Ontology for travel time prediction

Ontology building mainly depends on the contribution of domain experts in the knowledge creation activity. Metadata extraction and merging is carried out manually by domain experts. As shown in Figure 7-3, the TTP ontology designed by cooperation of the traffic domain experts, knowledge acquisition engineers, and system design engineers to organize the TTP inference structure consists of several design concepts and the relationships among these concepts, where one type of concepts is meta-concept drawn by red circle encrypting the domain knowledge donated by the traffic domain expert, or process control knowledge designed by system engineer, and the other is normal concept drawn in black circle representing the static knowledge or mining knowledge generated in the rules construction phase.

There are several relationships between these concepts, such as “is-a”, “includes”,

“modify”, “related-to”. These relationships connecting concepts in the ontology represent some interactions among them. For example, “real time TTP predictor” concept includes a

“Path selection” concept, and “Path selection” concept includes “Path to link decomposition” concept. When the TTP predictor concept is started, path selection process is then fired to find out the candidate paths between origin and destination, and the path selection process then fires the path to link decomposition process to get the links and intersections to be used to evaluate the travel time in each candidate path. In the following subsections, some major concepts in the TTP are detailedly discussed to outline this TTP ontology workflow.

72

Figure 7-3 Design ontology of the TTP system

7.2.1 TTP system workflow

The TTP system workflow which depicts the relationship of several system modules for the TTP is shown in Figure 7-4. “Heuristic path selection” module analyzes the (O, D, t) input data and generates the heuristic candidate paths from the origin to the destination with the assistance of the GIS engine and TIDB. The “path to link decomposition” module decomposes each candidate path to a set of continuous network objects from the origin to the destination, where a network object may be link or an intersection. The link travel time is then estimated by the “real-time predictor” and “historical predictor”, and the intersection objects travel time is estimated by the “intersection delay” module. After all the objects in the candidate paths are estimated, the travel time of a candidate path can be estimated by

73

summing up all the network object travel time in the candidate path, including links travel time and intersections delay. The “meta-rule weighted combination” module integrate the dynamic weight decision mechanism donated by the traffic domain experts, which decides the weight of real-time as well as historical predictors by considering the effect of the external events and spatiotemporal traffic patterns. Finally the “path selection” module select the shortest travel time path as the system suggested path and shows the estimated travel time of the suggested path.

Figure 7-4 travel time prediction inference workflow

74

7.2.2 Heuristic Path Selection

Path selection module is activated by the travel time predictor modules by the “includes”

relationship in the TTP ontology. Path selection problem in the urban road network is much more complicated than that in freeway since only few paths can be chosen in freeway path routing for a given (O, D, t) input. To minimize the path travel time, many strategies had been proposed for a routing path selection based on a given (O, D, t) input in the urban network, such as shortest path first, expressway first or signal less path first, etc. The common goal in these strategies is to minimize the path traveling time. To cope with the path selection problem, heuristic and domain knowledge are used in this dissertation. Since most of the taxi drivers can most likely select the heuristic optimal path according to their experience and the current traffic status. Our idea is to select top k paths from the journey set in the historical database as the candidate paths according to the request (O, D, t).

7.2.3 Historical Predictor

Historical predictor and real-time predictor inherited from the TTP concept include two parts: link travel time estimation and intersections delay prediction. After historical predictor inferring the travel time of each link and intersection delays in the candidate path, the total amount of the links travel time and intersection delays is the predict result. Link travel time estimation is inferred by rules obtained from the spatiotemporal congestion patterns.

Intersection delay prediction is reasoned by the rules obtained from the intersection delay patterns, which are classified by through delay (TD), right turn delay (RTD) and left turn delay (LTD). The rules transformed from these patterns are stored into the knowledge base (KB). When a (O, D, t) request is fed into the expert system as facts, the inference engine

75

automatically fires the rules related to the historical TTP prediction. Meta concept components in this ontology help to fill out the missing values and fixed some outliers. For example, if one rule shows that one link can be traveled at a speed in peak hour which is much higher than the speed limit, the meta-rule in “fix & adjust” component might fix and replace it with the speed limit of that link.

7.2.4 Real-Time Predictor

Real time TTP of a candidate path can be done by summing up the travel time of each links and intersections delay which constitute the path, where the current travel time of a link can be easily done by dividing the link length with current average traveling speed of that link, and the real time intersection delay is obtained from the real time traffic information generated in Phase I. In the case of missing current speed of some links, a speed evaluation meta-rule given by domain expert in the “default values” concept is fired to give a default speed depending on their heuristic experience and spatiotemporal conditions. For example, domain expert may give default speed of midnight on non-holiday as 20% more than the speed limit of the link. The process of determining the missing value in intersection delay can be done in the similar way.

7.2.5 Dynamic Linear Combination

“Dynamic linear combination” concept incorporates with “external event” concept to provide the real time event response ability for the TTP model, which raises the precision of TTP and makes it more practicable. Real time event response mechanism consists of several meta-rules, which is designed to handle the external events by dynamic tuning the weight of two predictors: Tc, Th through weight control variables: α and β. For example, if the system

76

receives a current external event, such as car accident on a link in the candidate path, event handling meta-rules will then reduce the weight of historical predictor (Th) and raise the weight of real time predictor (Tc). Because the effect of that car accident will be reflected at the corresponding link immediately, raising the weight of real time predictor might get higher precision. On the other hand, some meta-rules may raise the weight of historical predictor if the following two conditions are satisfied: if there is no current event, and the support and confidence of the related patterns are higher than the threshold set by the expert. It means that there is a strong support that traffic status most likely regresses to the intents of related historical patterns. Therefore, raise the weight of historical predictor might get higher precision.