Research Article
Short-Term Traffic Flow Prediction: A Method of Combined Deep Learnings
| Input: the predicted value of different single model at time and actual data yt | | Output: combined prediction value | (1) | begin | (2) | calculate the prediction error of the i th prediction method by equation (15) | (3) | fordo | (4) | construct the combined prediction information error matrix by equation (20) | (5) | R ← | (6) | calculate inverse matrix | (7) | calculate optimal weights by equation (21) | (8) | calculate combination prediction results by equation (16) | (9) | output | (10) | end | (11) | end |
|