n. abdolvand

The increasing use of technologies based on Internet of Things in cars and other transportation vehicles, as well as innovations in tracking systems and spatial information systems, have created the opportunity to collect tolls on urban roads in a more intelligent, more efficient, and a wider way. Considering the cultural and infrastructure variables in different cities, different approaches have been designed for this purpose, but so far no work has been done in this area in Tehran. Therefore, in this research, a system of hardware and software based on the Internet of things was developed based on GPS / GSM for automated urban tolls in Tehran, which manages the location of a user's car and manages toll payments at any given moment. In addition, in this system, considering the cultural issues in the country, the infrastructure in the metropolis of Tehran, and important issues of the city, the trespass submission system is designed in accordance with the existing surveillance cameras and an infrared-based structure was used to reduce the burden of image processing in order to improve efficiency. The data obtained from this system will have more potential than only the urban toll management.

The rapid development of technology, the Internet, and the development of electronic commerce have led to the emergence of recommender systems. These systems will assist the users in finding and selecting their desired items. The accuracy of the advice in recommender systems is one of the main challenges of these systems. Regarding the fuzzy systems capabilities in determining the borders of user interests, it seems reasonable to combine it with social networks information and the factor of time. Hence, this study, for the first time, tries to assess the efficiency of the recommender systems by combining fuzzy logic, longitudinal data and social networks information such as tags, friendship, and membership in groups. And the impact of the proposed algorithm for improving the accuracy of recommender systems was studied by specifying the neighborhood and the border between the users’ preferences over time. The results revealed that using longitudinal data in social networks information in memory-based recommender systems improves the accuracy of these systems.