The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Deep multi-layer neural networks are generally trained using variants of the gradient descent based algorithm. However, this kind of algorithms usually encounter a series of shortcomings, such as low training efficiency, local minimum, difficult control parameter tuning, and gradient vanishing or exploding. Besides, for a specific application, how to design the structure of the network, that is, how...
Due to the inherent intersymbol interference (ISI), the detection for faster-than-Nyquisy (FTN) signaling is long considered to be a challenging problem. In this paper, we study three equalization and detection schemes in terms of their performance and computational complexity for FTN signaling system. The first one is the widely employed optimal maximum a posterior (MAP) equalization implemented...
As far as a Turbo decoder is concerned, the lower Bit Err Rate (BER) at the expense of acceptable and feasible complexity, the better. In this paper, a method is proposed which employs additional redundant sequence added at the end of tail bits of an information sequence to improve performance of a Turbo decoder. Computer simulation results show that, when L=L'=1024, where L is the length of information...
Iterative decoding structure is the main feature of Turbo code decoding. It can improve the performance of Turbo decoding, but also increase the decoding complexity, time delay and power consumption. This paper proposes a parallel decoding structure of Turbo code based on double prediction control, i.e., using double prediction control module instead of two iterative decoding algorithms. Since the...
This paper presents an improved decoding structure of turbo code based on parallel prediction control. The SISO module could be equivalent to a linear module established by the values of the former exterior information of the component decoder. The value of No (n+1) exterior information could be predicted by the linear module. Compared to the traditional decoding algorithm, the computation quantity...
An improved decoding structure of LPCA-turbo (linear prediction control algorithm, turbo code) is presented in this paper. A linear module established by the values of the former exterior information of the component decoder could be equivalent to the SISO module. By the linear module the value of No (n + 1) exterior information could be predicted. The computation quantity and time of the LPCA will...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.