| Airport security screening plays a vital role in safeguarding passengers and preventing security threats. Traditional screening methods rely on manual observation and rule-based risk assessment, which can be time-consuming, inconsistent, and prone to human error. This study explores the application of ML techniques to enhance behavioral analysis in airport security screening. Various ML models, including supervised, unsupervised, and reinforcement learning approaches, are utilized to analyze passenger behavior, identify suspicious activities, and detect anomalies in real-time. Techniques such as facial recognition, gait analysis, and sentiment detection are integrated to assess behavioral patterns and flag potential threats. Anomaly detection algorithms, including clustering-based and deep learning models, help identify deviations from normal passenger behavior, allowing security personnel to focus on high risk individuals without disrupting the overall passenger flow. In this paper, the implementation of ML-based behavioral analysis in airport security screening has the potential to revolutionize threat detection by providing a more objective, efficient, and data-driven approach. By combining advanced analytics with human expertise, ML-driven security screening can enhance both safety and operational efficiency in modern airports. |
*** Title, author list and abstract as submitted during Camera-Ready version delivery. Small changes that may have occurred during processing by Springer may not appear in this window.