Comparative analysis of artificial intelligence networks in crime prevention Case Study: Counterfeit Medicines

Preventing crimes related to counterfeit drugs, due to the technologies used in the production and distribution of these drugs, will not have a bright outlook with traditional methods such as field surveillance. Therefore, adopting appropriate preventive measures requires the use of innovative technologies capable of detecting these crimes on a large scale and with high accuracy. In this regard, artificial neural networks such as recurrent neural networks, generative adversarial networks, and convolutional neural networks, inspired by the structure of the human brain, are capable of detecting these crimes. However, each of these networks has its drawbacks, ignoring which makes the legal system face difficulties in preventing these crimes. Therefore, the present study, through a case study method, seeks to identify the most efficient neural network for preventing these crimes. The outcome of this research indicates that the legislature has paid special attention to the monitoring technique in the prevention domain but has not defined the tools for this monitoring. Nevertheless, the Food and Drug Administration, using the Titac system (tracking code), identifies the discovery of crimes in this area. However, due to the non-intelligence of the system, it will not be able to detect all forms of fraud. Therefore, simultaneous use of three networks (recurrent neural networks, generative adversarial networks, and convolutional neural networks) in the form of a composite neural network seems to improve the detection of drug crimes on a large scale.