Authors : Taruni Gayithri; Jennifer Mary S.; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/4rvhyddz

Scribd : https://tinyurl.com/5n8dt7su

DOI : https://doi.org/10.38124/ijisrt/26apr1844

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Over the past decade, artificial intelligence and cloud computing have enabled a new generation of interactive systems that are scalable, responsive, and personalized. This paper describes the design, implementation, and evaluation of a cloud-deployed conversational assistant that combines transformer-based language models, intent classification, and scalable container orchestration to deliver low-latency, context-aware dialogue services. The system uses Hugging Face Transformers and TensorFlow for natural language understanding and generation, together with RESTful microservices packaged in containers and deployed to cloud platforms (AWS/GCP) for fault tolerance and global accessibility. Evaluation with a mixed user study and automated metrics shows strong intent classification accuracy, sub-second median response latency under moderate load, and positive subjective engagement scores. The paper discusses architectural choices, deployment best practices, privacy and security considerations, and directions for integrating domain adaptation and multimodal inputs.

Keywords : Air Quality Index (AQI), Environmental Monitoring, Flask Framework, MySQL Database, Twilio SMS Alerts, Predictive Modeling, Real-Time Analytics, Intelligent Systems, Scalable Web Architecture.

References :

1. A. Kumar, R. Singh, and P. Verma, “Air quality monitoring and prediction using particulate matter analysis: A comprehensive review,” Environmental Monitoring and Assessment, vol. 192, no. 6, pp. 1–18, 2020.
2. S. Gupta and A. Bansal, “Low-cost sensor-based air quality monitoring systems: Design challenges and deployment strategies,” International Journal of Environmental Science and Technology, vol. 18, no. 4, pp. 1123–1136, 2021.
3. M. Tiwari, N. Patel, and R. Sharma, “A lightweight AQI prediction model for real-time applications using pollutant concentration data,” Journal of Atmospheric Pollution Research, vol. 12, no. 3, pp. 445–454, 2021.
4. J. Chen and K. Li, “Web-based environmental monitoring platforms: Architecture, implementation, and case studies,” IEEE Access, vol. 8, pp. 157920–157934, 2020.
5. P. Das and S. Roy, “Design and development of an IoTenabled air pollution alert system using real-time sensor data,” IEEE Internet of Things Journal, vol. 7, no. 12, pp. 12384–12392, 2020.
6. A. Rahman and M. Alam, “Evaluation of simplified AQI computation models for urban air quality assessment,” Aerosol and Air Quality Research, vol. 21, no. 2, pp. 1–12, 2021.
7. S. Patel, V. Shah, and G. Chauhan, “Real-time environmental data analytics using cloud-integrated dashboards,” International Journal of Computing and Digital Systems, vol. 10, no. 5, pp. 857–868, 2021.
8. L. Zhang and T. Zhou, “SMS-based public alerting frameworks for environmental hazard detection,” IEEE Transactions on Humanitarian Technology, vol. 2, no. 1, pp. 34–45, 2021.
9. R. Malhotra and S. Mehra, “Flask-based web applications for environmental data visualization: Performance and scalability analysis,” International Journal of Web Engineering, vol. 6, no. 4, pp. 221–233, 2022.
10. B. Ahmed, F. Hussain, and T. Khan, “Air pollution forecasting techniques and their applications: A detailed review,” Atmospheric Environment, vol. 246, pp. 118–135, 2021.