时间序列基础模型在行人拥挤人数预测中的表现如何？一项跨数据集比较研究
How Good Are Time-Series Foundation Models for Pedestrian Crowd Count Forecasting? A Cross-Dataset Comparative Study
浏览论文内容
中文总结 AI 辅助
本研究通过跨数据集比较七种预测方法，评估时间序列基础模型在行人计数预测中的表现，发现模型选择需依据数据条件和预测视界，基础模型在数据丰富且季节性强的场景下优势明显。
中文摘要 AI 辅助
行人计数预测支持以行人为导向的智能交通系统（ITS），包括人群监控、行人交通人员配置和路线规划，以及在高峰期间的主动风险缓解。近期的时间序列基础模型（FMs）在异构预测基准上报告了强大的零样本准确性，但这些增益是否能可靠地转移到行人感知部署中仍不清楚。我们基准测试了七种单变量预测方法，涵盖四种范式：季节性朴素法、梯度提升树（LightGBM、CatBoost）、深度学习模型（N-HiTS、PatchTST）以及两个预训练基础模型（TimesFM、Chronos-2）。实验涵盖两个互补场景：（i）一个为期五天的特殊事件数据集SAIL2025，分辨率为3分钟，域内历史数据有限；（ii）墨尔本行人传感器作为多年小时级数据集（2010-2017），具有强季节性。我们比较了每个传感器在多个预测视界上的MAE和RMSE结果。结果显示了三个一致的发现。首先，在历史数据有限的情况下，季节性朴素法在高流量传感器的长视界预测中仍然是强基线，而训练模型在次日与前几天差异显著时可能会退化。其次，提升树在低流量传感器上可能具有竞争力，但在事件驱动的偏移下对高流量传感器表现出更高的敏感性。第三，基础模型在长上下文配置下的季节性和数据丰富场景中表现出色。这些发现强调了根据底层数据条件和预测视界来选择行人预测模型的重要性。
英文摘要
Pedestrian-count forecasting supports pedestrian-oriented Intelligent Transportation Systems (ITS), including crowd monitoring, pedestrian-traffic staffing and routing, and proactive risk mitigation during surges. Recent time-series foundation models (FMs) report strong zero-shot accuracy on heterogeneous forecasting benchmarks, but it remains unclear whether these gains transfer reliably to pedestrian sensing deployments. We benchmark seven univariate forecasting approaches spanning four paradigms: Seasonal Naive, gradient-boosted trees (LightGBM, CatBoost), deep learning models (N-HiTS, PatchTST), and two pretrained FMs (TimesFM, Chronos-2). Experiments cover two complementary regimes: (i) a five-day special event dataset SAIL2025 at 3-minute resolution with limited in-domain history; and (ii) Melbourne pedestrian sensors as a multi-year hourly dataset (2010--2017) with strong seasonality. We compare the MAE and RMSE results per sensor across datasets and multiple forecast horizons. Results show three consistent findings. First, with limited historical data, Seasonal Naive remains a strong baseline for long-horizon forecasting on high-volume sensors, while trained models can degrade when the next day differs substantially from prior days. Second, boosted trees can be competitive on lower-volume sensors but exhibit higher sensitivity on high-volume sensors under event-driven shift. Third, FMs excel in the seasonal and data-rich regime under long-context configuration. The findings highlight the importance of choosing pedestrian forecasting models based on both the underlying data conditions and the forecasting horizon.
发表机构
- Delft University of Technology（代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。
