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{209654,
        author = {Ms.V. Revathy and Mrs. Megha U. Vakani and Dr. S. Sivakumar and Mrs. Palak Modi and Ms. Pooja Vora and Ms. Ami Patel},
        title = {Design and Implementation of an Edge AI-Based Smart IoT System for Real-Time Environmental Monitoring and Intelligent Decision Making},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {2865-2869},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209654},
        abstract = {Environmental monitoring supports public health, industrial safety, agriculture, and sustainable development. Conventional IoT monitoring systems often transmit sensor readings to remote servers for analysis, creating dependence on network availability and potentially delaying alerts. This paper proposes an Edge Artificial Intelligence (Edge AI)-based smart Internet of Things system for real-time environmental monitoring and intelligent decision-making. The architecture integrates environmental sensors, an embedded edge controller, a lightweight machine learning model, wireless communication, and a remote dashboard. Temperature, relative humidity, particulate matter, and suitable gas-related measurements are acquired, validated, and processed locally. An anomaly-detection module identifies unusual patterns and supports local alert generation, while cloud connectivity enables historical storage and remote visualization. The design also considers sensor faults, temporary network outages, data buffering, and secure communication. A practical evaluation plan is defined for detection performance, processing latency, communication overhead, energy use, and operational reliability. The proposed framework offers an implementable basis for smart-campus, building, industrial, and urban monitoring. Quantitative performance claims require validation through a working prototype and documented experiments.},
        keywords = {Edge AI, Internet of Things, Environmental Monitoring, Machine Learning, Anomaly Detection, Embedded Systems, Intelligent Decision-Making.},
        month = {October},
        }