• Sit-to-stand intention recognition

      Wang, Zuobin; Li, Dayou; Lu, Hang; Qiu, Renxi; Maple, Carsten; University of Bedfordshire; Changchun University of Science and Technology; Warwick University (Springer Science and Business Media Deutschland GmbH, 2021-01-23)
      Sit-to-stand (STS) difficulties are common among elderly because of the decline of their cognitive capabilities and motor functions. The way to help is to encourage them to practice their own functions and to assist only at the point where they need during STS processes. The provision of such support requires the elderly’s intention of standing up to be recognised and the amount of support as well as the moment when the support would be needed to be predicted. The research presented in this paper focuses on intention recognition as it is difficult due to uncertainties existing in STS processes and differences in individual’s biomechanical features. This paper presents fuzzy logic based self-adaptive approach to the recognition of standing up intention from sensor signals that contain the uncertainties.
    • Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis

      Jakaite, Livija; Schetinin, Vitaly; Hladůvka, Jiří; Minaev, Sergey; Ambia, Aziz; Krzanowski, Wojtek; ; University of Bedfordshire; TU Wien; Stavropol State Medical University; et al. (Nature, 2021-01-27)
      Texture features are designed to quantitatively evaluate patterns of spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper we explore the ability of machine learning (ML) methods to design a radiology test of Osteoarthritis (OA) at early stage when the number of patients’ cases is small. In our experiments we use high-resolution X-ray images of knees in patients which were identified with Kellgren–Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although new study is required when a large number of patients’ cases will be available.
    • Design optimization of resource allocation in OFDMA-based cognitive radio-enabled Internet of Vehicles (IoVs)

      Eze, Joy C.; Zhang, Sijing; Liu, Enjie; Eze, Elias Chinedum; ; University of Bedfordshire (MDPI, 2020-11-09)
      Joint optimal subcarrier and transmit power allocation with QoS guarantee for enhanced packet transmission over Cognitive Radio (CR)-Internet of Vehicles (IoVs) is a challenge. This open issue is considered in this paper. A novel SNBS-based wireless radio resource scheduling scheme in OFDMA CR-IoV network systems is proposed. This novel scheduler is termed the SNBS OFDMA-based overlay CR-Assisted Vehicular NETwork (SNO-CRAVNET) scheduling scheme. It is proposed for efficient joint transmit power and subcarrier allocation for dynamic spectral resource access in cellular OFDMA-based overlay CRAVNs in clusters. The objectives of the optimization model applied in this study include (1) maximization of the overall system throughput of the CR-IoV system, (2) avoiding harmful interference of transmissions of the shared channels’ licensed owners (or primary users (PUs)), (3) guaranteeing the proportional fairness and minimum data-rate requirement of each CR vehicular secondary user (CRV-SU), and (4) ensuring efficient transmit power allocation amongst CRV-SUs. Furthermore, a novel approach which uses Lambert-W function characteristics is introduced. Closed-form analytical solutions were obtained by applying time-sharing variable transformation. Finally, a low-complexity algorithm was developed. This algorithm overcame the iterative processes associated with searching for the optimal solution numerically through iterative programming methods. Theoretical analysis and simulation results demonstrated that, under similar conditions, the proposed solutions outperformed the reference scheduler schemes. In comparison to other scheduling schemes that are fairness-considerate, the SNO-CRAVNET scheme achieved a significantly higher overall average throughput gain. Similarly, the proposed time-sharing SNO-CRAVNET allocation based on the reformulated convex optimization problem is shown to be capable of achieving up to 99.987% for the average of the total theoretical capacity.
    • AFM-based study of fullerenol (C60(OH)24)-induced changes of elasticity in living SMCC-7721 cells

      Liu, Yang; Wang, Zuobin; Wang, Xinyue; ; Changchun University of Science and Technology (Elsevier, 2014-12-18)
      In this study, the alterations of the morphology and biomechanical properties of living SMCC-7721 cancer cells treated with fullerenol (C60(OH)24) for 24, 48, and 72h were investigated using an atomic force microscope (AFM). Comparative analyses show that the elastic moduli of the SMCC-7721 cells exposed to fullerenol decrease significantly with the increase of the treatment periods. Furthermore, in different phases of the treatment, a global decrease in elasticity is accompanied by cellular morphological changes, and the time-dependent effect of the fullerenol can be observed using AFM and optical microscope. In addition, as the treatment duration increases, the indentation force and depth penetrated into the cell membrane by the AFM tip are in a declining trend. The reduction in the stiffness of the cells exposed to fullerenol could be associated with the disruption of the cellular cytoskeleton network. The investigation indicates that the elastic modulus of single living cells can be a useful biomarker to evaluate the effects of fullerenol or other anticancer agents on the cells and reveal instructive information for cellular dynamic behaviors.
    • Fabrication of hematite (α-Fe2O3) nanoparticles using electrochemical deposition

      Meng, Qing-Ling; Wang, Zuobin; Chai, Xiangyu; Weng, Zhankun; Ding, Ran; Dong, Litong; Changchun University of Science and Technology (Elsevier, 2016-02-04)
      In this work, cathodic electrochemical deposition was proposed to fabricate reproducible and homogeneous hematite (α-Fe 2 O 3 ) nanoparticles on indium-tin-oxide (ITO) films. The α-Fe 2 O 3 nanoparticles, which were quasi-hexagonally shaped, were deposited in an aqueous mixture of FeCl 2 and FeCl 3 at the temperatures 16.5 °C, 40 °C and 60 °C. The electrochemically deposited α-Fe 2 O 3 nanoparticles showed excellent stability and good crystallinity. The α-Fe 2 O 3 nanoparticles were characterized by Raman spectroscope and X-ray diffractometer (XRD). A scanning electron microscope (SEM) was used to measure the size and shape of the nanoparticles. The experiment results have shown that the size and shape of nanoparticles were determined by electrochemical deposition conditions including the deposition time, current density, reaction temperature and solution concentration. The proposed electrochemical deposition method has been proven to be a cost-effective, environment friendly and highly efficient approach in fabricating well decentralized α-Fe 2 O 3 nanoparticles for different potential applications.
    • Selective anticancer effect of Phellinus linteus on epidermoid cell lines studied by atomic force microscopy: anticancer activity on A431 cancer cells and low toxicity on HaCat normal cells

      Gao, Mingyan; Huang, Yuxi; Hu, Cuihua; Hu, Jing; Wang, Ying; Chen, Yujuan; Song, Guicai; Song, Zhengxun; Wang, Zuobin; Ministry of Education Key Laboratory for Cross-Scale Micro and Nano Manufacturing; et al. (Institute of Electrical and Electronics Engineers Inc., 2020-12-02)
      The research on the morphological and mechanical properties of single cells has provided a crucial way of understanding the cellular physiology and metabolism. In this study, the selective anticancer effects of Phellinus linteus on A431 and HaCat cells and their morphological and mechanical properties were systematically investigated by atomic force microscopy (AFM). Notably, the cell morphology on the micronano scale was observed under both the physiological environment and immobilization conditions. The significant morphological changes of A431 cells from the flat to spherical shape, the increase of cell height, and the decrease of the particles on the cell membrane were confirmed to be related to the cell apoptosis under the treatment of the Phellinus linteus water extract (PLWE). Moreover, the small morphology variations of HaCat cells showed that the PLWE presented a high anticancer effect on A431 cells but low toxicity on HaCat cells, which indicated a potential cell selectivity between cancer and normal cells. This work proved that Phellinus linteus could be used as a potential candidate for selective anticancer treatments.
    • Durotaxis behavior of bEnd.3 cells on soft substrate with patterned platinum nanoparticle array

      Wu, Xiaomin; Li, Li; Lei, Zecheng; Yang, Fan; Liu, Ri; Wang, Lu; Zhu, Xinyao; Wang, Zuobin; Changchun University of Science and Technology; University of Bedfordshire; et al. (Springer Science and Business Media, 2020-11-17)
      The directional arrangement of cells has crucial effect in tissue engineering fields such as wound healing and scar repair. Studies have shown that continuous nanostructures have directional regulatory effect on cells, but whether discontinuous nanostructures have the same regulatory effect on cells is also worthy of further study. Here, a series of discontinuous platinum nanoparticles (PtNPs) patterned on the surface of PDMS (PtNPs-PDMS&Glass) and glass (PtNPs-Glass) substrates were developed to investigate the effect on bEnd.3 cell durotaxis. The laser interference lithography and nanotransfer printing method were employed to fabricate the substrates. It was found that about 80% cells orderly arranged on the PtNPs-PDMS&Glass substrate, but only 20% cells orderly arrangement on the PtNPs-Glass substrate, and the number of cells on the PtNPs-PDMS&Glass substrate was five times more than that on the PDMS coated glass substrate (PDMS&Glass). The results suggested that patterning PtNPs on the PDMS substrate not only provided the topographical guidance for cells just like continuous nanostructures, but also promoted cell adhesion and growth. In addition, an improved whole cell coupling model was used to investigate and explain the cell durotaxis from the perspective of mechanism. These findings show the possibility of discontinuous nanostructures in regulating cell arrangement, and offer a useful method for the design of biological functional substrate, as well as help to understand the mechanism of cell durotaxis.
    • Atomic force microscopy imaging of the G-banding process of chromosomes

      Wang, Bowei; Li, Jiani; Dong, Jianjun; Yang, Fan; Qu, Kaige; Wang, Ying; Zhang, Jingran; Song, Zhengxun; Hu, Hongmei; Wang, Zuobin; et al. (Springer Science and Business Media, 2020-10-24)
      The chromosome is an important genetic material carrier in living individuals and the spatial conformation (mainly referring to the chromosomal structure, quantity, centromere position and other morphological information) may be abnormal or mutated. Thus, it may generate a high possibility to cause diseases. Generally, the karyotype of chromosome G-bands is detected and analyzed using an optical microscope. However, it is difficult to detect the G-band structures for traditional optical microscopes on the nanometer scale. Herein, we have studied the detection method of chromosome G-band samples by atomic force microscopy (AFM) imaging. The structures of chromosome G-banding are studied with different trypsin treatment durations. The experiment result shows that the treatment duration of 20 s is the best time to form G-band structures. The AFM images show the structures of chromosome G-bands which cannot be observed under an optical microscope. This work provides a new way for the detection and diagnosis of chromosome diseases on the nanometer scale.
    • Content-based image search system design for capturing user preferences during query formulation

      Artemi, Mahmoud; Liu, Haiming; University of Bedfordshire (CEUR-WS, 2020-07-30)
      Most existing studies of content-based image retrieval (CBIR) system design focus on learning users’ information needs through relevance feedback at the result assessment stage only. However, in many CBIR systems, the underlying machine learning mechanisms need the users’ feedback at query formulation stage for a better training and search performance, which unfortunately is often not supported by the search interface design. The lack of support for the users’ query formulation through an effective CBIR interface has been a drawback for system performance and the users’ search satisfaction and experiences. We propose a new CBIR system design approach based on Vakkari’s three-stage model, which encourages the users to provide feedback at the query formulation stage through a user-centered interface. The interface helps the users to form and express their information needs through enabling the users to participate in the training phase of the machine learning mechanism of the system. A user study with 28 participants shows how the proposed system design supports the users’ interaction through the user-centered search interface. The findings of this study highlight the importance for the users to engage in all stages of the search process, especially at the query formulation stage when the considered mechanism requires a training process, through a user-centered interaction design.
    • Infectious disease management systems in the Gulf region: the current status and potential impact

      Alanezi, Fahad; Hussain, F.; Yu, Hong Qing; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2017-07-17)
      No study has investigated the current state and potential impact of using infectious disease management systems in the Gulf Region. In this paper, we aim to investigatethe current published literature to identify the studies and the potential impact of these technologies on improving infectious disease management. This study reviews the published papers (1975-2014) using a systematic approach. This entails searchingpeer-reviewed articles in both English (PubMed, Web of Science, and IEEE Xplorer) and Arabic (Al Manhal, Mandumah, and AskZad) electronic databases using the following terms: "infectious diseases", "e-health", "infectious diseases management systems", and country name. We analysed 96 English articles and 68 Arabic articles. No studies met the inclusion criteria. In conclusion, there is a need to conduct extensive research in this region, such as designing asystem based on the needs of infectious patients as well as relevant social phenomena.
    • A study on perception of managing infectious disease through social networking in the Kingdom of Saudi Arabia

      Alanezi, Fahad; Hussain, F.; Yu, Hong Qing; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2017-07-17)
      The impact of infectious disease on the human population is very dangerous as it could cause severe damage, disruption in human life and can result in many deaths. There is an immediate need for effectively managing the infectious diseases and stop their spreading across other regions. The Infectious Disease management (IDM) process in a country like the Kingdom of Saudi Arabia (KSA), which is one of the developing countries with wide range of healthcare complications, and being one of the countries with high tourist inflow (hajj tourists) has to be very effective and efficient. Considering these factors, this paper presents the preliminary results of the stage one of the research work intended for developing a web IDM system integrating social networking concept. The study presented in this paper followed a mixed method strategy using survey questionnaires and the interviews as the part of data collection and analysis for assessing the perception of IDM through social networking in KSA. The outcome of the study indicated that most of the young participants supported the idea of using social networking in IDM. Other key outcomes include high level acceptance of using web technology and social networking with mapping strategy for creating awareness among the patients through education and information exchange. With in the participation.
    • Semantic lifting and reasoning on the personalised activity big data repository for healthcare research

      Yu, Hong Qing; Dong, Feng (Inderscience Publishers, 2019-10-08)
      The fast growing markets of smart health monitoring devices and mobile applications provide opportunities for common citizens to have capability for understanding and managing their own health situations. However, there are many challenges for data engineering and knowledge discovery research to enable efficient extraction of knowledge from data that is collected from heterogonous devices and applications with big volumes and velocity. This paper presents research that initially started with the EC MyHealthAvatar project and is under continual improvement following the project's completion. The major contribution of the work is a comprehensive big data and semantic knowledge discovery framework which integrates data from varied data resources. The framework applies hybrid database architecture of NoSQL and RDF repositories with introductions for semantic oriented data mining and knowledge lifting algorithms. The activity stream data is collected through Kafka's big data processing component. The motivation of the research is to enhance the knowledge management, discovery capabilities and efficiency to support further accurate health risk analysis and lifestyle summarisation.
    • Extracting reliable health condition and symptom information to support machine learning

      Yu, Hong Qing; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2020-04-09)
      Machine Learning (ML) technologies in recent times are widely applied in various areas to assist knowledge gaining and decision-making tasks and healthcare is one of the important area among these tasks. In this paper, we propose a process to identify reliable health data from online resources and process the data to enable being used by the ML technologies. As an example, we scrap a condition-symptom dataset with Natural Language Processing (NLP) features from one of the UK NHS website. In addition, we examine our data in depth by having symptom frequency, similarity and clustering analysis.
    • Experimental disease prediction research on combining natural language processing and machine learning

      Yu, Hong Qing; University of Bedfordshire (Institute of Electrical and Electronics Engineers Inc., 2020-01-20)
      Nowadays Artificial Intelligent (AI) technologies are applied widely in many different areas to assist knowledge gaining and decision-making tasks. Especially, health information system can get most benefits from the AI advantages. In particular, symptoms based disease prediction research and production became increasingly popular in the healthcare sector recently. Various researchers and organizations have turned their interest in using modern computational techniques to analyze and develop new approaches that can efficiently predict diseases with reasonable accuracy. In this paper, we propose a framework to evaluate the efficiency of applying both Machine Learning (ML) and Nature Language Processing (NLP) technologies for disease prediction system. As an example, we scraped a disease- symptom dataset with NLP features from one of the UK most trustable National Health Service (NHS) website. In addition, we will exam our data in depth having symptom frequency, similarity and clustering analysis. As result, we can see that the prediction can have a very positive efficient rate but still open issues need to be addressed.
    • Extracting and representing causal knowledge of health conditions

      Yu, Hong Qing; University of Bedfordshire (CEUR-WS, 2020-07-30)
      Most healthcare and health research organizations published their health knowledge on the web through HTML or semantic presentations nowadays e.g. UK National Health Service website. Especially, the HTML contents contain valuable information about the individual health condition and graph knowledge presents the semantics of words in the contents. This paper focuses on combining these two for extracting causality knowledge. Understanding causality relations is one of the crucial tasks to support building an Artificial Intelligent (AI) enabled healthcare system. Unlike other raw data sources used by AI processes, the causality semantic dataset is generated in this paper, which is believed to be more efficient and transparent for supporting AI tasks. Currently, neural network-based deep learning processes found themselves in a hard position to explain the prediction outputs, which is majorly because of lacking knowledge-based probability analysis. Dynamic probability analysis based on causality modeling is a new research area that not only can model the knowledge in a machine-understandable way but also can create causal probability relations inside the knowledge. To achieve this, a causal probability generation framework is proposed in this paper that extends the current Description Logic (DL), applies semantic Natural Language Processing (NLP) approach, and calculates runtime causal probabilities according to the given input conditions. The framework can be easily implemented using existing programming standards. The experimental evaluations extract 383 common disease conditions from the UK NHS (the National Health Service) and enable automatically linked 418 condition terms from the DBpedia dataset.
    • Editorial: Recent advances in 2020 2nd International Symposium on Big Data and Artificial Intelligence

      Crabbe, M. James C.; Li, Rita Yi Man; Dong, Rebecca Kechen; Manta, Otilia; Comite, Ubaldo; Oxford University; Hong Kong Shue Yan University; University of South Australia; Romanian-American University; University Giustino Fortunato (Association for Computing Machinery., 2021-01-16)
      The 2020 2nd International Symposium on Big Data and Artificial Intelligence was held in Johannesburg, South Africa, from October 15 - 16, 2020. It was organized by IETI, IDSAI, the University of Johannesburg (South Africa) and JRFM, with joint support from the Real Estate and Economics Research Lab of Hong Kong Shue Yan University, the Sustainable Real Estate Research Center of Hong Kong Shue Yan University, Shandong University of Finance and Economics (Mainland China), Guilin University of Technology (Mainland China), IAOE (Austria), the Department of Sport and Physical Education of Hong Kong Baptist University, Rattanakosin International College of Creative Entrepreneurship of Rajamangala University of Technology Rattanakosin (Thailand), Algebra University College (Croatia), and the Center for Financial and Monetary Research of Romanian Academy (Romania), University Giustino Fortunato (Italy). ISBDAI is there to discuss the challenges and possible solutions to these important issues. The conference focused on Artificial Intelligence, Computer Science, Cloud Computing, Big Data, the Internet of Things and the Mobile Web. The participants and speakers were from many countries and universities, including Mainland China, Hong Kong, Thailand, Romania, Italy, Singapore, Austria, Croatia, Australia, UK, Congo King, Portugal and Cyprus. The conference received a record 505 submissions, with 115 papers accepted for presentation. Positive recommendations of at least two reviewers were considered by the conference committees for acceptance of manuscripts. The Editors express a special gratitude to all the Committee Members and ACM-ICPS, who worked so speedily, efficiently, and professionally in support of the conference. Finally, on behalf of the Organizing Committee, we would like to thank all the authors, speakers, and participants for contributing to the success of ISBDAI 2020.
    • Cross hashing: anonymizing encounters in decentralised contact tracing protocols

      Ali, Junade; Dyo, Vladimir; University of Bedfordshire (2021-01-16)
      During the COVID-19 (SARS-CoV-2) epidemic, Contact Tracing emerged as an essential tool for managing the epidemic. App-based solutions have emerged for Contact Tracing, including a protocol designed by Apple and Google (influenced by an open-source protocol known as DP3T). This protocol contains two well-documented de-anonymisation attacks. Firstly that when someone is marked as having tested positive and their keys are made public, they can be tracked over a large geographic area for 24 hours at a time. Secondly, whilst the app requires a minimum exposure duration to register a contact, there is no cryptographic guarantee for this property. This means an adversary can scan Bluetooth networks and retrospectively find who is infected. We propose a novel ”cross hashing” approach to cryptographically guarantee minimum exposure durations. We further mitigate the 24-hour data exposure of infected individuals and reduce computational time for identifying if a user has been exposed using k-Anonymous buckets of hashes and Private Set Intersection. We empirically demonstrate that this modified protocol can offer like-for-like efficacy to the existing protocol.
    • BIRDS-bridging the gap between information science, information retrieval and data science

      Frommholz, Ingo; Liu, Haiming; Melucci, Massimo; University of Bedfordshire; University of Padova (Association for Computing Machinery, Inc, 2020-07-30)
      The BIRDS workshop aimed to foster the cross-fertilization of Information Science (IS), Information Retrieval (IR) and Data Science (DS). Recognising the commonalities and differences between these communities, the proposed full-day workshop brought together experts and researchers in IS, IR and DS to discuss how they can learn from each other to provide more user-driven data and infor-mation exploration and retrieval solutions. Therefore, the papers aimed to convey ideas on how to utilise, for instance, IS concepts and theories in DS and IR or DS approaches to support users in data and information exploration.
    • IoT for 5G/B5G applications in smart homes, smart cities, wearables and connected cars

      Uddin, Hasna; Gibson, Marcia; Safdar, Ghazanfar Ali; Kalsoom, Tahera; Ramzan, Naeem; Ur-Rehman, Masood; Imran, Muhammad Ali; University of Bedfordshire; University of West of Scotland; University of Glasgow (Institute of Electrical and Electronics Engineers Inc., 2019-10-07)
      Internet of things (IoT) is referred to as smart devices connected to the internet. A smart device is an electronic device, which may connect to other devices or are part of a network such as Wi-Fi. The increase of IoT devices has helped with advancing technology in many areas of society. Application of IoT in 5G/B5G devices has provided many benefits such as providing new ideas that can become projects for tech companies, generating big data (large volume of data which can be used to reveal trends, patterns and associations) and providing various ways of communicating. This has also had an impact on how companies improve their business with the use of advanced technology. However, the rapid growth of IoT has introduced a new platform for cybercriminals to attack. There has been published security measures on IoT to help deal with such risks and vulnerabilities. This survey paper will explore IoT in relation to smart homes, smart cities, wearables and connected cars. The benefits, risks and vulnerabilities will be discussed that comes along with using such devices connected to the internet.
    • Survey on security and privacy issues in cyber physical systems

      Nazarenko, Artem A.; Safdar, Ghazanfar Ali; Nova University of Lisbon; University of Bedfordshire (American Institute of Mathematical Sciences, 2019-04-16)
      The notion of Cyber-Physical Systems (CPS) is proposed by the National Scientific Foundation to describe a type of systems which combine hardware and software components and being the next step in development of embedded systems. CPS includes a wide range of research topics ranging from signal processing to data analysis. This paper contains a brief review of the basic infrastructure for CPS including smart objects and network aspects in relation to TCP/IP stack. As CPS reflect the processes of the physical environment onto the cyber space, virtualisation as an important tool for abstraction plays crucial role in CPS. In this context paper presents the challenges associated with mobility and vritualisation; accordingly three main types of virtualisation, namely network, devices and applications virtualisation are presented in the paper. These aspects are tightly coupled with security and safety issues. Therefore, different threats, attack types with corresponding subtypes and possible consequences are discussed as well as analysis of various approaches to cope with existing threats is introduced. In addition threat modelling approaches were also in scope of this work. Furthermore, needs and requirements for safety-critical CPS are reviewed. Thus the main efforts of this paper are directed on introducing various aspects of the CPS with regard to security and safety issues.