TY - GEN
T1 - Local AIS data analytics for efficient operation management in Vessel Traffic Service
AU - Xu, Gangyan
AU - Li, Fan
AU - Chen, Chun Hsien
N1 - Funding Information:
*Research supported by Singapore Maritime Institute research project (SMI-2014-MA-06).
Funding Information:
ACKNOWLEDGMENT This research is supported by Singapore Maritime Institute research project (SMI-2014-MA-06).
Publisher Copyright:
© 2017 IEEE.
PY - 2017/8
Y1 - 2017/8
N2 - Vessel Traffic Service (VTS) is vital for ensuring the safe and smooth maritime traffic in designated areas. With the rapid development of technologies and the extensive implementation of Automatic Identification System (AIS), a lot of data are available to support the decision-making processes in VTS. Although a lot of efforts have been made on exploring the data for various traffic management activities, few of them have been done using AIS data to facilitate the operation management in VTS. Focusing on this problem, this paper proposes an AIS data analytics framework to improve the efficiency of operation management in VTS. Through extracting the spatial-temporal data from discrete vessel kinematics status, the historical traffic analysis module is proposed, which could provide statistical information to support the planning issues in VTS. Besides, K-mean based property classification is introduced to transform the traffic data into easy-to-understand N-degree descriptions. Furthermore, to improve the ability of dealing with dynamics, a BPANN-based short-term traffic prediction module is also built. Finally, an experimental case study is given to verify the effectiveness of the proposed methods.
AB - Vessel Traffic Service (VTS) is vital for ensuring the safe and smooth maritime traffic in designated areas. With the rapid development of technologies and the extensive implementation of Automatic Identification System (AIS), a lot of data are available to support the decision-making processes in VTS. Although a lot of efforts have been made on exploring the data for various traffic management activities, few of them have been done using AIS data to facilitate the operation management in VTS. Focusing on this problem, this paper proposes an AIS data analytics framework to improve the efficiency of operation management in VTS. Through extracting the spatial-temporal data from discrete vessel kinematics status, the historical traffic analysis module is proposed, which could provide statistical information to support the planning issues in VTS. Besides, K-mean based property classification is introduced to transform the traffic data into easy-to-understand N-degree descriptions. Furthermore, to improve the ability of dealing with dynamics, a BPANN-based short-term traffic prediction module is also built. Finally, an experimental case study is given to verify the effectiveness of the proposed methods.
UR - http://www.scopus.com/inward/record.url?scp=85044962045&partnerID=8YFLogxK
U2 - 10.1109/COASE.2017.8256344
DO - 10.1109/COASE.2017.8256344
M3 - Conference article published in proceeding or book
AN - SCOPUS:85044962045
T3 - IEEE International Conference on Automation Science and Engineering
SP - 1668
EP - 1672
BT - 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017
PB - IEEE Computer Society
T2 - 13th IEEE Conference on Automation Science and Engineering, CASE 2017
Y2 - 20 August 2017 through 23 August 2017
ER -