Mission

My primary goal is to contribute to advancing scientific discovery by fostering a more accessible, ethical, and artificially intelligent (AI) data and information ecosystem. I am passionate about driving the automatic integration and harmonization of all scientific information, ensuring efficient organization, cleaning, archival, and practical mining for new insights. I believe in the transformative power of interdisciplinary collaboration, particularly between data science, artificial intelligence, and the core scientific disciplines. I am committed to advancing responsible and sustainable scientific computing and AI practices, minimizing their environmental impact, and ensuring ethical considerations are paramount in all research endeavors. Finally, I am dedicated to empowering underrepresented groups in computational, information, and data sciences, including women, refugees, and financially challenged populations, by creating inclusive and equitable opportunities for all. More

Vision

My research interests and experiences are centered around the role of data quality, curation, and engineering in artificial intelligence and their applications in the sciences. I develop and adapt methods and frameworks rooted in graph theory, natural language processing, machine learning, and deep learning. I apply the developed methods in information retrieval (computer science), data mining of digital libraries and information networks (information science), biomedical informatics (biology), non-profit studies (social sciences), and human-computer interaction (psychology). My vision is to aid and automate the process of scientific discovery and inquiry by developing ethical and artificially intelligent systems capable of integrating, cleaning, organizing, and mining scientific information automatically and efficiently.

Current Research Interests

Data Quality in AI: I investigate the critical role of data quality in training artificial intelligence
models, particularly in scientific domains where data integrity is essential.
Biomedical Data Integration: I develop efficient techniques for integrating large biomedical
datasets extracted from digital libraries with omics datasets using the Knowledge Graph data
model.
Graph-Based Representation Learning: I develop scalable graph-based representation
learning techniques to leverage the power of integrated datasets for applications in information
retrieval, search engines, and entity matching.

Main Research Experience:

1. Entity resolution and matching with graph theory and natural language processing
2. Biomedical information retrieval with graph representation learning

Secondary Research Experience:

1. Human factors in computing and information seeking with eye tracking
2. Scientific visualization of biological data

Current Skillset (Python, C\C++, Unix):

1. Graph theory and network mining algorithms
2. Applied linear algebra algorithms
3. Natural language processing algorithms
4. Machine learning and deep learning models and experimentation with TensorFlow
5. Setting up high-performance computing environments and data management systems

Older Skillset (C\C++, Java, SQL):

1. Experimental design and statistical analysis in eye-tracking studies
2. Image processing with OpenCV, mainly for filtering, localization, and mapping
3. Computer graphics with OpenGL and WebGL for creating scientific visualizations
4. Software engineering, especially web applications and services based on the MVC design pattern and backend ETL operations