GPS test set

　　The traffic flow prediction results on the training set and the corresponding error curve are shown in Figure 2. The original data in Figure 2 (a) represents the actual traffic flow speed Y, and the prediction curve represents the traffic flow speed value YP fitted by multivariate linear regression of principal component analysis. It can be seen from the figure that there is a significant difference between the predicted value and the true value at the peak value of traffic flow. In addition to the peak value, the multiple linear regression method can generally predict the speed of traffic flow. The error curve in Figure 2 (b) more graphically shows the difference between the actual value and the predicted value.

　　The traffic flow prediction results and corresponding error curves on the test set are shown in Figure 3. Figure 3 (a) The original data curve represents the actual traffic flow speed Y on the test set, and the prediction curve represents the predicted traffic flow speed YP on the test set. It can also be seen from the test set that the situation similar to the training set also occurs, and the prediction error at the peak of traffic flow rate is large. According to the results of the experiment, it may be that when the traffic flow rate is high, the road flow is relatively smooth, the driving speed of vehicles is fast, and the positioning of mobile GPS has a certain delay, which can not accurately reflect the driving speed of cars at that time. However, it just shows that there was no congestion on the road at that time, which is convenient for people to travel. However, this method can accurately predict the traffic flow rate at the place where the traffic flow rate is low within the allowable error range, and then it can be judged that there is congestion at the place where the traffic flow rate is low, and this section is not suitable for travel at this moment.

Read recommendations:

best gps tracker

Hidden GPS Trackers wholesaler

TK08AL- RFID Car GPS Tracker

GPS receiving antenna

GPS application in troposphere monitoring