Browsing by Author "Juvekar, Shaunak"

Now showing 1 - 2 of 2
  • Thumbnail Image
    LetsGo: Your Online Travel Coordinator
    Juvekar, Shaunak; Malik, Abdul; Raghu, Ramnath; Sethi, Raghav; Upadhayaya, Shrikanth (2023-12)
    LetsGo: Your Online Travel Coordinator is a web application designed to address the challenges Virginia Tech students face when trying to coordinate group travel. Recognizing the difficulty in forming travel groups, particularly when individuals have diverse destination preferences, LetsGo serves as a centralized platform for VT students to connect and organize shared trips. Unlike existing solutions with limited scopes, LetsGo operates as a social network-like platform, enabling students to create profiles, specify their desired destinations, and connect with others who share similar interests. Through secure messaging features, users can communicate and plan their journeys collaboratively. One key feature ensuring user safety is the platform's verification process, allowing only verified Virginia Tech students to participate. LetsGo aims to enhance the travel experience for students by fostering a sense of community and making group travel more accessible, cost-effective, and enjoyable.
  • Thumbnail Image
    Team 2 for End Users
    Paidiparthy, Manoj Prabhakar; Ramanujan, Ramaraja; Teegalapally, Akshita; Muralikrishnan, Madhuvanti; Balar, Romil Khimraj; Juvekar, Shaunak; Murali, Vivek (Virginia Tech, 2023-01-11)
    A huge collection of Electronic Theses and Dissertations (ETDs) has valuable information. However, accessing the information from these documents has proven to be challenging as the process is mostly manual. We propose to build a unique Information Retrieval System that will support searching, ranking, browsing, and recommendations for a large collection of ETDs. The system indexes the digital objects related to the ETD, like documents, chapters, etc. The user can then query the indexed objects through a carefully designed web interface. The web interface provides users with utilities to sort, filter, and query specific fields. We have incorporated machine learning models to support semantic search. To enhance user engagement, we provide the user with a list of recommended documents based on the user's actions and topics of interest. A total of 57,130 documents and 21,537 chapters were indexed. The system was tested by the Fall 2022 CS 5604 class, which had 28 members, and was found to fulfill most of the goals set out at the beginning of the semester.