An Improved Hammerstein Model for System Identification
System identification can easily model practical applications such as peer to peer (P2P) file-sharing traffic, driver assistance system, road traffic state, ethernet-based traffic flows. Therefore, system identification process can also be used in the sma
- PDF / 430,680 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 95 Downloads / 252 Views
1 Introduction System identification, the model of the system is achieved by utilizing data obtained from experimental or mathematical way [1–5]. System identification process can be used in the smart city concept. Since system identification can easily model practical applications such as peer to peer (P2P) file-sharing traffic, driver assistance system, road traffic state, ethernet-based traffic flows [6–9]. In recent years, various applications based on P2P file-sharing technology become prevailing. These applications provide convenience to the users; however, they also cause some problems such as noncopyright file-sharing and excessive network bandwidth occupation. In order to maintain a controllable network environment, network operators and network administrators begin to identify and control the P2P file-sharing traffic [6]. Road safety is one of the main objectives in designing driver assistance systems. On average, every 30 s, one person dies somewhere in the world due to a car crash. Among all fatal traffic accidents, 95% are caused by human errors. The obtained models can be used not only for the online identification of drunk drivers and, probably, stopping the car but also for designing proper controllers based on the configurations proposed in [7]. Road traffic congestion is a common problem all over the world. Many efforts have been done to reduce the impact of traffic congestion. One way is to use advanced Technologies such as sensor, communication and compute processing to traffic management field. These S. Mete (&) H. Zorlu S. Ozer Department of Electrical and Electronic Engineering, Erciyes University, Kayseri, Turkey e-mail: [email protected] H. Zorlu e-mail: [email protected] S. Ozer e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 L. Ismail and L. Zhang (eds.), Information Innovation Technology in Smart Cities, https://doi.org/10.1007/978-981-10-1741-4_4
47
48
S. Mete et al.
technologies can provide traffic flow data to the traffic management center. In order to utilize such data in drawing decision-making foundations for traffic operator, data conversion into traffic state is desirable [8]. Many existing works in the field of internet traffic identification is available in. Most of the approaches use statistics-based methods to identify the wide variety of traffic found on the internet, due to the fact that methods based on port numbers (transport layer) are consider unreliable. But some approaches show a high degree of reliability when detecting flows for certain applications for instance identification of real-time Ethernet (RTE) traffic flows (TFs) [9]. System identification is proceeded through linear and nonlinear models as to the linearity of the system [1–5]. Linear system identification that the input and the output of the system stated with linear equations is mostly used because of its advanced theoretical background [3, 4]. However, many systems in real life have nonlinear behaviors. Linear methods can be inadequate in identification of such systems and nonlinear methods are
Data Loading...
