An Ensemble Convolutional Recursive Neural Network Based on Deep Reinforcement Learning for Traffic Volume Forecasting
Bibliographic record
Abstract
Intelligent transportation systems are of great significance to urban sustainable development and management. As a crucial element of an intelligent transportation system, traffic volume prediction plays a vital role in providing technical guidance for decision-making and scheduling. This paper introduces an ensemble convolutional recursive neural network, leveraging deep reinforcement learning to enhance traffic volume forecasting. Firstly, variational mode decomposition is utilized to decompose the raw traffic volume series into multiple subseries, which can deal with the non-stationary data and improve prediction accuracy. Then, convolutional gated recurrent units and convolutional long and short-term memory networks are taken as base predictors, enabling the accurate prediction of regular and irregular components separately. Additionally, the deep Q-network (DQN) method is employed to integrate the prediction results of each subseries, which has the ability to dynamically model the changing condition of traffic volume. Comparative experiments on four distinct traffic volume series are conducted and it is evident that the DQN-based ensemble learning approach surpasses traditional reinforcement learning and heuristic algorithms in integrating subseries results. For instance, compared with the genetic algorithm, particle swarm optimization, and Q-learning, the mean absolute error value of DQN decreases by 2.418, 5.0, and 8.114 respectively. Furthermore, the proposed model exhibits markedly enhanced accuracy and stability compared to eighteen baseline models. Based on the experimental results, it can be found that the proposed model can provide valuable technical reference for intelligent transportation systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".