• Targeted ensemble machine classification approach for supporting IOT enabled skin disease detection

      Yu, Hong Qing; Reiff-Marganiec, Stephan; University of Derby (IEEE, 2021-03-26)
      The fast development of the Internet of Things (IoT) changes our life in many areas, especially in the health domain. For example, remote disease diagnosis can be achieved more efficiently with advanced IoT-technologies which not only include hardware but also smart IoT data processing and learning algorithms, e.g. image-based disease classification. In this paper, we work in a specific area of skin condition classification. This research work aims to provide an implementable solution for IoT-led remote skin disease diagnosis applications. The research output can be concluded into three folders. The first folder is about dynamic AI model configuration supported IoT-Fog-Cloud remote diagnosis architecture with hardware examples. The second folder is the evaluation survey regarding the performances of machine learning models for skin disease detection. The evaluation contains a variety of data processing methods and their aggregations. The evaluation takes account of both training-testing and cross-testing validations on all seven conditions and individual condition. In addition, the HAM10000 dataset is picked for the evaluation process according to the suitability comparisons to other relevant datasets. In the evaluation, we discuss the earlier work of ANN, SVM and KNN models, but the evaluation process mainly focuses on six widely applied Deep Learning models of VGG16, Inception, Xception, MobileNet, ResNet50 and DenseNet161. The result shows that each of the top four models for the major seven skin conditions has better performance for the specific condition than others. Based on the evaluation discovery, the last folder proposes a novel classification approach of the Targeted Ensemble Machine Classify Model (TEMCM) to enable dynamically combining a suitable model in a two-phase detection process. The final evaluation result shows the proposed model can archive better performance.
    • A Task-Oriented Framework for Networked Wearable Computing

      Galzarano, Stefano; Giannantonio, Roberta; Liotta, Antonio; Fortino, Giancarlo (IEEE, 2014)
    • TEAM: A trust evaluation and management framework in context-enabled vehicular ad-hoc networks.

      Ahmad, Farhan; Franqueira, Virginia N. L.; Adnane, Asma; University of Derby (IEEE, 2018-05-25)
      Vehicular ad-hoc network (VANET) provides a unique platform for vehicles to intelligently exchange critical information, such as collision avoidance messages. It is, therefore, paramount that this information remains reliable and authentic, i.e., originated from a legitimate and trusted vehicle. Trust establishment among vehicles can ensure security of a VANET by identifying dishonest vehicles and revoking messages with malicious content. For this purpose, several trust models (TMs) have been proposed but, currently, there is no effective way to compare how they would behave in practice under adversary conditions. To this end, we propose a novel trust evaluation and management (TEAM) framework, which serves as a unique paradigm for the design, management, and evaluation of TMs in various contexts and in presence of malicious vehicles. Our framework incorporates an asset-based threat model and ISO-based risk assessment for the identification of attacks against critical risks. The TEAM has been built using VEINS, an open source simulation environment which incorporates SUMO traffic simulator and OMNET++ discrete event simulator. The framework created has been tested with the implementation of three types of TMs (data oriented, entity oriented, and hybrid) under four different contexts of VANET based on the mobility of both honest and malicious vehicles. Results indicate that the TEAM is effective to simulate a wide range of TMs, where the efficiency is evaluated against different quality of service and security-related criteria. Such framework may be instrumental for planning smart cities and for car manufacturers.
    • Technical note: Intercomparison of three AATSR Level 2 (L2) AOD products over China

      Che, Yahui; Xue, Yong; Mei, Linlu; Guang, Jie; She, Lu; Guo, Jianping; Hu, Yincui; Xu, Hui; He, Xingwei; Di, Aojie; et al. (Copernicus Publications, 2016-08-02)
      One of four main focus areas of the PEEX initiative is to establish and sustain long-term, continuous, and comprehensive ground-based, airborne, and seaborne observation infrastructure together with satellite data. The Advanced Along-Track Scanning Radiometer (AATSR) aboard ENVISAT is used to observe the Earth in dual view. The AATSR data can be used to retrieve aerosol optical depth (AOD) over both land and ocean, which is an important parameter in the characterization of aerosol properties. In recent years, aerosol retrieval algorithms have been developed both over land and ocean, taking advantage of the features of dual view, which can help eliminate the contribution of Earth's surface to top-of-atmosphere (TOA) reflectance. The Aerosol_cci project, as a part of the Climate Change Initiative (CCI), provides users with three AOD retrieval algorithms for AATSR data, including the Swansea algorithm (SU), the ATSR-2ATSR dual-view aerosol retrieval algorithm (ADV), and the Oxford-RAL Retrieval of Aerosol and Cloud algorithm (ORAC). The validation team of the Aerosol-CCI project has validated AOD (both Level 2 and Level 3 products) and AE (Ångström Exponent) (Level 2 product only) against the AERONET data in a round-robin evaluation using the validation tool of the AeroCOM (Aerosol Comparison between Observations and Models) project. For the purpose of evaluating different performances of these three algorithms in calculating AODs over mainland China, we introduce ground-based data from CARSNET (China Aerosol Remote Sensing Network), which was designed for aerosol observations in China. Because China is vast in territory and has great differences in terms of land surfaces, the combination of the AERONET and CARSNET data can validate the L2 AOD products more comprehensively. The validation results show different performances of these products in 2007, 2008, and 2010. The SU algorithm performs very well over sites with different surface conditions in mainland China from March to October, but it slightly underestimates AOD over barren or sparsely vegetated surfaces in western China, with mean bias error (MBE) ranging from 0.05 to 0.10. The ADV product has the same precision with a low root mean square error (RMSE) smaller than 0.2 over most sites and the same error distribution as the SU product. The main limits of the ADV algorithm are underestimation and applicability; underestimation is particularly obvious over the sites of Datong, Lanzhou, and Urumchi, where the dominant land cover is grassland, with an MBE larger than 0.2, and the main aerosol sources are coal combustion and dust. The ORAC algorithm has the ability to retrieve AOD at different ranges, including high AOD (larger than 1.0); however, the stability deceases significantly with increasing AOD, especially when AOD > 1.0. In addition, the ORAC product is consistent with the CARSNET product in winter (December, January, and February), whereas other validation results lack matches during winter.
    • Temporal patterns: Smart-type reasoning and applications

      Chuckravanen, Dineshen; Daykin, Jacqueline; Hunsdale, Karen; Seeam, Amar; Aberythwyth University (Mauritius Branch Campus) (International Academy, Research, and Industry Association (IARIA), 2017-02)
      Allen’s interval algebra is a calculus for temporal reasoning that was introduced in 1983. Reasoning with quali- tative time in Allen’s full interval algebra is nondeterministic polynomial time (NP) complete. Research since 1995 identified maximal tractable subclasses of this algebra via exhaustive computer search and also other ad-hoc methods. In 2003, the full classification of complexity for satisfiability problems over con- straints in Allen’s interval algebra was established algebraically. Recent research proposed scheduling based on the Fishburn- Shepp correlation inequality for posets. We describe here three potential temporal-related application areas as candidates for scheduling using this inequality
    • Theoretical investigation into balancing high-speed flexible shafts, by the use of a novel compensating balancing sleeve

      Knowles, Grahame; Kirk, Antony; Stewart, Jill; Bickerton, Ron; Bingham, Chris; University of Lincoln (IMechE, 2013-12-31)
      Traditional techniques for balancing long, flexible, high-speed rotating shafts are inadequate over a full range of shaft speeds. This problem is compounded by limitations within the manufacturing process, which have resulted in increasing problems with lateral vibrations and hence increased the failure rates of bearings in practical applications. There is a need to develop a novel strategy for balancing these coupling shafts that is low cost, robust under typically long-term operating conditions and amenable to on-site remediation. This paper proposes a new method of balancing long, flexible couplings by means of a pair of balancing sleeve arms that are integrally attached to each end of the coupling shaft. Balance corrections are applied to the free ends of the arms in order to apply a corrective centrifugal force to the coupling shaft in order to limit shaft-end reaction forces and to impart a corrective bending moment to the drive shaft that limits shaft deflection. The aim of this paper is to demonstrate the potential of this method, via the mathematical analysis of a plain, simply supported tube with uniform eccentricity and to show that any drive shaft, even with irregular geometry and/or imbalance, can be converted to an equivalent encastre case. This allows for the theoretical possibility of eliminating the first simply supported critical speed, thereby reducing the need for very large lateral critical speed margins, as this requirement constrains design flexibility. Although the analysis is performed on a sub 15 MW gas turbine, it is anticipated that this mechanism would be beneficial on any shaft system with high-flexibility/shaft deflection.
    • Timing error detection and correction for power efficiency: an aggressive scaling approach

      Rathnala, Prasanthi; Wilmshurst, Tim; Kharaz, Ahmad H.; University of Derby (IET, 2018-12-06)
      Low-power consumption has become an important aspect of processors and systems design. Many techniques ranging from architectural to system level are available. Voltage scaling or frequency boosting methods are the most effective to achieve low-power consumption as the dynamic power is proportional to the frequency and to the square of the supply voltage. The basic principle of operation of aggressive voltage scaling is to adjust the supply voltage to the lowest level possible to achieve minimum power consumption while maintaining reliable operations. Similarly, aggressive frequency boosting is to alter the operating frequency to achieve optimum performance improvement. In this study, an aggressive technique which employs voltage or frequency varying hardware circuit with the time-borrowing feature is presented. The proposed technique double samples the data to detect any timing violations as the frequency/voltage is scaled. The detected violations are masked by phase delaying the flip-flop clock to capture the late arrival data. This makes the system timing error tolerant without incurring error correction timing penalty. The proposed technique is implemented in a field programmable gate array using a two-stage arithmetic pipeline. Results on various benchmarks clearly demonstrate the achieved power savings and performance improvement.
    • To flip or not to flip: a critical interpretive synthesis of flipped teaching

      Franqueira, Virginia N. L.; Tunnicliffe, Peter; University of Derby (Springer International Publishing, 2015-05-28)
      It became almost fashionable to refer to the term “flipped” in higher education. Expressions like flipped learning and flipped classroom are often used interchangeably as an indication of innovation, flexibility, creativity and pedagogical evolution. We performed an exploratory study on this topic following the Critical Interpretive Synthesis methodology for analysis of the literature. Our findings indicated that the term “Flipped Learning” is misleading and that, in fact, the synthetic concept behind it is “Flipped Teaching”. We derived a synthesising argument, in the format of two synthesis models, of the potential benefits promoted by flipped teaching and the potential issues which affect its success in practice. Those models allow STEM course tutors not only to make informed decisions about whether to flip teaching or not, but also to better prepare for flipping.
    • Tools and technologies for the implementation of Big Data

      Self, Richard; Voorhis, Dave; University of Derby (Butterworth-Heinemann, 2015-02-17)
      Application of Big Data for National Security provides users with state-of-the-art concepts, methods, and technologies for Big Data analytics in the fight against terrorism and crime, including a wide range of case studies and application scenarios. This book combines expertise from an international team of experts in law enforcement, national security, and law, as well as computer sciences, criminology, linguistics, and psychology, creating a unique cross-disciplinary collection of knowledge and insights into this increasingly global issue. The strategic frameworks and critical factors presented in Application of Big Data for National Security consider technical, legal, ethical, and societal impacts, but also practical considerations of Big Data system design and deployment, illustrating how data and security concerns intersect. In identifying current and future technical and operational challenges it supports law enforcement and government agencies in their operational, tactical and strategic decisions when employing Big Data for national security.
    • Tools and technologies for the implementation of Big Data.

      Self, Richard; Voorhis, Dave; University of Derby (Elsevier, 2015-02-27)
      This chapter uses the five V’s of Big Data (volume, velocity, variety, veracity, and value) to form the basis for consideration of the current status and issues relating to the introduction of Big Data analysis into organizations. The first three are critical to understanding the implications and consequences of available choices for the techniques, tools, and order to provide an understanding of choices that need to be made based on understanding the nature of the data sources and the content. All five V’s are invoked to evaluate some of the most critical issues involved in the choices made during the early stages of implementing a Big Data analytics project. Big Data analytics is a comparatively new field; as such, it is important to recognize that elements are currently well along the Gartner hype cycle into productive use. The concept of the planning fallacy is used with information technology project success reference class data created by the Standish Group to improve the success rates of Big Data projects. International Organization for Standardization 27002 provides a basis considering critical issues raised by data protection regimes in relation to the sources and locations of data and processing of Big Data.
    • A topological insight into restricted Boltzmann machines

      Mocanu, Decebal Constantin; Mocanu, Elena; Nguyen, Phuong H.; Gibescu, Madeleine; Liotta, Antonio (Springer, 2016)
    • A topological insight into restricted Boltzmann machines (extented abstract)

      Mocanu, Decebal Constantin; Mocanu, Elena; Nguyen, Phuong H.; Gibescu, Madeleine; Liotta, Antonio (2016)
    • Toward a flexible and fine-grained access control framework for infrastructure as a service clouds

      Li, Bo; Li, Jianxin; Liu, Lu; Zhou, Chao; University of Derby; State Key Laboratory of Software Development Environment; Beihang University; Beijing China; State Key Laboratory of Software Development Environment; Beihang University; Beijing China; School of Computing and Mathematics; University of Derby; U.K.; State Key Laboratory of Software Development Environment; Beihang University; Beijing China (Wiley, 2015-02-17)
      Cloud computing, as an emerging computing paradigm, greatly facilitates resource sharing and enables providing computing power as services over the Internet. However, it also brings new challenges for security and access control, especially in infrastructure as a service clouds. The introduction of virtualization layer increases new security risks, which should be restricted and confined by more stringent access control techniques. In this paper, we propose a flexible and fine-grained access control framework, named IaaS-oriented Hybrid Access Control (iHAC), which combines the advantages of both the role-based access control and type enforcement model. We consider access control issues from the perspective of virtual machines. A permission transition model is designed to dynamically assign permissions to virtual machines. A Virtual Machine Monitor (VMM)-based access control mechanism is presented to confine the virtual machine's behaviors in a fine-grained manner. A VMM-enabled network access control approach is proposed to regulate the communication among virtual machines. iHAC is successfully implemented in the Internet based Virtual Computing Infrastructure (iVIC)† platform, and several experiments are conducted to evaluate its effectiveness and efficiency. The results show that iHAC can make correct access control decisions with low performance overhead.
    • Towards a framework for the evaluation of efficient provisioning in opportunistic ad-hoc networks

      Smith, Anthony; Hill, Richard; University of Derby, Distributed and Intelligent Systems Research Group (IEEE Computer Society, 2011/20/26)
      In wireless ad-hoc networks where there is no continuous end-to-end path we move into the area of opportunistic networks. Forwarding messages via any encountered nodes, such as the mobile devices that many users already carry. Normally we are looking for the most efficient method of passing these messages across the network, but how do we evaluate the different methods. We propose to develop a framework that will allow us to evaluate how efficiently provisioning has been performed. This has been explored with the use of a case study and two benchmark protocols, Epidemic and PRoPHET. We present the results of this analysis and describe an approach to the validation of this through simulation.
    • Towards a trusted unmanned aerial system using blockchain (BUAS) for the protection of critical infrastructure

      Barka, Ezedin; Kerrache, Chaker Abdelaziz; Benkraouda, Hadjer; Shuaib, Khaled; Ahmad, Farhan; Kurugollu, Fatih; College of Information Technology, United Arab Emirates University; Department of Mathematics and Computer Science, University of Ghardaia, Algeria; Cyber Security Research Group, University of Derby, UK (Wiley, 2019-07-29)
      With the exponential growth in the number of vital infrastructures such as nuclear plants and transport and distribution networks, these systems have become more susceptible to coordinated cyber attacks. One of the effective approaches used to strengthen the security of these infrastructures is the use of Unmanned Aerial Vehicles (UAVs) for surveillance and data collection. However, UAVs themselves are prone to attacks on their collected sensor data. Recently, Blockchain (BC) has been proposed as a revolutionary technology which can be integrated within IoT to provide a desired level of security and privacy. However, the integration of BC within IoT networks, where UAV's sensors constitute a major component, is extremely challenging. The major contribution of this study is two-fold. (1) survey of the security issues for UAV's collected sensor data, define the security requirements for such systems, and identify ways to address them. (2) propose a novel Blockchain-based solution to ensure the security of, and the trust between the UAVs and their relevant ground control stations (GCS). Our implementation results and analysis show that using UAVs as means for protecting critical infrastructure is greatly enhanced through the utilization of trusted Blockchain-based Unmanned Aerial Systems (UASs).
    • Towards ABAC Policy Mining from Logs with Deep Learning

      Mocanu, Decebal Constantin; Turkmen, Fatih; Liotta, Antonio (2015)
    • Towards cloud based big data analytics for smart future cities

      Khan, Zaheer; Anjum, Ashiq; Tahir, Muhammad Atif; Soomro, Kamran Ahmed; University of Derby, UK (Springer, 2015-02-18)
      A large amount of land-use, environment, socio-economic, energy and transport data is generated in cities. An integrated perspective of managing and analysing such big data can answer a number of science, policy, planning, governance and business questions and support decision making in enabling a smarter environment. This paper presents a theoretical and experimental perspective on the smart cities focused big data management and analysis by proposing a cloud-based analytics service. A prototype has been designed and developed to demonstrate the effectiveness of the analytics service for big data analysis. The prototype has been implemented using Hadoop and Spark and the results are compared. The service analyses the Bristol Open data by identifying correlations between selected urban environment indicators. Experiments are performed using Hadoop and Spark and results are presented in this paper. The data pertaining to quality of life mainly crime and safety & economy and employment was analysed from the data catalogue to measure the indicators spread over years to assess positive and negative trends.
    • Towards wireless technology for safety critical systems.

      Johnston, A B; Schiffers, W; Kharaz, Ahmad H.; Rolls-Royce plc; University of Derby (IOP Science, 2018-11-13)
      Wireless technology provides an unprecedented level of design flexibility for new system designs and legacy system updates. However, there are several challenges which present themselves when adopting wireless technologies for use in safety systems. This paper elaborates on available design techniques which can resolve the implementation issues for a given application, to ensure data communication between nodes is safe (deterministic), secure, reliable and available.
    • Traffic assignment: methods and simulations for an alternative formulation of the fixed demand problem

      Bagdasar, Ovidiu; Berry, Stuart; O’Neill, Sam; Popovici, Nicolae; Raja, Ramachandran; University of Derby; Technical University of Cluj-Napoca (Elsevier, 2018-08-30)
      Motorists often face the dilemma of choosing the route enabling them to realise the fastest (i.e., shortest) journey time. In this paper we examine discrete and continuous optimisation and equilibrium-type problems for a simplified parallel link traffic model using a variance based approach. Various methodologies used for solving these problems (brute force, dynamic programming, tabu search, steepest descent) are explored and comparison is made with the Beckmann cost function traditionally employed in transport modelling.