Deep representation of raw traffic data: An embed-and-aggregate framework for high-level traffic analysis

Woosung Choi, Jonghyeon Min, Taemin Lee, Kyeongseok Hyun, Taehyung Lim, Soon Young Jung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In Intelligent Transportation Systems (ITS), it is widely used to extract a fixed-size feature vector from raw traffic data for high-level traffic analysis. In several existing works, the statistical approach has been used for extracting feature vectors, which directly extracts features by averaging speed or travel time of each vehicle. However, we can achieve a better representation by taking advantage of state-of-the-art machine learning algorithms instead of the statistical approach. In this paper, we propose a two-phase framework named embed-and-aggregate framework for extracting features from raw traffic data, and a feature extraction algorithm (Traffic2Vec) based on our framework exploiting state-of-the-art machine learning algorithms such as deep learning. We also implement a traffic flow prediction system based on Traffic2Vec as a proof-of-concept. We conducted experiments to evaluate the applicability of the proposed algorithm, and show its superior performance in comparison with the prediction system based on the statistical feature extraction method.

Original languageEnglish
Title of host publicationAdvances in Computer Science and Ubiquitous Computing - CSA-CUTE 17
PublisherSpringer Verlag
Pages1383-1390
Number of pages8
Volume474
ISBN (Print)9789811076046
DOIs
Publication statusPublished - 2018 Jan 1
EventInternational Conference on Computer Science and its Applications, CSA 2017 - Taichung, Taiwan, Province of China
Duration: 2017 Dec 182017 Dec 20

Publication series

NameLecture Notes in Electrical Engineering
Volume474
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

OtherInternational Conference on Computer Science and its Applications, CSA 2017
CountryTaiwan, Province of China
CityTaichung
Period17/12/1817/12/20

Keywords

  • Embedding
  • Feature extraction
  • High-level traffic analysis
  • Traffic data
  • Trajectory

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Fingerprint Dive into the research topics of 'Deep representation of raw traffic data: An embed-and-aggregate framework for high-level traffic analysis'. Together they form a unique fingerprint.

  • Cite this

    Choi, W., Min, J., Lee, T., Hyun, K., Lim, T., & Jung, S. Y. (2018). Deep representation of raw traffic data: An embed-and-aggregate framework for high-level traffic analysis. In Advances in Computer Science and Ubiquitous Computing - CSA-CUTE 17 (Vol. 474, pp. 1383-1390). (Lecture Notes in Electrical Engineering; Vol. 474). Springer Verlag. https://doi.org/10.1007/978-981-10-7605-3_220