Beatriz de la Iglesia's research has focused in data mining algorithms and application, with particular experience in health care data analysis and agritech applications. She has worked, among other themes, on the analysis of primary care datasets for cardiovascular disease risk evaluation; on text mining of gastroenterology procedural reports to identify key success indicators; on  linking data in the secondary care setting in order to create patient-centric databases suitable for clinical research; on the development of algorithms for clustering complex data with particular application to air pollution data; and on the analysis of twitter data for syndromic surveillance.  She has also worked on the analysis of crop images to quantify yiedl and on the quantification and detection of spray deposits from precision spraying systems.

She has a keen interest in helping advance the career of women in STEM having participated on international projects in this area.  She offers her mentoring to women including in an international setting.

She has published over 70 peer reviewed publications and is involved in a number of multi-disciplinary collaborations. 

Follow this link for details of current PhD opportunities in Computing Sciences. But feel free to email her to discuss projects outside these areas and alternative sources of funding.

Beatriz obtained her first degree, a first class BSc Honours in Applied Computing, at UEA in 1994.  She obtained her PhD in Computing Science in September 2001. The subject of her research was data mining and in particular the extraction of partial classification rules or nuggets using meta-heuristic algorithms. She also obtained a Postgraduate Diploma in Higher Education in 2004.  She took an ILM3 certificate in Leadership and Management in 2018 and further cemented her leadership skills in 2019 by participating in the Advance HE Aurora Leadership Programme.

• May 95 to January 97: worked in Norwich Union (now Aviva) full-time as a Teaching Company Associate for a Teaching Company Scheme between Norwich Union and UEA.
• January 97 to January 2001: tutor post for UEA lecturing on various courses, part-time.
• October 1999 to December 2001: half-time post as a senior research assistant in a bio-informatics project funded by a BBSRC grant.
• January 2001 to July 2012: Lecturer in Computing Science, UEA.
• July 2012 to 2022: Senior Lecturer in Computing Science, UEA.
• August 2022 to now: Professor of Data Science.
• August 2023 to now: Head of School

Beatriz de la Iglesia is part of the Data Science Laboratory. Her research interests include
Health informatics:

• primary care data analysis
• text mining of clinical reports
• linking hospital data to enable analysis of clinical pathways
• text mining of gastroenterology reports to characterise upper gastrointestinal cancers
• Twitter mining for syndromic surveillance

Algorithm development:

• meta-heuristics and multi-objective algorithms for classification and clustering
• association rule mining
• privacy preserving data mining
• image analysis using deep learning
• imputation for missing data

Big data:

• fusion algorithms to cluster heterogeneous data
• analysis of twitter data for syndromic surveillance
• methodological issues in the extraction, preparation and analysis of big data
• consumer behaviour analysis from loyalty card data.

Beatriz has also got consultancy experience mining financial data, particularly in the context of general insurance and life insurance, but also credit card data, looking for business exploitable patterns.    
 

• Head of School (current)
• Director of the Data Science MSc (current)
• Director of PgT Programmes (previous)
• Chair of Examiners (UG) (previous)
• Admissions Deputy Director PGT (previous)
• Coursework Co-ordinator PgT Students (previous)
• Induction Programme Director (previous)
• Deputy Director of Learning and Teaching (previous)

Data Science Laboratory

Solution of large problems using meta-heuristics; data mining; health informatics; missing data imputation; clustering; classification; text mining; image analysis; deep learning algorithms.