• Identifying Mubasher software products through sentiment analysis of Arabic tweets

      AL-Rubaiee, Hamed Saad; Qiu, Renxi; Li, Dayou; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2016-05-02)
      Social media has recently become a rich resource in mining user sentiments. In this paper, Twitter has been chosen as a platform for opinion mining in trading strategy with Mubasher products, which is a leading stock analysis software provider in the Gulf region. This experiment proposes a model for sentiment analysis of Saudi Arabic (standard and Arabian Gulf dialect) tweets to extract feedback from Mubasher products. A hybrid of natural language processing and machine learning approaches on building models are used to classify tweets according to their sentiment polarity into one of the classes positive, negative and neutral. Firstly, document's Pre-processing are explored on the dataset. Secondly, Naive Bayes and Support Vector Machines (SVMs) are applied with different feature selection schemes like TF-IDF (Term Frequency-Inverse Document Frequency) and BTO (Binary-Term Occurrence). Thirdly, the proposed model for sentiment analysis is expanded to obtain the results for N-Grams term of tokens. Finally, human has labelled the data and this may involve some mistakes in the labelling process. At this moment, neutral class with generalisation of our classification will take results to different classification accuracy.
    • Identifying pneumonia in chest X-rays: a deep learning approach

      Jaiswal, Amit Kumar; Tiwari, Prayag; Kumar, Sachin; Gupta, Deepak; Khanna, Ashish; Rodrigues, Joel J.P.C.; University of Bedfordshire; University of Padova; South Ural State University; Maharaja Agrasen Institute of Technology; et al. (Elsevier, 2019-06-04)
      The rich collection of annotated datasets piloted the robustness of deep learning techniques to effectuate the implementation of diverse medical imaging tasks. Over 15% of deaths include children under age five are caused by pneumonia globally. In this study, we describe our deep learning based approach for the identification and localization of pneumonia in Chest X-rays (CXRs) images. Researchers usually employ CXRs for the diagnostic imaging study. Several factors such as positioning of the patient and depth of inspiration can change the appearance of the chest X-ray, complicating interpretation further. Our identification model (https://github.com/amitkumarj441/identify_pneumonia) is based on Mask-RCNN, a deep neural network which incorporates global and local features for pixel-wise segmentation. Our approach achieves robustness through critical modifications of the training process and a novel post-processing step which merges bounding boxes from multiple models. The proposed identification model achieves better performances evaluated on chest radiograph dataset which depict potential pneumonia causes.
    • IEEE Access special section: advances in interference mitigation techniques for device-to-device communications

      Ur-Rehman, Masood; Gao, Yue; Chaudhry, Mohammad Asad Rehman; Safdar, Ghazanfar Ali; Xu, Yanli; University of Essex; Queen Mary University of London; University of Toronto; University of Bedfordshire; Shanghai Maritime University (IEEE, 2019-12-17)
      Editorial
    • Imaging quality assessment of different AFM working modes on living cancer cells

      Wang, Guoliang; Sun, Baishun; Wu, Xiaomin; Zhang, Wenxiao; Qu, Yingmin; Song, Zhengxun; Wang, Zuobin; Li, Dayou; Changchun University of Science and Technology; University of Bedfordshire (IEEE, 2020-02-02)
      Since the invention of atomic force microscope (AFM) in 1986, its capabilities in biophysical research, such as living cell imaging, molecule imaging and recognition and drug treatment analysis, have been deeply investigated. Various types of working modes of atomic force microscopy have been employed for imaging and analyzing living cells. The physical properties of living cells can be directly illustrated by its good resolution images. In this paper, the applications of three AFM working modes including contact, tapping and quantitative imaging (QI) modes for the investigation of living lung cancer cells (A549) are presented. Meanwhile, the quality of images of the cells obtained by different working modes is compared through the image quality assessment (IQA) methods.
    • Imaging the substructures of individual IgE antibodies with atomic force microscopy

      Hu, Jing; Gao, Mingyan; Wang, Ying; Liu, Mengnan; Wang, Jianfei; Li, Jiani; Song, Zhengxun; Chen, Yujuan; Wang, Zuobin (American Chemical Society, 2019-10-29)
      The interaction between antibodies and substrates directly affects its conformation and thus its immune function. Therefore, it is desirable to study the structure of antibodies at the single molecule level. Herein, the substructures of Immunoglobulin E (IgE) on solid surfaces were investigated. For this purpose, the tapping-mode atomic force microscopy (AFM) was applied to observe the individual IgE substructures adsorbed onto Mg2+ and Na+ modified mica substrates in air. As expected, the AFM images revealed that the IgE antibodies exhibited different conformations on the surface of mica substrate, consisting of the four basic orientations: three domain, two equivalent domain, two unequal domain and single domain morphologies. Moreover, the differences of the different orientations in single IgE antibodies were also identified clearly.
    • IManageCancer: developing a platform for empowering patients and strengthening self-management in cancer diseases

      Graf, Norbert; Hoffman, Stefan; Koumakis, Lefteris; Pravettoni, Gabrielli; Marias, Kostas; Tsiknakis, Manolis; Kiefer, Stefan; Kondylakis, Haridimos; Bucur, Anca; Dong, Feng; et al. (Institute of Electrical and Electronics Engineers Inc., 2017-11-13)
      Cancer research has led to more cancer patients being cured, and many more enabled to live with their cancer. As such, some cancers are now considered a chronic disease, where patients and their families face the challenge to take an active role in their own care and in some cases in their treatment. To this direction the iManageCancer project aims to provide a cancer specific self-management platform designed according to the needs of patient groups while focusing, in parallel, on the wellbeing of the cancer patient. In this paper, we present the use-case requirements collected using a survey, a workshop and the analysis of three white papers and then we explain the corresponding system architecture. We describe in detail the main technological components of the designed platform, show the current status of development and we discuss further directions of research.
    • Impingement behaviour of single ethanol droplet on a liquid film of glycerol solution

      Lu, Lili; Pei, Yiqiang; Qin, Jing; Peng, Zhijun; Wang, Yuqian; Zhu, Qingyang; Tianjin University; University of Bedfordshire (Elsevier Ltd, 2020-05-16)
      Research on single drop impact, especially in the past two decades, has been motivated by a need for better predictive capability in many industries. However, there are few reports in the literature describing the case of single droplet impinging on liquid films with different physicochemical properties. In this study, laser-induced fluorescence (LIF) methods were used to clarify the impingement behaviour of millimetre-sized single ethanol droplets onto films of different concentrations of glycerol solution. The impingement behaviour is found to differ depending on the Weber number of the incident droplet and the viscosity and the thickness of the liquid film. New results on coalescence/splash thresholds criteria are obtained taking into account the incident droplet Weber number and liquid film characteristics. In addition, the formation mechanism and composition of secondary droplets and crown structures after collision are analysed. For the crown structure parameters, we found that the evolution of the crown height over time is affected by the combination of droplet and liquid film characteristics. The maximum height and diameter of the crown are proportional to the Weber number of the incident droplet, and these parameters can be predicted by the combination of the incident droplet Weber number and the liquid film Ohnesorge number.
    • An implementation of SLAM using ROS and Arduino

      Ibáñez, Adrián Lendínez; Qiu, Renxi; Li, Dayou; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2018-02-08)
      This paper aims to explore the Simultaneous Localization and Mapping (SLAM) problem in the context of implementation using the Robot Operating System (ROS) framework and the Arduino technology. The implementation of an inexpensive differential drive robot for SLAM is detailed and verified by mapping experiments conducted within domestic environments. Furthermore, a modest, yet convenient, theoretical explanation of the algorithm (Rao-Blackwellization particle filter) behind the platform is also presented. Overall, this report leads to a simple and cost effective way - including a code base and guidelines - to create robots for 2D mapping using modern technologies such as ROS.
    • Implementing learning models in virtual worlds - from theory to (virtual) reality

      Christopoulos, Athanasios; Conrad, Marc; Shukla, Mitul; University of Bedfordshire (Scitepress, 2018-01-01)
      The main advantage of Desktop Virtual Reality is that it enables learners to interact with each other both in the physical classroom and in a 3D environment. Even though, no explicit theories or models have been developed to contextualise Virtual Learning, instructional designers have successfully employed the traditional approaches with positive results on learners’ motivation and engagement. However, there is very little we know when the question comes to the importance of examining and taxonomising the impact of interactions on motivation and engagement as a synergy of learners’ concurrent presence. To evaluate the potential of interactions holistically and not just unilaterally, a series of experiments were conducted in the context of our Hybrid Virtual Learning classes underpinned from the instructional designer’s decisions to increase the incentives for interactions. Learners’ thoughts and preconceptions about the use of virtual worlds as an educational tool were surveyed, whils t, their actions and interactions (in both environments) were observed during their practical sessions. The take away is that the higher the levels of interactivity are, the higher the chances to attract students’ attention and engagement with the process will be.
    • The importance of controlling your online presence - understanding and pre-empting attacks that use your public information

      Gibson, Marcia; Brown, Antony; Short, Emma; Barnes, Jim; University of Bedfordshire (Andrews UK, 2015-04-19)
    • Improved DNA straightening and attachment via optimal Mg2+ ionic bonding under electric field for AFM imaging in liquid phase

      Liu, Ziya; Xu, Hongmei; Wang, Ying; Yang, Fan; Yin, Yaoting; Zhang, Sheng; Weng, Zhankun; Song, Zhengxun; Wang, Zuobin; Changchun University of Science and Technology; et al. (Elsevier Ltd, 2019-05-25)
      In this research, a novel method is proposed to improve DNA straightening under an applied electric field to facilitate imaging in a liquid phase by modifying the substrate with varying Mg2+ ion concentrations. A two-dimensional network of DNA structures was successfully stretched on Mg2+-modified mica substrates under a DC electric field (1 V, 1 A) and imaged in gaseous and aqueous phases by atomic force microscopy. The results revealed that an optimum concentration of Mg2+ ion (4.17 μmol/ml) allowed DNA straightening under an electric field, thus facilitating its imaging in the liquid phase. Furthermore, DNA adhesion under different concentrations of Mg2+ was measured and a maximum adhesion force of 76.19 pN was achieved. This vital work has great potential in gene knockout and targeted gene editing.
    • Improving adhesion between nanoparticles and surface of mica substrate by aminosilane modification

      Yin, Yaoting; Xu, Hongmei; Wang, Ying; Liu, Ziyu; Zhang, Sheng; Weng, Zhankun; Song, Zhengxun; Wang, Zuobin (Springer, 2019-11-09)
      In the manipulation of nanoparticles for precise placement, the relatively low adhesion of the nanoparticles to the substrate surface has emerged as a problem. Owing to the fact that nanoparticles manipulated using atomic force microscopy (AFM) often cannot be accurately placed at their predetermined destinations or may even go astray, becoming “lost,” the success rate of manipulation attempts is low. We investigated the possibility of enhancing the adhesion between magnetic nanoparticles and a substrate surface by modifying a mica substrate with a solution of 3-aminopropyltriethoxysilane (APTES). The morphology of the mica surface before and after modification was analyzed, and the adhesive force was calculated by using AFM in contact mode. The effect of different APTES-solution concentrations on the adhesive force was analyzed as well. The results demonstrate that the adhesion of the nanoparticles to the modified substrate was substantially stronger than their adhesion to an unmodified surface, a finding that can be used to improve the success rate of nanoparticle manipulation.
    • Improving malware detection time by using RLE and N-gram

      Mira, Fahad; Huang, Wei; Brown, Antony; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2017-10-26)
      Malware is a widespread problem and despite the common use of anti-virus software, the diversity of malware is still increasing. A major challenge facing the anti-virus industry is how to effectively detect thousands of malware samples that are received every day. In this paper, a novel approach based Run Length Encoding (RLE) algorithm and n-gram are proposed to improve malware detect on dynamic analysis of based on API sequences.
    • Improving reliability of message broadcast over internet of vehicles (IoVs)

      Eze, Elias Chinedum; Zhang, Sijing; Liu, Enjie; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2015-12-28)
      With the envisioned era of Internet of Things (IoTs), all aspects of Intelligent Transportation Systems (ITS) will be connected to improve transport safety, relieve traffic congestion, reduce air pollution, enhance the comfort of transportation and significantly reduce road accidents. In IoVs, regular exchange of current position, direction, velocity, etc., enables mobile vehicles to predict an upcoming accident and alert the human drivers in time or proactively take precautionary actions to avoid the accident. The actualization of this concept requires the use of channel access protocols that can guarantee reliable and timely broadcast of safety messages. This paper investigates the application of network coding concept to increase content of every transmission and achieve improved broadcast reliability with less number of retransmission. In particular, we proposed Code Aided Retransmission-based Error Recovery (CARER) scheme, introduced an RTB/CTB handshake to overcome hidden node problem and reduce packets collision rate. The performance of CARER is clearly shown with detailed theoretical analysis and further validated with simulation experiments.
    • Improving the efficiency of robot task planning by automatically integrating its planner and common-sense knowledge base

      Al-Moadhen, Ahmed; Packianather, Michael; Qiu, Renxi; Setchi, Rossi; Ji, Ze; Cardiff School of Engineering (Springer Science and Business Media Deutschland GmbH, 2015-12-31)
      This chapter presents a newly developed approach for intelligently generating symbolic plans for mobile robots acting in domestic environments, such as offices and houses. The significance of this approach lies in its novel framework which consists of new modelling of high-level robot actions and their integration with common-sense knowledge in order to support robotic task planner. This framework will enable direct interactions between the task planner and the semantic knowledge base. By using common-sense domain knowledge, the task planner will take into consideration the properties and relations of objects and places in its environment, before creating semantically related actions that will represent a plan. A new module has been appended to the framework which is called Semantic Realization and Refreshment Module (SRRM). This module has the ability to discover and select entities in the robot’s world (entities related to robot plan) which are semantically equivalent or have a degree of similarity (where they don’t exceed a predefined threshold) by using techniques and standards (metrics) for similarities. SRRM supports robotic task planning to generate approximate plans to solve its tasks when there is no exact plan can be generated according to initial and goal state by extending initial state and action details with similar or equivalent objects. The extended framework enables direct interactions between task planner, Semantic Action Models (SAMs) and knowledge-base through creating planning domain (or extended planning domain) with predicates (or semantically equivalent or similar predicates) which specify domain features. The proposed framework and approach are tested on some scenarios that cover most aspects of robot planning system.
    • Improving the immersion in virtual reality with real-time avatar and haptic feedback in a cricket simulation

      Jayaraj, Lionel; Wood, Jim; Gibson, Marcia; University of Bedfordshire (IEEE, 2017-10-30)
      The basis of this research is concerned with designing and implementing a system that allows a player to engage in a virtual reality (VR) game with better immersion. The research was based on the idea that an avatar generated using real-time motion capture would improve the player's immersion by increasing the perception of presence. When playing the VR games a common problem was observed. The user's avatar (Virtual agent) was not improved as most of the games were played using limited controllers. The inputs from these controllers were noted as insufficient to generate the entire body's animation. This research attempts to solve this problem by proposing/implementing full body motion capture and the establishment of the self-avatar in real time in a VR game. This involved designing a system that utilizes the effective technologies for 3D imaging, transmission and haptic feedback. The research attempts to measure the immersion by enhancing measuring instruments (Norman, 2010). It is complimented by a user-based study that involves/involved collecting both qualitative and quantitative data through questionnaire and observation.
    • Improving the validity of lifelogging physical activity measures in an internet of things environment

      Yang, Po; Hanneghan, Martin; Qi, Jun; Deng, Zhikun; Dong, Feng; Fan, Dina (Institute of Electrical and Electronics Engineers Inc., 2015-12-28)
      Recently, the popular use of wearable devices and mobile apps makes the effectively capture of lifelogging physical activity data in an Internet of Things (IoT) environment possible. The effective collection of measures of physical activity in the long term is beneficial to interdisciplinary healthcare research and collaboration from clinicians, researchers to patients. However, due to heterogeneity of connected devices and rapid change of diverse life patterns in an IoT environment, lifelogging physical activity information captured by mobile devices usually contains much uncertainty. In this paper, we provide a comprehensive review of existing life-logging physical activity measurement devices, and identify regular and irregular uncertainties of these activity measures in an IoT environment. We then project the distribution of irregular uncertainty by defining a walking speed related score named as Daily Activity in Physical Space (DAPS). Finally, we present an ellipse fitting model based validity improvement method for reducing uncertainties of life-logging physical activity measures in an IoT environment. The experimental results reflect that the proposed method effectively improves the validity of physical activity measures in a healthcare platform.
    • Improving utility of GPU in accelerating industrial applications with user-centered automatic code translation

      Yang, Po; Dong, Feng; Codreanu, Valeriu; Williams, David; Roerdink, Jos B.T.M.; Liu, Baoquan; Anvari-Moghaddam, Amjad; Min, Geyong; University of Bedfordshire; SURFsara; et al. (IEEE Computer Society, 2017-07-24)
      Small to medium enterprises (SMEs), particularly those whose business is focused on developing innovative produces, are limited by a major bottleneck in the speed of computation in many applications. The recent developments in GPUs have been the marked increase in their versatility in many computational areas. But due to the lack of specialist GPUprogramming skills, the explosion of GPU power has not been fully utilized in general SME applications by inexperienced users. Also, the existing automatic CPU-to-GPU code translators are mainly designed for research purposes with poor user interface design and are hard to use. Little attentions have been paid to the applicability, usability, and learnability of these tools for normal users. In this paper, we present an online automated CPU-to-GPU source translation system (GPSME) for inexperienced users to utilize the GPU capability in accelerating general SME applications. This system designs and implements a directive programming model with a new kernel generation scheme and memory management hierarchy to optimize its performance. A web service interface is designed for inexperienced users to easily and flexibly invoke the automatic resource translator. Our experiments with nonexpert GPU users in four SMEs reflect that a GPSME system can efficiently accelerate real-world applications with at least 4× and have a better applicability, usability, and learnability than the existing automatic CPU-to-GPU source translators.
    • Improving utility of GPU in accelerating industrial applications with user-centred automatic code translation

      Yang, Po; Dong, Feng; Codreanu, Valeriu; Williams, David; Roerdink, Jos B.T.M.; Anvari-Moghaddam, Amjad; Min, Geyong; University of Bedfordshire; Liverpool John Moores University; SURFsara; et al. (IEEE, 2017-07-24)
      SMEs, particularly those whose business is focused on developing innovative produces, are limited by a major bottleneck on the speed of computation in many applications. The recent developments in GPUs have been the marked increase in their versatility in many computational areas. But due to the lack of specialist GPU (Graphics processing units) programming skills, the explosion of GPU power has not been fully utilized in general SME applications by inexperienced users. Also, existing automatic CPU-to-GPU code translators are mainly designed for research purposes with poor user interface design and hard-to-use. Little attentions have been paid to the applicability, usability and learnability of these tools for normal users. In this paper, we present an online automated CPU-to-GPU source translation system, (GPSME) for inexperienced users to utilize GPU capability in accelerating general SME applications. This system designs and implements a directive programming model with new kernel generation scheme and memory management hierarchy to optimize its performance. A web service based interface is designed for inexperienced users to easily and flexibly invoke the automatic resource translator. Our experiments with non-expert GPU users in 4 SMEs reflect that GPSME system can efficiently accelerate real-world applications with at least 4x and have a better applicability, usability and learnability than existing automatic CPU-to-GPU source translators