http://repository.iiitd.edu.in/xmlui/handle/123456789/966 BTPs 2026-09-02T07:52:50Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2072 Title: Designing Tactile graphics for the blind and visually impaired Authors: Verma, Ashwin; Gupta, Richa (Advisor) Abstract: This project builds upon the previous version of TacTile, which was developed in the prior semester using an EfficientNetV2-B0 and YOLO-based backbone. In the current version, we transitioned to using the MediaPipe Hand Landmark detector combined with a plain JSON file to store coordinates of the desired regions. To improve the robustness of the application, we have now trained a YOLOv8 model specifi- cally on cropped map regions. This enhancement ensures that the application functions reliably regardless of the phone’s height or position, as long as it remains parallel to the map surface. We are still using mediapipe for Hand Landmark ditector. 2025-07-25T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2071 Title: The Dot Store - a comprehensive study, UX research and in-depth implementation Authors: Dwivedi, Shivam; Grover, Anuj (Advisor) Abstract: The Dot Store, started in May 2023 as an independent project under the guidance of Dr. Anuj Grover, began as an in-depth business research endeavor involving numerous surveys and interviews to identify needs within the creator economy. This research highlighted significant opportunities, leading to the official launch of The Dot Store as a startup in September 2023. The platform was designed to empower creators by turning their product ideas into reality, han- dling all aspects from design to sales, thus addressing the challenge creators face in monetizing their content. The first creator was onboarded in October 2023, with the first sale marking the beginning of a profitable venture, achieving a max monthly revenue of Rs. 120,000/- and a max net profit of Rs. 34,000/- in August 2024. Throughout this B.Tech project, the focus was on solidifying the business fundamentals, establishing standard operating procedures, and expanding the startup further. The Dot Store operated from 532 in the IIITD Innovation and Incubation Centre at IIITD with a core team of three and an extended network of 12 volunteers till July 2024, afterwards it shifted its operations to working partially out of student startup working space in E-Cell IIITD and partially remote. Furthermore, during this BTP, the venture’s innovative approach and business potential were recognized during its progression through three stages of the television show Shark Tank India, although it did not reach the final round. This report details the development of The Dot Store, reflecting on both the challenges faced and the achievements made in creating a sustainable and empowering platform for creators of all sizes. The project exemplifies the practical application of academic and entrepreneurial principles to create a viable business solution in the modern digital landscape. 2024-11-22T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2050 Title: Dynamic neural networks for continual learning Authors: Ghosh, Ratnango; Gupta, Vaibhav; Bagler, Ganesh (Advisor) Abstract: This report proposes a novel ensemble pipeline designed to address adaptive streaming natural language processing (NLP) challenges while mitigating catastrophic forgetting. Our architecture integrates five core components: dynamic slang detection, fruit fly–inspired sparse encoding, a memory-augmented streaming transformer, dual continual-learning defenses (Elastic Weight Consolidation and Unlabeled Knowledge Distillation), and an associative output layer. The pipeline operates across multiple temporal scales—short-term attention sinks and sliding windows, medium-term reservoir sampling, and long-term stable knowledge preservation—enabling efficient handling of real-time, evolving text streams. Key results from preliminary simulations indicate a 75% reduction in forgetting degradation, 20× speedup on long sequence processing, and 90% retention of prior-task performance after domain shifts. Our findings demonstrate the feasibility of layered defenses against forgetting and real-time adaptation to linguistic drift, offering robust performance for applications in chatbots, social media monitoring, and information retrieval. 2025-07-18T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2049 Title: Pipeline for end-to-end training of DL-augmented LS channel estimation Authors: Aadya; Darak, Sumit Jagdish (Advisor) Abstract: This work presents an enhanced training strategy for LSDNN (Least Squares Deep Neural Net- work) [1], a lightweight deep neural network designed to improve LS channel estimation in pilot-based OFDM systems. The approach offers two key advantages: (1) it enables LSDNN to be trained using practical data sources, such as transmitted codewords and demapper LLRs, and (2) it achieves superior Bit Error Rate (BER) performance through this end-to-end training. By removing the need for perfect CSI during training, the proposed method simplifies implementation in real-world scenarios and aligns with the goal of deploying the system on hardware such as Software Defined Radios (SDRs). Compared to our baseline model, LSDNN strikes a balance between performance and efficiency, with significantly lower computational complexity, fewer parameters, and reduced memory requirements, while delivering competitive results. The model’s ability to generalize to unseen channel models further underscores its potential for real-world applications. This work demonstrates how deep learning can complement traditional signal processing to create efficient, adapt- able, and high-performance wireless communication systems. 2024-12-03T00:00:00Z