Abnormal Driving Detection Using GPS Data
Abnormal Driving Detection Using GPS Data
复制标题
使用 GPS 数据检测异常驾驶
DOI：
10.1109/honet59747.2023.10374718
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Tappen, Ruth
中科院分区：
文献类型：
--
作者：
Boateng, Charles;Yang, Kwangsoo;Ara Ghoreishi, Seyedeh Gol;Jang, Jinwoo;Jan, Muhammad Tanveer;Conniff, Joshua;Furht, Borko;Moshfeghi, Sonia;Newman, David;Tappen, Ruth
给定一个GPS数据集，包括以一秒的间隔捕获的驾驶记录，这项研究解决了异常驾驶检测（ADD）的挑战。该研究介绍了一种综合的方法，利用数据预处理，降维和聚类技术。对地速度（SOG）、对地航向（COG）、经度（lon）和纬度（lat）数据被聚合到分钟级段中。我们使用奇异值分解（SVD）来降低维度，从而使K均值聚类能够识别独特的驾驶模式。结果显示，该方法在区分正常与异常驾驶行为方面的有效性，为驾驶员安全，保险风险评估和个性化干预提供了有前途的见解。
Given a GPS dataset comprising driving records captured at one-second intervals, this research addresses the challenge of Abnormal Driving Detection (ADD). The study introduces an integrated approach that leverages data preprocessing, dimensionality reduction, and clustering techniques. Speed Over Ground (SOG), Course Over Ground (COG), longitude (lon), and latitude (lat) data are aggregated into minute-level segments. We use Singular Value Decomposition (SVD) to reduce dimensionality, enabling K-means clustering to identify distinctive driving patterns. Results showcase the methodology's effectiveness in distinguishing normal from abnormal driving behaviors, offering promising insights for driver safety, insurance risk assessment, and personalized interventions.