Improving reliability of travel time estimation
A technology of travel time and average travel time, which is applied in traffic flow detection, instruments, traffic control systems, etc., and can solve the problem of insufficient calculation of average travel time statistics and accurate quantity estimation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
example
[0059]Take an example with three links link1, link2 and link3. We can further consider E[X_1]=f(E[X_2], E[X_3]). In practice, the user does not know f(), so it must be obtained numerically based on historical data. For urban roads, this function may be constantly changing over time, but due to the periodic stationary nature of urban traffic, f() remains constant at a specific time of day. To get f(), say at 9 AM, we collect all archives E[X_i] at 9 AM and perform regression analysis to find the closest function to f() and call it f(). Since we cannot obtain the exact f(), there is an error associated with approaching it, so we call it e_f (determinable by regression analysis). Now to get a reliable estimate of E[X_] at the current moment, we first calculate the sample mean using the mean of the travel times on link1. Associated with the sample mean, we also obtain the sample variance giving the confidence of the sample mean. If this sample variance is less than e_f, we use...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 