Year-2024 http://repository.iiitd.edu.in/xmlui/handle/123456789/1722 2026-05-27T21:00:59Z 2026-05-27T21:00:59Z Kumar, Vickery Kumar, Suyash Surya, Pourav Kosta, Pragya (Advisor) Sarkar, Shamik (Advisor) Singh, Pushpender (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1981 2026-05-26T22:30:26Z 2024-12-11T00:00:00Z

Deep learning based electromagnetic field estimation for neural engineering applications Kumar, Vickery; Kumar, Suyash; Surya, Pourav; Kosta, Pragya (Advisor); Sarkar, Shamik (Advisor); Singh, Pushpender (Advisor) Understanding neural activity through stimulation offers significant potential for neuroscience research and clinical applications. However, experimental setups involving magnetic or electrical stimulation, such as those used to analyze neural responses in the rat sciatic nerve, are often resource-intensive and costly. This project proposes a deep learning-based approach to predict neural response data, eliminating the need for physical stimulation hardware. Leveraging previously collected data from simulations and experimental setups, we aim to train a model that accurately predicts neural excitation under various stimulation conditions. This novel approach has the potential to reduce costs, streamline experiments, and enable scalable analysis of neural activity, fostering advancements in neuroengineering research .

2024-12-11T00:00:00Z Gupta, Kshitij Chaterjee, Bapi (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1980 2026-05-26T22:03:42Z 2025-07-17T00:00:00Z

ConcurBench: a benchmark framework for evaluating LLM-generated concurrent code Gupta, Kshitij; Chaterjee, Bapi (Advisor) This thesis presents ConcurBench, a novel benchmark framework designed to evaluate the capa- bilities of Large Language Models (LLMs) in generating concurrent code. Concurrent program- ming remains one of the most challenging domains in software development, requiring careful attention to thread safety, synchronization, and race conditions. As LLMs increasingly become part of software development workflows, understanding their ability to generate correct concur- rent code is crucial. ConcurBench addresses this need by providing a comprehensive evaluation framework that ex- tracts high-quality concurrent functions from popular open-source repositories, annotates them with natural language requirements, and tests LLMs’ ability to regenerate these functions with varying levels of context. The framework implements a multi-level context evaluation approach, testing LLMs with no context (function signature only), local context (surrounding function- s/imports), and full context (entire file context). The thesis details the design and implementation of ConcurBench’s pipeline architecture, in- cluding repository discovery and collection, function extraction, test discovery, LLM annotation, function generation, and evaluation. Key innovations include a dynamic test harness generation system that can compile and test LLM-generated code against original implementations without modification, and an orchestration wrapper script that enables scalable, automated evaluation across multiple functions and LLMs. Experimental results demonstrate that context significantly impacts LLMs’ ability to generate correct concurrent code, with full context providing substantial improvements in functional correctness. The benchmark provides valuable insights into the strengths and limitations of current LLMs in handling concurrent programming tasks and establishes a methodology for evaluating future advancements in this domain.

2025-07-17T00:00:00Z Dabas, Ram Dagar, Kartik Tejas, Kumar Shankhwar, Kalpana (Advisor) Ratn, Anoop (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1979 2026-05-26T22:18:14Z 2024-11-27T00:00:00Z

Development of an interactive wall using computer vision Dabas, Ram; Dagar, Kartik; Tejas, Kumar; Shankhwar, Kalpana (Advisor); Ratn, Anoop (Advisor) This report presents the development of an Interactive Wall, a gesture-based drawing application that integrates Computer Vision, Machine Learning, and Unity to enable intuitive interaction with a virtual canvas. Using Mediapipe, the system captures real-time hand and body gestures for seamless drawing, erasing, and interaction. Key advancements include robust tracking algorithms, efficient Python-Unity communication via gRPC and UDP, and advanced rendering techniques such as shaders, decals, and render textures to create realistic brush strokes and effects. Unity’s physics engine adds dynamic, lifelike interaction with virtual objects, enhancing immersion. Optimizations such as Kalman filtering for smoother gestures and post-processing for visual enhancements improve accuracy and responsiveness. The system is scalable, can support multi-user interaction, AI-based gesture prediction, and customizable brush textures to enrich the user experience after further developments. This report outlines the design, implementation, and testing phases, addressing challenges like occlusions and real-time performance. The Interactive Wall demonstrates the togetherness of gesture recognition and immersive virtual environments, offering a novel and engaging digital interaction platform.

2024-11-27T00:00:00Z Kunal Ishan Vajpayee, Pankaj (Advisor) http://repository.iiitd.edu.in/xmlui/handle/123456789/1978 2026-05-25T22:00:19Z 2024-11-27T00:00:00Z

Tech consultancy for institute administration Kunal; Ishan; Vajpayee, Pankaj (Advisor) The project titled ”Tech Consultancy for Institute Administration” aims to address the various inefficiencies faced by students and administration in a college, especially where manual tasks can be automated through technological interventions. The primary focus of the first phase of the project is the issue surrounding the canteen services, where long wait times, inefficiencies in ordering, and the inconvenience of having to physically go to the canteen for food are common problems for students. The initial problem was identified through a series of surveys conducted with students and administrative staff, which revealed that long waiting times for food, and the inconvenience of having to walk to the canteen to place orders, were significant barriers to students opting for canteen food. Furthermore, the college’s cleaning and management team (FMS) faced similar issues of inefficient communication and management, which were exacerbated by the reliance on manual methods such as WhatsApp for handling cleaning requests. To address the food ordering issue in the first phase, the proposed solution involves implementing a campus-wide delivery service designed to streamline the process of food ordering and delivery. The system involves two agents: one responsible for collecting orders from various eating points across the campus and preparing them for delivery, and the second, a delivery agent, responsible for delivering the food to the students. This solution eliminates the need for students to wait in long queues or walk to the canteen, offering them more convenience and saving valuable time. The system is designed using a combination of React for the front-end and Django for the back- end, ensuring scalability and flexibility as the project moves forward. This phase focuses on implementing and testing the delivery service model, collecting user feedback, and refining the business model. The primary objective is to assess the viability of the delivery service, improve operational efficiency, and create a foundation for future expansion in the second phase of the project. In addition to the technical implementation, the project also includes the creation of a Business Model Canvas to assess the financial and operational feasibility of the solution, as well as a detailed User Journey to map out the experience of both students and delivery agents. The second phase of the project will expand the solution, refine the delivery process, and potentially include integration with other campus services, such as laundry and facility management. The project represents a significant step towards transforming the campus infrastructure and creating a more student-friendly environment. Beyond this first phase, the goal is to develop a sustainable, scalable solution that could be extended to other institutions, laying the groundwork for a potential startup venture focused on optimizing campus services through technology.

2024-11-27T00:00:00Z