Belfast Soundwalks

The Belfast Soundwalks project, led by Professor Pedro Rebelo and co-ordinated by Dr Sarah Bass (Sonic Arts Research Centre) in collaboration with Belfast City Council (BCC), aims to use sonic art to engage the public through the development of a locative mobile phone app. Targeting both tourists and citizens of the city, this project aims to sonically enhance the experience of a number of areas of the city, including destinations that may not traditionally be accessed as attractions by visitors and/or disregarded or undervalued by local residents. The project will bring together a number of sonic artists/composers who will create approximately ten soundwalks around the city, while liaising with BCC to distribute the resulting app to the public in line with their tourism and cultural strategy. The project is centred on the development of smart phone apps which provide unique listening experiences associated with key places in the city. The user’s location in the city is tracked through GPS which triggers sound materials ranging from speech to environmental sound and abstract imagined sound worlds. Additionally, local community groups will be consulted in order to evaluate and reflect upon the effectiveness of the soundwalks.

The project builds on the success of the Literary Belfast app and aims to further strengthen links between Queen’s University Belfast and Belfast City Council through facilitating the dissemination of an art form not widely experienced by the general public. Through the newly created Institute for Collaborative Research in the Humanities, directed by Professor John Thompson we are articulating this project with Queen’s consortium partners, Newcastle University and Durham University.

“The Arts and Humanities Research Council (AHRC) funds world-class, independent researchers in a wide range of subjects: ancient history, modern dance, archaeology, digital content, philosophy, English literature, design, the creative and performing arts, and much more. This financial year the AHRC will spend approximately £98m to fund research and postgraduate training in collaboration with a number of partners. The quality and range of research supported by this investment of public funds not only provides social and cultural benefits but also contributes to the economic success of the UK. For further information on the AHRC, please go to: www.ahrc.ac.uk”.

High accuracy android malware detection using ensemble learning

With over 50 billion downloads and more than 1.3 million apps in Google’s official market, Android has continued to gain popularity amongst smartphone users worldwide. At the same time there has been a rise in malware targeting the platform, with more recent strains employing highly sophisticated detection avoidance techniques. As traditional signature based methods become less potent in detecting unknown malware, alternatives are needed for timely zero-day discovery. Thus this paper proposes an approach that utilizes ensemble learning for Android malware detection. It combines advantages of static analysis with the efficiency and performance of ensemble machine learning to improve Android malware detection accuracy. The machine learning models are built using a large repository of malware samples and benign apps from a leading antivirus vendor. Experimental results and analysis presented shows that the proposed method which uses a large feature space to leverage the power of ensemble learning is capable of 97.3 % to 99% detection accuracy with very low false positive rates.

The significance of bruising in the pre-mobile infant

The majority of children in our society are loved andcherished. The occasional cases of intentional injury to a childresulting in death or significant harm evoke powerful anduncomfortable feelings (Devaney et al, 2013), and the publicoutcry may result in health and social workers facing criticism.Identifying whether an infant is at risk of abuse is a challengefor practitioners, and can be a source of stress and anxiety(Brandon et al, 2011). Bruising is a strong indicator of childabuse involving intentional injury (Kemp et al, 2014). Theincidence of bruising correlates to developmental stage, withnon-mobile infants least likely to incur bruising. Therefore, itspresence in pre-mobile infants requires immediate assessment.A search of the literature around bruising in pre-mobile infantsrevealed themes of missed opportunities for early intervention,the role of the father in the family and the significance of childdevelopment. Sharing of knowledge and expertise within themultidisciplinary team is key to safeguarding infants.

Footprints in the sand: a persistent spatial impression of fishing in a mobile groundfish assemblage

Fishing is well known to curtail the size distribution of fish populations. This paper reports the discovery of small-scale spatial patterns in length appearing in several exploited species of Celtic Sea demersal 'groundfish'. These patterns match well with spatial distributions of fishing activity, estimated from vessel monitoring records taken over a period of 6 years, suggesting that this 'mobile' fish community retains a persistent impression of local-scale fishing pressure. An individual random-walk model of fish movement best matched these exploitation 'footprints' with individual movement rates set to <35 km per year. We propose that Celtic Sea groundfish may have surprisingly low movement rates for much of the year, such that fishing impact is spatially heterogeneous and related to local fishing intensity.

Towards a Mobile Assistive Technology for Monitoring and Assessing Cognitive Fatigue in Individuals with Acquired Brain Injury

Those living with an acquired brain injury often have issues with fatigue due to factors resulting from the injury. Cognitive impairments such as lack of memory, concentration and planning have a great impact on an individual’s ability to carry out general everyday tasks, which subsequently has the effect of inducing cognitive fatigue. Moreover, there is difficulty in assessing cognitive fatigue, as there are no real biological markers that can be measured. Rather, it is a very subjective effect that can only be diagnosed by the individual. Consequently, the traditional way of assessing cognitive fatigue is to use a self-assessment questionnaire that is able to determine contributing factors. State of the art methods to evaluate cognitive! fa tigue employ cognitive tests in order to analyse performance on predefined tasks. However, one primary issue with such tests is that they are typically carried out in a clinical environment, therefore do not have the ability to be utilized in situ within everyday life. This paper presents a smartphone application for the evaluation of fatigue, which can be used daily to track cognitive performance in order to assess the influence of fatigue.

A Fast Algorithm for Sparse Support Vector Machines for Mobile Computing Applications

This research presents a fast algorithm for projected support vector machines (PSVM) by selecting a basis vector set (BVS) for the kernel-induced feature space, the training points are projected onto the subspace spanned by the selected BVS. A standard linear support vector machine (SVM) is then produced in the subspace with the projected training points. As the dimension of the subspace is determined by the size of the selected basis vector set, the size of the produced SVM expansion can be specified. A two-stage algorithm is derived which selects and refines the basis vector set achieving a locally optimal model. The model expansion coefficients and bias are updated recursively for increase and decrease in the basis set and support vector set. The condition for a point to be classed as outside the current basis vector and selected as a new basis vector is derived and embedded in the recursive procedure. This guarantees the linear independence of the produced basis set. The proposed algorithm is tested and compared with an existing sparse primal SVM (SpSVM) and a standard SVM (LibSVM) on seven public benchmark classification problems. Our new algorithm is designed for use in the application area of human activity recognition using smart devices and embedded sensors where their sometimes limited memory and processing resources must be exploited to the full and the more robust and accurate the classification the more satisfied the user. Experimental results demonstrate the effectiveness and efficiency of the proposed algorithm. This work builds upon a previously published algorithm specifically created for activity recognition within mobile applications for the EU Haptimap project [1]. The algorithms detailed in this paper are more memory and resource efficient making them suitable for use with bigger data sets and more easily trained SVMs.

Event-driven implicit authentication for mobile access control

In order to protect user privacy on mobile devices, an event-driven implicit authentication scheme is proposed in this paper. Several methods of utilizing the scheme for recognizing legitimate user behavior are investigated. The investigated methods compute an aggregate score and a threshold in real-time to determine the trust level of the current user using real data derived from user interaction with the device. The proposed scheme is designed to: operate completely in the background, require minimal training period, enable high user recognition rate for implicit authentication, and prompt detection of abnormal activity that can be used to trigger explicitly authenticated access control. In this paper, we investigate threshold computation through standard deviation and EWMA (exponentially weighted moving average) based algorithms. The result of extensive experiments on user data collected over a period of several weeks from an Android phone indicates that our proposed approach is feasible and effective for lightweight real-time implicit authentication on mobile smartphones.