This paper proposes a method based on the clustering algorithm, deep learning, and transfer learning (TL) for short‐term traffic prediction with limited data. To address the challenges posed by limited data and the complex and diverse traffic patterns observed in traffic networks, we propose a profile model based on few‐shot learning to extract each detector's unique profiles. These profiles are then used to cluster detectors with similar patterns into distinct clusters, facilitating effective learning with limited data. A Convolutional Neural Network ‐ Long Short‐Term Memory (CNN‐LSTM)‐based predictive model is proposed to learn and predict traffic volumes for each detector within a cluster. The proposed method demonstrates resilience to detector failures and has been validated using the Performance Measurement System dataset. In scenarios with less than 2 months of training data and 10% failed detectors, the mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) for station‐level traffic volume prediction increase from 12.7 vehs/5 min, 20.9 vehs/5 min, and 10.5% to 13.9 vehs/5 min, 24.2 vehs/5 min, and 11.7%, respectively. For lane‐level traffic volume prediction, the average MAE, RMSE, and MAPE increase from 4.7 vehs/5 min, 7.7 vehs/5 min, and 15% to 5.6 vehs/5 min, 9.6 vehs/5 min, and 16.8%. Furthermore, the proposed method extends its applicability to traffic speed and occupancy prediction tasks. TL is integrated to improve speed/occupancy prediction accuracy by leveraging knowledge obtained from traffic volume, considering the correlation between traffic flow, speed, and occupancy. When less than 1 month of traffic speed/occupancy data is available for learning, the proposed method achieves an MAE, RMSE, and MAPE of 0.7 km/h, 1.3 km/h, and 1.3% for station‐level traffic speed prediction and 0.5%, 1.1%, and 11% for station‐level traffic occupancy.

中文翻译：

---

通过有限数据的聚类和深度迁移学习进行流量预测

本文提出了一种基于聚类算法、深度学习和迁移学习（TL）的方法，用于有限数据的短期流量预测。为了解决有限数据和交通网络中观察到的复杂多样的交通模式带来的挑战，我们提出了一种基于小样本学习的轮廓模型，以提取每个检测器的独特轮廓。然后使用这些配置文件将具有相似模式的检测器聚类到不同的簇中，从而促进利用有限数据进行有效学习。提出了一种基于卷积神经网络-长短期记忆（CNN-LSTM）的预测模型来学习和预测集群内每个检测器的流量。所提出的方法展示了对探测器故障的恢复能力，并已使用性能测量系统数据集进行了验证。在训练数据少于 2 个月且检测器失败 10% 的场景中，站点级交通量预测的平均绝对误差 (MAE)、均方根误差 (RMSE) 和平均绝对百分比误差 (MAPE) 从 12.7 增加车/5 分钟、20.9 车/5 分钟和 10.5% 分别为 13.9 车/5 分钟、24.2 车/5 分钟和 11.7%。对于车道级交通量预测，平均 MAE、RMSE 和 MAPE 从 4.7 辆/5 分钟、7.7 辆/5 分钟和 15% 增加到 5.6 辆/5 分钟、9.6 辆/5 分钟和 16.8%。此外，所提出的方法将其适用性扩展到交通速度和占用预测任务。集成 TL 是为了利用从交通量中获得的知识，考虑交通流、速度和占用率之间的相关性，来提高速度/占用率预测的准确性。当少于 1 个月的交通速度/占用数据可供学习时，该方法实现了站级交通速度预测的 MAE、RMSE 和 MAPE 分别为 0.7 km/h、1.3 km/h 和 1.3%，以及 0.5车站级客流量占用率分别为%、1.1%和11%。