Travel-Time Prediction Using Conversion Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current travel-time prediction methods lack accuracy for mid-term predictions, particularly over intermediate periods, and fail to adapt effectively to changing traffic conditions such as gridlock shifts.
Innovation Solution
A travel-time prediction apparatus and method that inputs link-specific data and day-type information to calculate conversion parameters for travel-time transition patterns, using a prediction function to minimize errors between past and real-time data, enabling accurate mid-term predictions by adjusting for current conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional travel-time prediction methods are used, then prediction can be made for long-term ranges or immediate future, but prediction accuracy for mid-term ranges deteriorates
Solution Approach 1:
The patent segments the prediction time range into three distinct categories: short-term (immediate future), mid-term (intermediate period), and long-term (half day or one full day). Each segment uses specialized prediction methods optimized for its specific time horizon, with mid-term prediction being the focus of the invention to fill the accuracy gap in intermediate periods.
Solution Approach 2:
The patent dynamically adjusts the prediction approach based on the target time range. The system selects different prediction algorithms and data processing methods depending on whether the prediction target is short-term, mid-term, or long-term, enabling optimal accuracy for each temporal segment rather than using a single static method.
2Measurement precision
If fixed-point measurement methods are used, then prediction accuracy is improved for highways, but adaptability to all road segments deteriorates
Solution Approach 1:
The patent creates a universal prediction system that can handle all road segments regardless of measurement infrastructure. By integrating multiple data sources including probe car systems, variable message sign data, and traffic volume information, the system provides accurate predictions for highways, urban roads, and intermediate roads alike, eliminating the limitation of fixed-point measurement methods.
Solution Approach 2:
The patent uses intermediary data sources such as probe car systems and variable message sign information to bridge the gap between fixed measurement points and all road segments. These intermediaries provide additional traffic flow data that enables accurate predictions on roads without fixed sensors, extending the system's versatility while maintaining accuracy.
3Adaptability or versatility
If probe-car system data is used, then applicability to all road segments is improved, but prediction accuracy for mid-term ranges deteriorates
Solution Approach 1:
The patent merges probe car system data with additional information sources including variable message sign data and traffic volume data. This combination creates a more comprehensive data set that maintains the universal applicability of probe car systems while improving mid-term prediction accuracy through supplementary traffic flow information and pattern recognition.
Data Source
AI summary
Disclosed is a travel-time prediction apparatus that is capable of making a mid-term prediction of travel time accurately by combining present conditions and statistical information. The apparatus includes a travel-time transition pattern database storing travel-time transition patterns obtained by statistically processing past time-series data of each road link according to type of data. Upon accepting a travel-time transition pattern corresponding to a specified link and day type from the database, the apparatus calculates conversion parameters of a travel-time transition pattern for which an error between the travel-time transition pattern and a sequentially input travel-time time-series data will be reduced, and then makes a prediction using a prediction function obtained by converting the travel-time transition pattern by the calculated conversion parameters. The calculated predicted value and the conversion parameters are distributed as traffic information.