Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196462,
        author = {Mohammad Ifham Gulzar and Hemavathi J},
        title = {CROWDMIND: A SMART CROWD FLOW PREDICTION SYSTEM FOR URBAN SPACES USING MACHINE LEARNING AND GEOSPATIAL ANALYTICS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2715-2721},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196462},
        abstract = {Urban areas are experiencing rapid growth, leading to increased crowd congestion in public spaces such as transportation hubs, shopping complexes, tourist destinations, and educational institutions. High crowd density can result in safety risks, reduced mobility efficiency, and poor user experience. Traditional crowd monitoring approaches, which rely on surveillance systems or manual observation, often lack scalability and predictive capability. In this work, we present CrowdMind, an intelligent system designed to monitor and predict crowd flow using mobility data and machine learning techniques. The system collects anonymized GPS data from mobile devices and processes it using spatial clustering and time-series forecasting models. The proposed approach integrates DBSCAN for real-time crowd detection, Long Short-Term Memory (LSTM) networks for temporal prediction, and the Prophet model for capturing seasonal trends in crowd behavior. The system architecture includes a mobile interface, a FastAPI-based backend, machine learning models developed using TensorFlow and Scikit-learn, and a MongoDB database for geospatial data storage. Additionally, the system provides features such as optimal time recommendations, crowd visualization, and emergency alerts during high congestion scenarios. Experimental evaluation shows that the system can effectively identify crowd hotspots and provide reliable predictions. 
CrowdMind contributes to the development of smarter urban mobility and efficient crowd management solutions.},
        keywords = {Crowd Prediction, Smart Cities, Machine Learning, DBSCAN, LSTM, Geospatial Analytics, Urban Mobility.},
        month = {April},
        }