- Developed a dynamic scraping algorithm using Python, Tesseract, and IndicTranslate to extract over 3 million historical revenue court cases from government court records and SOLR to index them.- Developed and took independent responsibility for a Graph network based document validation system to validate the completeness of a title chain and predict flag potential missing links in the chain with an accuracy of 91%.

Final Year Unergraduate Thesis : Advised by Professor Chen Change LoyTitle: Text Restoration using Image Super Resolution ( doi: https://hdl.handle.net/10356/166103 )• Investigated the quality of existing datasets for Scene Text Image Super Resolution task and highlighted several drawbacks.• Leveraged Real-ESRGAN architecture, PyTorch, OpenCV to build high resolution and Low resolution scene text and synthetic text images and trained a GAN Network for the STISR task.• Improved the PSNR and SSIM evaluation on benchmark datasets and existing State of the Art models by 10%.

• Provided strong leadership to team of 55 individuals to organise various tech related events and activities with aim of educating and equipping people with skills necessary for industry.• Oversaw 14 workshops with average participation of 120 each on various topics pertinent to Industry4.0• Organised Singapore’s largest Student-run hackathon, iNTUition v8.0, with 700+ participants from SE Asia, and finances of $25000 raised from leading firms (e.g. Goldman Sachs, Google, Indeed etc) in industry.

- Organised over 5 workshops with participation of over 50 each and a hackathon with over 520 participants. -Lead Speaker for an AWS Cloud Fundamentals Workshop, which had over 55 participants. - Managed a team of 15 Tech officers who conducted workshops, as well as work on year-long projects with aim to make impact and add value to society. - Spearheaded the development of the iNTUition Playground, an Avatar-based virtual world for the flagship Hackathon- iNTUition v7.0 which saw 500+ participants and over 50+ Sponsor representatives from Technology pioneers like SAP, HP, Bigo etc

• Performed Root cause analysis for fault detection in manufacturing lines using Bayesian Belief Networks to reduce downtime by 15%.• Developed pre-processing tool of automation pipeline, incremental learning algorithms to update the BBN and leveraged Pytest to unit test the tool, and FastAPI, Streamlit & Plotly to deploy the user-interface.

• Developed a general brand detection model pipeline to identify logos in daily objects present in product listings and classify brands by employing the OpenCV, YOLOv5 and Pytorch Frameworks.• Employed image pre-processing techniques, produced custom training edge cases, finetuned open-source CNN models, etc to improve recall & precision from 0.1 to 0.35 & 0.6 respectively (150 class model)

One of the team members as a part of the Cisco Talent Outreach Program.