What question did this study set out to answer?

This research aims to develop a system for predicting terrorist attacks using machine learning and sensor data.

May 7, 2026

ThreatSense: Terrorist attack Prediction Using Machine Learning

Key Points

This research aims to develop a system for predicting terrorist attacks using machine learning and sensor data.
Developed ThreatSense system integrating data from motion sensors and acoustic sensors.
Utilized advanced machine learning algorithms for prediction including XGBoost and LSTM.
Incorporated explainable AI techniques to enhance transparency of predictions.
The model classifies threats into five levels, from low risk to critical threat.
Demonstrated accurate detection of suspicious activities through integrated multi-modal data.

Abstract

Terrorism remains one of the major global security threats affecting public safety and national stability. Early detection of potential terrorist activities can significantly reduce damage and loss of life. In this research, we present ThreatSense, a terrorist attack prediction system based on machine learning and IoT sensor networks. The system integrates data from surveillance cameras, motion sensors, acoustic sensors, and social media feeds to detect suspicious activities. Advanced algorithms such as XGBoost and LSTM are used to analyze multi-modal data and predict threat levels. To improve transparency and reliability, the system also incorporates explainable AI techniques like SHAP to identify which features contribute to threat prediction. The model classifies threat levels into five categories ranging from low risk to critical threat. Overall, this paper explains system design, methodology, data analysis, results, and future scope showing how AI and IoT can support proactive threat detection.

Mark Helpful

Bookmark

Relay