Smart Women Safety Prediction and Alert System

Abstract

Women’s safety is a major concern, especially in urban areas where risks can vary with location, time, and previous incidents. Most existing safety applications mainly focus on emergency assistance rather than identifying risky areas in advance. This paper presents a web-based Smart Women Safety Prediction & Alert System that combines Machine Learning, GIS, incident analysis, and emergency alerts. K-Means clustering is used to identify incident hotspots, while Logistic Regression predicts Low, Medium, and High risk levels. The system provides Incident Reporting, Safety Map, Safe Route, Nearby Police, Emergency Contacts, and Quick SOS features. Using 12,000 incident records, the system generated 10 clusters, and the Logistic Regression model achieved 84.42% accuracy. PostgreSQL with PostGIS, React.js, and Flask were used for system development. The proposed system combines safety prediction, location-based analysis, and emergency support in a single web platform.

Introduction

The Smart Women Safety Prediction & Alert System is a web-based platform designed to combine women’s safety prediction, GIS-based analysis, incident reporting, safer route planning, and emergency assistance in one system.

The system addresses a limitation of many existing women-safety applications, which mainly provide SOS alerts or emergency support after an incident occurs. The proposed system instead uses historical and user-reported incident data to identify risky areas and predict safety levels in advance.

Key Features

• Incident Reporting: Users can report safety incidents, allowing the system’s incident database to be continuously updated.

• Hotspot Identification: K-Means clustering groups incidents based on their geographic locations to identify areas with high incident concentration.

• Risk Prediction: Logistic Regression predicts whether a location has Low, Medium, or High risk based on location and time-related features.

• Safety Map: GIS technology displays risky areas and incident hotspots on an interactive map.

• Safe Route: The system considers risk information along routes to help users identify safer travel paths.

• Nearby Police: The system identifies the nearest police station based on the user’s selected location.

• Emergency Support: Users can manage emergency contacts and activate a two-click SOS, which sends alerts containing location information through SMS.

Conclusion

This research presented the design and implementation of a Smart Women Safety Prediction & Alert System that combines machine learning, GIS-based analysis, incident reporting, and emergency alert services within a web-based platform. The system integrates K-Means clustering for identifying incident hotspots and Logistic Regression for predicting location-based risk levels as Low, Medium, and High.The implementation demonstrated that historical and user-reported incident data can be used to provide safety-related information through the Safety Map, while the Safe Route and Nearby Police features provide additional location-based support. The system also allows users to report incidents and manage emergency contacts, making the platform useful for both safety analysis and user assistance. The Logistic Regression model achieved an accuracy of approximately 84.42%, and the K-Means clustering process generated 10 incident clusters from the 12,000-record dataset. The emergency module was also successfully integrated with the application through the two-click Quick SOS mechanism. During testing, the system identified the nearest police station, retrieved the registered emergency contacts, sent the configured SMS notification, and stored the SOS event in the PostgreSQL database. Overall, the developed system provides a practical approach to combining risk prediction, hotspot identification, GIS-based safety analysis, and emergency assistance in a single platform. The implementation provides a foundation that can be further improved using larger datasets, updated safety information, mobile application support, and integration with additional emergency services.

References

[1] M. Ara and N. Rajeshwari, “AI-Based Women Safety and Alert System,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), 2026. [2] A. K. Sinha, A. V. Kumar, R. Saha, A. Roy, and K. J. Kadel, “Women Security Application Using Smart Emergency Response System and Real-Time Location Tracking,” International Scientific Journal of Engineering and Management (ISJEM), 2025. [3] P. Vasantha, R. Swathi, R. Anka Sravani, P. Deepthi, and R. Srivalli, “AI-Powered Women Safety System with Predictive Crime Alerting,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET), 2025. [4] B. Lokesh, A. Peddininti, and A. R. Uppala, “Women Safety Analytics – Protecting Women from Safety Threats,” International Research Journal on Advanced Engineering Hub (IRJAEH), 2025. [5] A. S. Indalkar, P. A. Tamgave, S. P. Khalate, S. D. Gurav, and S. T. Pawar, “Technological Interventions for Women’s Safety: A Review of Emergency Alert, Live Tracking, and Real-Time Monitoring Features in Mobile Applications,” Journal of Emerging Technologies and Innovative Research (JETIR), 2025. [6] K. P. V. N. Satya Sree, Ch. Bahnu Sri, G. Naga Sandhya, and G. Gangadhar Gowtham, “Safe Path: A Real Time Women Safety Application,” Journal of Nonlinear Analysis and Optimization: Theory & Applications, 2025. [7] K. Shankar, S. C. Prajwal, V. G. Kumar, P. Anusha, R. C. S. Kameswar, and S. Bhanu Prakash, “Women Safety App to Detect Danger and Prevent Automatically Using Machine Learning,” Proceedings of the International Conference on Computational Innovations and Emerging Trends (ICCIET), 2024. [8] Prakruthi N., Radhika, Niriksha, and Manjunatha, “A Survey for Women Safety Alert System with Location-Based Notification and Community Awareness,” International Journal of Advanced Research in Science, Communication and Technology (IJARSCT), 2024. [9] A. Eranpurwala, F. Indorewala, N. Mapari, and S. Mishra, “Women Safety Application for Safe Route Prediction,” International Research Journal of Engineering and Technology (IRJET), 2021. [10] K. Agarwal, A. Srivastava, K. Sharma, S. K. Satapathy, S.-B. Cho, and S. Mishra, “SafeRoutes: Charting a Secure Path – A Holistic Approach to Women’s Safety through Advanced Clustering and GPS Integration,” IEEE Access, 2017.

Copyright

Copyright © 2026 Shravani Dasthari, Rajeshwar Amirishetty . This 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.