Vara Prasad Gudi
Graduate Researcher
Graduate Researcher
Passionate about the intersection of software engineering and machine learning, I am a dedicated researcher with a robust foundation in AI and ML, cultivated through academic excellence and hands-on research. As a graduate student at UMass Amherst and a former Data Analytics Intern at Ecolab, I have honed my skills in developing cutting-edge solutions to drive societal impact. Explore my journey and projects to see how I leverage technology for the greater good.
Are you ready to explore new frontiers and create groundbreaking projects? I am eager to connect with like-minded individuals who share my passion for enhancing Technology. Let's exchange ideas and discover exciting possibilities that can drive us towards success. I'm excited to connect and collaborate—let's make magic happen!
Developed and automated end-to-end data pipelines, integrating diverse sources such as Azure SQL DB, Excel, JSON, SharePoint, text files, Snowflake, SAP, and third-party APIs. Utilized Python for writing scripts for data extraction and transformation, employing Python-SAP scripting, Azure Logic Apps, and API calls to streamline data integration into the Azure environment. The process involved performing extensive SQL queries for large, raw datasets, followed by comprehensive cleaning and transformation in Jupyter Notebooks. Automated these processes using Azure Function Apps and scheduled them via the Azure CI/CD pipeline. Additionally, leveraged Microsoft Power Platform tools for further automation and created visualizations using Power BI, SharePoint, and Python Jupyter Notebooks to support decision-making for vertical leadership.
Social Engineering Investigation i.e. Investigate E-mails sent in and report suspicious items Performed Digital Investigation i.e. Analyze a Packet Capture file using an open source tool to identify and investigate any potential threats
Answered student queries over email. Interacted with students for any Academic help and report it to core committee. Occasionally interacted with core committee to give suggestions regarding Academics.
Handled Projects like Authentication Bypass, Scanning using OWASP ZAP, Scanning & Attacking for Open ports and worked on System Hacking and Exploiting Server Vulnerabilities. Also, into Hands-on Training on various Ethical hacking concepts and Kali Linux Tools.
Worked on PHP Stack as an API developer for the SpacTube module, which is an interaction gateway for parents and teachers to manage a video gallery and engage for early child development that makes use of the YouTube API to handle requests from the organization's YouTube channel. As a PHP developer, I contributed on the Consult-Us module, which is an online video conference app for interaction between doctors and children that includes live streaming and a Real-Time Voice and Video Engagement feature supported by the Agora API.
Marketing the company services with pragmatic strategies. Working on the street-smart execution of marketing pitches turn them into sales. Select target customers and implement tricks to achieve sales targets on that day. Suggest Sales and Marketing Ideas/methodologies to the company.
Worked closely to the technical lead and made decisions to provide technology and technical support to the community. Helped in Conducting Technical Events like WebHunt, Capture The Flag, CyberPunk and other Technical Talks in the club, contributed some blogs, developed some skills.
Connected with the developer community and contributed some technical blogs on various topics like Programming, Security, Softwares, Beginner Projects on my experiences with Technology.
This research, under Prof. Mohit Iyyer, evaluates multiple strategies to enhance Out-of-Distribution (OOD) robustness using fine-tuned and pre-trained models such as BERT, RoBERTa, and Llama. By implementing zero-shot, k-shot, few-shot, chain-of-thought prompting, and explanation-based techniques, a 20-30% improvement in OOD accuracy over supervised fine-tuning baselines was achieved. Additionally, 4-bit quantization for memory optimization was integrated using Unsloth, maintaining performance with explanation-based prompting. The findings of the research have been submitted to the 14th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis.
This research, under Prof. Hamed Zamani, crafted a model to generate precise prompts from articles, boosting language model (LLM) accuracy through targeted fine-tuning. Additionally, query generation with lexical augmentation was implemented, resulting in a 22.5% accuracy improvement and a 50% increase in F1-score. Furthermore, document retrieval was enhanced by implementing top-k extraction using the BM25 algorithm, significantly improving performance.
Published a chapter in the book "Explainable Artificial Intelligence (XAI): Concepts, Enabling Tools, Technologies and Applications," published by The IET Digital Library, provides a comprehensive insight into the role of XAI in the medical field. With its Chapter DOI: 10.1049/PBPC062E_ch, it emphasizes the necessity for transparency in AI systems among healthcare professionals. The chapter thoroughly explores applications in areas such as medical image analysis with deep learning, clinical decision support, and broader healthcare. It also highlights XAI's role in enhancing trust in healthcare, with in-depth discussions on its integration in healthcare frameworks for pandemic prevention, and specific medical applications like allergy diagnosis. This research significantly contributes to the understanding of how XAI can be a transformative force in medical science, emphasizing the importance of explainability in the deployment of AI solutions for improved health outcomes.
This research, conducted under the guidance of Assistant Prof. Sheela Jayachandran at the School of Computer Science and Engineering (SCOPE) at VIT-AP, presents a groundbreaking Python-based machine learning algorithm for image analysis. The Fuzzy Image Clustering via Featured Interval Extraction algorithm excels with a 100% accuracy rate in overlap distance evaluation, significantly outperforming existing methods in datasets with high overlap. Its versatility and precision in multivariate statistical applications not only mark a significant advancement in the field but also earned recognition through a utility patent (IP India Application No. 202341029896). This work highlights the potential for enhancing image analysis techniques and contributes substantially to the research community.
This research, under Assistant Prof. Sheela Jayachandran at VIT-AP's School of Computer Science and Engineering, has significantly advanced waste management technology. By integrating the YOLOv4 algorithm with IoT, the team developed a system that not only surpasses previous models in accuracy but also improves efficiency. This innovation led to a notable 10% increase in detection precision and a 12% boost in processing speed, showcasing a scalable solution that melds deep learning with environmental sustainability. The impact of this groundbreaking work is further acknowledged through the publication of a design patent (IP India Application No. 202341070187), marking a milestone in sustainable technology development.
This research, led by Associate Prof. Somya Ranjan Sahoo at VIT-AP's SCOPE, innovatively applies fuzzy logic to traffic control systems, resulting in a 30% improvement in traffic flow and a 20% reduction in vehicle wait times. The study involved a Pygame simulation of a complex four-way intersection, showcasing its potential in urban traffic management. The team's findings, demonstrating a 45% efficiency increase over static systems, were recognized for their significance in urban planning and smart cities, culminating in a publication in an IEEE journal.