Lyudmila Mihaylova, PhD
Professor of Signal Processing and Control
Dr Lyudmila Mihaylova MEng, SM IEEE
Professor of Signal Processing and Control
Department of Automatic Control and Systems Engineering
University of Sheffield
Tel: (+44) (0)114 222 5675
Email: L.S.Mihaylova@sheffield.ac.uk, firstname.lastname@example.org
Prof. Lyudmila Mihaylova and her team are working to develop novel methods for autonomous intelligent systems: for sensing, tracking and decision making, machine learning and their engineering applications. Prof. Mihaylova undertook pioneering work on traffic flow estimation with particle filtering for intelligent transportation systems which was followed later with developments for large scale systems, including large scale transportation and video processing systems. She has experience with a range of image modalities, including optical, thermal, LIDAR, SAR and hyperspectral image processing. Previously she had academic positions with Lancaster University (2006-2013), University of Bristol (2004-2006), and research visiting positions with the University of Ghent, Belgium, the Katholic University of Leuven, Belgium and the Bulgarian Academy of Sciences, Bulgaria. Her interests are in the area of nonlinear filtering, sequential Monte Carlo Methods, statistical signal processing and sensor data fusion. Her work involves the development of novel techniques, e.g. for high dimensional problems (including vehicular traffic flow estimation and image processing) and localisation and positioning in sensor networks. Prof. Mihaylova is an Associate Editor of the IEEE Transactions on Aerospace and Electronic Systems and an Associate Editor of Elsevier Signal Processing Journal. Prof. Mihaylova is a senior member of the IEEE, Signal Processing Society, the President of the International Society of Information Fusion (ISIF) and an ISIF board member.
Prof. Mihaylova has also been serving the scientific community as a member of the Programme/ Organising Committee of international conferences and symposia, including the International Conferences on Information Fusion, the American Control Conferences, EUSIPCO, conferences on Intelligent Transportation Systems and the German workshops on Multiple Sensor Data Fusion. She has given a number of invited talks, e.g. the keynote speech for the 5th IET International Conference on Wireless, Mobile and Multimedia Networks (2013), Beijing, China, and tutorials including for the EU Marie Curie ITN (2010, Sweden, 2012, Germany) and COST-NEARCTIS workshop (2010, Switzerland). Her research is funded by sponsors such as EPSRC, EU, MOD and industry.
Broad research in the areas of signal processing, Bayesian methods, Monte Carlo methods, nonlinear estimation, target tracking, sensor data fusion, control, autonomous and complex systems (e.g. image and video processing, transportation systems, large scale systems) – both at theoretical and applied level. Assisted living and eHealth systems is another application area of my research.
My Research Group
We share knowledge, we grow. We actively work as a team.
- Peng Wang, Efficient Methods for Dealing with Big Data and Complex Large Scale Systems, funded by the CSI-Cobot and ShiRAS projects
- Zhenglin Li, Machine Learning and IoT Methods for Automated Analysis of Medical Data, funded by the IoT4Healthy Sleep Pitch-In project
- Waqas Aftab, Machine Learning Methods for CCTV Surveillance, funded by the In2Stempo project
- James Douthwaite, Cooperative Robot Manufacturing, funded by the CSI-Cobot project
- Fodio Longman, Machine Learning Methods for Oil Spill Segmentation in Remote Sensing Images, revising the thesis, after a PhD viva, minor corrections
- Kennedy Offor, Sensor Data Fusion for Improving Traffic Mobility in Smart Cities, PhD viva soon
- Mahed Javed, Deep Learning Methods for Detection and Classification, a 3rd year PhD student
- Richard Rudd-Orthne, Artificial Intelligence Methods to Mission Critical Systems and Automated Threat Analysis, second year PhD student
- Yueda Lin, Machine Learning Methods for Autonomous Systems, start in September 2018
- Yifei Zhu, Machine Learning Methods for Autonomous Systems, start in September 2018
- Fethi Candan, Methods for Coordination and Control of a Swarm of UAVs, Start in September 2019
- Rui Zhang, Simultaneous Localisation and Mapping of PipeBots for Pipe Networks, Start in November 2019
- Jingxuan Su, Machine Learning Methods for Smart Farms, Start in November 2019
- Rohit Chakraborty, Methods for Air Pollution Monitoring and Prediction, co-supervised with Prof. Martin Mayfield and Prof Tony Ryan, Start in October 2018
- Brian Peach, Data Mining for Intelligent Transport Road Networks, co-supervised with Prof. Gwilym Pryce and Dr Mauricio Alvarez
Alumni from Sheffield
- Hayder Amer, Novel Internet of Vehicles Approaches for Smart Cities, PhD in July 2019
- Danil Kuzin, Sparse Machine Learning Methods for Autonomous Decision Making, PhD degree, March, 2019
- Maria Luisa Davila Garcia, Image Processing Methods for Automatic in-vitro Morphology Analysis, PhD degree, December, 2018
- Chao Liu, Dealing with Incomplete Data for Localisation in Complex Envoronments, PhD degree, October 2018
- Ruilong Chen, Machine Learning Methods for Autonomous Object Recognition and Restoration in Images, PhD degree, September 2018
- Aroland Kiring, Shrinkage Based Particle Filters for Tracking in Wireless Sensor Networks with Correlated Sparse Measurements, 2014-2018, PhD degree, April 2018
- Olga Isupova, Machine Learning Methods for Behaviour Analysis in Video, funded by the EU Marie Curie TRAX project, 2014-2017, PhD in August 2017
- Allan de Freitas, Sequential Monte Carlo Methods for Tracking Groups an Extended Objects in Complex Environments, funded by the EU Marie Curie TRAX project, 2014-2017, PhD in July 2017
- Youngjoo Kim, Efficient Methods for Dealing with Big Data and Complex Large Scale Systems, Postdoctoral researcher from June 2018 till February 2019
- Matthew Hawes, Efficient Methods for Dealing with Big Data, funded by the BTaToT and EU SETA projects, Postdoctoral researcher, Sept. 2014 - Dec. 2017
- Naveed Salman, Postdoctoral researcher, May 2014 - June 2016
- Atta ur-Rehman, Postdoctoral researcher, Dec. 2013 - Jan. 2016, now Assistant Professor at the at University of Engineering and Technology, Lahore, Pakistan
- Nikolay Petrov, PhD student (2009-2013) and Postdoctoral researcher, August 2013 - August 2014
Other graduated PhD students
- Nickolay Petrov, Anna Zvikhachevskaya, Mahsa Honary, Chris Nemeth, Ali Arshad, Dennis Rodionov
I am grateful to the sponsors of my research: EPSRC, MoD/DSTL, EU, industrial and other partners. A brief description of projects of mine is given below.
- NSF-EPSRC: ShiRAS. Towards Safe and Reliable Autonomy in Sensor Driven Systems, EP/T013265/1, PI, 2019-2022, £220,246. Modern data-driven algorithms trained over enormous datasets have revolutionised contemporary autonomous systems with their accurate predictive power. However, due to technical limitations, it is a challenge to integrate large-scale data from many different and complex sensors. Capturing the confidence of these algorithms also remains a challenge. In response to this demand, ShiRAS will develop pioneering approaches that will introduce autonomy at different levels in sensor-driven systems. The main focus is on machine learning methods with quantified uncertainty of the provided solutions. Within the field of machine learning, deep learning approaches have resulted in the state-of-the-art accuracy in visual object detection, speech recognition and translation, and many other domains. Deep learning can discover intricate structure in large data sets by using multiple levels of representation, where each level is a higher, more abstract representation of the data. However, a rigorous mathematical framework for uncertainty propagation and update in machine learning models has been largely underexplored. Most current deep learning techniques process the raw data in a deterministic way and do not capture model confidence or trust. Uncertainty can emanate from the noise in the raw data and the parameters of the approach and this impact is a critical part for any predictive system's output. By representing the unknown parameters using distributions instead of point estimates and propagating these distributions from the input to the output of the system, we propose promising machine learning methods able to handle uncertainty in a unified way.
- Confident safety integration for Cobots (CSI: Cobot), 2019-2020, funded by Lloyd's Register Foundation, co-I, PI Dr James Law, jointly with other co-Is Prof. John Clark, Dr Jonathan Aitken, Dr Radu Calinescu (University of York) and Dr Rob Alexander (University of York). This project will demonstrate how novel safety techniques can be applied to build confidence in the deployment of uncaged collaborative robot systems operating in spaces shared with users. Existing collaborative processes provided by our industrial partners will act as case studies and demonstrators. These vary in complexity, but are suitably constrained in that they provide a tractable safety problem whilst providing a good representation of current industry applications and needs.
- Internet of Things for Healthy Sleep, Pitch-In project (Oct. 2019-May 2020), PI, with Dr Mahnaz Arvaneh, co-I, £60,000. This is a joint project with the University of Oxford and Sheffield Teaching Hospital.
- Internet of Things for Overcome Barriers in the Steel Rolling Measurement Technology, Knowledge Exchange project (Feb.- Oct. 2019), PI, co-Is Dr Peng Wang and Dr Mahnaz Arvaneh, £42,000
Recently Completed Projects
- SETA: An open, sustainable, ubiquitous data and service ecosystem for efficient, effective, safe, resilient mobility in metropolitan areas, 5.2 million euro Horizon 2020 project, 2016-2019, co-I, jointly with Fabio Ciravegnia, PI, (2016-2019). SETA created technology and methodology for changing the way mobility is organised, monitored and planned in large metropolitan areas. The solutions focused on the management of high-volume, high-velocity, multi-dimensional, heterogeneous, cross-media, cross-sectoral data and information which is sensed, crowdsourced, acquired, linked, fused, and used to model mobility with a precision, granularity and dynamicity that is impossible with today’s technologies. Such models provide always-on, pervasive services to citizens and business, as well as decision makers to support safe, sustainable, effective, efficient and resilient mobility. The consortium involves partners from 5 countries, UK, Italy, Spain, Poland and The Netherlands. Funded by EU, the project partners are University of Sheffield (Lead), Delft University (NL), University of Cantabria (Spain), Sheffield Hallam University (UK), Knowledge now Limited (UK), The FLOOW Limited (UK), TSS-TRANSPORT SIMULATION SYSTEMS SL (Spain), Software Mind SA (Poland), AIZOON Consulting SRL (Italy), AYUNTAMIENTO DE SANTANDER (Spain), Citta di Torino (Italy), Birmingham City Council, Scyfer B.V. (NL).
- Mobility grant with China, funded by the Royal Academy of Engineering 1 April 2016 - 31 March 2018, £9,500.
- TRAX : TRAcking in compleX sensor systems, EU FP7 Marie Curie project, €609,981 (2013-2017)
- The TRAX research project is an International Training Network (ITN) sponsored by the EU under the Marie Curie actions in the Seventh Framework Program (FP7). TRAX concentrates on Tracking in Complex Sensor Systems, focussing on complexities due to large volumes of data, complex object dynamics and measurement models, as well as large scale systems. The project partners are a well-known and well-respected mixture of academia, research institutes, small and large business companies, including University of Sheffield and Rinicom from the United Kingdom, Linköping University and Ericsson from Sweden, Fraunhofer FKIE from Germany, and University of Twente, Xsens and Thales from The Netherlands.
- Remote Sensing for Hedgerow Assessment in Agricultural Areas, Grantham centre grant (March-July 2017), £9,567. There is an imminent necessity to help analyse data of many types in automated and semi-automated manners, especially multispectral, hyperspectral, thermal, ISAR and LiDAR data. This project aims to ensemble methods for imagery data to support analysis of hedgerows in agricultural areas by synthesising data from multiple sources.
- BTaRoT: Bayesian Tracking and Reasoning over Time , £446,037, EP/K021516/1, EPSRC funded (2013-2016)
This EPSRC funded project provided new advances in methods for reasoning about many objects that evolve in a scene over time. Information about such objects arrives, typically in a real-time data feed, from sensors such as radar, sonar, LIDAR and video. The Bayesian methodology is adopted due to its power to solve a wealth of complex inference problems, to take into account prior information and to incorporate it in flexible manners in the solutions. The main focus is on scalable approaches able to deal both with groups composed of a small number of objects (up to 20) and large groups, consisting of hundreds Partners for the project: Prof. Simon Godsill, Dr Sumeetpal S. Singh from Cambridge University and supported by QinetiQ.
- Information Fusion: Framework Architectures for Dynamic Heterogeneous Information Fusion, Funded by Sellex Gallileo, £111,000 (2012-2014) This project focuses on extracting knowledge from large amounts of data and fusion methods related with tracking and behavior analysis. The main approach is based on combinatorial pattern matching and statistical data mining methods. The project is part of the Centres of Excellence funded by Selex Gallileo and comprises Aberdeen University, Cambridge University, Cranfield University, University of Sheffield, Lancaster University, and Robert Gordon University.
- EU FP7 Marie Curie Initial Training Network project: MC Impulse (“Monte Carlo Based Innovative Management and Processing for an Unrivalled Leap in Sensor Exploitation”), Dec. 2009 - Dec. 2013 (€400,000).
- Object Tracking over Sensor Networks, EP/E027253/1, £228,883, 2007-2010
- Object Tracking over Sensor Networks - Pathway to Impact, August 2010 - March 2011, EPSRC (£4,795)
For a current list of PhD projects related to my areas of research please see the PhD Research Projects web pages. The Figures below show results from the methods and technique developed by me and my team.
Localisation and Positioning in Wireless Sensor Networks
Target Tracking in Sensor Networks and Sensor Data Fusion
Sensor Data Fusion
Extended Object Tracking in Sensor Networks
Contour Segmentation for Medical Diagnostics
Modelling, and Estimation Methods for Intelligent Transportation Systems
- AER324 Aircraft Dynamics and Control
- ACS6123 Intelligent and Vision Systems
- ACS402 Industrial Training Program in Avionics and Autonomous Systems
Some Recent Invited Talks
- Plenary talk at the "First Joint International Conference on Design and Construction of Smart Cities Components", , Cairo, Egypt, 17-19 December 2019
- Invited speaker, Science and Technology Organisation Specialists’ Meeting on “Artificial Intelligence for Military Multisensor Fusion Engines NATO-SET-262, 5-6 November 2018, Budapest, Hungary
- Invited speaker, Northwestern Polytechnical University, Xi'an, and Chongqing University of Post and Telecommunications, China, July, 2017
- Invited speaker, the 4th International Conference on Control Engineering & Information Technology (CEIT-2016)
- Invited speaker for the Advances and Innovations on Traffic Modeling and Control, Control Summer School of GIPSA-Lab, CNRS, 12-16 Sept 2016, Grenoble, France
- Invited talk at the Allan Turing Scoping Workshop: "Recursive Bayesian Estimation with Big Data", 10-12 February 2016, British Library, London
- Invited talks for the "Advances and Innovations on Traffic Modeling and Control", Control Summer School of GIPSA-Lab, CNRS, 12-16 Sept 2016, Grenoble, France
- Invited talk: "Sequential Monte Carlo Methods for Tracking and Inference in Intelligent Transportation Systems", Institute of Pure and Applied Mathematics (IPAM) Workshop II: Traffic Estimation, University of California, UCLA, Los Angeles, October 12 - 16, 2015
- Plenary talk: "Recent Advances in Bayesian Methods for Tracking Groups, Extended Objects and Challenges with Big Data", IEEE Sensor Data Fusion Workshop, 6-8 October, Bonn, Germany 2015.
- Invited Talk: "Machine Learning for Autonomous Systems and Knowledge Extraction from Big Data", Queen Mary University of London, UK, 23 Oct 2014
- Plenary talk: "Advances and Challenges to Localisation in Wireless Sensor Networks'', The IET 5th International Conference on Wireless, Mobile and Multimedia Networks, (ICWMMN2013), Beijing, China, Nov. 22-25, 2013.
- Invited talk: "Modelling, Estimation and Control for Intelligent Transportation Systems'', Jiatong University, Beijing, China, 25 November 2013.
- Member, EPSRC Peer Review College, 2012 –
- Elected as the president of the International Society of Information Fusion in March 2016, On the Board of Directors of ISIF, since 2011
- Associate Editor for the IEEE Transactions on Aerospace and Electronic Systems, since 2011
- Associate Editor of Elsevier Signal Processing Journal, since 2008
- On the Editorial Board of Intelligent Decision Technologies. An International Journal, from 2011
- Associate Editor for the IEEE Intelligent Transportation Systems Conference, Washington DC, USA, Oct. 5-7, 2011
- Associate Editor for the American Control Conferences, since 2008 till present
- Senior Member of the IEEE, Signal Processing Society
- Member of the British Machine Vision Association (BMVA)
- Member of the International Society of Information Fusion (ISIF)
- O. Isupova, D. Kuzin, L. Mihaylova, Dynamic Hierarchical Dirichlet Process for Anomaly Detection in Video
- A. de Fretias, L. Mihaylova, Algorithms and models for autonomous crowds tracking with box particle filtering and convolution particle filtering
- M. Hawes, Compressive Sensing Based Design of Sparse Tripole Arrays
- M. Hawes, L. Mihaylova, Signal Model for Bayesian Compressive Sensing Approaches
- L. Mihaylova et al., Programs for mobility tracking and group object tracking
- A. Y. Carmi, L. Mihaylova, S. J. Godsill (Editors), Compressed Sensing and Sparse Filtering, Series Signals and Communication Technology, Springer, Berlin Heidelberg, ISBN 978-3-642- 38397-7, 2014.
- P. Georgieva, L. Mihaylova, L. Jain (Editors), Advances in Intelligent Signal Processing and Data Mining: Principles and Applications (Studies in Computational Intelligence) , Springer, Berlin Heidelberg, Vol. 410, Jan. 2013, ISSN 1860-949X, ISBN 978-3-642-28695- 7.
- A Box Particle Filter Method for Tracking Multiple Extended Objects. IEEE Transactions on Aerospace and Electronic Systems. View this article in WRRO
- Gradient Based Sequential Markov Chain Monte Carlo for Multi-target Tracking with Correlated Measurements. IEEE Transactions on Signal and Information Processing over Networks, 4(3), 510-518. View this article in WRRO
- Reliable non-linear state estimation involving time uncertainties. Automatica, 93, 379-388. View this article in WRRO
- Spatio-Temporal Structured Sparse Regression With Hierarchical Gaussian Process Priors. IEEE Transactions on Signal Processing, 66(17), 4598-4611. View this article in WRRO
- Autonomous Flame Detection in Videos with a Dirichlet Process Gaussian Mixture Color Model. IEEE Transactions on Industrial Informatics, 14(3), 1146-1154. View this article in WRRO
- Motion anomaly detection and trajectory analysis in visual surveillance. Multimedia Tools and Applications. View this article in WRRO
- Learning Methods for Dynamic Topic Modeling in Automated Behavior Analysis. IEEE Transactions on Neural Networks and Learning Systems, 29(9), 3980-3993. View this article in WRRO
- Optimization-Based Hybrid Congestion Alleviation for 6LoWPAN Networks. IEEE Internet of Things Journal, 4(6), 2070-2081. View this article in WRRO
- Guaranteed computation of robot trajectories. Robotics and Autonomous Systems, 93, 76-84. View this article in WRRO
- Location and Orientation Optimisation for Spatially Stretched Tripole Arrays Based on Compressive Sensing. IEEE Transactions on Signal Processing, 65(9), 2411-2420. View this article in WRRO
- Tracking with Sparse and Correlated Measurements via a Shrinkage-based Particle Filter. IEEE Sensors Journal, 17(10), 3152-3164. View this article in WRRO
- Bayesian Compressive Sensing Approaches for Direction of Arrival Estimation with Mutual Coupling Effects. IEEE Transactions on Antennas and Propagation, 65(3), 1357-1368. View this article in WRRO
- Overview of Environment Perception for Intelligent Vehicles. IEEE Transactions on Intelligent Transportation Systems, 18(10), 2584-2601. View this article in WRRO
- Particle Approximations of the Score and Observed Information Matrix for Parameter Estimation in State Space Models With Linear Computational Cost. Journal of Computational and Graphical Statistics, 25(4), 1138-1157. View this article in WRRO
- Localisation of Sensor Nodes with Hybrid Measurements in Wireless Sensor Networks. Sensors. View this article in WRRO
- Location Prediction Optimisation in Wireless Sensor Networks Using Kriging Interpolation. IET Wireless Sensor Systems, 6(3), 74-81. View this article in WRRO
- Autonomous crowds tracking with box particle filtering and convolution particle filtering. Automatica, 69, 380-394. View this article in WRRO
- An Improved Simulated Annealing Technique for Enhanced Mobility in Smart Cities. Sensors, 16(7), 1-23. View this article in WRRO
- A Beamformer-Particle Filter Framework for Localization of Correlated EEG Sources. IEEE Journal of Biomedical and Health Informatics. View this article in WRRO
- Subgradient-based Markov Chain Monte Carlo particle methods for discrete-time nonlinear filtering. Signal Processing, 120, 532-536. View this article in WRRO
- Compressive sensing based design of sparse tripole arrays. Sensors (Switzerland), 15(12), 31056-31068. View this article in WRRO
- Multi-Target Tracking and Occlusion Handling with Learned Variational Bayesian Clusters and a Social Force Model. IEEE Transactions on Signal Processing, 64(5), 1320-1335. View this article in WRRO
- Autonomous detection and tracking under illumination changes, occlusions and moving camera. SIGNAL PROCESSING, 117, 343-354. View this article in WRRO
- Box-Particle Probability Hypothesis Density Filtering. IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 50(3), 1660-1672. View this article in WRRO
- Overview of Bayesian sequential Monte Carlo methods for group and extended object tracking. DIGITAL SIGNAL PROCESSING, 25, 1-16. View this article in WRRO
- Introduction to Compressed Sensing and Sparse Filtering, 1-23.
- Sequential Monte Carlo Methods for State and Parameter Estimation in Abruptly Changing Environments. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 62(5), 1245-1255. View this article in WRRO
- Probability hypothesis density filtering for real-time traffic state estimation and prediction. Networks and Heterogeneous Media, 8(3), 825-842. View this article in WRRO
- An introduction to box particle filtering [lecture notes]. IEEE Signal Processing Magazine, 30(4), 166-171. View this article in WRRO
- Bernoulli particle/box-particle filters for detection and tracking in the presence of triple measurement uncertainty. IEEE Transactions on Signal Processing, 60(5), 2138-2151. View this article in WRRO
- Parallelized particle and Gaussian sum particle filters for large-scale freeway traffic systems. IEEE Transactions on Intelligent Transportation Systems, 13(1), 36-48. View this article in WRRO
- Video Distribution Techniques Over WiMAX Networks for m-Health Applications. IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, 16(1), 24-30.
- Contour segmentation in 2D ultrasound medical images with particle filtering. MACHINE VISION AND APPLICATIONS, 22(3), 551-561. View this article in WRRO
- Group Object Structure and State Estimation With Evolving Networks and Monte Carlo Methods. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 59(4), 1383-1396. View this article in WRRO
- Localization of Mobile Nodes in Wireless Networks with Correlated in Time Measurement Noise. IEEE TRANSACTIONS ON MOBILE COMPUTING, 10(1), 44-53. View this article in WRRO
- Mobility tracking in cellular networks using particle filtering. IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 6(10), 3589-3599.
- Sequential Monte Carlo tracking by fusing multiple cues in video sequences. IMAGE AND VISION COMPUTING, 25(8), 1217-1227.
- Freeway traffic estimation within particle filtering framework. AUTOMATICA, 43(2), 290-300. View this article in WRRO
- A compositional stochastic model for real time freeway traffic simulation. TRANSPORTATION RESEARCH PART B-METHODOLOGICAL, 40(4), 319-334. View this article in WRRO
- A multisine approach for trajectory optimization based on information gain. Robotics and Autonomous Systems, 43(4), 231-243.
- Localisation of an Unknown Number of Land Mines Using a Network of Vapour Detectors. Sensors, 14(11), 21000-21022. View this article in WRRO