Review this prior art and click on the thumbs up (or down) to indicate whether this submission should be forwarded to IP Australia.
If you login then you can add an annotation by typing in the box at the bottom of the screen to comment on the relevance of the prior art to the claims of the patent application.
| Summary / Description | A similar traffic prediction system for guiding traffic to avoid congestion. DynaMIT is similar to the application because it uses historical data as well as various other factors like topology information, queue and speed (corresponds to density in application). In addition, it also does pre-trip prediction and en-route prediction (i.e. real-time update of route). |
| Type of Prior Art | Online Publication |
| URL | http://citeseerx.ist.psu.edu/vi... |
| Author/Creator | Moshe Ben-Akiva, Michel Bierlaire, Haris Koutsopoulos, Rabi Mishalani |
| Title | DynaMIT: a simulation-based system for traffic prediction |
| Publication Date | February 28, 1998 |
| Publisher | DACCORD Short Term Forecasting Workshop |
| Directions to Document Location | |
| Additional Information | |
| Notes | |
Excerpt DynaMIT is a real time dynamic traffic assignment system that provides traffic predictions and travel guidance. To maximize the quality of the prediction, a rolling horizon framework has been implemented. It enables frequent re-estimation of the current state of the network, which is the starting point of the prediction process, to continuously exploit the real-time information collected by the surveillance system. ... combine aggregate and disaggregate traffic representation in the same framework. |
A method of scheduling the movement of trains, each over a selected route, by predicting the occurrence of congestion due to the planned movement of the trains over a selected route comprising:
(a) identifying factors which contribute to congestion (200);
(b) assigning a metric for each factor (210);
(c) evaluating the metrics associated with a selected route (220);
(d) if the evaluate metrics exceed a predetermined threshold (230), scheduling one or more trains scheduled for the selected route to alternate routes (240).
| Relevance | This method is the standard model used for multi-factor decision making system. |
The method of Claim 1 wherein the step of identifying includes evaluating the historical performance of train movement over a selected route.
| Relevance | Figure 1 and various paragraphs in the article talks about utilising historical data for the prediction. |
The method of Claim 1 wherein the step of evaluating includes cumulating the metrics for a selected route.
| Relevance | Aggregated information are used as described in section 3.1 Mesoscopic Demand Simulation. |
A method of scheduling the movement of trains, each over a selected route, by predicting the occurrence of congestion due to the planned movement of the trains over a selected route comprising:
(a) identifying factors which contribute to congestion (200);
(b) assigning a metric for each factor (210);
(c) evaluating the metrics associated with a first planned movement of plural trains over a selected route (220);
(d) evaluating the metric associated with a second planned movement over a selected route (220);
(e) selecting the planned movement having the lowest metric for scheduling the movement of trains over the selected route.
| Relevance | This method is the standard model used for multi-factor decision making system. |
The method of claim 6 wherein the factors include at least one of train density, environmental, temporal, seasonal, and track topology.
| Relevance | train density, environmental, temporal and seasonal data may very well be part of the historical data, whereas the track topology is explicitly used in the prior art as network topology data. |
United States