The use of digital technologies in providing health care services is collectively known as eHealth. Considerable progress has been made in the development of eHealth services, but concerns over service integration, large scale deployment, and security, integrity and confidentiality of sensitive medical data still need to be addressed. This paper presents a solution proposed by the Data Capture and Auto Identification Reference (DACAR) project to overcoming these challenges. The DACAR platform uses a Single Point of Contact, a rule based information sharing policy syntax and data buckets hosted by a scalable and cost-effective Cloud infrastructure, to allow the secure capture, storage and consumption of sensitive health care data. Currently, a prototype of the DACAR platform has been implemented. To assess the viability and performance of the platform, a demonstration application, namely the Early Warning Score, has been developed and deployed within a private Cloud infrastructure at Edinburgh Napier University. Simulated experimental results show that the end-to-end communication latency of 97.8% of application messages were below 100ms. Hence, the DACAR platform is efficient enough to support the development and integration of time critical eHealth services. A more comprehensive evaluation of the DACAR platform in a real life medical environment is under development at Chelsea & Westminster Hospital in London.

This article presents a transfer learning model via convolutional neural networks (CNNs) with skip connection topology, to avoid the vanishing gradient and time complexity, which are usually common in transfer learning networks. Three pretrained CNN architectures, namely AlexNet, VGG16 and GoogLeNet are employed to equip with skip connections. The transfer learning is implemented through fine-tuning and freezing the CNN architectures with skip connections based on magnetic resonance imaging (MRI) slices of brain tumor dataset. Furthermore, in the preprocessing, a frequency-domain information enhancement technique is employed for better image clarity. Performance evaluation is conducted on the transfer learning networks with skip connections to obtain improved accuracy in brain MRI classifications.

The aim of this paper is to provide profiles for crimes which can be used to model the context for information sharing between the police and community partner organisations. This context can then be integrated with information-sharing syntax used by Single Point of Contact (SPoC) agents to process information sharing requests [1]. The questionnaires attempt to classify crimes into categories, with identify profiles of crime-types, according to the level of information sharing they necessitate between community partner organisations. Crimes are separated into classifications, which are based on the perceived level of necessary informationexchange among police and community partners. The aim of the questionnaire is to gather academic responses to identify the level of risk in order that it can be defined as risk assessment level, which is key to enhancing the public"s reassurance in the police.

No abstract

We live in a world where trust relationships are becoming ever more important. The paper defines a novel modelling system of trust relationships using Binary Decision Diagrams (BDDs), and outlines how this integrates with an information sharing architecture known as safi.re (Structured Analysis and Filtering Engine). This architecture has been used on a number of information sharing projects, including within health and social care integration, and in sharing between the police and their community partners. The research aims to abstract the relationships between domains, organisations and units, into a formal definition, and then implement these as governance rules, and using the trust relationship definition, and the rules.