Professor Ivan Jordanov
Biography
I am a Professor of Computational Intelligence at the School of Computing. I have a PhD in Computer Aided Optimization, MSc in Applied Mathematics and Informatics from the Technical University of Sofia; and BSc in Mechanical and Electrical Engineering from the Naval University, Bulgaria.
I joined the University of Portsmouth in 2003 after 3 years with De Montfort University as a Senior Lecturer; 2 years with the University of Wales Institute, Cardiff as a Senior Researcher; and 16 years with the Technical University Sofia as Associate Professor.
Research interests
Computational Intelligence (Machine Learning, Deep Learning, Neural Networks, Data Analytics, and Heuristic Global Optimisation)
My current research interest includes all aspects of analysis, design, modelling and investigation of supervised and unsupervised Machine Learning paradigms. These comprise designing, developing and proposing classical and deep learning neural network architectures (Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) neural networks, self-attentive NNs), applied for solving real world image, time series, and pattern recognition, identification, and classification problems, based on large and big data sets. For example, I am a PI of a just successfuly completed 3-year (2021-2024) EPSRC EP-V002511-1 project “Deep Learning Models for Fetal Monitoring and Decision Support in Labour”, a collaboration with Oxford University and Oxford NHS Trust (total cost: £762k (£610k funded by EPSRC)). Other my projects include: UK Space Agency, UNITAR and UNOSAT “Common Sensing: Work Package 350: Climate-related hazards”; Expedia Inc. “Distributed Neural Networks for Missing Big Data Imputation”; SBRI “Deep Learning for Firearm Detection from X-ray Images”; DSTL/CDE “Neural Networks Generic Radar Signals Identification and Classification”, EPSRC (GR/S01702/01) "Investigation of Intelligent Techniques for Interpreting Freeform Surfaces from On-line Sketching"; NATO Science and Cooperation “Intelligent Techniques in Computer Graphics and Visualisation”; UNIDO “Optimization Techniques in Computer Graphics and CAD”; ROYAL SOCIETY Research Fellowship; RAE Distinguished Visiting Fellowship (as a host), and others.
My research in Data Analytics area is related to statistical pre-processing, dimensionality reduction and discrimination (PCA, ICA, LDA, etc.), dealing with missingness and data imputation methods, imbalanced datasets, data augmentation, etc.
My earlier research in Global Optimization field includes investigation of evolutionary techniques and heuristic approaches based on so-called Low Discrepancy Sequences, applied for combinatorial and global search optimization problems.
Research outputs
2024
A deeper look into remote sensing scene image misclassification by CNNs
Balarabe, A. T., Jordanov, I.
16 Jan 2024, In: IEEE Access, 21p.
2023
Multimodal deep learning for predicting adverse birth outcomes based on early labour data
Asfaw, D., Georgieva, A., Impey, L., Jordanov, I., Lee, R., Namburete, A.
19 Jun 2023, In: Bioengineering. 10, 6, 17p., 730