TY - GEN
T1 - A Correlated Time Series Forecast System
AU - Abildgaard, Nicolaj Casanova
AU - Bang, Casper Weiss
AU - Hansen, Jonas
AU - Jacobsen, Tobias Lambek
AU - Knudsen, Thomas Hojriis
AU - Lisby, Nichlas Orts
AU - Guo, Chenjuan
AU - Yang, Bin
N1 - Funding Information:
Acknowledgements: This work was supported by Independent Research Fund Denmark under agreements 8022-00246B and 8048-00038B.
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/6
Y1 - 2020/6
N2 - In a cyber-physical system (CPS), different entities often interact with each other across time. With the development of various sensing technologies, the time-varying interactions among entities are often recorded as multiple, correlated time series. A typical CPS is a road transportation system, where the traffic on different road segments interact with each other. Traffic sensors are often deployed to capture travel speeds on different road segments, which results in multiple, potentially correlated, speed time series. Under this setting, an increasingly pertinent task is to forecast future speeds, which is essential in a wide variety of traffic planning scenarios. We present a system for correlated time series forecast. The system is able to employ different learning algorithms to perform correlated time series forecast, which facilities end users to choose the most appropriate algorithm for their specific service. The system is developed and integrated into aSTEP, a spatio-Temporal data analytic platform developed by Aalborg University, and is tested using a wide variety of correlated time series data, including a user demand time series from a local mobility-As-A-service company.
AB - In a cyber-physical system (CPS), different entities often interact with each other across time. With the development of various sensing technologies, the time-varying interactions among entities are often recorded as multiple, correlated time series. A typical CPS is a road transportation system, where the traffic on different road segments interact with each other. Traffic sensors are often deployed to capture travel speeds on different road segments, which results in multiple, potentially correlated, speed time series. Under this setting, an increasingly pertinent task is to forecast future speeds, which is essential in a wide variety of traffic planning scenarios. We present a system for correlated time series forecast. The system is able to employ different learning algorithms to perform correlated time series forecast, which facilities end users to choose the most appropriate algorithm for their specific service. The system is developed and integrated into aSTEP, a spatio-Temporal data analytic platform developed by Aalborg University, and is tested using a wide variety of correlated time series data, including a user demand time series from a local mobility-As-A-service company.
UR - http://www.scopus.com/inward/record.url?scp=85090384618&partnerID=8YFLogxK
U2 - 10.1109/MDM48529.2020.00054
DO - 10.1109/MDM48529.2020.00054
M3 - Article in proceeding
AN - SCOPUS:85090384618
T3 - Proceedings - IEEE International Conference on Mobile Data Management
SP - 242
EP - 243
BT - Proceedings - 2020 21st IEEE International Conference on Mobile Data Management, MDM 2020
PB - IEEE
T2 - 21st IEEE International Conference on Mobile Data Management, MDM 2020
Y2 - 30 June 2020 through 3 July 2020
ER -