Identifying Crime Prediction Strategies in Schools Using the Internet of Things (IOT)

Purpose: The establishment and implementation of information and communication technology (ICT) in combating crime have made some societies more modern and innovative in crime detection. Accordingly, societies equipped with modern capabilities have greater opportunities. To enhance identification and intervention in this area, it is essential to propose a system that utilizes social tools from the Internet of Things to support the identification of criminals and the prediction of crime in the real world. One of the most critical areas for implementing the Internet of Things (IoT) to predict crimes is within schools. Students represent both the most vital and vulnerable components of the educational system and the national capital of any country. Therefore, it is essential to leverage modern technologies for crime prediction in schools. The purpose of this study is to investigate the role of the Internet of Things in predicting crimes in schools.
Method: This article is focused on its purpose and employs quantitative methods and surveys for implementation. The statistical population for this research consists of experts and criminologists in Tehran in 2023. The sample size was determined using the formula for an indefinite population. In a pilot study involving 30 questionnaires, the variance of the original sample was found to be 0.32. Ultimately, 157 individuals were selected as the sample using a simple random sampling method. The instrument used in this research is a researcher-developed questionnaire focused on the Internet of Things in schools, specifically regarding crime prediction. The data collected were analyzed using statistical inference tests and structural equation modeling.
Findings: The structural relationship analysis revealed that the direct effect of "Internet of Things capabilities" on crime prediction, with a coefficient of 0.81, indicates that these capabilities can significantly contribute to predicting crime in schools. In second place, the "Internet of Things applicability in identifying crime patterns, with a coefficient of 0.63, significantly influences crime prediction in schools. Finally, the "Internet of Things functional requirements in schools, with a coefficient of 0.52, also impacts crime prediction in educational settings. Overall, these modeling results align with the inferential findings from testing the hypotheses.
Conclusion: By using the Internet of Things in environmental design and maintenance, we can enhance local safety and environmental control, identify crime patterns, increase police awareness of criminal activity, conduct crime analysis, and utilize artificial intelligence algorithms. This approach enables us to accurately predict the occurrence of crimes in specific locations and take proactive measures to prevent them. Therefore, specialized systems and infrastructures for the development of the Internet of Things (IoT) in schools and other critical and sensitive locations should be utilized effectively, and appropriate platforms should be established to support their development. Therefore, planners, policymakers, and criminologists can leverage real data to significantly manage crime prevention processes in schools, thereby reducing the incidence of crime as the infrastructure develops.