| Title |
Artificial intelligence-enabled smart city construction |
| ID_Doc |
45054 |
| Authors |
Jiang, YX; Han, LF; Gao, YF |
| Title |
Artificial intelligence-enabled smart city construction |
| Year |
2022 |
| Published |
Journal Of Supercomputing, 78, 18 |
| DOI |
10.1007/s11227-022-04638-6 |
| Abstract |
This work aims to promote smart city construction and smart city management. Firstly, this work analyzes the relevant theories and processing methods of short-term traffic flow prediction. Secondly, the random forest regression (RFR) theory in machine learning is discussed to realize the short-term traffic flow prediction model (STTPM). Meanwhile, STTPM data are processed by k-nearest neighbors (KNN) and optimized by Complete Ensemble Empirical Mode Decomposition (CEEMD) and RFR method. Finally, the KNN-CEEMD-RFR model is proposed, and the performance of the model is evaluated. The results show that the proposed KNN-CEEMD-RFR model has better traffic prediction effect than support vector regression, RFR model, and CEEMD-RFR model. The prediction of support vector regression model is the worst, followed by RFR model. The mean square error of CEEMD-RFR is about 2% lower than that of RFR without data preprocessing. The mean square error of KNN-CEEMD-RFR model is 4% smaller than that of CEEMD-RFR model. Finally, the prediction accuracy of the proposed KNN-CEEMD-RFR model is more than 92%, which has a very ideal prediction effect. This work provides specific ideas for the application of artificial intelligence in smart city construction and smart city management. The proposed KNN-CEEMD-RFR model for smart city has made an important contribution to the development of traffic management in smart city management. |
| Author Keywords |
Artificial intelligence; Smart City; K-Nearest Neighbor; Random forest regression; Traffic flow prediction |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:000815426200001 |
| WoS Category |
Computer Science, Hardware & Architecture; Computer Science, Theory & Methods; Engineering, Electrical & Electronic |
| Research Area |
Computer Science; Engineering |
| PDF |
|