Worked under Dr. Manas Gaur1. Curated a survey that offers a systematic critical review of the existing conversational agents in mental health, followed by new insights into the improvements of VMHAs with contextual knowledge, datasets, and their emerging role in clinical decision support.We also provide new directions toward enriching the user experience of VMHAs with explainability, safety, and wholesome trustworthiness.Link to my research: https://arxiv.org/abs/2304.131912. Developed an ensemble model to recognize the potential of smaller FLMs (Foundational Language Models) over larger FLMs (e.g., XLNET, T5) to access the liability of larger FLMs concerning hallucination and predictive uncertainty.Link to my research: https://arxiv.org/abs/2308.122723. To access the reliability of language models and their outcomes, we devised a knowledge-guided LM ensembling approach that leverages reinforcement learning to integrate knowledge from ConceptNet and Wikipedia as knowledge graph embeddings using BERT model on GLUE benchmark datasets to mimics human annotators resorting to external knowledge to compensate for information deficits in the datasets.Link to my research: https://arxiv.org/abs/2308.13467

1. Developed a prediction model for dementia, utilizing machine learning techniques, such as Random Forest and Temporal Long Short-Term Memory networks (T-LSTM), that account for variations in sex and individual SocioEconomic Status (SES).2. My research seeks to explore the correlation between the Area Deprivation Index (ADI), determined at the group level of census block, and the advancement to dementia in participants initially cognitively impaired.

Worked as trainee on business intelligence domain with hands-on training on latest BI tools like SSIS ,SSRS, Microsoft SQL Server, PL/SQL and on INFORMATICA.

My work was to design and develop a computational model for quality assay of organic oils using regression modelling [Machine Learning] on MATLAB.Using NIR-SPECTROMETER to get the actual data samples of oil and plot against the standard data samples to analyse the quality parameters of organic oils.