TY - JOUR
T1 - SafeDrive
T2 - Online Driving Anomaly Detection From Large-Scale Vehicle Data
AU - Zhang, Mingming
AU - Chen, Chao
AU - Wo, Tianyu
AU - Xie, Tao
AU - Bhuiyan, Md Zakirul Alam
AU - Lin, Xuelian
N1 - Funding Information:
Manuscript received December 24, 2016; accepted January 12, 2017. Date of publication February 24, 2017; date of current version August 1, 2017. This work was supported by the China Key Research and Development Program under Grant 2016YFB0100902, the National Natural Science Foundation of China under Grant 61602067 and Grant 61421003, Fundamental Research Funds for the Central Universities under Grant 106112015CDJXY180001. The work of T. Xie was supported in part by the Natural Science Foundation under Grant CCF-1409423, Grant CNS-1434582, Grant CNS-1513939, and Grant CNS-1564274. Paper no. TII-16-1574. (Corresponding author: T. Wo.) M. Zhang, T. Wo, and X. Lin are with Beihang University, Beijing 100191, China (e-mail: zhangmm@act.buaa.edu.cn; woty@act.buaa. edu.cn; linxl@act.buaa.edu.cn).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8
Y1 - 2017/8
N2 - Identifying driving anomalies is of great significance for improving driving safety. The development of the Internet-of-Vehicle (IoV) technology has made it feasible to acquire big data from multiple vehicle sensors, and such big data play a fundamental role in identifying driving anomalies. Existing approaches are mainly based on either rules or supervised learning. However, such approaches often require labeled data, which are typically not available in big data scenarios. In addition, because driving behaviors differ under vehicle statuses (e.g., speed and gear position), to precisely model driving behaviors needs to fuse multiple sources of sensor data. To address these issues, in this paper, we propose SafeDrive, an online and status-aware approach, which does not require labeled data. From a historical dataset, SafeDrive statistically offline derives a state graph (SG) as a behavior model. Then, SafeDrive splits the online data stream into segments and compares each segment with the SG. SafeDrive identifies a segment that significantly deviates from the SG as an anomaly. We evaluate SafeDrive on a cloud-based IoV platform with over 29 000 real connected vehicles. The evaluation results demonstrate that SafeDrive is capable of identifying a variety of driving anomalies effectively from a large-scale vehicle data stream with an overall accuracy of 93%; such identified driving anomalies can be used to timely alert drivers to correct their driving behaviors.
AB - Identifying driving anomalies is of great significance for improving driving safety. The development of the Internet-of-Vehicle (IoV) technology has made it feasible to acquire big data from multiple vehicle sensors, and such big data play a fundamental role in identifying driving anomalies. Existing approaches are mainly based on either rules or supervised learning. However, such approaches often require labeled data, which are typically not available in big data scenarios. In addition, because driving behaviors differ under vehicle statuses (e.g., speed and gear position), to precisely model driving behaviors needs to fuse multiple sources of sensor data. To address these issues, in this paper, we propose SafeDrive, an online and status-aware approach, which does not require labeled data. From a historical dataset, SafeDrive statistically offline derives a state graph (SG) as a behavior model. Then, SafeDrive splits the online data stream into segments and compares each segment with the SG. SafeDrive identifies a segment that significantly deviates from the SG as an anomaly. We evaluate SafeDrive on a cloud-based IoV platform with over 29 000 real connected vehicles. The evaluation results demonstrate that SafeDrive is capable of identifying a variety of driving anomalies effectively from a large-scale vehicle data stream with an overall accuracy of 93%; such identified driving anomalies can be used to timely alert drivers to correct their driving behaviors.
KW - Anomaly
KW - Internet-of-Vehicles
KW - big data
KW - data stream
KW - driving behavior
KW - on-board diagnostics (OBD)
KW - state graph (SG)
UR - http://www.scopus.com/inward/record.url?scp=85029445152&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85029445152&partnerID=8YFLogxK
U2 - 10.1109/TII.2017.2674661
DO - 10.1109/TII.2017.2674661
M3 - Article
AN - SCOPUS:85029445152
SN - 1551-3203
VL - 13
SP - 2087
EP - 2096
JO - IEEE Transactions on Industrial Informatics
JF - IEEE Transactions on Industrial Informatics
IS - 4
M1 - 7864432
ER -