Published as First Author in: A Cell Press Journal - iScience.
This study presents an ensemble transformer framework for detecting depression-related emotions and classifying their severity in social media text. It addresses the need for scalable and trustworthy AI solutions in mental health by integrating four transformer models.
Submitted to the journal: Biomedical Signal Processing and Control, Elsevier.
Designed a novel transformer-based ensemble model—DepTformer-XAI-SV—that leverages DistilBERT, ALBERT, XLM-RoBERTa, and DeBERTa-BiLSTM with explainable AI to detect depression-related emotions and assess severity from social media text.
Published to the 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE)
Proposed a transformer-based ensemble model combining ViT, DeiT, Swin Transformer, and BEiT for enhanced oral cancer segmentation.
Promoted to Senior Software Engineer at Gigalogy for leading end-to-end development of AI-powered SaaS integrations, optimizing infrastructure, and mentoring team members while driving impactful solutions for e-commerce platforms.
Also, responsible for architectural design, client communication, and agile project management to ensure timely and scalable deliveries.