Professor Shengxiang Yang

Job: Professor of Computational Intelligence, Director of the Centre for Computational Intelligence (CCI)

Faculty: Technology

School/department: School of Computer Science and Informatics

Research group(s): Centre for Computational Intelligence (CCI)

Address: De Montfort University, The Gateway, Leicester, LE1 9BH UK

T: +44 (0)116 207 8805

E: syang@dmu.ac.uk

W: www.tech.dmu.ac.uk/~syang/

 

Personal profile

Shengxiang Yang is Professor of Computational Intelligence and Director of the Centre of Computational Intelligence (CCI), De Montfort University. Before joining the CCI in July 2012, he worked at Brunel University, University of Leicester, and King's College London as a Senior Lecturer, Lecturer, and Post-doctoral Research Associate, respectively.

Shengxiang's main research interests lie in evolutionary computation. He is particularly active in the area of evolutionary computation in dynamic and uncertain environments. Shengxiang has also published on the application of evolutionary computation in communication networks, logistics, transportation systems, and manufacturing systems, etc.

Research group affiliations

Centre for Computational Intelligence

Publications and outputs 

  • A two-layer optimisation management method for the microgrid with electric vehicles
    A two-layer optimisation management method for the microgrid with electric vehicles Zheng, Zedong; Yang, Shengxiang The energy management of the microgrid (MG) with electric vehicles (EVs) is a large-scale optimization problem where the goal should take into account the performance and economic benefits of the power system while meeting the travel needs of EVs. Due to the development of vehicle to grid (V2G) technologies and demand response (DR), the relationship between EVs and MG becomes currently closer, which leads to a more complex situation. Therefore, the relationship of interest between MG and EVs has to be clarified to improve the performance of MG and EVs to achieve a win-win situation. This paper proposes a two-tier energy management strategy that considers the benefits for both MG and EVs. The first layer ensures the performance of the MG, while the second layer reduces the charging cost from the perspective of the car owners. In addition, based on the existence of uncertain parameters, mixed type variables and nonlinear constraints in the optimization problem, the differential evolution, stochastic search and greedy algorithm are used to analyze and find the optimal solution. Simulation results verify the effectiveness of the proposed strategy and solutions, which benefit both the MG and EV owners. The file attached to this record is the author's final peer reviewed version.
  • Memory-based multi-population genetic learning for dynamic shortest path problems
    Memory-based multi-population genetic learning for dynamic shortest path problems Diao, Yiya; Li, Changhe; Zeng, Sanyou; Mavrovouniotis, Michalis; Yang, Shengxiang This paper proposes a general algorithm framework for solving dynamic sequence optimization problems (DSOPs). The framework adapts a novel genetic learning (GL) algorithm to dynamic environments via a clustering-based multi-population strategy with a memory scheme, namely, multi-population GL (MPGL). The framework is instantiated for a 3D dynamic shortest path problem, which is developed in this paper. Experimental comparison studies show that MPGL is able to quickly adapt to new environments and it outperforms several ant colony optimization variants. The file attached to this record is the author's final peer reviewed version.
  • Finding and tracking multi-density clusters in an online dynamic data stream
    Finding and tracking multi-density clusters in an online dynamic data stream Fahy, Conor; Yang, Shengxiang Change is one of the biggest challenges in dynamic stream mining. From a data-mining perspective, adapting and tracking change is desirable in order to understand how and why change has occurred. Clustering, a form of unsupervised learning, can be used to identify the underlying patterns in a stream. Density-based clustering identifies clusters as areas of high density separated by areas of low density. This paper proposes a Multi-Density Stream Clustering (MDSC) algorithm to address these two problems; the multi-density problem and the problem of discovering and tracking changes in a dynamic stream. MDSC consists of two on-line components; discovered, labelled clusters and an outlier buffer. Incoming points are assigned to a live cluster or passed to the outlier buffer. New clusters are discovered in the buffer using an ant-inspired swarm intelligence approach. The newly discovered cluster is uniquely labelled and added to the set of live clusters. Processed data is subject to an ageing function and will disappear when it is no longer relevant. MDSC is shown to perform favourably to state-of-the-art peer stream-clustering algorithms on a range of real and synthetic data-streams. Experimental results suggest that MDSC can discover qualitatively useful patterns while being scalable and robust to noise. The file attached to this record is the author's final peer reviewed version.
  • Energy consumption forecasting for the nonferrous metallurgy industry using hybrid support vector regression with an adaptive state transition algorithm
    Energy consumption forecasting for the nonferrous metallurgy industry using hybrid support vector regression with an adaptive state transition algorithm Huang, Zhaoke; Yang, Chunhua; Zhou, Xiaojun; Yang, Shengxiang Background/introduction: The nonferrous metallurgy industry is a major energy consumer in China, and accurate energy consumption forecasting for the nonferrous metallurgy industry can help government policymakers with energy planning. Methods: For this purpose, a hybrid support vector regression (HSVR) with an adaptive state transition algorithm (ASTA) named ASTA-HSVR is proposed to forecast energy consumption in the nonferrous metallurgy industry. The proposed support vector regression (SVR) model consists of a linear weighting of ϵ-SVR and ν-SVR. The ASTA was developed to optimize the parameters of the HSVR. Results: Two cases of energy consumption from the nonferrous metallurgy industry in China are used to demonstrate the performance of the proposed method. The results indicate that the ASTA-HSVR method is superior to other methods. Conclusions: In this study, a hybrid support vector regression with an adaptive state transition algorithm (ASTA-HSVR) was developed and successfully applied to energy consumption forecasting for the nonferrous metallurgy industry. However, it should be noted that the outliers were not considered in this study. In the future, we expect to extend the ASTA-HSVR method to include energy consumption forecasting problems with outliers. 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.
  • A similarity-based cooperative co-evolutionary algorithm for dynamic interval multi-objective optimization problems
    A similarity-based cooperative co-evolutionary algorithm for dynamic interval multi-objective optimization problems Gong, Dunwei; Xu, Biao; Zhang, Yong; Guo, Yinan; Yang, Shengxiang Dynamic interval multi-objective optimization problems (DI-MOPs) are very common in real-world applications. However, there are few evolutionary algorithms that are suitable for tackling DI-MOPs up to date. A framework of dynamic interval multi-objective cooperative co-evolutionary optimization based on the interval similarity is presented in this paper to handle DI-MOPs. In the framework, a strategy for decomposing decision variables is first proposed, through which all the decision variables are divided into two groups according to the interval similarity between each decision variable and interval parameters. Following that, two sub-populations are utilized to cooperatively optimize decision variables in the two groups. Furthermore, two response strategies, rgb0.00,0.00,0.00i.e., a strategy based on the change intensity and a random mutation strategy, are employed to rapidly track the changing Pareto front of the optimization problem. The proposed algorithm is applied to eight benchmark optimization instances rgb0.00,0.00,0.00as well as a multi-period portfolio selection problem and compared with five state-of-the-art evolutionary algorithms. The experimental results reveal that the proposed algorithm is very competitive on most optimization instances. 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.
  • An adaptation reference-point-based multiobjective evolutionary algorithm
    An adaptation reference-point-based multiobjective evolutionary algorithm Zou, Juan; Fu, Liuwei; Yang, Shengxiang; Zheng, Jinhua; Ruan, Gan; Pei, Tingrui; Wang, Lei It is well known that maintaining a good balance between convergence and diversity is crucial to the performance of multiobjective optimization algorithms (MOEAs). However, the Pareto front (PF) of multiobjective optimization problems (MOPs) affects the performance of MOEAs, especially reference point-based ones. This paper proposes a reference-point-based adaptive method to study the PF of MOPs according to the candidate solutions of the population. In addition, the proportion and angle function presented selects elites during environmental selection. Compared with five state-of-the-art MOEAs, the proposed algorithm shows highly competitive effectiveness on MOPs with six complex characteristics. 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.
  • A scalable test suite for dynamic multiobjective optimization
    A scalable test suite for dynamic multiobjective optimization Jiang, Shouyong; Kaiser, Marcus; Yang, Shengxiang; Kollias, Stefanos; Krasnogor, Natalio Dynamic multiobjective optimization (DMO) has gained increasing attention in recent years. Test problems are of great importance in order to facilitate the development of advanced algorithms that can handle dynamic environments well. However, many of the existing dynamic multiobjective test problems have not been rigorously constructed and analyzed, which may induce some unexpected bias when they are used for algorithmic analysis. In this paper, some of these biases are identified after a review of widely used test problems. These include poor scalability of objectives and, more important, problematic overemphasis of static properties rather than dynamics making it difficult to draw accurate conclusion about the strengths and weaknesses of the algorithms studied. A diverse set of dynamics and features is then highlighted that a good test suite should have. We further develop a scalable continuous test suite, which includes a number of dynamics or features that have been rarely considered in literature but frequently occur in real life. It is demonstrated with empirical studies that the proposed test suite is more challenging to the DMO algorithms found in the literature. The test suite can also test algorithms in ways that existing test suites cannot. 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.
  • A framework for inducing artificial changes in optimization problems
    A framework for inducing artificial changes in optimization problems Tinos, Renato; Yang, Shengxiang Environmental changes are traditionally considered intrinsic in evolutionary dynamic optimization. However, by ignoring that changes can instead be induced, we are ignoring that environmental changes can be eventually beneficial. To investigate the impact of artificial changes on the optimization speed up, we propose a framework for inducing artificial changes in any pseudo-Boolean or continuous optimization in this paper. Seven types of changes can be induced. Knowing when and how the changes occur allows us to design new strategies for evolutionary algorithms. Through computational experiments and illustrative examples, the impact of introducing changes in the optimization process is investigated. Experimental results indicate that changing the environments according to the proposed framework can lead to higher speed up, but not for all problems and change types. The best performance was obtained by change types that introduce plateaus and/or modify the gradient of regions of the fitness landscape around the current best solution. By doing this, the evolutionary dynamics is modified, eventually allowing the population to escape faster from local optima and reach new zones of the fitness landscape. Given a pseudo-Boolean or continuous optimization static problem, the proposed framework can be used to dynamically change the problem to speed up the optimization.
  • A knee-point-based evolutionary algorithm using weighted subpopulation for many-objective optimization
    A knee-point-based evolutionary algorithm using weighted subpopulation for many-objective optimization Zou, Juan; Ji, Chunhui; Yang, Shengxiang; Zhang, Yuping; Zheng, Jinhua; Li, Ke Among many-objective optimization problems (MaOPs), the proportion of nondominated solutions is too large to distinguish among different solutions, which is a great obstacle in the process of solving MaOPs. Thus, this paper proposes an algorithm which uses a weighted subpopulation knee point. The weight is used to divide the whole population into a number of subpopulations, and the knee point of each subpopulation guides other solutions to search. Besides, Additionally, the convergence of the knee point approach can be exploited, and the subpopulation-based approach improves performance by improving the diversity of the evolutionary algorithm. Therefore, these advantages can make the algorithm suitable for solving MaOPs. Experimental results show that the proposed algorithm performs better on most test problems than six other state-of-the-art many-objective evolutionary algorithms. 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.
  • Hybrid of memory andprediction strategies for dynamic multiobjective optimization
    Hybrid of memory andprediction strategies for dynamic multiobjective optimization Liang, Zhengping; Zheng, Shunxiang; Zhu, Zexuan; Yang, Shengxiang Dynamic multiobjective optimization problems (DMOPs) are characterized by a time-variant Pareto optimal front (PF) and/or Pareto optimal set (PS). To handle DMOPs, an algorithm should be able to track the movement of the PF/PS over time efficiently. In this paper, a novel dynamic multiobjective evolutionary algorithm (DMOEA) is proposed for solving DMOPs, which includes a hybrid of memory and prediction strategies (HMPS) and the multiobjective evolutionary algorithm based on decomposition (MOEA/D). In particular, the resultant algorithm (MOEA/D-HMPS) detects environmental changes and identifies the similarity of a change to the historical changes, based on which two different response strategies are applied. If a detected change is dissimilar to any historical changes, a differential prediction based on the previous two consecutive population centers is utilized to relocate the population individuals in the new environment; otherwise, a memory-based technique devised to predict the new locations of the population members is applied. Both response mechanisms mix a portion of existing solutions with randomly generated solutions to alleviate the effect of prediction errors caused by sharp or irregular changes. MOEA/D-HMPS was tested on 14 benchmark problems and compared with state-of-the-art DMOEAs. The experimental results demonstrate the efficiency of MOEA/D-HMPS in solving various DMOPs. 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.

Click here to view a full listing of Shengxiang Yang's publications and outputs.

Research interests/expertise

  • Evolutionary Computation

  • Swarm Intelligence

  • Meta-heuristics

  • Dynamic Optimisation Problems

  • Multi-objective Optimisation Problems

  • Relevant Real-World Applications

Areas of teaching

Research Methods for Intelligent Systems and Robotics MSc, Software Engineering MSc, Computing MSc, and Business Intelligence Systems and Data Mining MSc Degrees.

Qualifications

BSc in Automatic Control, Northeastern University, China (1993)

MSc in Automatic Control, Northeastern University, China (1996)

PhD in Systems Engineering Northeastern University, China (1999)

Courses taught

I have taught numerous modules at both undergraduate and postgraduate level. Quite a number of modules I taught were significantly developed by myself. The modules I taught are usually designed to be practice-oriented with problem-solving lab sessions based on Java or C++ programming, and hence are highly interesting to and greatly useful for students. They are also very important for different degree programmes in Computer Science and relevant subjects. Some of the modules I have taught are listed as follows:

  • CS3002 Artificial Intelligence (2010 – 2012, Brunel University): 3rd year Computer Science (Artificial Intelligence) BSc module, module leader

  • CS2005 Networks and Operating Systems (2010 – 2012, Brunel University): 2nd year Network Computing BSc module, part module

  • CS5518 Business Integration (2011-2012, Brunel University): Business Systems Integration MSc module, part module

  • CO2017 Networks and Distributed Systems (2005–2010, University of Leicester): 2nd year Computer Science BSc module, module leader

  • CO2005 Object-Oriented Programming Using C++ (2006–2009, University of Leicester): 2nd year Computer Science BSc module, module leader

  • CO1003 Program Design (2006-2007, University of Leicester): 1st year Computer Science BSc module, module leader

  • CO3097 Programming Secure and Distributed Systems (2003–2005, University of Leicester): 3rd year Computer Science BSc & Advanced Computer Science MSc module, module leader

  • CO1017 Operating Systems and Networks (2001 – 2004, University of Leicester): 1st year Computer Science BSc module, module leader

  • CO1016 Computer Systems (2000 – 2002, University of Leicester): 1st year Computer Science BSc module, part module

I have also co-ordinated several BSc projects, as shown below.

  • CS3072/CS3074/CS3105/CS3109 BSc Final Year Projects (2010 – 2012, Brunel University): Co-ordination Team Member

  • CO3012/CO3013/CO3015 Computer Science BSc Final Year Projects (2004 – 2010, University of Leicester): Co-ordinator

  • CO3120 Computer Science with Management BSc Final Year Project (2007 – 2010, University of Leicester): Co-ordinator

  • CO3014 Mathematics and Computer Science BSc Final Year Project (2004 – 2010, University of Leicester): Co-ordinator

  • CO2015 Second Year BSc Software Engineering Project (2003 – 2004, University of Leicester): Co-ordinator

Honours and awards

  • Nominatee to the Best Paper Award for EvoApplications 2016: Applications of Evolutionary Computation, for the paper "Direct memory schemes for population-based incremental learning in cyclically changing environments" by Michalis Mavrovouniotis and Shengxiang Yang, published in EvoApplications 2016: Applications of Evolutionary Computation, Lecture Notes in Computer Science, vol. 9598, pp. 233-247, 2016.

  • Nominatee for the Best-Paper Award of the ACO-SI Track at the 2015 Genetic and Evolutionary Computation Conference, for the paper "An ant colony optimization based memetic algorithm for the dynamic travelling salesman problem" by Michalis Mavrovouniotis, Felipe Martins Muller and Shengxiang Yang, published in the Proceedings of the 17th Annual Conference on Genetic and Evolutionary Computation, pp. 49-56, 2015.

  • Winner of the 2014 IEEE Congress on Evolutionary Computation Best Student Paper Award, for the paper entitled "A test problem for visual investigation of high-dimensional multi-objective search" by Miqing Li, Shengxiang Yang and Xiaohui Liu, published in the Proceedings of the 2014 IEEE Congress on Evolutionary Computation, pp. 2140-2147, 2014.

  • Nominatee for the 2005 Genetic and Evolutionary Computation Conference Best Paper Award, for the paper "Memory-based immigrants for genetic algorithms in dynamic environments" by Shengxiang Yang, published in the Proceedings of the 2005 Genetic and Evolutionary Computation Conference, Vol. 2, pp. 1115-1122, 2005.

  • Visiting Professor (2012 – 2014, 2016-2018), College of Information Engineering, Xiangtan University, China

  • Visiting Professor (2011 – 2017), College of Mathematics and Statistics, Nanjing University of Information Science and Technology, China

Membership of professional associations and societies

  • Founding Chair, Task Force on Intelligent Network Systems (TF-INS), Intelligent Systems Applications Technical Committee (ISATC), IEEE Computational Intelligence Society (IEEE CIS), 2012–2018.

  • Chair, Task Force on Evolutionary Computation in Dynamic and Uncertain Environments (ECiDUE), Evolutionary Computation Technical Committee (ECTC), IEEE Computational Intelligence Society (IEEE CIS), 2011–2018.

  • Senior Member, IEEE, since 2014.

  • Member, IEEE, 2000 – 2013.

  • Member, IEEE Computational Intelligence Society (IEEE CIS), since 2005.

  • Member, Evolutionary Computation Technical Committee (ECTC), IEEE Computational Intelligence Society (IEEE CIS), since 2011.

  • Member, Intelligent Systems Applications Technical Committee (ISATC), IEEE Computational Intelligence Society (IEEE CIS), since 2013.

  • Member, Task Force on Evolutionary Computation in Dynamic and Uncertain Environments (ECiDUE), Evolutionary Computation Technical Committee (ECTC), IEEE Computational Intelligence Society (IEEE CIS), 2003 – 2010.

Current research students

First Supervisor:

  • Muhanad Tahrir Younis: Swarm intelligence for dynamic job scheduling in grid computing, started from October 2014

  • Conor Fahy: Evolutionary computation for data stream analysis, started from October 2015

  • Zedong Zheng: started from October 2016
  • Matthew Fox: started from October 2017

Second Supervisor:

  • Ahad Arshad: PhD candidate, co-supervised with Prof. Paul Fleming at De Montfort University, started in October 2017.
  • William Lawrence: PhD candidate, co-supervised with Dr. Mario Gongora at De Montfort University, started in April 2012

Complete PhD Students (I was the 1st Supervisor):

  • Changhe Li: Particle swarm optimisation in stationary and dynamic environments, 2011

  • Imtiaz Ali Korejo: Adaptive mutation operators for evolutionary algorithms, 2011

  • Sadaf Naseem Jat: Genetic algorithms for university course timetabling problems, 2012

  • Shakeel Arshad: Sequence based memetic algorithms for static and dynamic travelling salesman problems, 2012

  • Michalis Mavrovouniotis: Ant Colony Optimization in Stationary and Dynamic Environments, 2013

  •  Miqing Li: Evolutionary Many-Objective Optimization: Pushing the Boundaries, 2015
  • Jayne Eaton: Ant Colony Optimisation for Dynamic and Dynamic Multi-objective Railway Rescheduling Problems, 2017
  • Shouyong Jiang: Evolutionary Algorithms for Static and Dynamic Multiobjective Optimization, 2017

Externally funded research grants information

  • EU Horizon 2020 Marie Sklodowska-Curie Individual Fellowships (PI, Project ID: 661327, 09/2015-08/2017, €195,455): Evolutionary Computation for Dynamic Constrained Optimization Problems (ECDCOP)
  • EPSRC (PI, Standard Research Project, EP/K001310/1, 18/2/2013-17/02/2017, £445,069): Evolutionary Computation for Dynamic Optimisation in Network Environments

  • EPSRC (PI, Standard Research Project, EP/E060722/1 and EP/E060722/2, 1/1/2008-1/7/2011, £307,469): Evolutionary Algorithms for Dynamic Optimisation Problems: Design, Analysis and Applications

  • EPSRC (PI, Overseas Travel Grants GR/S79718/01, 1/11/2003-31/1/2004, £6,700): Adaptive and Hybrid Genetic Algorithms for Production Scheduling Problems in Manufacturing. This grant supported my research visit to Waseda University, Japan, during my Sabbatical leave period. Additionally, Waseda University, Japan contributed JPY140,000 (~£800) toward the visit

  • State Key Laboratory of Synthetical Automation of Process Industry, Northeastern University, China (PI, Open Research Project, 1/1/2012-31/12/2013, CNY300,000 (~£30,000)): Evolutionary Computation for Dynamic Scheduling Problems in Process Industries

  • State Key Laboratory of Synthetical Automation of Process Industry, Northeastern University, China (PI, Open Research Project, 1/1/2010-31/12/2011, CNY150,000 (~£15,000)): Evolutionary Computation for Dynamic Optimization and Scheduling Problems

  • Transport iNet, European Regional Development Fund (Co-I, 11/11/2013 - 28/02/2015, £62,134), Evolutionary Computation for Optimised Rail Travel (EsCORT). This is a linked project between De Montfort University and Go Travel Solutions, a Leicester based SME specialising in assisting businesses to develop sustainable travel solutions, covering people and goods.
  • Hong Kong Polytechnic University Research Grants (Co-I, Grant G-YH60, 1/7/2009-30/6/2010, HKD120,000 (~£10,000)): Improved Evolutionary Algorithms with Primal-Dual Population for Dynamic Variation in Production Systems. Partners:

In addition, I have also received several conference travel grants from UK Research Councils, e.g., Royal Society Conference Travel Grant (£700 in 2007 and £719 in 2005) and Royal Academy of Engineering Conference Grant (£800 in 2007 and £1,200 in 2006).

Internally funded research project information

  • De Montfort University Higher Education Innovation Fund (HEIF) 2017-18 (Co-I, 01/12/2017-31/07/2018, £14,000): Brian-Computer-Interface Prototyping System: Data-based Filtering and Dynamic Characterisation.
  • De Montfort University Higher Education Innovation Fund (HEIF) 2015-16 (PI, 01/01/2016-31/07/2016, £24,800): Development of a Dynamic Resource Scheduling Prototype System for Airports.

  • De Montfort University PhD Studentships 2017-18 (PI, 1/10/2017–30/09/2020, approximately £60,000): supporting stipend and fees for one EU/Home PhD student for three years

  • De Montfort University Fee Waiver PhD Scholarships 2016-17 (PI, 1/10/2016–30/09/2019, approximately £40,000): supporting fees for one overseas PhD student for three years

  • De Montfort University PhD Studentships 2015-16 (PI, 1/10/2015–30/09/2018, approximately £60,000): supporting stipend and fees for one EU/Home PhD student for three years

  • De Montfort University PhD Studentships 2013-14 (PI, 1/10/2013–30/09/2016, approximately £80,000): supporting stipend and fees for one overseas PhD student for three years

  • De Montfort University PhD Studentships 2013-14 (PI, 1/4/2013–31/03/2016, approximately £60,000): supporting stipend and fees for one home PhD student for three years

  • Brunel University PhD Studentships 2011-12 (PI, 01/10/2011–30/09/2014, approximately £80,000): supporting stipend and fees for one overseas PhD student for three years

  • University of Leicester PhD Studentships 2008-09 (PI, 1/10/2008–30/9/2011, approximately £50,000): supporting stipend and fees for one PhD student for three years

  • University of Leicester Research Fund 2001 (PI, 1/1/2001- 31/12/2001, £3,200): Using Neural Network and Genetic Algorithm Methods for Job-Shop Scheduling Problem.

Professional esteem indicators

Shengxiang-Yang

Search Who's Who

 

 
News target area image
News

DMU is a dynamic university, read about what we have been up to in our latest news section.

Events target area image
Events

At DMU there is always something to do or see, check out our events for yourself.

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.