利用神经网络逆控制系统提高 Turbo码译码性能

董正宏; 周辉; 朱仁峰

利用神经网络逆控制系统提高 Turbo码译码性能

装备指挥技术学院?电子工程系, 北京 101416

基金项目: 国家部委基金资助项目

详细信息

作者简介:
董正宏(1977-),男,江苏阜宁人,博士生, h dz@319Lab.com.

中图分类号: TN 911.22
计量
- 文章访问数: 3297
- HTML全文浏览量: 213
- PDF下载量: 854
- 被引次数: 0
出版历程
- 收稿日期: 2004-05-14
- 网络出版日期: 2005-09-30

Using neural network inverse control system to improve the performance of turbo decoding

Department of Electronic Engineering, The Academy of Equipment Command & Technology (AECT), Beijing 101416,China

摘要

摘要: 对Turbo码译码逆模型建立问题,提出使用神经网络结构的非线性滤波器来建立Turbo码译码自适应逆模型.采用最优常系数比例因子统计得到Turbo码期望衰减系数,通过利用期望衰减系数训练神经网络非线性自回归外输入NARX滤波器,建立全局范围内的Turbo码译码逆输入输出映射模型.在线性逆控制系统中采用该自适应逆模型,与非线性逆控制结构的自适应逆控制系统相比,具有系统结构简单、运算量小等特点.仿真结果表明在信噪比大于0 dB时,该自适应逆模型算法收敛迅速、稳定,计算误差保持在较小的范围之内.自适应逆译码模型从译码机理角度提供了一种改善译码性能的新途径.
- 译码模型 /
- 神经网络 /
- Turbo码 /
- 自适应逆控制系统
Abstract: To solve inverse decoding model problem of turbo codes, an adaptive inverse turbo decoding model was proposed, based on neural network nonlinear filter.　Desired coefficients attenuation of cross-entropy (CE) was gotten by using optimal constant scaling factor with statistical principle. The auto-regressive exogenous input (NARX) neural network was trained to build the mapping model between the input and output of turbo inverse decoding all round by the desired coefficients attenuation. Compared with the nonlinear inverse control system nonlinear structure based,the proposed adaptive inverse model with linear structure has simpler structure, less computation. Simulations show that when the signal to noise ratio (SNR) is greater than 0 dB,the inverse model algorithm converges rapidly and stably with computational error being within a minimal bound. The proposed adaptive inverse model for turbo decoding has agreement with turbo decoding mechanism and provides a new way to improve the performance of turbo decoding.
- inverse decoding model /
- neural network /
- Turbo codes /
- adaptive inverse control

HTML全文

参考文献(1)

[1] Nieh J, Handko J G, Northcutt J D, et al. SVR4 unix scheduler unacceptable for multimedia applications. In:Proc of 4th Int Workshop on Network and Operating System Support for Digital Audio and Video(NOSDAV'93). Lancaster, 1993 [2] Chu Haohua, Klara Nahrstedt. CPU service class for multimedia applications. In:Multimedia Computing and System,1999 IEEE International Conference, 1999. 296~301 [3] Johan Eker, Per Hagander. A feedback scheduler for real-time controller tasks[J]. Control Engineering Practice 2000,8(4):1369~1378 [4] 张怡, 张拥军. 一种支持连续媒体CPU调度方法[J]. 计算机研究与发展,2000,37(2):233~237 Zhang Yi, Zhang Yongjun. A CPU scheduling method supporting QoS for continuous media [J]. Journal of Computer Research & Development, 2000,37(2):233~237(in Chinese) [5] 张拥军, 刘晔.基于QoS的连续媒体任务调度[J]. 计算机研究与发展,1999,36(8):996~999 Zhang Yongjun, Liu Ye. Task scheduling based on QoS control for continuous media services[J]. Journal of Computer Research & Development, 1999,36(8):996~999(in Chinese) [6] Essick R. An event-based fair share scheduler. In:Proceedings of the Winter 1990 USENIX Conference. Berkeley:USENIX, 1990. 147~162 [7] Steere D C, Goel A. A feedback-driver proportion allocator for real-rate scheduling. In:Proc of 3rd USENIX Symp on Operating Systems Design and Implementation(OSSDI'99). New Orieans, 1999. 145~158 [8] Jones M B, Rosu D, Rosu M C. CPU reservations and time constrains:efficient, predictable scheduling of independent activities. In:Proc of 16th ACM Symp on Operating System Principles(SOSP'97). St Malo,1997.198~211 [9] Joson Nieh, Chris Vaill, Hua Zhong. Virtual-time round-robin:an O(1) proportional share scheduler. http://suif.stanford.edu/~neih [10] Plagemeann T. Operating system support for multimedia systems[J].IEEE Computer Communications, 2000, 23(4):267~280 [11] Demers A, Keshav S, Shenker S. Analysis and simulation of a fair queuing algorithm[J]. Internet-Working:Research and Experience, 1990,1(1):3~26 [12] Zhang L. Virtual clock:a new traffic control algorithm for packet switching networks[J]. ACM Transactions on Computer Systems 1991, 9(3):101~124 [13] Anderson D P, Tzou S Y, Wahbe R, et al. Support for continuous media in the DASH system. In:Proc of 10th Int Conf on Distributed Computing System(ICDCS'90). Paris,1990. 184~197 [14] Coulson G, Campbell A, Robin P, et al. The design of a QoS controlled ATM based communication system in chorus[J]. IEEE Journal on Selected Areas of Communications, 1995,13(4):686~699 [15] Liu C L, Layland J W. Scheduling algorithms for multiprogramming in hard-real-time environment[J]. Journal of Association for Computer Machinery, 1973, 20(1):46~61 [16] Sprunt Betal. A periodic task scheduling for hard real-time systems. Real-Time Systems, 1989, 23(2):27~60 [17] Krishna C M, Kang Shin G. Real-time systems[M]. Beijing:Tsinghua University Press, 2001 [18] Anita Mital, Manimaran G, Siva Ram, et al. Integrated dynamic scheduling of hard and QoS degradable real-time tasks in multiprocessor system[J]. Journal of Systems Architecture 2000,46(9):793~801 [19] 周小四, 王淑华, 杨杰. 数字图像监控网络报警系统设计[J]. 计算机工程, 2002, 28(4):61~64 Zhou Xiaosi, Wang Shuhua, Yang jie. Design of digital alert system through network[J]. Computer Engineering, 2002, 28(4):61~64(in Chinese) [20] 周小四, 杨杰. 用于监控智能报警系统的图像识别技术[J]. 上海交通大学报, 2002, 36(4):498~501 Zhou Xiaosi, Yang Jie, Image recognition techniques applied to intelligent system for monitor alarm [J]. Journal of Shanghai Jiaotong University, 2002,36(4):498~501(in Chinese) [21] Cote G, Kossentini F. Optima intro coding of blocks for robust video communication over the internet. In:EUROSEIP Image Communication Special Issue on Real-time Video over the Internet, 1999 [22] William Stallings. Operating systems:internals and design principles. America:Prentice-Hall International Inc, 2001 [23] 孙文彦. 实时传输中的多媒体同步技术的研究. 北京:北京航空航天大学算机学院, 2000 Sun Wenyan. Research for multimedia synchronization of real-time tranaport. Beijing:School of Computer Science and Technology, Beijing University of Aeronautics and Astronautics, 2000(in Chinese) [24] David A, Solomon Mark, Russinovich E. Inside microsoft windows 2000[M]. Beijing:Tsinghua University Press, 2001. 398~399

施引文献

资源附件(0)

访问统计