Skip to content

Yuan Shen

Computer Science


Yuan Shen is an Independent Research Fellow at the Department of Computer Science of the School of Science and Technology. He is also the tutor of Machine Learning for Data Analytics for Year 2 students, as well as the tutor of Machine Learning for Data Analytics for apprenticeship students.

Career overview

Yuan Shen obtained his diploma and PhD degrees in Physics at the University of Zurich (Switzerland).

After completing his study in Physics, he moved on to receive research training in the area of Computational Statistics and Machine Learning at the University of Warwick, Aston University, and the University of Birmingham.

Since 2017, he has taken Teaching and Research academic positions, first as Lecturer at Xi'an JiaotongLiverpool University and now as Independent Research Fellow at Nottingham Trent University.

Research areas

  1. Machine Learning for Signal Processing (MLSP)
    1. Time-series Data Analysis with Bayesian Inference in Dynamical Systems;
    2. Spatio-temporal Data Analysis with Hierarchical Probabilistic Models;
    3. Classification of Spatial and/or temporal Data with Learning in Model Space;
    4. Big Data Analytics by Deep Neural Networks and Higher-order Tensor Factorisation
  2. MLSP for Healthcare
    1. Imaging Data Analytics:
      1. Brain imaging data in various conditions (fMRI in cognitive learning and/or dementia; EEG in sleep and/or epilepsy; PET in epilepsy);
      2. Multi-spectral imaging data in various conditions (retinal imaging in Age-related Macular Degeneration)
    2. Omics Data Analytics
      1. Genomics data in various conditions (e.g. gene expression data in breast cancer)
      2. Metabolomics data in various conditions (e.g.  dialysis LC-MS data in Cushing's disease)

Postdoctoral Research Training

  1. Markov Chain Monte Carlo for Models in Stochastic Geometry (an EPSRC project led by Dr Thonnes at The University of Warwick);
  2. Variational Inference in Stochastic Dynamic Models (an EPSRC project led by Dr Cornford at Aston University);
  3. Multispectral Retinal Image Analysis: A new technique for the assessment of Age-related Macular Degeneration (a Dunhill Medical Trust project led by Dr Styles at The University of Birmingham)
  4. Unified probabilistic modelling of adaptive spatial-temporal structure in the human brain (a BBSRC project led by Prof Tino at The University of Birmingham);
  5. Personalised medicine through learning in the model space (an EPSRC project led by Prof Tino at The University of Birmingham).

Student Supervision

  1. PhD student projects
    • Nahed Alowadi (completed in 2018) – Population-level spatiotemporal probabilistic modeling of fMRI data (Co-supervision with 25% capacity, Director of the study is Prof Peter Tino at the School of Computer Science of The University of Birmingham)
    • Hanin Alahmadi (completed in 2019) – Efficient Feature Extraction Methods for High-order Tensor Data (Co-supervision with 25% capacity, Director of study is Prof Peter Tino at the School of Computer Science of The University of Birmingham);
    • Gulrukh Turabee (October 2020 - ) – Application of Transfer Learning and Few-shot Learning in Epilepsy EEG Data Analytics (Director of the study);
  2. MSc/MRes student projects
    • Gulrukh Turabee (completed in 2019) – Classification of all-night  EEG data for predicting sleep stages: a deep learning approach (Co-supervision with 50% capacity at Nottingham Trent University)
    • Ruchi Bharat Patel (completed in 2020) – Unsupervised feature selection for identification of bio-marker genes: a deep learning approach (Nottingham Trent University);
  3. FYP student projects
    • Shengjie Sun (completed in 2018) – Efficient Markov Chain Monte Carlo Algorithms for Bayesian Inference in Dynamical Systems (Supervision at XJTLU)


  1. Understanding dynamic steroid biosynthesis in health and disease through machine learning in the space of mechanistic models (co-PI, March - August 2020, seed corn project funded by EPSRC Centre for Predictive Modelling in Healthcare)