Knowledge based TTP

7.3.1 Rules constructed from traffic patterns

Two kinds of rules are constructed in this phase: rules transformed from the traffic patterns, and meta-rules donated by domain experts. The traffic patterns, mining from the historical journey set in previous phase, will then be transformed to the format of if-then rules by mapping the condition and action parts of the rule from attributes of the patterns, and decide the support and confidence of each generated rule by computing the probabilities of the rule. The if-then format rules are stored in the knowledge base, and can be easily read by inference engine and then make TTP inference. For example, SAP of Equation (5.2) can be transformed to if-then rules (SAP rules) by combining the link attribute in the traffic network database, as illustrated in Equation (7.4). The Sid, Tid, Eid information are transformed to the condition part of the if-then rule, and the congestion level (Cg) can be transformed to

77

estimated speed in the action part by considering the link attributes (speed limit, category).

And thus the estimated travel time can be calculated by dividing the length of the link with the estimated speed. Equation (7.5) shows the link travel time (LTT) estimation rule, which cooperates with STA rule and link attributes to compute the link travel time.

[SAP rule] … (7.4)

IF

(Sid and Tid and Eid) THEN

Congestion level at the Link(Sid) = Cg, Support = Sup,

Confidence = Con

[LTT rule] … (7.5)

IF

(Cg = L) and Cate(Sid) THEN

Speed at Link(Sid) = S,

LTT at Link(Sid) = Length(Sid) / S

7.3.2 Historical travel-time 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

78

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 (O, D, t) request is fed into the expert system as facts, the inference engine 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.

7.3.3 Real-time travel-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 determine the missing value in intersection delay is done in the similar way.

79

7.3.4 Dynamic weighted combination scheme

“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. Events are collected from external data sources and saved in TIDB (traffic information database) as discussed in the traffic information generation and sharing framework as discussed in Chapter 4. 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. Table 7-1 illustrates some examples of the weight assignment meta-rules donated by domain experts.

For the “event consideration” as an example, if the system 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, raise the weight of real time predictor might get higher precision. On the other hand,

“historical support is strong” meta-rule 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, raising the weight of historical predictor might get higher precision.

80

Table 7-1 Examples of the dynamic weight assignment meta-rules Weight 

Prediction time is much earlier than the departure time.

α =0, β=1 Temporal distance 

to real‐time info. is  short. 

Real-time info. in TIDB is close to the link entry time.

Raise the weight of α

Temporal distance  to real‐time info. is  long. 

Real-time info. in TIDB is far from the link entry time.

Raise the weight of α

Event 

consideration 

A real-time event is happened at some link, and some probing car just passes by the link.

Raise the weight of α

Historical support  is strong 

The support and confidence of historical patterns are strong

Raise the weight of β