|
PhD Studentships
Project 1: Data Mining and Multi Level Combination for Cancellation
Forecasting Prof. Bogdan Gabrys (CIRG), Ms Silvia Riedel (LSB), Prof. John Fletcher (BU SM School) Accurate forecasting of the demand for airline tickets is critical
within revenue management applications used by large airlines like
Lufthansa. In this project the information stored in the airline Passenger
Name Records (PNRs) will be exploited through the use of data mining
techniques and used within novel adaptable (multilevel) classifier
and forecast combination framework for improvement of the cancellation
forecasts and overall demand prediction quality. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Lufthansa Systems Berlin (LSB), the world leading IT service provider for the airline and aviation industry. The PhD student will have an opportunity to frequently visit and work in LSB offices in Berlin. Strongly motivated candidates particularly with but not restricted to Computing and Mathematical background are encouraged to apply. For further details please follow this link. Project 2: Self-adapting and Monitoring Soft Sensors for Process
Industry Prof. Bogdan Gabrys (CIRG), Dr Paul Rogers (CIRG), Dr Uwe Tanger (Degussa AG) This project will be an application driven investigation of the possible
exploitation of various computational intelligence and nature-inspired
techniques for development of self-aware, -monitoring, -validating
and -adapting soft sensors for process industry based on a more general
class of locally adaptable and highly flexible predictive models required
in industrial environments. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and Degussa AG, a multinational specialty chemistry company with €11.2 billion turnover in 2004. As part of the project, the PhD student will have an opportunity to frequently visit and work in Degussa Labs in Germany. Strongly motivated candidates particularly with but not restricted to Computing and Engineering background are encouraged to apply. For further details please follow this link. Project 3: Physically Inspired Artificial Learning Models Dr Dymitr Ruta (BT Intelligent Systems Labs) and Prof. Bogdan Gabrys (CIRG) The main aim of the proposed research project is to explore and investigate the tremendous similarities between physical world and artificial intelligence in the context of machine learning in order to find inspirations and design the new breed of nature-inspired classification, clustering and regression techniques that would be capable of learning more efficiently from large sources of uncertain multi-type data and information. The work will include theoretical and explorative modelling in Matlab and Java addressing variety of problems in quantum computing, thermodynamics of information, Kolmogorov complexity, information uncertainty, kernel methods and many more. Strongly motivated candidates particularly with but not restricted to Computing, Mathematical and Physical background are encouraged to apply. This is a collaborative research project between Computational Intelligence Research Group (CIRG) and British Telecommunications (BT) Intelligent Systems Labs, one of the largest industrial R&D labs of this type in UK. As part of the project, the PhD student will have an opportunity to frequently visit and work in BT Intelligent Systems Labs in Ipswich. For further details please follow this link. Project 4: Using Computational Intelligence Techniques to Support Incidental Learning Michael Jones, Prof. Bogdan Gabrys and Dr Paul Rogers Incidental Learning is a term, originating in the Computational Intelligence Research Group at Bournemouth University, which describes a novel approach to providing online learners with a more active role in the learning process. Incidental Learning involves the development of a 'cognitive assistant', which continuously filters a wide range of additional support materials (gathered from a variety of external sources) in a manner which is appropriate to the learner's current cognitive load. The focus for the proposed research is the design of the filtering
process, which will use computational intelligence techniques to create
a system which will classify the potential usefulness of the additional
support materials, most of which will be unstructured. Statistical,
machine learning, and hybrid intelligent techniques will be used in
the design of the filtering system. The continuous nature of the filtering
process imposes performance constraints, which will also form part
of the research. Strongly motivated candidates particularly with but not restricted to Computing and Mathematical background are encouraged to apply. For further details please follow this link. Interested candidates should follow the application procedure listed
on the University of Bournemouth www
pages. |
