TY - GEN
T1 - Cluster-based correlation of severe braking events with time and location
AU - Cao, Guoyan
AU - Michelini, John
AU - Grigoriadis, Karolos
AU - Ebrahimi, Behrouz
AU - Franchek, Matthew A.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/7/7
Y1 - 2015/7/7
N2 - In this paper, a systematic strategy is proposed to identify severe braking events occurrence correlation with time and location. The proposed approach, which is constructed based on batch clustering and real-time clustering techniques, incorporates historical and real-time data to predict the time and location of severe braking events. Batch clustering is implemented with the combination of subtractive clustering and fuzzy c-means clustering to generate clusters representing the initial correlation patterns. Real-time clustering is then developed to create and update real-time correlation patterns on the foundation of the batch clustering using evolving Gustafson Kessel Like (eGKL) algorithm. Real-time driving data of operating vehicles each equipped with a data acquisition and wireless communication platform are used to validate the proposed strategy. Drivers can be notified of the potential severe braking locations through maps, and recognize the events occurrence at different times and locations through the variation of the identified correlation patterns.
AB - In this paper, a systematic strategy is proposed to identify severe braking events occurrence correlation with time and location. The proposed approach, which is constructed based on batch clustering and real-time clustering techniques, incorporates historical and real-time data to predict the time and location of severe braking events. Batch clustering is implemented with the combination of subtractive clustering and fuzzy c-means clustering to generate clusters representing the initial correlation patterns. Real-time clustering is then developed to create and update real-time correlation patterns on the foundation of the batch clustering using evolving Gustafson Kessel Like (eGKL) algorithm. Real-time driving data of operating vehicles each equipped with a data acquisition and wireless communication platform are used to validate the proposed strategy. Drivers can be notified of the potential severe braking locations through maps, and recognize the events occurrence at different times and locations through the variation of the identified correlation patterns.
KW - clustering
KW - correlation identification
KW - evolving Gustafson Kessel Like approach
KW - severe driving events
UR - http://www.scopus.com/inward/record.url?scp=84941092481&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84941092481&partnerID=8YFLogxK
U2 - 10.1109/SYSOSE.2015.7151986
DO - 10.1109/SYSOSE.2015.7151986
M3 - Conference contribution
AN - SCOPUS:84941092481
T3 - 2015 10th System of Systems Engineering Conference, SoSE 2015
SP - 187
EP - 192
BT - 2015 10th System of Systems Engineering Conference, SoSE 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 10th System of Systems Engineering Conference, SoSE 2015
Y2 - 17 May 2015 through 20 May 2015
ER -