Abstract
With the development of my country's economy, people's material development level is getting higher and higher, and people's travel requirements are increasing. However, during peak hours and holidays, traffic congestion is easy to occur, so the importance of traffic flow forecasting is not important. It goes without saying. However, most of the current traffic flow forecasting methods are based on shallow models, which essentially record data through statistical methods. However, this method has the disadvantage of not being able to conduct more in-depth analysis of the data, so its traffic flow forecasting is often inaccurate. Due to its powerful learning ability, deep neural network is widely used in image processing, text recognition and other fields, but it is rarely used for traffic flow prediction. Therefore, the purpose of this paper is to study the intelligent traffic flow prediction model based on deep neural network. This paper is devoted to statistics and analysis of traffic flow data, combined with the improved deep neural network to establish a corresponding traffic model, so as to achieve the purpose of reducing traffic jams and even traffic accidents. The experimental research in this paper shows that the application of this deep neural model to traffic flow prediction, and through our optimized model effect, not only makes the traffic flow prediction close to 9% error rate, but also utilizes the characteristics of the deep neural network on the original basis. Using the function of traffic sign recognition, it can be said that the fitting degree is very good, which fully proves the effectiveness of our improved model.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.