Research on Lane Occupancy Rate Forecasting Based on the Capsule Network
This paper proposes a hybrid lane occupancy rate prediction model called 2LayersCapsNet, which combines the improved capsule network and convolutional neural networks (CNNs). The model uses CNNs to mine the spatial-temporal correlation characteristics of the lane occupancy rate and then uses an impr...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9006880/ |
| _version_ | 1818446406005817344 |
|---|---|
| author | Ran Tian Jiaming Bi Qiang Zhang Yanxing Liu |
| author_facet | Ran Tian Jiaming Bi Qiang Zhang Yanxing Liu |
| author_sort | Ran Tian |
| collection | DOAJ |
| description | This paper proposes a hybrid lane occupancy rate prediction model called 2LayersCapsNet, which combines the improved capsule network and convolutional neural networks (CNNs). The model uses CNNs to mine the spatial-temporal correlation characteristics of the lane occupancy rate and then uses an improved capsule network to mine the interrelationships in traffic data measured by sensors in continuous time intervals to predict the lane occupancy rate. The model can solve the problem of CNNs losing important spatiotemporal information caused by the maximum pooling operation and can obtain better prediction results. To verify the efficiency of the 2LayersCapsNet model, the model is compared with the capsule network model (CapsNet), convolutional neural networks model (CNNs), recurrent neural networks model (RNNs), long short-term memory model (LSTM) and stacked autoencoders model (SAEs) with similar network structures and parameter settings on the PEMS-SF data set. The experimental results indicate that the 2LayersCapsNet model can obtain a prediction model faster than the CapsNet model and that 2LayersCapsNet performs better than the CNNs, RNNs, LSTM and SAEs with respect to three evaluation metrics, namely, MAPE, MAE and RMSE, on four prediction tasks. |
| first_indexed | 2024-12-14T19:47:13Z |
| format | Article |
| id | doaj.art-50b58881a67c483d946bed7b14d28efd |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T19:47:13Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-50b58881a67c483d946bed7b14d28efd2022-12-21T22:49:32ZengIEEEIEEE Access2169-35362020-01-018387763878510.1109/ACCESS.2020.29756559006880Research on Lane Occupancy Rate Forecasting Based on the Capsule NetworkRan Tian0https://orcid.org/0000-0001-8189-1842Jiaming Bi1Qiang Zhang2Yanxing Liu3Department of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaDepartment of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaDepartment of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaDepartment of Computer Science and Engineering, Northwest Normal University, Lanzhou, ChinaThis paper proposes a hybrid lane occupancy rate prediction model called 2LayersCapsNet, which combines the improved capsule network and convolutional neural networks (CNNs). The model uses CNNs to mine the spatial-temporal correlation characteristics of the lane occupancy rate and then uses an improved capsule network to mine the interrelationships in traffic data measured by sensors in continuous time intervals to predict the lane occupancy rate. The model can solve the problem of CNNs losing important spatiotemporal information caused by the maximum pooling operation and can obtain better prediction results. To verify the efficiency of the 2LayersCapsNet model, the model is compared with the capsule network model (CapsNet), convolutional neural networks model (CNNs), recurrent neural networks model (RNNs), long short-term memory model (LSTM) and stacked autoencoders model (SAEs) with similar network structures and parameter settings on the PEMS-SF data set. The experimental results indicate that the 2LayersCapsNet model can obtain a prediction model faster than the CapsNet model and that 2LayersCapsNet performs better than the CNNs, RNNs, LSTM and SAEs with respect to three evaluation metrics, namely, MAPE, MAE and RMSE, on four prediction tasks.https://ieeexplore.ieee.org/document/9006880/Lane occupancy rateforecastingcapsule networkconvolutional neural network |
| spellingShingle | Ran Tian Jiaming Bi Qiang Zhang Yanxing Liu Research on Lane Occupancy Rate Forecasting Based on the Capsule Network IEEE Access Lane occupancy rate forecasting capsule network convolutional neural network |
| title | Research on Lane Occupancy Rate Forecasting Based on the Capsule Network |
| title_full | Research on Lane Occupancy Rate Forecasting Based on the Capsule Network |
| title_fullStr | Research on Lane Occupancy Rate Forecasting Based on the Capsule Network |
| title_full_unstemmed | Research on Lane Occupancy Rate Forecasting Based on the Capsule Network |
| title_short | Research on Lane Occupancy Rate Forecasting Based on the Capsule Network |
| title_sort | research on lane occupancy rate forecasting based on the capsule network |
| topic | Lane occupancy rate forecasting capsule network convolutional neural network |
| url | https://ieeexplore.ieee.org/document/9006880/ |
| work_keys_str_mv | AT rantian researchonlaneoccupancyrateforecastingbasedonthecapsulenetwork AT jiamingbi researchonlaneoccupancyrateforecastingbasedonthecapsulenetwork AT qiangzhang researchonlaneoccupancyrateforecastingbasedonthecapsulenetwork AT yanxingliu researchonlaneoccupancyrateforecastingbasedonthecapsulenetwork |