详情

原文传递 Self-Supervised Deep Learning Framework for Anomaly Detection in Traffic Data

题名：	Self-Supervised Deep Learning Framework for Anomaly Detection in Traffic Data
正文语种：	eng
作者：	Morris, Clint;Yang, Jidong J.;Chorzepa, Mi Geum;Kim, S. Sonny;Durham, Stephan A.
作者单位：	Univ Georgia Sch Environm Civil Agr & Mech Engn Athens GA 30602 USA;Univ Georgia Sch Environm Civil Agr & Mech Engn Athens GA 30602 USA;Univ Georgia Sch Environm Civil Agr & Mech Engn Athens GA 30602 USA;Univ Georgia Sch Environm Civil Agr & Mech Engn Athens GA 30602 USA;Univ Georgia Sch Environm Civil Agr & Mech Engn Athens GA 30602 USA
关键词：	Anomaly detection;Wavelet transform;Recurrence plots;Variational autoencoder (VAE);Recurrent neural networks (RNN);Self-supervised deep learning
摘要：	The current state of practice in traffic data quality control features rule-based data checking and validation processes, where the rules are subjective and insensitive to variation inherited with traffic data. In this paper, self-supervised deep learning approaches were explored to leverage the existence of multiple sources of traffic volume data, which permitted cross-checking of one data source against another for improved robustness. Two types of models were developed, aiming at detecting data anomalies at two distinct timescales. Particularly, a novel variational autoencoder (VAE)-based model was formulated for discerning data anomalies at the daily level and four recurrent model structures, including recurrent neural networks (RNN), gated recurrent units (GRU), long short-term memory (LSTM) units, and liquid time constant (LTC) networks, were evaluated for detecting anomalies in finer incremental timescales (i.e., 5-min intervals). The effectiveness of the proposed methods was demonstrated using two independent sources of traffic data from the Georgia Department of Transportation: (1) traffic counts collected by inductive loops as part of the statewide traffic count program, and (2) traffic volumes acquired by a video detection system as part of the Georgia 511, an advanced traveler information system in Georgia. Based on our experiments, the VAE-based model achieved a precision of 0.95, recall of 0.92, and F-1 score of 0.94. Among the recurrent models, the fully connected LTC produced the lowest prediction error and achieved a precision of 0.82, recall of 0.88, and F-1 score of 0.85. (C) 2022 American Society of Civil Engineers.
出版年：	2022
期刊名称：	Journal of Transportation Engineering
卷：	148
期：	5
页码：	04022020.1-04022020.15