http://repository.iiitd.edu.in/xmlui/handle/123456789/45 2026-09-09T22:55:40Z 2026-09-09T22:55:40Z U K, Sarvajeet Goel, Lakshay Rajput, Nabh Bagler, Ganesh (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2119 2026-09-09T22:00:38Z 2024-11-27T00:00:00Z

Title: Development of search APIs for flavorDB2: BTech project in API creation and data management Authors: U K, Sarvajeet; Goel, Lakshay; Rajput, Nabh; Bagler, Ganesh (Advisor) Abstract: This report presents the development of robust search APIs for FlavorDB2, an advanced database of flavor molecules and their associated properties, aimed at enhancing data accessibility and usability for researchers in computational gastronomy and food science. The project involved migrating raw CSV datasets to a MongoDB database, followed by the implementation of RESTful APIs using the Spring Boot framework. The APIs enable complex and multidimensional queries, allowing users to retrieve data based on molecular identifiers, regulatory statuses, food categories, and synthesis processes. Advanced features like query filtering and aggregation ensure precise results and scalability.

2024-11-27T00:00:00Z Singh, Jyotirmaya Ranjan, Aayush Agarwal, Arnav Akhtar, Md. Shad (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2117 2026-09-09T22:00:27Z 2024-04-29T00:00:00Z

Title: Propaganda analysis Authors: Singh, Jyotirmaya; Ranjan, Aayush; Agarwal, Arnav; Akhtar, Md. Shad (Advisor) Abstract: The pervasive influence of propaganda across various media platforms poses significant chal lenges for the discernment of biased information. This project report presents a comprehensive examination of propaganda, proposing a nuanced definition that encapsulates its multifaceted nature, which includes content, intent, techniques, medium, and impact among other elements. We explore the challenges associated with collecting data from diverse sources like social media platforms and news outlets, and describe our pivot to sourcing content through tailored search queries to compile a dataset of propagandistic articles. This dataset aims to enable sophisti cated Natural Language Processing (NLP) models to identify and analyze the subtle nuances of propaganda. Additionally, we detail our rigorous annotation process, which includes guidelines for identifying propaganda techniques and narrative classes, and outline measures to ensure high inter-annotator reliability. By enhancing the understanding of propaganda’s complex dynamics, this work contributes to the development of more effective tools for media literacy and informa tion integrity in the digital age.

2024-04-29T00:00:00Z Kumar, Niteen Agarwal, Niket Buduru, Arun Balaji (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2116 2026-09-09T22:00:46Z 2025-07-18T00:00:00Z

Title: Solving healthcare application of speech processing Authors: Kumar, Niteen; Agarwal, Niket; Buduru, Arun Balaji (Advisor) Abstract: In order to improve human-computer interaction and create emotionally intelligent systems, au tomatic emotion classification from speech is essential. Large pre-trained audio language models (ALMs) have shown good generalization on a variety of tasks, but little is known about how well they perform on low-resource and multilingual datasets, particularly when code-switched or bilingual speech is involved. In this study, we examine the ability of cutting-edge pre-trained models to categorize emotions from a bilingual speech dataset that includes both Tamil and English utterances. To ensure balanced representation in both languages, our carefully selected dataset contains labeled audio samples from core emotion classes, including happy, sad, angry, and neutral. Using sophisticated ALMs such as Wav2Vec2, HuBERT, and Whisper, we extract fixed-length embeddings. We then assess these representations using Convolutional Neural Net works (CNNs) and Fully Connected Networks (FCNs). We investigate a dual-branch CNN archi tecture supplemented with a contrastive loss component to address intra-class language variance and inter-class emotion similarity. Our findings shed light on embedding-level language-agnostic emotion representation and demonstrate the potential of ALMs in robust emotion recognition, even in multilingual contexts.

2025-07-18T00:00:00Z Vyas, Madhav Grover, Anuj (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/2115 2026-09-08T22:00:40Z 2024-11-30T00:00:00Z

Title: Development of large language models and tools to study patents and develop insights Authors: Vyas, Madhav; Grover, Anuj (Advisor) Abstract: The development and evolution of Static Random Access Memory (SRAM) has been a cornerstone in the advancement of semiconductor technology, largely due to its ability to deliver high-speed performance while consuming minimal power. SRAM is widely utilized in applications requiring fast and efficient memory access, such as microprocessors, cache memory, and embedded systems. As the demandfor morepowerful, energy-efficient, and scalable memory solutions grows, understanding the underlying innovations and trends within SRAM technology has become increasingly vital. This project presents a novel approach by combining the power of Large Language Models (LLMs) with a chatbot designed specifically for the analysis of SRAM-related patents. The mainobjective of this project is to harness the capabilities of LLMs to create a tool that can provide comprehensive, context-sensitive, and insightful information from SRAM patents. By systematically classifying and analyzing a wide array of patent data, this system is able to cover key aspects of SRAM technology, such as technical specifications, design innovations, architectural variations, performance optimization techniques, manufacturing advancements, and emerging trends in the field. The rich variety of data available in patent documents presents a unique opportunity to identify cutting-edge developments, breakthroughs, and potential challenges facing the SRAMindustry.

2024-11-30T00:00:00Z