About

I am a Research Fellow at the Department of Data Science and AI, Monash University, specializing in Time Series Analysis and Machine Learning applications. I successfully completed my PhD at the Faculty of Information Technology, Monash University, under the guidance of Professor Geoff Webb, Dr François Petitjean and Dr Paul Reichl. My doctoral thesis, titled “Time series classification at scale”, focused on advancing Scalable Time Series Classification techniques. Specifically, I developed efficient algorithms capable of handling large time series datasets, resulting in faster and more effective classification processes.

During my doctoral studies, I received recognition for my contributions in the field. I was honored to receive a best paper award for my work on "Efficient search of the best warping window for Dynamic Time Warping". This paper introduced a novel algorithm for learning the parameters of Dynamic Time Warping (DTW), a widely used measure for comparing time series. Additionally, my dedication and research excellence were acknowledged through the prestigious Mollie Holman medal awarded by Monash University, recognizing my doctoral thesis as the best in the Faculty of Information Technology.

My expertise extends beyond academia, as I actively apply time series analysis to real-world challenges. I have collaborated with the Institute of Railway Technology (IRT) at Monash University to enhance railway track maintenance through the application of advanced time series analysis techniques.

Presently, I am continuing my research endeavors in Scalable Time Series Classification while expanding my focus to Time Series Extrinsic Regression (TSER). TSER involves predicting continuous scalar values based on time series data. Unlike classification tasks, where the target is discrete, and forecasting tasks, which may not rely on recent or seasonal values, TSER presents unique challenges. To address these challenges, I am devoted to developing innovative methodologies that leverage machine learning techniques. Furthermore, I am exploring the potential of utilizing EEG devices for various applications, such as diagnosing epilepsy and detecting driver's distractions. These areas of research hold substantial promise for improving the lives of epilepsy patients and enhancing road safety.

In addition to my core research interests, I am actively involved in a Defense Advanced Research Projects Agency's (DAPRA) project called Computational Cultural Understanding (CCU), where I lead the effort in predicting changes in conversations. This project aims to deepen our understanding of cultural dynamics and improve communication strategies.

Furthermore, I am engaged in providing data science services to Stemly, where I contribute my expertise in developing autonomous supply chain demand forecasting solutions. Through this collaboration, I strive to optimize supply chain operations and enhance forecasting accuracy.

In summary, my multifaceted research background encompasses Scalable Time Series Classification, Time Series Extrinsic Regression, EEG-based applications, cultural understanding, and supply chain analytics. By addressing fundamental challenges in these domains, I aim to make meaningful contributions to academia, industry, and society as a whole.