Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature

Road anomaly detection with crowdsourced sensor data has become an increasingly important field of research over the last few years. Traditional ways for road anomaly detection are either threshold-based detection techniques or feature-based detection techniques. However, road anomaly patterns from...

Full description

Bibliographic Details
Main Authors: Yuanyi Chen, Mingxuan Zhou, Zengwei Zheng, Meimei Huo
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8721045/
id doaj-83839bd3e2cd449ba27eb52724e71d7d
record_format Article
spelling doaj-83839bd3e2cd449ba27eb52724e71d7d2021-03-29T23:33:53ZengIEEEIEEE Access2169-35362019-01-017676666767810.1109/ACCESS.2019.29187548721045Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant FeatureYuanyi Chen0https://orcid.org/0000-0003-4038-6983Mingxuan Zhou1Zengwei Zheng2Meimei Huo3Department of Computer Science and Computing, Zhejiang University City College, Hangzhou, ChinaDepartment of Computer Science and Computing, Zhejiang University City College, Hangzhou, ChinaDepartment of Computer Science and Computing, Zhejiang University City College, Hangzhou, ChinaDepartment of Computer Science and Computing, Zhejiang University City College, Hangzhou, ChinaRoad anomaly detection with crowdsourced sensor data has become an increasingly important field of research over the last few years. Traditional ways for road anomaly detection are either threshold-based detection techniques or feature-based detection techniques. However, road anomaly patterns from crowdsourcing data are often shifted in time and exhibit local distortions/noise, thus existing methods rely on the original sensor data greatly limit the accuracy of road anomaly detection. In this paper, we present a road anomaly detection model by learning scale-invariant features from the differences between small local segments of road anomaly samples. Specifically, the proposed model consists of two phases: 1) Road anomaly segmentation. The phase is designed to roughly extract road anomaly subsequence using piecewise aggregate approximation representation of sensor series data, and 2) Road anomaly detection. In this phase, we observe the differences among road anomaly classes are attributed to small local segments, then we learn scale-invariant features from these small local segments for road anomaly detection. To demonstrate the utility of our proposed model, we have performed a comprehensive experimental evaluation on two real-world datasets and one large-scale simulation dataset. The experimental results show our proposed model outperforms all baselines significantly in terms of road anomaly detection.https://ieeexplore.ieee.org/document/8721045/Road anomaly detectionmobile crowdsourcingaccelerometer readingssliding windowscale-invariant feature
collection DOAJ
language English
format Article
sources DOAJ
author Yuanyi Chen
Mingxuan Zhou
Zengwei Zheng
Meimei Huo
spellingShingle Yuanyi Chen
Mingxuan Zhou
Zengwei Zheng
Meimei Huo
Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
IEEE Access
Road anomaly detection
mobile crowdsourcing
accelerometer readings
sliding window
scale-invariant feature
author_facet Yuanyi Chen
Mingxuan Zhou
Zengwei Zheng
Meimei Huo
author_sort Yuanyi Chen
title Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
title_short Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
title_full Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
title_fullStr Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
title_full_unstemmed Toward Practical Crowdsourcing-Based Road Anomaly Detection With Scale-Invariant Feature
title_sort toward practical crowdsourcing-based road anomaly detection with scale-invariant feature
publisher IEEE
series IEEE Access
issn 2169-3536
publishDate 2019-01-01
description Road anomaly detection with crowdsourced sensor data has become an increasingly important field of research over the last few years. Traditional ways for road anomaly detection are either threshold-based detection techniques or feature-based detection techniques. However, road anomaly patterns from crowdsourcing data are often shifted in time and exhibit local distortions/noise, thus existing methods rely on the original sensor data greatly limit the accuracy of road anomaly detection. In this paper, we present a road anomaly detection model by learning scale-invariant features from the differences between small local segments of road anomaly samples. Specifically, the proposed model consists of two phases: 1) Road anomaly segmentation. The phase is designed to roughly extract road anomaly subsequence using piecewise aggregate approximation representation of sensor series data, and 2) Road anomaly detection. In this phase, we observe the differences among road anomaly classes are attributed to small local segments, then we learn scale-invariant features from these small local segments for road anomaly detection. To demonstrate the utility of our proposed model, we have performed a comprehensive experimental evaluation on two real-world datasets and one large-scale simulation dataset. The experimental results show our proposed model outperforms all baselines significantly in terms of road anomaly detection.
topic Road anomaly detection
mobile crowdsourcing
accelerometer readings
sliding window
scale-invariant feature
url https://ieeexplore.ieee.org/document/8721045/
work_keys_str_mv AT yuanyichen towardpracticalcrowdsourcingbasedroadanomalydetectionwithscaleinvariantfeature
AT mingxuanzhou towardpracticalcrowdsourcingbasedroadanomalydetectionwithscaleinvariantfeature
AT zengweizheng towardpracticalcrowdsourcingbasedroadanomalydetectionwithscaleinvariantfeature
AT meimeihuo towardpracticalcrowdsourcingbasedroadanomalydetectionwithscaleinvariantfeature
_version_ 1724189213244522496