The improvements of traffic data NN rules based on hypothesis interval

In the practical application of the Intelligent Transportation System (ITS), the collected and stored data through Nearest Neighbor Query can easily be contaminated by noise data. The reason is that the sensitivity of Nearest Neighbor Rules (NN Rules) to the noise data leads to the limits of Nearest Neighbor Query's practical application. To solve this problem, by using the insensitivity of Hypothesis Interval to noise data, this thesis improves NN Rules and proposes a classification mode of traffic data collection nearest neighbor rules. When the model predicts the samples, not only the distance from the test samples to the nearest neighbor is considered, but also the degree of the class to which this nearest neighbor belongs is taken into account.