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{175865,
        author = {Magham Sai Prasanna and Dr Syamala Rao P and Mullu Sanjay Kumar and Konala Jeeva and Mohammad Shakeeth},
        title = {Emergency Safety Control System using Machine Learning and Recent Contact Monitoring},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {6813-6818},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175865},
        abstract = {High crime rates and health risks contribute to human safety concern, mainly for women, girls, and the elderly. Personal safety is the top priority, particularly for vulnerable groups such as women, girls, and the elderly. Most of the injury- related deaths among the elderly are caused by falls, and women also have unsafe incidents that require immediate intervention. This paper proposes an Emergency Safety Control System based on smartphone sensors and the Random Forest machine learning algorithm to detect falls and send notifications to preselected emergency contacts. The system collects real-time accelerometer data, performs a trained Random Forest model, and sends a notification to guarantee a prompt response. The algorithm achieves a remarkable accuracy of 94.41%, which is a very useful tool to separate falls from normal activity. A nice feature of the system is the smart contact selection feature: although users can manually input emergency contacts, the system will automatically select the most recently contacted person if no manual selection is available. This guarantees the most appropriate people are notified for a quicker and better response. The system design ensures reliability, cost, and ease of use without the need for external hardware. The system is also scalable to ensure it can be used in different environments. Experimental results confirm the effectiveness of the system in detecting falls and providing timely notifications, which is a practical and reliable approach to personal safety in real-world applications.},
        keywords = {Emergency Alert System, Fall Detection, Machine Learning, Intelligent Contact Selection, Real-time Data Process- ing, Personal Safety.},
        month = {April},
        }