of this PhD research is the intelligent management of distributed time series. The main focus will be in the management of heterogeneous streams of dynamically changing data and the provision of intelligent analytics techniques that will build knowledge over multiple streams. The study involves the spatio-temporal aspect of the data as well as the contextual information to support solutions fully adapted to the application domain and the underlying infrastructure. Novel techniques for distribution adaptation, model inconsistency checking, distributed time series correlation and decentralized concept drift identification will be proposed and evaluated. The implementation process will adopt widely known frameworks for supporting streaming environments (e.g., Storm).

Enrolment & Opportunity: The successful candidate will enroll as a PhD student at the School of Computing Science, University of Glasgow, under the supervision of Dr Christos Anagnostopoulos and Dr Kostas Kolomvatsos and will join the Pervasive & Distributed Intelligence (Essence) Research Team of the University of Glasgow. Our team explore several different issues such as: distributed sensor networks, mobile computing, statistical learning, scalable & adaptive information processing, intelligent systems, and bio-inspired processing algorithms.

Skills: The ideal candidate will have a background in Computer Science and some background in either Mathematics and/or Statistics. Special areas of interest include basics on statistics, and/or mathematical modelling/optimization. A good understanding of the basic Adaptation algorithms 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.

Knowledge Management in Edge Computing: Dealing with Uncertainty

Research Fields: knowledge management, uncertainty reasoning, fusion, edge computing.

Description:Edge computing offers an infrastructure that may limit the latency that end users enjoy when try to communicate with the back-end network infrastructure. Various processing schemes can be proposed for the management of data present at the edge of the network. The aim is to extract knowledge and support applications for a wide range of domains. This PhD research studies the potential innovations in the derived knowledge management at the edge focusing on the uncertainty. The study covers distributed solutions to manage and reason over the uncertainty present that is related to the knowledge that other nodes present in the network may have. Statistical and computational intelligence models related to the aggregation/fusion of knowledge extracted by edge nodes should incorporate the local view of each node and the inherent uncertainty derived by the application domain.

Enrolment & Opportunity: The successful candidate will enroll as a PhD student at the School of Computing Science, University of Glasgow, under the supervision of Dr Christos Anagnostopoulos and Dr Kostas Kolomvatsos and will join the Pervasive & Distributed Intelligence (Essence) Research Team of the University of Glasgow. Our team explores several different issues such as: distributed sensor networks, mobile computing, statistical learning, scalable & adaptive information processing, intelligent systems, and bio-inspired processing algorithms.

Skills:The ideal candidate will have a background in Computer Science and some background in either Mathematics and/or Statistics. Special areas of interest include basics on statistics, and/or mathematical modelling/optimization. A good understanding of the basic Adaptation algorithms 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.