• Laplacian group sparse modeling of human actions

      Zhang, Xiangrong; Yang, Hao; Jiao, L.C.; Yang, Yang; Dong, Feng; Xidian University; University of Bedfordshire (Elsevier Ltd, 2014-02-20)
      Recently, many local-feature based methods have been proposed for feature learning to obtain a better high-level representation of human behavior. Most of the previous research ignores the structural information existing among local features in the same video sequences, while it is an important clue to distinguish ambiguous actions. To address this issue, we propose a Laplacian group sparse coding for human behavior representation. Unlike traditional methods such as sparse coding, our approach prefers to encode a group of relevant features simultaneously and meanwhile allow as less atoms as possible to participate in the approximation so that video-level sparsity is guaranteed. By incorporating Laplacian regularization the method is capable to ensure the similar approximation of closely related local features and the structural information is successfully preserved. Thus, a compact but discriminative human behavior representation is achieved. Besides, the objective of our model is solved with a closed-form solution, which reduces the computational cost significantly. Promising results on several popular benchmark datasets prove the efficiency and effectiveness of our approach. © 2014 Elsevier Ltd.
    • Learner experience in hybrid virtual worlds: interacting with pedagogical agents

      Christopoulos, Athanasios; Conrad, Marc; Shukla, Mitul; University of Bedfordshire (SciTePress, 2019-12-31)
      Studies related to the Virtual Learning approach are conducted almost exclusively in Distance Learning contexts and focus on the development of frameworks or taxonomies that classify the different ways of teaching and learning. Researchers may be dealing with the topic of interactivity but mainly focusing on the interactions that take place within the virtual world. However, in non-distance learning contexts, where students not only share the virtual but also the physical space, different types of interplay can be observed. In this paper, we classify these ‘hybrid’ interactions and further correlate them with the impact that the instructional design decisions have on motivation and engagement. In particular, a series of experiments were conducted in the context of different Hybrid Virtual Learning units, with Computer Science and Technology students participating in the study, whilst, the chosen instructional design approach included the employment of different Pedagogical Agents who aimed at increasing the incentives for interaction and therefore, engagement. The conclusions provide suggestions and guidelines to educators and instructional designers who wish to offer interactive and engaging learning activities to their students.
    • Learning computing heritage through gaming – whilst teaching digital development through history

      Wood, Jim; Liu, Haiming; Briggs, Thomas; University of Bedfordshire; Bletchley Park Trust Museum (British Computing Society, 2016-07-14)
      This paper analyses the potential of computer games and interactive projects within the learning programmes for cultural heritage institutions through our experiences working in partnership between higher education and a museum. Gamification is cited as a key disruptive technology for the business and enterprise community, and developments in games technology are also driving the expansion of digital media into all different screen spaces, and various platforms. Our research aims to take these as beneficial indicators for pedagogic development, using gaming to support knowledge transfer related to a museum setting, and using the museum as a key scenario for our students to support the practice of game development. Thus gamification is applied as both a topic and a methodology for educational purposes.
    • Learning polynomial neural networks of a near-optimal connectivity for detecting abnormal patterns in biometric data

      Nyah, Ndifreke; Jakaite, Livija; Schetinin, Vitaly; Sant, Paul; Aggoun, Amar; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2016-09-01)
      Existing Machine Learning (ML) approaches known from the literature require the user to set and experimentally adjust parameters of a decision model to achieve the best result. When artificial neural networks (ANNs) are employed, a typical problem is setting of a proper network structure and learning parameters that are required to minimise possible overfitting. We propose a new evolutionary strategy of learning an ANN structure of a near-optimal connectivity from the given data and show that such structures are less prone to overfitting. The resultant ANN consists of a reasonably small number of neurons that are concisely described by a set of short-term polynomial functions of variables that make a distinct contribution to the output. The proposed technique has been tested on the ML benchmarks and the results showed that the performance is comparable with that obtained by the conventional ML methods that require ad hoc tuning.
    • Letter to the editor: gratitude and good outcomes: rediscovering positivity and perspective in an uncertain time

      Minaev, Sergey; Schetinin, Vitaly; Kirgizov, Igor; Grigorova, Alina Nikolaevna; Akselrov, Michael; Gerasimenko, Igor (Springer, 2021-11-08)
    • Life style related risk association mining

      Effiok, Emmanuel; Liu, Enjie; Hitchcock, Jonathan James; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2019-04-25)
      IoT application in health care provides ways to monitor and collect health related biomarkers, in particular, life-style related data, by recording and analyzing long-Term data, to provide insight to patients' status. In order to make most use of this application, linking the collected patients' data with a disease predictive model will generate a personalized disease progression and predictions. It is also important to understand one's health risks in order to benefit from new research about specific diseases and plan for preventive monitoring. Risk factors for a disease are results of various medical researches. In this paper, we propose an approach for risk factor selection and mining.
    • Life-logging data aggregation solution for interdisciplinary healthcare research and collaboration

      Deng, Zhikun; Yang, Po; Zhao, Youbing; Zhao, Xia; Dong, Feng; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2015-12-28)
      The wide-spread use of wearable devices and mobile apps in the Internet of Things (IoT) environments makes effectively capture of life-logging personal health data come true. A long-term collection of these health data will benefit to interdisciplinary healthcare research and collaboration. But most wearable devices and mobile apps in the market focus on personal fitness plan and lack of compatibility and extensibility to each other. Existing IoT based platforms rarely achieve a successful heterogeneous life-logging data aggregation. Also, the demand on high security increases difficulties of designing reliable platform for integrating and managing multi-resource life-logging health data. This paper investigates the possibility of collecting and aggregating life-logging data with the use of wearable devices, mobile apps and social media. It compares existing personal health data collection solutions and identifies essential needs of designing a life-logging data aggregator in the IoT environments. An integrated data collection solution with high secure standard is proposed and deployed on a stateof-the-art interdisciplinary healthcare platform: MHA [15] by integrating five life-logging resources: Fitbit, Moves, Facbook, Twitter, etc. The preliminary experiment demonstrates that it successfully record, store and reuse the unified and structured personal health information in a long term, including activities, location, exercise, sleep, food, heat rate and mood.
    • Lifelogging data validation model for Internet of Things enabled healthcare system

      Yang, Po; Stankevicius, Dainius; Marozas, Vaidotas; Deng, Zhikun; Liu, Enjie; Lukoševicǐus, Arunas; Dong, Feng; Xu, Lida; Min, Geyong; Liverpool John Moores University; et al. (IEEE, 2016-07-19)
      Internet of Things (IoT) technology offers opportunities to monitor lifelogging data by a variety of assets, like wearable sensors, mobile apps, etc. But due to heterogeneity of connected devices and diverse human life patterns in an IoT environment, lifelogging personal data contains huge uncertainty and are hardly used for healthcare studies. Effective validation of lifelogging personal data for longitudinal health assessment is demanded. In this paper, lifelogging physical activity (LPA) is taken as a target to explore how to improve the validity of lifelogging data in an IoT enabled healthcare system. A rule-based adaptive LPA validation (LPAV) model, LPAV-IoT, is proposed for eliminating irregular uncertainties (IUs) and estimating data reliability in IoT healthcare environments. A methodology specifying four layers and three modules in LPAV-IoT is presented for analyzing key factors impacting validity of LPA. A series of validation rules are designed with uncertainty threshold parameters and reliability indicators and evaluated through experimental investigations. Following LPAV-IoT, a case study on a personalized healthcare platform myhealthavatar connecting three state-of-the-art wearable devices and mobile apps are carried out. The results reflect that the rules provided by LPAV-IoT enable efficiently filtering at least 75% of IU and adaptively indicating the reliability of LPA data on certain condition of IoT environments.
    • Lifestyle risk association aggregation

      Effiok, Emmanuel; Liu, Enjie; Hitchcock, Jonathan James; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2019-08-15)
      IoT application in health care provides ways to monitor and collect health related biomarkers, in particular, lifestyle related data, by recording and analyzing long-term data, to provide insight to patients' status. In order to make most use of this application, linking the collected patients' data with a disease predictive model will generate a personalized disease progression and predictions. Various risk factors have been researched extensively to find the effect on the disease. However, risk factors are fragmented all over medical literature, and often each publication reports on one or a few risk factors, a combination of several of those factors, often from different research. In this paper, we propose an approach to explore the combination of risk factors. The outcome will form a base for a complete risk prediction model that can be used for many health applications.
    • A linear logic approach to the composition of RESTful web services

      Zhao, Xia; Liu, Enjie; Yu, Hong Qing; Clapworthy, Gordon J.; University of Bedfordshire (Inderscience, 2015-10-09)
      RESTful web services, which are declarative, lightweight and easy to access, are already widely used for exposing services on the internet and have attracted increasing interest from industry. The rising number of services being implemented and made available on the web is creating a demand for modelling techniques that can abstract REST design from the implementation in order to better specify, analyse and implement large-scale RESTful web systems. It can also help by providing suitable RESTful web service composition methods which can reduce costs by efficiently re-using the large number of services that are already available and by exploiting existing services for complex business purposes. This paper introduces a formal model of RESTful web services in linear logic and proposes a formal method approach for RESTful web service composition based on planning using linear logic via theorem proving. This is a two-stage planning method that finds resources for the composition at both the abstract resource and the service operation levels. It greatly improves the searching efficiency and guarantees the correctness and completeness of the service composition process. The paper demonstrates a further validation of the planning method through its implementation in the interactive Coq logic proof assistant.
    • Linewidth study of pixelated aluminum nanowire gratings on polarization performance

      Yu, Miao; Song, Zhengxun; Dong, Litong; Li, Li; Cao, Liang; Li, Wenjun; Song, Yingying; Lei, Li; Wang, Zuobin; Changchun University of Science and Technology; et al. (Optical Society of America, 2020-02-01)
      Nowadays, nanowire gratings are widely used in various applications such as imaging sensors and high-resolution microscopes. Structure parameters are the main factors that affect the optical performance of the gratings. This work aims to present the influence of the linewidth of pixelated aluminum nanowire gratings with a fixed period on the transmittance and extinction ratio in the visible region. By controlling the exposure doses of electron beam lithography (EBL), different linewidths of pixelated aluminum nanowire gratings with a period of 170 nm were fabricated. The significant effects of linewidth difference on the polarization performance were verified by the simulations of finite-difference time-domain (FDTD) software. The simulations were divided into two parts: the discussion of the pure aluminum without considering oxidation and the discussion of the surface aluminum being oxidized into the aluminum oxide. An optical system was built to evaluate the performance of the fabricated structures. The results show that the trends of the measurement results are consistent with that of simulation. This work will give a guide to the fabrication and evaluation of the nanowire gratings.
    • A linked dataset of medical educational resources

      Dietze, Stefan; Taibi, Davide; Yu, Hong Qing; Dovrolis, Nikolas (British Educational Research Association, 2015-04-06)
      Reusable educational resources became increasingly important for enhancing learning and teaching experiences, particularly in the medical domain where resources are particularly expensive to produce. While interoperability across educational resources metadata repositories is yet limited to the heterogeneity of metadata standards and interface mechanisms with a lack of shared or aligned controlled vocabularies, Linked Data (LD) principles, based on W3C standards and supported through a wide range of tools, open up opportunities to alleviate such problems. We introduce the “mEducator Linked Educational Resources” dataset, which offers a range of open educational resources for the medical domain, exposed through LD principles. Data have been generated through a combination of manual curation and semi‐automated harvesting techniques, and state‐of‐the‐art enrichment and clustering techniques were deployed in order to classify and categorize data, toward improved reusability and access. Data are currently used by a range of educational applications and is accessible for third parties and developers, for instance through the LinkedUp Catalog and other registries, to facilitate further take‐up and applications.
    • Literature Explorer: effective retrieval of scientific documents through nonparametric thematic topic detection

      Wu, Shaopeng; Zhao, Youbing; Parvinzamir, Farzad; Ersotelos, Nikolaos; Wei, Hui; Dong, Feng; University of Bedfordshire; Queen's University Belfast (Springer Verlag, 2019-08-02)
      Scientific researchers are facing a rapidly growing volume of literatures nowadays. While these publications offer rich and valuable information, the scale of the datasets makes it difficult for the researchers to manage and search for desired information efficiently. Literature Explorer is a new interactive visual analytics suite that facilitates the access to desired scientific literatures through mining and interactive visualisation. We propose a novel topic mining method that is able to uncover “thematic topics” from a scientific corpus. These thematic topics have an explicit semantic association to the research themes that are commonly used by human researchers in scientific fields, and hence are human interpretable. They also contribute to effective document retrieval. The visual analytics suite consists of a set of visual components that are closely coupled with the underlying thematic topic detection to support interactive document retrieval. The visual components are adequately integrated under the design rationale and goals. Evaluation results are given in both objective measurements and subjective terms through expert assessments. Comparisons are also made against the outcomes from the traditional topic modelling methods.
    • Low latency parallel turbo decoding implementation for future terrestrial broadcasting systems

      Zhang, Xun; Luo, Hua; Zhang, Yue; Li, Wei; Huang, Li-Ke; Cosmas, John; Li, Dayou; Maple, Carsten; Institute Supérieur d’Electronique de Paris; University of Warwick; et al. (Institute of Electrical and Electronics Engineers Inc., 2017-06-21)
      As a class of high-performance forward error correction codes, turbo codes, which can approach the channel capacity, could become a candidate of the coding methods in future terrestrial broadcasting (TB) systems. Among all the demands of future TB system, high throughput and low latency are two basic requirements that need to be met. Parallel turbo decoding is a very effective method to reduce the latency and improve the throughput in the decoding stage. In this paper, a parallel turbo decoder is designed and implemented in field-programmable gate array (FPGA). A reverse address generator is proposed to reduce the complexity of interleaver and also the iteration time. A practical method of modulo operation is realized in FPGA which can save computing resources compared with using division operation. The latency of parallel turbo decoder after implementation can be as low as 23.2 us at a clock rate of 250 MHz and the throughput can reach up to 6.92 Gbps.
    • A low profile antenna for millimeter-wave body-centric applications

      Ur-Rehman, Masood; Malik, Nabeel A.; Yang, Xiaodong; Abbasi, Qammer Hussain; Zhang, Zhiya; Zhao, Nan; University of Bedfordshire; Xidian University; University of Glasgow (Institute of Electrical and Electronics Engineers Inc., 2017-05-03)
      Millimeter-Wave (mm-Wave) frequencies are a front runner contender for the next generation body-centric wireless communications. In this paper, the design of a very low-profile antenna is presented for body-centric applications operating in the mm-Wave frequency band centered at 60 GHz. The antenna has an overall size of 14 × 10.5 × 1.15 mm3 and is printed on a flexible printed circuit board. The performance of the antenna is evaluated in off-body, on-body, and body-to-body communication scenarios using a realistic numerical phantom and verified through measurements. The antenna has a bandwidth of 9.8 GHz and offers a gain of 10.6 dBi in off-body (free space) configuration, while 12.1 dBi in on-body configuration. It also achieves an efficiency of 74% in off-body and 63% in on-body scenario. The small and flexible structure of the antenna along with excellent impedance matching, broad bandwidth, high gain, and good efficiency makes it a suitable candidate to attain simultaneous data transmission/reception at mm-Wave frequencies for the 5G body-centric applications.
    • A low profile penta-band antenna for portable devices

      Shameem, Usama; Ur-Rehman, Masood; Qaraqe, Khalid; Abbasi, Qammer Hussain; University of Bedfordshire; Texas A & M University, Qatar (Institute of Electrical and Electronics Engineers Inc., 2016-03-17)
      Recent years have seen a rapid growth of portable wireless communication systems. Limited form factor and operation at multiple frequencies of these devices require novel solutions of efficient embedded antennas. It has increased the demand of microstrip patch antennas due to their inherent properties of being low profile, simple design, small size and ease of fabrication and integration. Miniaturisation requirements have seen rise of multiband patch antennas. This paper presents the design and analysis of a novel multiband microstrip patch antenna. The antenna consists of a rectangular slot with two E-shaped stubs on both of its sides. An inverted T-shaped stub is present on the upper side of the slot while an I-shaped stub is there on the bottom side. A T-shaped feeding line feeds the antenna. The slot, stubs and feed collectively produce five frequency bands centred at 1.5 GHz, 2.2 GHz, 3.1 GHz, 4.2 GHz and 5.3 GHz for LTE/4G/5G, WiBro/WiMax, Satcomm and WLAN applications. The antenna offers small size, good impedance bandwidth and high gain at all operating frequencies.
    • Low-cost and data anonymised city traffic flow data collection to support intelligent traffic system

      Handscombe, Jonathon; Yu, Hong Qing; University of Bedfordshire (MDPI, 2019-01-16)
      There are many methods of collecting traffic flow data, especially using smart phone apps. However, few current solutions balance the need for collecting full route data whilst respecting privacy and remaining low-cost. This project looks into the creation of a wireless sensor network (WSN) that can balance these requirements in an attempt to negate some of the concerns that come with this type of technology. Our proposed system only collects location data within a defined city area. This data is collected with a randomized identifier, which limits repeated identification of the source vehicle and its occupants. Data collected is shared between vehicle and roadside base stations when the two are in range. To deal with the fluid nature of this scenario, a purposely designed Media Access Control (MAC) protocol was designed and implemented using the beacon-slotted ALOHA (Advocates of Linux Open-source Hawaii Association) mechanism.
    • A machine learning framework to detect and document text-based cyberstalking

      Ghasem, Zinnar; Frommholz, Ingo; Maple, Carsten; University of Bedfordshire; University of Warwick (CEUR-WS, 2015-12-31)
      Cyberstalking is becoming a social and international problem, where cyberstalkers utilise the Internet to target individuals and disguise themselves without fear of any consequences. Several technologies, methods, and techniques are used by perpetrators to terrorise victims. While spam email filtering systems have been effective by applying various statistical and machine learning algorithms, utilising text categorization and filtering to detect text- and email-based cyberstalking is an interesting new application. There is also the need to gather evidence by the victim. To this end we discuss a framework to detect cyberstalking in messages; short message service, multimedia messaging service, chat, instance messaging and emails, and as well as to support documenting evidence. Our framework consists of five main modules: a detection module which detects cyberstalking using message categorisation; an attacker identification module based on cyberstalkers' previous messages history, personalisation module, aggregator module and messages and evidence collection module. We discuss our ongoing work and how different text categorization and machine learning approaches can be applied to identify cyberstalkers.
    • Management of scientific documents and visualization of citation relationships using weighted key scientific terms

      Wei, Hui; Zhao, Youbing; Liu, Enjie; Wu, Shaopeng; Deng, Zhikun; Parvinzamir, Farzad; Dong, Feng; Clapworthy, Gordon J. (SciTePress, 2016-12-31)
      Effective management and visualization of scientific and research documents can greatly assist researchers by improving understanding of relationships (e.g. citations) between the documents. This paper presents work on the management and visualization of large corpuses of scientific papers in order to help researchers explore their citation relationships. Term selection and weighting are used for mining citation relationships by identifying the most relevant. To this end, we present a variation of the TF-IDF scheme, which uses external domain resources as references to calculate the term weighting in a particular domain; document weighting is taken into account in the calculation of term weighting from a group of citations. A simple hierarchical word weighting method is also presented. The work is supported by an underlying architecture for document management using NoSQL databases and employs a simple visualization interface.
    • Measuring student acceptance of game based learning for game and technology education curriculum development

      Saleh, Nada; Prakash, Edmond C.; Manton, Rob; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2015-01-12)
      Technological education is the modernized practice of learning through the use of technologies. Edutainment is a kind of education which integrates entertainment for educational purposes and uses video games for education. It is a hybrid learning system that depends basically on narrative, visual materials or game-like formats, with less didactic address styles and on a more informal way. Game based learning or edutainment, just like other technology-based education methods, is being used in western or developed countries. Saudi Arabia is considered a developing country just like other Arab countries; hence, computer education has recently appeared in Saudi Arabian education. Therefore, studying this new development in the Saudi educational systems will effect significantly on the speed of developing the educational systems in Saudi Arabia. However, no edutainment games have been designed for this new curriculum. Therefore this research ultimately aims to design a new edutainment game to be used for the computer technology curriculum. To design an efficient edutainment game system, edutainment game effectiveness and the attitudes of students will be measured to know their technology acceptance level for the new edutainment tool and curriculum. The study is carried out using Technology Acceptance Model (TAM), based on four factors; usability, usefulness, ease of use and effectiveness.