Factors like traffic volume, the make and model of the vehicles, and driver behaviour are just as crucial to a road’s operational performance and safety as the weather. Weather conditions like fog and rain have an impact on visibility, which in turn affects how frequently accidents happen on a given road or the likelihood of getting into an accident. In this study, meteorological data were analysed using multiple linear regression to forecast precipitation and visibility for the benefit of various stockholders. For the purpose of analysing the data (10 years with 4018 samples), the mean square error (MSE) and its rooted version (RMSE), mean absolute error (MAE), and R-squared are used. As a result, the only way to judge the precision of models is through residuals. The empirical findings can be used by practitioners. The findings that were discovered to produce forecasts for the visibility and the rainfall.
Ruhiat Sultana, Mehveen Mehdi Khatoon, Muneeba Zuha
Bhoj Reddy Engineering College for Women, India
Linear Regression, Prediction Accuracy, Weather Data, Correlation
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 1 | 0 | 4 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Data Science and Machine Learning
( Volume: 4 , Issue: 2 , Pages: 420 - 424 )
Date of Publication :
March 2023
Page Views :
172
Full Text Views :
11
|