Hooman Oroojeni

Dr Hooman Oroojeni BSc, MSc, PhD

Senior Lecturer in Data Science

Hooman obtained his PhD from Goldsmiths, University of London and joined the Greenwich University in 2018. His expertise spans various domains, such as agent-based computing, parameter/model optimisation, and machine learning, focusing on deep learning algorithms. His research includes working on Deep Neuroevolution, tensor decomposition, and the applications of Dispersive Flies Optimisation. His educational background includes a PhD in computer science (AI), an MSc in Computer Networking, and a BSc in Software Engineering.

Computer science and computing

Responsibilities within the university

Module leader

  • Artificial Intelligence Applications
  • Data Warehousing and Business Intelligence

Module contribution

  • Introduction to Artificial Intelligence
  • Machine Learning

Awards

University of Greenwich Vice Chancellor Scholarship

Research / Scholarly interests
  • TinyML: Interested in TinyML, focusing on optimising machine learning models for low-power, small devices, blending computational efficiency with energy conservation.
  • Tomography Reconstruction: Interested in Tomography Reconstruction, which involves reconstructing images from signals, with applications in medical imaging and material science.
  • Swarm Intelligence: Explore Swarm Intelligence, drawing inspiration from nature to develop algorithms for complex problem-solving in optimisation.

Recent publications

Orlov, N.D., Muqtadir, S.A., Oroojeni, H., Averbeck, B., Rothwell, J. and Shergill, S.S., 2022. Stimulating learning: A functional MRI and behavioural investigation of the effects of transcranial direct current stimulation on stochastic learning in schizophrenia. Psychiatry Research, 317, p.114908.

al-Rifaie, M.M., Hooman, O.M. and Mihalis, N., 2020. Dispersive flies optimisation: modifications and application. In Swarm Intelligence Algorithms (pp. 145-161). CRC Press.

Hooman, O.M., Oldfield, J. and Nicolaou, M.A., 2019, September. Detecting early Parkinson’s disease from keystroke dynamics using the tensor-train decomposition. In 2019 27th European Signal Processing Conference (EUSIPCO) (pp. 1-5). IEEE.

Hooman, O.M., Al-Rifaie, M.M. and Nicolaou, M.A., 2018, September. Deep neuroevolution: Training deep neural networks for false alarm detection in intensive care units. In 2018 26th European Signal Processing Conference (EUSIPCO) (pp. 1157-1161). IEEE.