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{195308,
        author = {K. Vishnu Vardhan and K. Ramana and T. Sravan Kumar and V. Chandra Shekar and Rabiya Begum},
        title = {An Automated Women Safety Framework Using Machine Learning and Real-Time Risk Assessment},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {7893-7900},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195308},
        abstract = {The safety of women remains a critical issue, particularly in urban and semi-urban environments where threats may occur unexpectedly. Most existing safety applications depend mainly on manual alerts such as panic buttons, calls, or SMS, which may not be possible during emergencies. To overcome this limitation, this research proposes an advanced women safety framework using machine learning for early threat detection and rapid response. The system continuously analyzes real-time GPS location, movement patterns, time-based risk zones, and user behavioral activities. It also incorporates historical incident data to identify unsafe areas and generate an accurate risk score. Based on the extracted features, the model classifies situations as safe or unsafe using supervised machine learning techniques. When the system detects a potential threat, it automatically triggers alerts without requiring manual input. Emergency notifications containing live location and risk information are sent to trusted contacts and local authorities. This automation reduces response time and increases the chance of immediate support. Experimental evaluation shows that the proposed model provides improved accuracy and reliability compared to traditional manual systems. The framework also reduces false alarms by using intelligent classification and risk-based decision making. It can be integrated into mobile safety apps, wearable IoT devices, and smart city platforms. The solution is scalable, efficient, and suitable for real-time implementation. Overall, the proposed system enhances women safety by enabling proactive monitoring and automated emergency response.},
        keywords = {Women’s Safety, Machine Learning, Threat Detection, Emergency Alert System, Predictive Analytics},
        month = {March},
        }