<journal article>
Unusual driving spots discovery from driving probe data using machine learning

Creator
Language
Publisher
Date
Source Title
Vol
First Page
Last Page
Publication Type
Access Rights
Rights
Related DOI
Related URI
Related HDL
Abstract 自動車の走行状況や道路状況などを知るため.スマートフォンセンサーをはじめ,GPS を利用したAutomatic Vehicle Location (AVL) など,様々な装置を利用し,プローブデータ(自動車の走行データ)の獲得が行われて,機械学習手法を利用した走行挙動の分析が行われてきている.本研究では,機械学習手法と特徴選択手法を組み合わせた,通常とは異なる走行挙動(異常走行挙動)の識別手法を提...案する.具体的には会津若松市オープンデータ活用実証事業により提供されている公用車・公共交通車両走行情報履歴データにSVM (Support Vector Machine) と特徴選出の手法を用いた異常走行挙動の識別手法を提案する.本手法を適用した際の,異常走行挙動の識別結果と識別精度,識別に寄与した特徴についても考察する.
Driving probe data are captured to analyze driving behavior of a car and the road conditions. Probe devices are realized by smartphone or AVL (Automatic Vehicle Location) with GPS (Global positioning system). Some researchers apply machine learning methods for analysis of driving probe data. In this research, we propose a method to distinguish unusual driving behavior (sudden braking) using machine learning method. We apply SVM (support vector machine) and feature selection method to the driving probe data provided by Aizuw-Wakamatsu City Open Data Utilization Verification Project. We report the effect of feature selection for unusual driving behavior detection, using F-measure and accuracy. We also show that selected features identify unusual driving condition (place and date).
show more

Hide fulltext details.

pdf ipsj-its76-aizu pdf 1.22 MB 678  

Details

PISSN
NCID
Record ID
Related URI
Subject Terms
Created Date 2019.06.10
Modified Date 2023.08.18

People who viewed this item also viewed