Abstract:
GPS accuracy can be compromised in urban areas due to multipath issues, leading to low accuracy in GPS location. Therefore, map matching has been introduced as a method to reduce the GPS location error. However, current map matching methods require high-frequency GPS data, and may not perform well with low-frequency data. To address this issue, this study explores the use of machine learning technology and classification methods to adjust the low-frequency GPS location. The model developed in this research employs features such as speed, heading, and location of the previous GPS point for machine learning training, ultimately leading to more accurate map matching for low-frequency GPS data.
The objective of this study is to develop a more accurate and efficient map matching method for low-frequency GPS data using machine learning techniques. Experiment results show that the Random Forest machine learning model produced the highest precision, recall, and F1-Score. Additionally, this model is less sensitive to changes in data frequency. However, the Decision Tree model was the fastest in terms of prediction time and required less time for training than the Random Forest model.
In conclusion, this study shows that machine learning technology can be used to improve map matching methods for low-frequency GPS data. The Random Forest model appears to be the most effective in terms of accuracy, while the Decision Tree model is the fastest. These findings can be used to optimize map matching for a wide range of applications, including transportation and navigation.
