I am genuinely interested in any research topic that involves data mining, machine learning, and knowledge discovery. This interest naturally extends to the algorithms design and intelligent software systems engineering.
Data mining and machine learning
Currently, a vast amount of IoT devices, wearable and mobile devices, and various research instruments (such as next-generation sequencing) generate large amounts of temporal data which may shed a light on many real-life phenomena through previously unknown associations. Discovering these associations requires the development of self-learning intelligent systems that are capable of big data summarization, abstraction, and extraction of phenomena-characteristic features. I enjoy working on the design of algorithms for high-throughput data analysis and implementation of intelligent systems enabling the discovery of novel features and their associations.
Software process engineering
In my opinion, the successful software development - the one which delivers a functional software in time and under budget - is the result of a development discipline that is a combination of appropriate tools, processes, attitude, and habits. An effective combination of these enables teams and individuals not only to reach their goals efficiently, but to deliver reliable and performant software systems and components. The understanding of these "magic mixtures", and specifically habits (i.e., recurrent behavioral patterns), was in focus of my doctorate research. Currently, I am interested in extending this work towards the software process design.
Years ago, I become a research assistant at ASGPB and was accidentally involved in bioinformatics -- my special thanks to Dr. Alam -- ten years later, I still work in the field. The best part about doing bioinformatics is the collaboration with researchers from a variety of scientific disciplines -- we have biologists, physicists, mathematicians, statisticians, and computer scientists working within the same project. I find the everyday interactions within the team and with external collaborators very rewarding and enriching. Moreover, bioinformatis involves data mining, machine learning, and software engineering. And soon, as the sequencing gets cheaper and the interest for studying of genetic data dynamics forms, it shall incorporate the temporal, and spatio-temporal data mining!