Publications

  • Geometric Defuzzification Revisited
    Geometric Defuzzification Revisited Greenfield, Sarah In this paper the Geometric Defuzzification strategy for type-2 fuzzy sets is reappraised. For both discretised and geometric fuzzy sets the techniques for type-1, interval type-2, and generalised type-2 defuzzification are presented in turn. In the type-2 case the accuracy of Geometric Defuzzification is assessed through a series of test runs on interval type-2 fuzzy sets, using Exhaustive Defuzzification as the benchmark method. These experiments demonstrate the Geometric Defuzzifier to be wildly inaccurate. The test sets take many shapes; they are not confined to those type-2 sets with rotational symmetry that have previously been acknowledged by the technique’s developers to be problematic as regards accuracy. Type-2 Geometric Defuzzification is then examined theoretically. The defuzzification strategy is demonstrated to be built upon a fallacious application of the concept of centroid. This explains the markedly inaccurate experimental results. Thus the accuracy issues of type-2 Geometric Defuzzification are revealed to be inevitable, fundamental and significant. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link.
  • Use of Bayesian Inference Method to Model Vehicular Air Pollution in Local Urban Areas
    Use of Bayesian Inference Method to Model Vehicular Air Pollution in Local Urban Areas Orun, A.; Elizondo, David; Goodyer, E.; Paluszczyszyn, D. Traffic Related Air Pollution (TRAP) studies are usually investigated using different categories such as air pollution exposure for health impacts, urban transportation network design to mitigate pollution, environmental impacts of pollution, etc. All of these subfields often rely on a robust air pollution model, which also necessitates an accurate prediction of future pollutants. As is widely accepted by the heath authorities, TRAP is considered to be the major health issue in urban areas, and it is difficult to keep pollution at harmless levels if the time sequenced dynamic pollution and traffic parameters are not identified and modelled efficiently. In our work here, artificial intelligence techniques, such as Bayesian Networks with an optimized configuration, are used to deliver a probabilistic traffic data analysis and predictive modelling for air pollution (SO2, NO2 and CO) at very local scale of an urban region with up to 85% accuracy. The main challenge for traditional data analysis is a lack of capability to reveal the hidden links between distant data attributes (e.g. pollution sources, dynamic traffic parameters, etc.), whereas some subtle effects of these parameters or events may play an important role in pollution on a long-term basis. This study focuses on the optimisation of Bayesian Networks to unveil hidden links and to increase the prediction accuracy of TRAP considering its further association with a predictive GIS system The file attached to this record is the author's final peer reviewed version.
  • Robust Predictive Speed Regulation of Converter-Driven DC Motors Via A Discrete-Time Reduced-Order GPIO
    Robust Predictive Speed Regulation of Converter-Driven DC Motors Via A Discrete-Time Reduced-Order GPIO Yang, Jun; Wu, Hao; Hu, Liang; Li, Shihua Converter-driven direct current (DC) motors exhibit various advantages in industry, but impose several challenges to higher-precision speed regulation in the presence of parametric uncertainties and exogenous, time-varying load torque disturbances. In this paper, the robust predictive speed regulation problem of a generic DC-DC buck converter-driven permanent magnet DC motors is addressed by using an output feedback discrete-time model predictive control (MPC) algorithm. A new discrete-time reduced-order generalized proportional-integral observer (GPIO) is proposed to reconstruct the virtual system states as well as the lumped disturbances. The estimates of GPIO are then collected for output speed prediction. An optimized duty ratio law of the converter is obtained by solving a constrained receding horizon optimization problem, where the operational constraint on control input is explicitly taken into account. Finally, the effectiveness of the proposed new algorithm is demonstrated by various experimental testing results. The file attached to this record is the author's final peer reviewed version.
  • Bayesian Estimation of A Periodically-Releasing Biochemical Source Using Sensor Networks
    Bayesian Estimation of A Periodically-Releasing Biochemical Source Using Sensor Networks Hu, Liang; Su, Jinya; Hutchinson, Michael; Liu, Cunjia; Chen, Wen-Hua This paper develops a Bayesian estimation method to estimate source parameters of a biochemical source using a network of sensors. Based on existing models of continuous and instantaneous releases, a model of discrete and periodic releases is proposed, which has extra parameters such as the time interval between two successive releases. Different from existing source term estimation methods, based on the sensor characteristic of chemical sensors, the zero readings of sensors are exploited in our algorithm where the zero readings may be caused by the concentration being below the threshold of the sensors. Two types of Bayesian inference algorithms for key parameters of the sources are developed and their particle filtering implementation is discussed. The efficiency of the proposed algorithms for periodic release is demonstrated and verified by simulation where the algorithm with the exploitation of the zero readings significantly outperforms that without.
  • Recent Advances on State Estimation for Power Grids with Unconventional Measurements
    Recent Advances on State Estimation for Power Grids with Unconventional Measurements Hu, Liang; Wang, Zidong; Liu, Xiaohui; Vasilakos, A. V.; Alsaadi, F. E. State estimation problem for power systems has long been a fundamental issue that demands a variety of methodologies depending on the system settings. With the recent introduction of advanced devices of phasor measurement units (PMUs) and dedicated communication networks, the infrastructure of power grids has been greatly improved. Coupled with the infrastructure improvements are three emerging issues for the state estimation problems, namely, the coexistence of both traditional and PMU measurements, the incomplete information resulting from delayed, asynchronous and missing measurements due to communication constraints, and the cyber-attacks on the communication channels. In this study, the authors aim to survey some recent advances on the state estimation methods which tackle the above three issues in power grids. Traditional state estimation methods applied in power grids are first introduced. Latest results on state estimation with mixed measurements and incomplete measurements are then discussed in great detail. In addition, the techniques developed to ensure the cyber-security of the state estimation schemes for power grids are highlighted. Finally, some concluding remarks are given and some possible future research directions are pointed out.
  • State estimation under false data injection attacks: Security analysis and system protection
    State estimation under false data injection attacks: Security analysis and system protection Hu, Liang; Wang, Zidong; Han, Quing-Long; Liu, Xiaohui The security issue in the state estimation problem is investigated for a networked control system (NCS). The communication channels between the sensors and the remote estimator in the NCS are vulnerable to attacks from malicious adversaries. The false data injection attacks are considered. The aim of this paper to find the so-called insecurity conditions under which the estimation system is insecure in the sense that there exist malicious attacks that can bypass the anomaly detector but still lead to unbounded estimation errors. In particular, a new necessary and sufficient condition for the insecurity is derived in the case that all communication channels are compromised by the adversary. Moreover, a specific algorithm is proposed for generating attacks with which the estimation system is insecure. Furthermore, for the insecure system, a system protection scheme through which only a few (rather than all) communication channels require protection against false data injection attacks is proposed. A simulation example is utilized to demonstrate the effectiveness of the proposed conditions/algorithms in the secure estimation problem for a flight vehicle. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link
  • COLREGS-COMPLIANT PATH PLANNING FOR AUTONOMOUS SURFACE VEHICLES: A MULTIOBJECTIVE OPTIMIZATION APPROACH
    COLREGS-COMPLIANT PATH PLANNING FOR AUTONOMOUS SURFACE VEHICLES: A MULTIOBJECTIVE OPTIMIZATION APPROACH Hu, Liang; Naeem, W.; Rajabally, E.; Watson, G.; Mills, T.; Bhuiyan, Z.; Salter, I. In this paper, a multiobjective optimization framework is proposed for on-line path planning of autonomous surface vehicles (ASVs), where both collision avoidance and COLREGscompliance are taken into account. Special attention has been paid to situational awareness and risk assessment, particularly when the target ship is in breach of the COLREGs rules defined by the International Maritime Organisation. In order to implement COLREGs, the rules together with physical constraints are formulated as mathematical inequalities. A multiobjective optimization problem based on particle swarm optimization is then solved, the solution of which represents a newly-generated path. It is shown through simulations that the proposed method is able to generate COLREGs-compliant and collision-free paths even for non-cooperative targets i.e. vessels that are in breach of COLREGs. The file attached to this record is the author's final peer reviewed version. The Publisher's final version can be found by following the DOI link. Open access.
  • Water Advisory Demand Evaluation and Resource Toolkit
    Water Advisory Demand Evaluation and Resource Toolkit Iliya, S.; Paluszczyszyn, D.; Goodyer, E.; Kubrycht, T. The purpose of this feasibility study is to determine if the application of computational intelligence can be used to analyse the apparently unrelated data sources (social media, grid usage, traffic/transportation and weather) to produce credible predictions for water demand. For this purpose the artificial neural networks were employed to demonstrate on datasets localised to Leicester city in United Kingdom that viable predictions can be obtained with use of data derived from the expanding Internet-of-Things ecosystem. The outcomes from the initial study are promising as the water demand can be predicted with accuracy of 0.346 m3 in terms of root mean square error.
  • Conic deformation of the subglottic mucosa and its impact on the aerodynamics of the airflow over the vocal folds
    Conic deformation of the subglottic mucosa and its impact on the aerodynamics of the airflow over the vocal folds Goodyer, E. N.; Muller, F.; Hess, M.; Kandan, K.; Farukh, Farukh Objective: This study mapped the variation in tissue elasticity of the subglottic mucosa, applied that data to provide initial models of the likely deformation of the mucosa during the myoelastic cycle, and hypothesised as to the impact on the process of phonation. Study Design: 6 donor human larynges were dissected along the sagittal plane to expose the vocal folds and subglottic mucosa. A Linear Skin Rheometer was used to apply a controlled shear force, and the resultant displacement was measured. This data provided a measure of the stress/strain characteristics of the tissue at each anatomical point. A series of measurements were taken at 2mm interval inferior of the vocal folds, and the change in elasticity determined. Results: It was found that the elasticity of the mucosa in the subglottic region increased linearly with distance from the vocal folds in all 12 samples. A simple deformation model indicated that under low pressure conditions the subglottic mucosa will deform to form a cone, which could result in a higher velocity thus amplifying the low pressure effect resulting from the Venturi principle, and could assist in maintaining laminar flow. Conclusions: This study indicated that the deformation of the subglottic mucosa could play a significant role in the delivery of a low pressure air flow over the vocal folds.
  • An Intelligent traffic network optimisation by use of Bayesian inference methods to combat air pollution
    An Intelligent traffic network optimisation by use of Bayesian inference methods to combat air pollution Elizondo, David; Orun, A. Traffic flow related air pollution is one of the major problems in urban areas, and is often difficult to avoid it if the time sequenced dynamic pollution and traffic parameters are not identified and modelled efficiently. In our introduced work here, an artificial intelligence technique such as Bayesian networks are used for a robust traffic data analysis and modelling. The most common challenge in traditional data analysis is a lack of capability of unveiling the hidden links between the distant data attributes (e.g. pollution sources, dynamic traffic parameters, geographic location characteristics, etc.), whereas some subtle effects of these parameters or events may play an important role in pollution on a long term basis. CCI Group has contributed to the research

Click here to access all DIGITS outputs

Computational-Intelligence-for-Privacy-and-Security

constructivenetworks

INTERNATIONAL-JOURNAL-FOR-TRAFFIC-AND-TRANSPORT-ENGINEERINGPrincipal-Manifolds-for-Data-Visualization-and-Dimension-Reduction

 
Technology Degree Show
Technology Degree Show

The Technology Degree Show highlights the work and achievements of our final year students.

DMU research news target area image
DMU research news

Read about our latest research efforts.

Mission and vision target area image
Mission and vision

Read about our mission and vision and how these create a supportive and exciting learning environment.