School of Architecture, Building and Civil Engineering, Loughborough University, Loughborough LE11 3TU, United Kingdom..
Centre for Transport Studies, Department of Civil and Environmental Engineering, Imperial College London, London, SW7 2AZ.
Accid Anal Prev. 2022 Feb;165:106511. doi: 10.1016/j.aap.2021.106511. Epub 2021 Dec 8.
Real-time crash prediction is a heavily studied area given their potential applications in proactive traffic safety management in which a plethora of statistical and machine learning (ML) models have been developed to predict traffic crashes in real-time. However, one of the fundamental issues relating to the application of these models is spatio-temporal transferability. The present paper attempts to address this gap of knowledge by combining Generative Adversarial Network (GAN) and transfer learning to examine the transferability of real-time crash prediction models under an extremely imbalanced data setting. Initially, a baseline model was developed using Deep Neural Network (DNN) with crash and microscopic traffic data collected from M1 Motorway in the UK in 2017. The dataset utilised in the baseline model is naturally imbalanced with 257 crash cases and 16,359,163 non-crash cases. To overcome data imbalance issue, Wasserstein GAN (WGAN) was utilised to generate synthetic crash data. Non-crash data were randomly undersampled due to computational limitations. The calibrated model was then applied to predict traffic crashes for five other datasets obtained from M1 (2018), M4 (2017 & 2018 separately) and M6 Motorway (2017 & 2018 separately) by using transfer learning. Model transferability was compared with standalone models and direct transfer from the baseline model. The study revealed that direct transfer is not feasible. However, models become transferable temporally, spatially, and spatio-temporally if transfer learning is applied. The predictability of the transferred models outperformed existing studies by achieving high Area Under Curve (AUC) values ranging between 0.69 and 0.95. The best transferred model can predict nearly 95% crashes with only a 5% false alarm rate by tuning thresholds. Furthermore, the performances of transferred models are on par with or better than the standalone model. The findings of this study proves that transfer learning can improve model transferability under extremely imbalanced settings which helps traffic engineers in developing highly transferable models in future.
实时碰撞预测是一个备受关注的领域，因为它在主动交通安全管理中有广泛的应用，已经开发了大量的统计和机器学习 (ML) 模型来实时预测交通碰撞。然而，这些模型应用的一个基本问题是时空可转移性。本文试图通过结合生成对抗网络 (GAN) 和迁移学习来解决这一知识差距，以检查在极不平衡数据设置下实时碰撞预测模型的可转移性。最初，使用从英国 M1 高速公路 2017 年收集的碰撞和微观交通数据，使用深度神经网络 (DNN) 开发了一个基线模型。基线模型使用的数据天然不平衡，有 257 个碰撞案例和 16,359,163 个非碰撞案例。为了克服数据不平衡问题，使用 Wasserstein GAN (WGAN) 生成合成碰撞数据。由于计算限制，非碰撞数据被随机欠采样。然后，使用迁移学习将校准后的模型应用于从 M1(2018 年)、M4(2017 年和 2018 年分别)和 M6 高速公路(2017 年和 2018 年分别)获得的另外五个数据集来预测交通碰撞。将模型的可转移性与独立模型和基线模型的直接转移进行了比较。研究表明，直接转移是不可行的。然而，如果应用迁移学习，模型在时间、空间和时空上都具有可转移性。通过调整阈值，转移模型的可预测性优于现有研究，获得了 0.69 到 0.95 之间的高曲线下面积 (AUC) 值。最佳转移模型可以预测近 95%的碰撞，假警报率仅为 5%。此外，转移模型的性能与独立模型相当或优于独立模型。本研究的结果证明，迁移学习可以在极不平衡的设置下提高模型的可转移性，这有助于交通工程师在未来开发高度可转移的模型。
