CPC G08G 1/0133 (2013.01) [G06N 20/00 (2019.01); G08G 1/0116 (2013.01); G08G 1/04 (2013.01); G08G 1/042 (2013.01); G08G 1/052 (2013.01)] | 13 Claims |
1. A traffic prediction apparatus comprising:
at least one memory storing instructions, and
at least one processor configured to execute the instructions to:
acquire a plurality of pieces of waterfall data that each comprise a generation position of a vibration generated by a vehicle traveling on a road, a generation time of the vibration, and an amplitude of the vibration;
process each piece of waterfall data by transforming the each piece of waterfall data;
obtain a ground truth for each piece of waterfall data using a secondary acquisition mechanism;
generate a trained model by training a model using as training data a portion of the processed pieces of waterfall data and the ground truth, the ground truth used as labels for the portion of the processed pieces of water fall data;
predict a traffic property for each piece of processed waterfall data within a predetermined time range and within a predetermined position range, based on the trained model;
generate a graph of the pieces of waterfall data having a horizontal axis indicating distance from a predetermined point to the generation position of each piece of waterfall data and having a vertical axis indicating the generation time of each piece of waterfall data; and
control a ratio between the vertical axis and the horizontal axis of the graph.
|