THE WOMEN SAFETY TRACKER APP

Abstract

Ensuring women's safety in public and private
spaces remains a pressing social and
technological challenge. Although numerous
mobile applications offer emergency calling and
location sharing, most of them operate only after
the user manually activates an alert and do not
provide any intelligence to assess the
surrounding risk. This paper presents the
Women Safety Tracker App, an AI-enabled
safety platform that combines real-time GPS
tracking, machine learning-based risk
prediction, and automated emergency
communication.
The proposed system evaluates multiple
contextual parameters, including road condition,
traffic density, crowd level, street-light
availability, time of day, and historical crime
statistics, to estimate the likelihood of danger.
Based on this analysis, the system classifies the
environment into Safe, Moderate Risk, or High
Risk. When a high-risk situation is detected, the
application automatically sends a WhatsAppbased
SOS alert containing the user's live
location to pre-registered emergency contacts.
The application is developed using HTML,
CSS, and JavaScript for the user interface,
Python and Flask for backend services, SQLite
for data management, and Twilio API for alert
delivery. Experimental testing confirms that the
system provides timely alerts, accurate risk
classification, and reliable real-time location
sharing.
The Women Safety Tracker App transforms
conventional emergency tools into an intelligent
and proactive personal safety system capable of
delivering rapid assistance and improving
situational awareness