My Research Interests
I am from Pune, India where I studied Bachelors of Science and Masters in Bioinformatics. This was where my interests in science, biology and computers were born and nurtured. My training in bioinformatics took me to Singapore to work as a Senior Research Assistant at the National Neuroscience Institute. This is where I got introduced to ontologies, Semantic Web and Linked Data that could be used to solve biological problems.
That brought me to Germany where I pursued my PhD in Computer Science in the University of Leipzig. My focus was on consumption of Linked Data for healthcare, educational and economic research leveraging data quality. Then I got the opportunity to pursue my research ideas further as a postdoctoral researcher at Stanford University in the Biomedical Informatics department. This is where I brought the worlds of Semantic Web and Biology together. After spending just a little over a year at Stanford, my professor got an opportunity to start a Data Science Institute at the University of Maastricht, Netherlands. I followed suit and have been here since January 2017.
One of the main problems I am tackling is assessment and improvement of data quality specifically for Linked Data. I demonstrated the feasibility of using semi-automated and crowdsourcing (human non-experts) methods for Linked Data quality assessment for a specific use case as part of my thesis. As part of my postdoc, I am developing methods for using crowdsourcing as a means of quality assessment of biomedical metadata specifically. In particular, I am investigating the optimal combination of humans (non experts via crowdsourcing and domain experts) and machines (via machine learning) towards data quality assessment. Just imagine how much meaningful data, application and discoveries will come out of putting all three stakeholders together, each with their own expertise (yes even the non-experts!).