Data analysis based dynamic prediction model for public security in internet of multimedia things networks

Internet of Multimedia Things (IoMT) has gained popularity due to its immersive growth and real-time applications range from smart health to smart transportation systems. These systems always have various threats related to security breaches and privacy. With the passage of time, all types of cybercrimes and terrorism activities and its planning were initiated by using these networks and technologies. Terrorist attacks are unavoidable because of well-organized and well-planned attack planning. The all the data among these threat actors transmitted by using IoMT sensors and devices. Therefore, there is a need to analyze this type of data and predict the terrorist activities for in-time decision making. This paper presents a complete overview of existing models for such type of data and proposes a Terrorist Attacks Internet of Multimedia Things (TA-IoMT) model and a predictive model for public security in IoMT networks. The proposed model provides more effective data handling, cloud storage data management, and prediction to control and detect these kinds of activities. The results show an average of 89% accuracy, 0.73% sensitivity, and 0.92% specificity as compared to existing solutions.