Research Officer
Swansea University Medical School
Telephone: (01792) 295641
Email: JavaScript is required to view this email address.

Dr Haider Raza’s research sits within the “The Centre for Improvement in Population Health through E-records Research (CIPHER)”, Medical School, Swansea University.  His research theme is “Patient & Population Health and Informatics (PPHI)".  His research interests focus on data-driven approaches to epidemiology and public health problems using computing techniques, such as machine learning, data science, medical statistics, computational intelligence, predictive analytics and data mining. He is mainly involved in intelligent data analysis of complex health records, and creation of novel approaches for extracting personally useful information, such as rules and patterns for health conditions from routine health related data to support improved lifestyles and prevent disease. His research interests are:

  • Machine Learning and Data Mining for Epidemiological Datasets
  • Artificial Intelligence, Pattern Recognition, and Neural Engineering, Data Science and Big Data.
  • Dataset Shift/Change-Detection
  • Data driven approach to healthcare modelling and analytics using big health-related data
  • ElectroEncephalography (EEG) and MagnetoEncephalography (MEG) based Brain-Computer Interfacing (BCI)

Previously, Dr Raza has worked as a Research Assistant (Post-Doc) in Brain-Computer Interfacing at Intelligent System Research Centre (ISRC), Ulster University, Londonderry, UK (December-2015 to June-2016). His PhD project at Ulster University was "Adaptive Learning for Modelling Non-Stationarity in EEG based Brain-Computer Interfacing" (2012-2016).  

Areas of Expertise

  • Machine Learning
  • Signal Processing and Feature Extraction
  • EEG and BCI based Brain-Computer Interfacing
  • Epidemiology
  • Adaptive and Predictive Modeling
  • Data Mining and Data Science


  1. EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments. Pattern Recognition 48(3), 659-669.
  2. Adaptive learning with covariate shift-detection for motor imagery-based brain–computer interface. Soft Computing 20(8), 3085-3096.
  3. (2015). Optimising frequency band selection with forward-addition and backward-elimination algorithms in EEG-based brain-computer interfaces. , 1-7. doi:10.1109/IJCNN.2015.7280737
  4. (2015). Learning with covariate shift-detection and adaptation in non-stationary environments: Application to brain-computer interface. , 1-8. doi:10.1109/IJCNN.2015.7280742
  5. (2015). A study on cortico-muscular coupling in finger motions for exoskeleton assisted neuro-rehabilitation. , 4610-4614. doi:10.1109/EMBC.2015.7319421

See more...