EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intelligent transportation model based on least squares method and linear regression

Yukai Wang*, Huiling Zhao, Kaiwei Ren, Bingrui Ding

International Scientific Technical and Economic Research · 16.01.2025 · 1 (1) · 20-34

DOI: 10.71451/sd1rag22 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Scientific Technical and Economic Research, online erschienen am 16.01.2025. Verfasst von Yukai Wang* und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This article covers four questions about the development of high-speed rail in China. For question 1, we use a linear regression model to predict the total mileage of high-speed rail in the future. Based on the time and total high-speed rail mileage data for the past 10 years in the appendix, and using the LinearRegression model in the Sklearn library for fitting and forecasting. By fitting the model, we obtain slope and intercept parameters that describe the relationship with time. To verify the accuracy of the model. Further, we used the trained model to predict the total mileage of high-speed rail in the next 50 years and printed out the results. In addition, we save the prediction results to a CSV file for subsequent analysis and application. For question 2, we analyzed the relationship between high-speed rail passenger traffic and years from 2008 to 2021 through linear regression models. In the fitting process, we obtain the regression coefficient and intercept, which describe the linear relationship between high-speed rail passenger traffic and the year. By plotting scatterplots and regression straight lines, the fit of the data and the regression model was visualized. The results show that with the growth of time, the passenger volume of high-speed rail shows an increasing trend. By outputting the linear regression equation, we get a specific mathematical expression to describe the relationship between high-speed rail passenger traffic and year. For question 3, the optimization coefficient is mainly used to construct an efficiency model that comprehensively considers factors such as high-speed rail operating mileage, passenger traffic and passenger turnover. By defining the function of computational efficiency and the optimization objective function, the scipy. optimize. minimize() function is used to optimize and obtain the coefficient of the optimal solution. Finally, the final optimization equation is output, indicating the degree to which various factors affect efficiency. The goal of the entire procedure is to find the best coefficients to maximize the overall efficiency. Finally, we wrote a report on the future development of China's high-speed railway, covering construction planning, technological innovation, policy support and market demand, and provided prospects and suggestions for future development. This study is of great significance for understanding the development trend of high-speed rail passenger traffic and predicting future passenger traffic. In addition, the method can also be applied to data analysis and prediction in other fields to provide reference and guidance for decision-making.

Zitieren

APA

Wang*, Y., Zhao, H., Ren, K., & Ding, B. (2025). Intelligent transportation model based on least squares method and linear regression. International Scientific Technical and Economic Research, 1(1), 20-34. https://doi.org/10.71451/sd1rag22

Vancouver

Wang* Y, Zhao H, Ren K, Ding B. Intelligent transportation model based on least squares method and linear regression. International Scientific Technical and Economic Research. 2025;1(1):20-34. doi:10.71451/sd1rag22

BibTeX
@article{Wang2025,
  author = {Wang*, Yukai and Zhao, Huiling and Ren, Kaiwei and Ding, Bingrui},
  title = {Intelligent transportation model based on least squares method and linear regression},
  journal = {International Scientific Technical and Economic Research},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {20--34},
  doi = {10.71451/sd1rag22}
}
Kostenlos starten →