Ileana Montoya Perez profile picture
Ileana
Montoya Perez
Doctoral Researcher, ​Department of Computing
Doctoral Researcher, Data analytics
MSc. in Information Technology
Data analysis and performance evaluation with challenging data sets: prostate cancer as a case study. A close collaboration between Depts. of Computing (UTU), Radiology and Urology (TYKS).

Contact

Areas of expertise

Data analysis
Machine learning
Statistics
Databases
Web-development

Biography

MSc. Ileana Montoya Perez, a Ph.D. candidate and project researcher in computer science at the University of Turku (UTU), graduated as a Systems and computer engineer in 2000, worked as a software developer for the industry, and in education as an ICT coordinator for over ten years. She received her master’s degree in Information Technology in April 2014 from UTU. Since May 2014, she has worked as a web developer on an interdisciplinary project between Dept. of Urology (TYKS) and the Dept. of Computing (UTU), designing and building databases and web applications to collect and present retrospective data for bladder and prostate cancer research. At the same time, she started her research on machine learning methods for performance evaluation when the available data is limited and challenging. This research has been active collaboration between the Dept. of Computing, Dept. of Radiology, and Dept. of Urology. Since the start of 2021, she is been part of the PRIVASA group, researching the technical aspect of privacy-preserving of artificial intelligence (AI) for synthetic and anonymous health data.

Teaching

Areas of interest in teaching are data analysis and machine learning, especially performance evaluation methods. 

Research

Currently working on two research areas: Data analysis and performance evaluation with challenging data sets: prostate cancer as a case study, and privacy-preservation of AI for synthetic and anonymous health data. The former aims to develop, apply, and evaluate machine learning methods to combinations of clinical variables, kallikreins, and magnetic resonance imaging (MRI) parameters for detecting and characterizing prostate tumors, while the latter aims to evaluate and develop techniques for preserving the privacy of health data by generating differentially private synthetic data or by applying differential privacy to study statistics to maintain participants' privacy. 

Publications

Sort by: