用深度学习预测摩托骑行者时间压力，提升主动安全干预精度。
Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions
- 融合卷积与双阶段注意力的轻量模型，仅0.21毫秒推理时间。
- 高压下骑行速度高48%、急刹多36%、危险转弯增58%。
- 可驱动预警、反馈等主动干预，适配智能交通系统部署。
时间压力显著影响摩托车骑行者的冒险行为与事故风险，但现有智能交通系统对此研究不足。本文提出MotoTimePressure（MTPS）模型，结合卷积预处理、双阶段时序注意力与Squeeze-and-Excitation特征重校准，在129,209个特征窗口数据上实现91.53%准确率和98.93% ROC AUC，优于六种基线方法，参数仅172K，模型大小0.66 MB，CPU推理耗时0.21毫秒。数据来自51名经验男骑手在模拟器中完成的153次会话，涵盖无、低、高三种时间压力条件，每段序列包含63项特征，包括车辆动力学、控制输入、违规行为及环境信息。实证分析显示，高压状态相比无压状态：速度高出48%，速度波动增加36.4%，路口危险变道增多58%，急刹次数上升36%，后刹车力提高50%。由于时间压力无法实时直接测量，本文证明其在碰撞预测中的有效性：以MTPS预测结果为特征，Informer准确率从91.25%升至93.51%，TimesNet从92.10%升至93.90%，接近理想性能（93.72%和94.06%）。阈值化的时间压力状态能反映骑行者认知负荷，支持自适应警示、触觉反馈、车路协同信号与速度引导等主动干预，契合安全系统理念。
原文摘要 · Abstract (English)
Time pressure critically influences risky maneuvers and crash proneness among powered two-wheeler riders, yet its prediction remains underexplored in intelligent transportation systems. To address this gap, we propose MotoTimePressure (MTPS), a deep learning model combining convolutional preprocessing, dual-stage temporal attention, and Squeeze-and-Excitation feature recalibration, achieving 91.53% accuracy and 98.93% ROC AUC, outperforming six baselines, with only 172K parameters, 0.66 MB model size, and 0.21 ms inference on CPU. To validate and benchmark MTPS, we present a dataset of 129,209 feature windows from 153 simulator sessions by 51 experienced male PTW riders under No, Low, and High Time Pressure conditions. Each sequence captures 63 features spanning vehicle kinematics, control inputs, behavioral violations, and environmental context. Our empirical analysis shows High Time Pressure induces 48% higher speeds, 36.4% greater speed variability, 58% more risky turns at intersections, 36% more sudden braking, and 50% higher rear brake forces versus No Time Pressure. Since time pressure cannot be directly measured in real time, we demonstrate its utility in collision prediction and threshold determination. Using MTPS-predicted time pressure as a feature improves collision risk accuracy for both Informer (91.25% to 93.51%) and TimesNet (92.10% to 93.90%), approaching oracle performance (93.72% and 94.06%, respectively). Thresholded time pressure states capture rider cognitive stress and enable proactive ITS interventions, including adaptive alerts, haptic feedback, V2I signaling, and speed guidance, supporting safer two-wheeler mobility under the Safe System Approach.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。