Dr Duncan Mullier

Described within this paper is an adaptive hypermedia system (AHS) that utilises symbolic AI and connectionist AI to provide generic student modelling. The needs for generic tutoring systems are discussed, in terms of a system that is applicable to a multitude of teaching domains, whilst maintaining diagnostic facilities of the student. The hypermedia architecture is based on a semantic-network allowing the use of automatic reasoning to produce weighted links. A type of student model is employed to record information about the student so that the weighted links can be tailored for the student's interests. A neural network is used to grade the student into an ability level based upon their interactions with tutorials. A further neural network is used to recognise the movements students make as they browse the hypermedia and link it to tasks and abilities. This offers the potential to extract information about the student without direct dialogues.

This paper discusses two projects aimed at utilising the educational potential of hypermedia whilst avoiding the danger of the user becoming lost in hyperspace. The first project adopts a connectionist approach to configure dynamically the links made available to the user. The paper outlines the neural network approaches adopted and reports on results to date. The second project concerns the development of educational packages providing a range of navigational aids to the user, and the paper reports on empirical work involving the use of such a package by students in a tutorial context. © 1997 IEEE.

Abstract

The research field of cloud computing has witnessed tremendous progress as commercial cloud providers brought powerful distributed infrastructures within reach of small and medium enterprises (SMEs) through their revolutionary pay-as-you-go model. Simultaneously, the popularisation of containers has empowered virtualisation with seamless orchestration technologies for the deployment and management of large-scale distributed systems across different geolocations and providers. Big data is another research area which has developed at an extraordinary pace as industries endeavour to discover innovative and effective ways of processing large volumes of structured, semi-structured and unstructured data emitted at high velocity by an increasing number of internet-enabled devices. This research aims to integrate the latest advances within the fields of cloud computing, virtualisation and big data for a systematic approach to stream processing. The novel contributions of this research are: 1) MC-BDP, a reference architecture for big data stream processing in a containerised, multi-cloud environment; 2) a case study conducted with the Estates and Sustainability departments at Leeds Beckett University to evaluate an MC-BDP prototype within the context of energy efficiency for smart buildings.

As the use of smartphone proliferates, and human interaction through social media is intensified around the globe, the amount of data available to process is greater than ever before. As consequence, the design and implementation of systems capable of handling such vast amounts of data in acceptable timescales has moved to the forefront of academic and industry-based research. This research represents a unique contribution to the field of software engineering for Big Data in the form of an investigation of the big data architectures of three well-known real-world companies: Facebook, Twitter and Netflix. The purpose of this investigation is to gather significant non-functional requirements for real-world big data systems, with an aim to addressing these requirements in the design of our own unique reference architecture for big data processing in the cloud: MC-BDP (Multi-Cloud Big Data Processing). MC-BDP represents an evolution of the PaaS-BDP (Platform as a Service for Big Data Processing) architectural pattern, previously developed by the authors. However, its presentation is not within the scope of this study. The scope of this comparative study is limited to the examination of academic papers, technical blogs, presentations, source code and documentation officially published by the companies under investigation. Ten non-functional requirements are identified and discussed in the context of these companies’ architectures: batch data, stream data, late and out-of-order data, processing guarantees, integration and extensibility, distribution and scalability, cloud support and elasticity, fault tolerance, flow control and flexibility and technology agnosticism. They are followed by the conclusion and considerations for future work.

The field of cloud computing has witnessed tremendous progress, with commercial cloud providers offering powerful distributed infrastructures to small and medium enterprises (SMEs) through their revolutionary pay-as-you-go model. Simultaneously, the rise of containers has empowered virtualisation, providing orchestration technologies for the deployment and management of large-scale distributed systems across different geolocations and providers. Big data is another research area which has developed at an extraordinary pace as industries endeavour to discover innovative and effective ways of processing large volumes of structured, semi-structured, and unstructured data. This research aims to integrate the latest advances within the fields of cloud computing, virtualisation, and big data for a systematic approach to stream processing. The novel contributions of this research are: (1) MC-BDP, a reference architecture for big data stream processing in a containerised, multi-cloud environment; (2) a case study conducted with the Estates and Sustainability departments at Leeds Beckett University to evaluate an MC-BDP prototype within the context of energy efficiency for smart buildings. The study found that MC-BDP is scalable and fault-tolerant across cloud environments, key attributes for SMEs managing resources under budgetary constraints. Additionally, our experiments on technology agnosticism and container co-location provide new insights into resource utilisation, cost implications, and optimal deployment strategies in cloud-based big data streaming, offering valuable guidelines for practitioners in the field.

DScent was a joint project between five UK universities combining research theories in the disciplines of computational inference, forensic psychology and expert decision-making in the area of counter-terrorism. This document discusses the work carried out by Leeds Metropolitan University which covers the research, design and development work of an investigator support system in the area of deception using artificial intelligence. For the purposes of data generation along with system and hypothesis testing the project team devised two closed world games, the Cutting Corners Board Game and the Location Based Game. DScentTrail presents the investigator with a ‘scent trail’ of a suspect’s behaviour over time, allowing the investigator to present multiple challenges to a suspect from which they may prove the suspect guilty outright or receive cognitive or emotional clues of deception (Ekman 2002; Ekman & Frank 1993; Ekman & Yuille 1989; Hocking & Leathers 1980; Knapp & Comadena 1979). A scent trail is a collection of ordered, relevant behavioural information over time for a suspect. There are links into a neural network, which attempts to identify deceptive behavioural patterns of individuals. Preliminary work was carried out on a behavioural based AI module which would work separately alongside the neural network, with both identifying deception before integrating their results to update DScentTrail. Unfortunately the data that was necessary to design such a system was not provided and therefore, this section of research only reached its preliminary stages. To date research has shown that there are no specific patterns of deceptive behaviour that are consistent in all people, across all situations (Zuckerman 1981). DScentTrail is a decision support system, incorporating artificial intelligence (AI), which is intended to be used by investigators and attempts to find ways around the problem stated by Zuckerman above.

The DScentTrail System has been created to support and demonstrate research theories in the joint disciplines of computational inference, forensic psychology and expert decision-making in the area of counter-terrorism. DScentTrail is a decision support system, incorporating artificial intelligence, and is intended to be used by investigators. The investigator is presented with a visual representation of a suspect‟s behaviour over time, allowing them to present multiple challenges from which they may prove the suspect guilty outright or receive cognitive or emotional clues of deception. There are links into a neural network, which attempts to identify deceptive behaviour of individuals; the results are fed back into DScentTrail hence giving further enrichment to the information available to the investigator.

This article presents findings concerned with the use of neural networks in the identification of deceptive behaviour. A game designed by psychologists and criminologists was used for the generation of data used to test the appropriateness of different AI techniques in the quest for counter-terrorism. A feed forward back propagation network was developed and subsequent neural network experiments showed on average a 60% success rate and at best a 68% success rate for correctly identifying deceptive behaviour. These figures indicate that, as part of an investigator support system, a neural network would be a valuable tool in the identification of terrorists prior to an attack. © Springer-Verlag London Limited 2011.