A Deep Learning Algorithm for Travel Time Prediction
Bibliographic record
Abstract
Accurate prediction of vehicle travel times is crucial for enhancing intelligent transportation systems, optimizing routing solutions, improving ride-sharing services, and managing traffic effectively. There are various methods available for predicting vehicle travel times between two locations, including both model-based and data-driven approaches. Traditional models often fall short because they assume Euclidean distance when predicting travel times between points. In this study, we focus on predicting vehicle travel times for road segments and entire routes using detailed trajectory data that includes latitude, longitude, time of day, time of week, driver habits, and driver ID. Each trajectory consists of a sequence of GPS points that track a vehicle's movements over time. By defining a road segment as the route between three consecutive GPS points, we can break down the trajectory into smaller segments, enabling more accurate travel time estimates. Given the complexity of travel time prediction, which is influenced by traffic flow conditions at different times and locations, we propose a deep learning algorithm. This algorithm utilizes advanced techniques, including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Temporal Convolutional Networks (TCNs). Our approach demonstrates significant improvements over existing methods. Using the Mean Absolute Percent Error (MAPE) metric, we compared our model with established ones, employing large-scale Chengdu taxi datasets. Our results indicate a 2.9% improvement in travel time prediction accuracy, highlighting our model's potential to surpass current solutions and paving the way for future research in travel time estimation.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".