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{197449,
        author = {Mrs.R.Akilandeswari M.E and Pavithra.R and Keerthana.R and Monisha.P and Hemalatha.N},
        title = {SMART IOT BASED AUTOMATED LIGHT AND INTELLIGENT SURVEILLANCE SYSTEM USING ML},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {15859-15864},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197449},
        abstract = {Urban security challenges, rising crime rates, and increasing energy consumption in conventional surveillance systems necessitate intelligent, automated, and energy-efficient monitoring solutions. Traditional CCTV systems operate continuously regardless of activity, resulting in excessive power usage, redundant data storage, higher operational costs, bandwidth overload, and delayed emergency response due to manual supervision. This paper presents a Smart IoT-Based Automated Lighting and Intelligent Surveillance System using Machine Learning that integrates an Arduino PIR motion sensor, automated LED lighting, and an edge-based trained classification model for real-time abnormal activity detection. The system activates lighting and surveillance modules only when human motion is detected, thereby minimizing unnecessary energy consumption and extending device lifespan. Captured frames are processed locally using edge computing to reduce latency, enhance data privacy, and limit cloud dependency, while the machine learning model classifies activities such as unauthorized entry, theft like movements, loitering, and aggressive behavior with high accuracy. Upon detecting suspicious activity, the system instantly transmits Telegram alerts containing timestamped image evidence, enabling rapid remote response and improved situational awareness. Experimental evaluation demonstrates detection accuracy up to 95%, significant reduction in false alarms, approximately 40% power savings, optimized storage utilization, and improved overall system efficiency compared to traditional CCTV systems. 
The proposed system offers a scalable, low-cost, secure, and intelligentsurveillance framework suitable for smart cities, residential complexes, commercial establishments, industrial zones, and other high-security environments.},
        keywords = {Smart Surveillance, IoT Automation, Machine Learning, Intruder Detection, YOLO, Automated Lighting, Real-Time Alerts},
        month = {April},
        }