A Decision Level Fusion Algorithm for Time Series in Cyber Physical System

• Published in: Big Data Computing and Communications Vol. 9784; pp. 409 - 420
• Main Authors: Yang, Jinshun, Zhang, Xu, Wang, Dongbin
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Cyber-Physical Systems (CPS); Decision level fusion; Feedback; Multiple decision trees; Network hardware; Time series
• ISBN: 9783319425528; 3319425528
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-42553-5_35

Cyber-Physical Systems (CPS) is a new intelligent complex system that generates and processes large amounts of data. To improve the ability of information abstraction, data fusion is usually introduced in CPS. Since the characters of CPS are different from the existing system’s such as close loop feedback and auto-control in a long term period, the decision level fusion method that has been proposed is hard to migrate to CPS directly. In this paper, a novel multiple decision trees weighting fusion algorithm for time series with internal feedback is proposed in view of the long-term valuable historical data of the CPS. Moreover, simulations using JAVA language are performed on mobile medical platform to validate the algorithm and the results show that the historical data have the ability to influence the decision fusion for making an overall judgment and the system can achieve a stable state.