Self-Supervised Deep Learning Framework for Anomaly Detection in Traffic Data
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 F₁ 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 F₁ score of 0.85.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/issn/24732907
-
Supplemental Notes:
- © 2022 American Society of Civil Engineers.
-
Authors:
- Morris, Clint
- Yang, Jidong J
-
0000-0003-4823-6322
- Chorzepa, Mi Geum
- Kim, S Sonny
-
0000-0002-3468-0230
- Durham, Stephan A
-
0000-0002-6177-3491
- Publication Date: 2022-5
Language
- English
Media Info
- Media Type: Web
- Features: References;
- Pagination: 04022020
-
Serial:
- Journal of Transportation Engineering, Part A: Systems
- Volume: 148
- Issue Number: 5
- Publisher: American Society of Civil Engineers
- ISSN: 2473-2907
- EISSN: 2473-2893
- Serial URL: http://ascelibrary.org/journal/jtepbs
Subject/Index Terms
- TRT Terms: Data quality; Machine learning; Predictive models; Traffic data; Traffic volume; Validation
- Identifier Terms: Georgia Department of Transportation
- Geographic Terms: Georgia
- Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;
Filing Info
- Accession Number: 01841334
- Record Type: Publication
- Files: TRIS, ASCE
- Created Date: Apr 1 2022 8:58AM