IDEAS home Printed from https://ideas.repec.org/a/pop/procee/v12y2024465-480.html
   My bibliography  Save this article

Leveraging NVIDIA AI technologies in the development of REQAPP: a machine learning platform for gathering and defining requirements for smart cities applications

Author

Listed:
  • Andra Paula AVASILOAIE

    (POLITEHNICA Bucharest)

  • Augustin SEMENESCU

    (POLITEHNICA Bucharest)

  • Eduard Cristian POPOVICI

    (POLITEHNICA Bucharest)

  • Razvan CRACIUNESCU

    (POLITEHNICA Bucharest)

  • Ionut Cosmin CHIVA

    (POLITEHNICA Bucharest)

Abstract

This paper introduces REQAPP, an innovative machine learning (ML)-powered platform utilizing NVIDIA AI technologies, such as Retrieval-Augmented Generation (RAG) chatbots, to optimize the elicitation and definition of software requirements. The platform is designed for smart city applications, including e-government, social innovation, urban planning, and urban development. REQAPP addresses the challenge of accurately gathering and refining user needs, especially for complex public sector projects, by learning and adapting from iterative interactions. The study builds on advancements in requirement engineering and the integration of ML in software development. By leveraging NVIDIA AI frameworks and tools, it extends existing research on adaptive learning systems and interactive AI solutions to meet the unique needs of smart city stakeholders. The development and evaluation of REQAPP are demonstrated through four case studies, each focusing on a distinct application domain, such as online stores, ticket booking systems, resource-sharing platforms, and urban planning tools. Using NVIDIA AI technologies, including RAG chatbots, the platform offers a conversational interface that guides users through the requirements elicitation process while dynamically refining its models based on feedback and context. The results showcase REQAPP’s ability to reduce ambiguity in requirement definitions and improve user engagement. The incorporation of RAG chatbots enhances the system's capacity to provide accurate and context-aware suggestions, accelerating the requirements gathering process and ensuring alignment with stakeholder expectations. REQAPP presents a significant advancement for academics, practitioners, and policymakers involved in smart city projects. This study contributes to the field by introducing an original AI-driven framework that combines state-of-the-art NVIDIA technologies with a machine learning-centric approach. REQAPP’s adaptability and focus on real-world smart city applications make it a valuable tool for future AI-enhanced development processes.

Suggested Citation

  • Andra Paula AVASILOAIE & Augustin SEMENESCU & Eduard Cristian POPOVICI & Razvan CRACIUNESCU & Ionut Cosmin CHIVA, 2024. "Leveraging NVIDIA AI technologies in the development of REQAPP: a machine learning platform for gathering and defining requirements for smart cities applications," Smart Cities International Conference (SCIC) Proceedings, Smart-EDU Hub, Faculty of Public Administration, National University of Political Studies & Public Administration, vol. 12, pages 465-480, september.
  • Handle: RePEc:pop:procee:v:12:y:2024:465-480
    as

    Download full text from publisher

    File URL: https://scrd.eu/index.php/scic/article/view/712/728
    Download Restriction: no

    File URL: https://scrd.eu/index.php/scic/article/view/712
    Download Restriction: no
    ---><---

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;
    ;

    JEL classification:

    • O35 - Economic Development, Innovation, Technological Change, and Growth - - Innovation; Research and Development; Technological Change; Intellectual Property Rights - - - Social Innovation

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:pop:procee:v:12:y:2024:465-480. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    We have no bibliographic references for this item. You can help adding them by using this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Professor Catalin Vrabie (email available below). General contact details of provider: https://edirc.repec.org/data/fasnsro.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.