Artificial Intelligence, Machine Learning, Deep Learning, Internet of Things, Cloud Computing, Image Processing.

During my doctoral research at the Department of Information Technology, NITK Surathkal, under the guidance of Prof. Ananthanarayana V S, I focused on developing an intelligent AI-driven framework for disease prediction and clinical recommendation using multimodal medical data. My work explored the integration of radiology images, clinical text reports, and other medical data to improve diagnostic accuracy, particularly in scenarios with limited or unstructured data.

I designed and evaluated novel deep learning architectures, including multi-scale, lightweight, and cross-modal networks, to predict a range of conditions such as pulmonary abnormalities and acute brain infarcts, while also generating automated clinical recommendations and radiology reports. A key aspect of my research involved leveraging tensor fusion, data augmentation, and explainable AI techniques to ensure both robust performance and interpretability of the models.

Overall, my research contributes to the development of clinically meaningful AI solutions, bridging advanced machine learning techniques with practical healthcare applications, and advancing the precision and efficiency of medical diagnostics.

As part of my M.Tech dissertation at the Centre for Development of Advanced Computing (C-DAC), Pune, I carried out research titled: “Study and Implementation of Web Services and Their Management Using the Hadoop Ecosystem with Extensions for Web Service Selection”. The project focused on addressing the challenges of efficient discovery, storage, and management of large-scale web services in a Service-Oriented Architecture (SOA) environment. To handle massive and distributed datasets, I designed a Hadoop-based Web Service Management System (HWSMS) integrating HDFS, MapReduce, and HBase for scalable storage and retrieval.

Furthermore, I proposed and implemented algorithms for Optimal Web Service Search (OWSS) and Parallel Web Service Selection (PWSS) to enable faster, reliable, and QoS-aware service selection. Experimental evaluation demonstrated improved performance, scalability, and reliability, establishing the potential of big data frameworks in web service management and intelligent selection.