http://repository.iiitd.edu.in/xmlui/handle/123456789/1008 2026-09-20T15:21:42Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2148 Trajectory prediction and forecasting of moving objects on roads Singh, Ganeev; Anand, Saket (Advisor); Kaul, Sanjit Krishnan (Advisor) This project explores the implementation and analysis of advanced SLAM (Simultaneous Localization and Mapping) techniques for autonomous vehicles, focusing on real-time trajectory prediction and forecasting of moving objects. Using the ALIVE vehicle platform equipped with multiple Velodyne LiDAR sensors and Intel RealSense cameras, three cutting-edge SLAM frameworks—KISS-ICP, ORB-SLAM3, and CT-ICP—were integrated and evaluated. Each framework contributes unique strengths: KISS-ICP for lightweight and efficient LiDAR-based mapping, ORB-SLAM3 for robust visual-inertial SLAM, and CT-ICP for continuous trajectory estimation in dynamic environments. The challenges encountered during implementation, such as ROS compatibility issues and parameter tuning, were systematically addressed to achieve robust and reliable localization and mapping performance. This report provides insights into the comparative strengths of these frameworks and highlights their applicability in enhancing autonomous navigation systems for unstructured and dynamic scenarios. 2024-11-27T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2147 Placement solutions for tier-2/3 engineering colleges Bansal, Nikunj; Biyani, Pravesh (Advisor) This project report examines the job placement process and challenges faced by students at Engineering Colleges . It begins by explaining the current procedure followed by the placement cell for inviting companies, conducting interviews, and providing job offers to students. The report identifies the key stakeholders involved in the placement process, such as the placement cell, students, the institute itself, and the companies hiring for various roles. Through surveys and interviews, the report highlights the main issues faced by students, such as the limited availability of non-software job roles and biases based on their field of study. It also outlines the goals of increasing job opportunities beyond software roles and collaborating with more companies. The report looks at the typical journey of a student through the placement process, internship policies, and how companies are categorized based on salary and job profiles offered. By analyzing insights from different stakeholders, the report provides a detailed understanding of the placement practices at Engineering Colleges and suggests ways to improve the process to better serve the diverse interests and skills of students. In simple terms, the report studies the job placement challenges at Engineering Colleges and proposes solutions to make the process more inclusive and aligned with students’ career aspirations. 2024-11-27T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2146 Controllable lay summary generation for medical text Jain, Dhruv; Panigrahi, Swapnil; Akhtar, Md. Shad (Advisor) Biomedical summarization aims to transform complex scientific literature into concise, accessible summaries tailored to diverse audiences. This paper introduces a novel approach to controlling the ”layness” of biomedical summaries by varying technical depth and complexity for three audience categories: pre-med students, researchers, and domain experts. Using large language models (LLMs) like GPT-4o and Gemini, we evaluate one-shot and few-shot prompting strategies, developing metrics S1 and S2 to quantify the balance between accessibility and technical precision. The methodology highlights the challenges of reproducibility, dependency on prompts, and the limitations of automated evaluation for nuanced aspects like readability and factuality. The findings reveal that one- shot prompting consistently outperforms alternative strategies in generating tailored summaries. However, scalability and subjective human evaluations remain significant barriers. 2024-12-03T00:00:00Z http://repository.iiitd.edu.in/xmlui/handle/123456789/2145 Remote sensing-based prediction of cyanobacterial harmful algal blooms in riverine systems Abhishek; Rani, Garima (Advisor); Kumar, Mayank Cyanobacterial Harmful Algal Blooms (CyanoHABs) pose signifi cant environmental and public health challenges, particularly in inland water bodies affected by nutrient enrichment and climate variability. This study explores the application of Sentinel-3 Ocean and Land Colour Instrument (OLCI) Level-1b satellite data for detecting and analyzing CyanoHABs in the Yamuna River, a highly urbanized and ecologically stressed river system in northern India. Using chlorophyll a concentration and meteorological parameters such as temperature, rainfall, and relative humidity, this research investigates the spatial and temporal dynamics of algal blooms. A systematic preprocessing workflow involving spatial filtering, flag masking, and outlier detec tion was employed to ensure data accuracy. Correlation analysis and visualization techniques were applied to examine the relationships be tween chlorophyll-a concentrations and environmental factors. Re sults indicate a strong positive correlation with temperature, a weak positive relationship with rainfall, and a moderate negative correla tion with humidity. Seasonal patterns reveal peak chlorophyll-a levels during pre-monsoon months, declining during post-monsoon and win ter periods. These findings underscore the utility of remote sensing combined with machine learning approaches for monitoring and pre dicting CyanoHABs, offering insights for early warning systems and water quality management strategies. 2025-07-01T00:00:00Z