As the use of smart phones 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 realworld 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.

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.

This paper discusses two projects aimed at utilising the educational potential of hypermedia whilst avoiding the danger of the user becoming "lost in I?yperspace". The $rst project adopts a connectionist approach to con$gure 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. 1) IntroductionIn the face of growing economic pressures, Leeds Metropolitan University is seeking increasingly to use educational hypermedia [l] to solve the practical problems of providing for increasing student numbers given static or decreasing resources, a widespread problem shared with many other educational institutions [2]. Use of educational hypermedia raises a number of user interface issues, a major one of which concerns user navigation. The issue is how, on the one hand, to prevent the user from becoming overwhelmed with information and losing track of where they are going, whilst on the other hand permitting them to make the most of the facilities the hypermedia offers.Two broad approaches to th~s issue can be identified. One is to restrict the number of links made available to the student. The concem that this might lead to an impoverished set of learning opportunities can be countered by seeking dynamically to configure the available links as the user proceeds. A second approach is to make all the links available but seek to assist the user by one or more navigational aids. We are currently conducting research concerning both of these approaches, and seelung to combine this with our ongoing educational provision, with a view to offering our students increasingly powerful student-based learning opportunities. This paper will review our research on each of these approaches in turn. 2) Restricting links through adaptive hypermediaElsom-Cook 131 argues that the perfect tutoring system should be able to slide between the two extremes of total constraint and total absence of constraint, according to the student's needs and current state of knowledge. In a similar vein, Hartley (141, cf.[5]) argues that when there is a mismatch between the strategy of the learning system and learning style of the student, performance is degraded, suggesting a need for support for different styles and viewpoints of users. With this in mind, one of our aims is to build hypermedia systems with the ability to adapt to their students' needs as they progress from novice to expert users, and ultimately to modify their strategy according to their experiences with other students ([b], [7]). Our current prototypes achieve this via a combination of knowledge-based representations (which we refer to as "semantic hypermedia") and neural network models (konnectionist modelling").We argue that this approach overcomes two major concerns in the domain of ...

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.

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.