The School of Engineering

Intelligent and Autonomous Systems

People

Dr Djamel Azzi, Dr Salem Aljareh, Dr Rinat Khusainov, Dr Nick Savage, Dr Branislav Vuksanovic, Dr Linda Yang and Dr Shikun Zhou

Research Activities

Embedded and Distributed Autonomous Intelligent Systems

We conduct high quality research into mobile robotics and the application of artificial intelligence to provide advanced solutions to practical problems. We are interested, among other topics, in wireless sensor networks and their use in assisted living applications such as patient status monitoring, the detection of falls and the recognition of Activities of Daily Living (ADL). Having close links with industry through our knowledge transfer activities, we can provide excellent and relevant supervision in this area.

Recent examples of the involvement of the School in such work consists in a collaborative knowledge transfer project with Smart-e Ltd (www.smart-e.co.uk) manufacturers of audio/video switching and distribution equipment. The project, which was co-funded by SEEDA and Smart-e, aimed to research the range of available solutions for the implementation of web-based intelligent monitoring and control of Smart-e's range of audio-visual equipment. The outcome of the project was a successful future proof hardware and software platform which has enhanced the range of products on offer from the company.

More recent and current work with industry is the collaborative project with Karis Ltd. aimed at developing an Intelligent Care management System to provide a cost effective reliable solution to look after the needs of the elderly in their own homes. The project is funded by the company involved and the TSB (£217K). Staff are also involved in consultancy work, recent examples of which are recently completed projects investigating architectures, algorithms, and protocols for management of distributed Petabyte-scale data storage systems, and interoperability issues between Building Management Systems (BMS) and equipment large-scale data centres.

Intelligent Context Aware Systems

Context-awareness has become an essential part in personalised applications, health care and pervasive systems. We conduct and supervise research projects to provide intelligent context-aware information services in mobile environments which support interaction amongst people, artefacts and places on a global scale. For example, the recently completed PhD project JHPeer, under the supervision of Dr Linda Yang, systematically developed a context-aware framework for supporting the rapid development of personalised applications in mobile environments. A mobile news recommender system was successfully implemented on top of the JHPeer framework.

Other ongoing projects include: Automatic Recommendations for M-Learning, Mobile Mentoring of Seriously Ill Patients, Context-aware Search Engine, Software Simulation and Modelling of the Air Space Operations. Research has also focused on novel computer interfaces incorporating physiological and emotional feedback from users, to improve and enhance their interaction experience.

Security and Fraud Detection

Currently, our researchers are designing and implementing knowledge-based authentication software, improving fraud detection processing and systems to automatically collect web-based empirical data. Other projects include behavioural authentication, forensic analysis of volatile memory, watermarking techniques to improve the security of biometrics-based authentication systems and protocols for security negotiation.

Knowledge based authentication has been commercially used by the consumer credit industry for more than 10 years and more recently by government agencies such as the Inland Revenue. Currently, knowledge-based authentication software is typically bundled with the reference consumer credit data provided by the vendor, which are not affordable for many businesses and academic institutions. The research aims to design and implement knowledge-based authentication software that will be provided free to the public using an open source license.

The current research is focused on improving the fraud detection processing and a system using CAPTCHA techniques to automatically collect empirical test data from the Internet. An example of work completed in this area of research is an Eduserv funded (£100K) project which investigated the use of questions about personal information as the basis for authentication instead of the widely used password method. The research aimed to improve accuracy and usability by generating random authentication questions from a set of personal data. One novel aspect of the research was the application of signal processing techniques such as the Metropolis algorithm and the Expectation-Maximization (EM) algorithm to the field of authentication and fraud detection.

Staff in the School are also active in the area of digital forensics. A project currently under way titled ‘Forensic Live Response and Event Reconstruction’ requires information to be forensically gathered from RAM on a computer system. The information that is gathered will is used to identify what the computer system was being used for, leading to the development of techniques to reconstruct events that occurred on the computer system. The aim is to leverage information that has previously been "hidden" to forensic investigators.