针对两轮车在时间压力下的碰撞风险，提出轻量级边缘AI模型，精准预测并支持实时部署。
MotoSafety: Edge-AI with Learned Temporal Importance for Two-Wheeler Collision Risk Assessment Under Time Pressure
- 基于学习的时间重要性机制，融合多源传感器数据动态评估风险
- 在12.9万条数据上实现94.97%准确率，推理延迟仅0.135毫秒
- 适合低成本硬件部署，可迁移至人体活动与临床场景
两轮车骑行者在中低收入国家面临严峻安全挑战，但关于认知压力（如时间压力）如何影响碰撞风险的研究仍有限。本文构建了一个包含超过12.9万条标注多变量时序特征窗口的综合性数据集，来自51名参与者在153次模拟骑行中在无、低、高时间压力条件下的数据。每个序列捕捉64个属性，涵盖车辆运动、骑手操控、空间接近度及规则遵守情况。基于此，提出MotoSafety——一种基于学习时间重要性（LTI）概念的新型边缘AI框架。该框架在分类任务中达到94.97%准确率和99.33% ROC AUC，优于十种基线模型（包括TimesNet和LLM4TS），在预测任务中实现0.039 MSE和0.094 MAE，误差比Time-LLM和iTransformer低4.4倍。模型仅含115万参数，推理延迟0.135毫秒，适用于低成本CPU设备部署。利用真实时间压力作为归纳偏置，准确率从94.09%提升至94.97%；使用预测时间压力也达94.82%。仅用21个IMU+GPS特征即可实现93.91%准确率，具备实际部署潜力。该架构在人类活动识别（97.66%）和临床领域（99.65%）亦展现良好迁移能力。本轻量化框架推动了两轮车碰撞风险评估发展，助力智能交通系统的安全系统方法。
原文摘要 · Abstract (English)
Powered two-wheeler riders face critical safety challenges in low- and middle-income countries, yet limited studies exist on how cognitive stressors such as Time Pressure influence collision risk. We address this gap by introducing a comprehensive dataset consisting of over 129,000 labeled multivariate time-series feature windows, gathered across 153 simulator rides from 51 participants under No, Low, and High TP scenarios. Across each sequence, we capture 64 distinct attributes covering vehicle motion, rider control actions, spatial proximity, and rule compliance indicators. Using this dataset, we introduce MotoSafety, a new edge-AI framework built on the Learned Temporal Importance (LTI) concept. MotoSafety achieves 94.97% accuracy and 99.33% ROC AUC, outperforming ten baselines, including TimesNet and LLM4TS, and achieves 0.039 MSE and 0.094 MAE for forecasting (4.4x lower error than Time-LLM and iTransformer). With only 1.15M parameters and 0.135 ms latency, it is suitable for edge deployment on low-cost CPU hardware. Using ground truth TP as an inductive bias improves accuracy from 94.09% to 94.97%, while predicted TP achieves 94.82%. Using only 21 IMU+GPS features, it achieves 93.91% accuracy, indicating practical deployment. Beyond PTW safety, the architecture shows better transferability to human activity (97.66%) and clinical (99.65%) domains. This lightweight framework advances PTW collision risk assessment, supporting the Safe System Approach for Intelligent Transportation Systems.
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。