AI-Based Suspicious Identification System for Agency Security Monitoring using Big Data Fusion

Terrorism is now a global issue, particularly the use of objects, car bombs, and even human suicide attacks. However, these issues can be avoided by reporting any anomalies that occur in the area. Unfortunately, it is not possible to use people to inspect the entire area. This study presents an AI-based suspicious identification system for agency security monitoring based on big data fusion, which employs specific data from an agency’s person, thing, and vehicle that appear at various times and locations. The best machine learning algorithm was used to train this data, and the results were displayed in real-time on the web application. In our experiment, we used ANN, SVM, k-NN, decision tree, and Naive Bayes to train the suspicious model with Scikit-learn on Python. The decision tree algorithm has the highest classification accuracy of 98.867% and the fastest prediction speed of 0.005 milliseconds per sample, according to the experiment results.