WOMEN SAFETY ANALYTICS – PROCTETING WOMEN FROM SAFETY THREATS

Abstract

This project present an AI-based Women Safety Analytics framework designed to protect women potential safety threats by utilizing advanced technologies. The proposed architecture focuses on real-time monitoring using mobile devices, wearable sensors, and surveillance systems. It utilizes a hybrid Deep Learning (DL) model combining Long Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs) to analyze spatial-temporal patterns and predict safety risk levels. Validated using real-time and simulated datasets, the AI framework demonstrated high accuracy in threat detection and successfully predicted unsafe situations in advance. The implementation of this system is expected to reduce response time, enhance personal security, and improve emergency response efficiency, offering a scalable solution for intelligent safety management. The modern society demands high levels of safety, awareness, and rapid response systems, making traditional reactive safety approaches inadequate. KEYWORDS: Artificial Intelligence (AI), Women Safety Analytics, Predictive Monitoring, Machine Learning, Sensors, IoT Sensors, Safety Risk Index (SRI), Threat detection, Real-Time Alerts, TimeSeries Data