Skip to main content
Log in

Solution of assigning binary indexes to codevectors by a kind of hopfield neural network

  • Published:
Journal of Electronics (China)

Abstract

A method of assigning binary indexes to codevectors in vector quantization (VQ) system, which is called pseudo-Gray coding, is presented in this paper by constructing a kind of Hopfield neural network. Pseudo-Gray coding belongs to joint source/channel coding, which could provide a redundancy-free error protection scheme for VQ of analog signals when the binary indexes of signal codevectors are used as channel symbols on a discrete memoryless channel. Since pseudo-Gray coding is of combinatorial optimization problems which are NP-complete problems, globally optimal solutions are generally impossible. Thus, a kind of Hopfield neural network is used by constructing suitable energy function to get sub-optimal solutions. This kind of Hopfield neural network is easily modified to solve simplified version of pseudo-Gray coding for single-bit-error channel model. Simulating experimental results show that the method introduced here could offer good performances.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Khalid Sayood, Fuling Liu, Jerry D. Gibson, A constrained joint source/channel coder design, IEEE J. on SAC, 12(1994)9, 1584–1592.

    Google Scholar 

  2. J. G. Dunham, R M. Gray, Joint source and noise channel trellis encoding, IEEE Trans. on IT, IT-27(1981)4, 516–518.

    Article  Google Scholar 

  3. E. Ayanoglu, R. M. Gray, Design of joint source/channel trellis waveform coders, IEEE Trans. on IT, IT-33(1987)6, 855–865.

    Article  Google Scholar 

  4. N. Farvardin, V. Vaishampayan, Optimal quantizer design for noise channels, IEEE Trans. on IT, 33(1987)6, 827–838.

    Article  MATH  Google Scholar 

  5. K. Sayood, J. C. Borkenhagen, Use of residual redundancy in the design of joint source/channel coders, IEEE Trans. on Commun., 39(1991)6, 838–846.

    Article  Google Scholar 

  6. Xue Xiangyang, Fan Chanxin, SOFM—A simple scheme of joint source/channel coding, Chinese Conference on Neural Network’93, 1993.10, 978–981, (in Chinese).

  7. J. R. B. De. Marca, N. S. Jayant, An algorithm for assigning binary indices to the codevectors of a multi-dimensional quantizer, in Proc. IEEE ICC’87, 1987, 1128–1132.

  8. Kenneth Zeger, Allen Gersho, Pseudo-Gray coding, IEEE Trans. on Commun., 38(1990)12, 2147–2158.

    Article  Google Scholar 

  9. N. Farvardin, A study of vector quantization for noisy channels, IEEE Trans. on IT, 36(1990)4, 799–809.

    Article  Google Scholar 

  10. Li Lihua, Shi Yuhui, He Zhenya, A redundancy-free channel coding scheme for VQ based on neural network, Journal of China Institute of Communications, 13(1992)5, 11–15, (in Chinese).

    Google Scholar 

  11. J. H. Chen, et al., A low-delay CELP coder for the CCITT 16kb/s speech coding standard, IEEE J. on SAC, 10(1992)5, 830–849.

    Google Scholar 

  12. Shen Qin, Hu Dewen, Shi Chun, Application Technologies of Neural Networks, Changsha, Press of National University of Defence Technology, China, 1993,12, (in Chinese).

    Book  Google Scholar 

  13. Behrooz Kamgar-Parsi, Behzad Kamgar-Parsi, Hopfield Model and Optimization Problems, in Neural Networks for Perception, Vol.2, Computation, Learning and Architectures, Edited by Harry Wechsler, Academic Press, Inc., 1992.

Download references

Author information

Authors and Affiliations

Authors

About this article

Cite this article

Lin, J. Solution of assigning binary indexes to codevectors by a kind of hopfield neural network. J. of Electron.(China) 18, 79–88 (2001). https://doi.org/10.1007/s11767-001-0011-x

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11767-001-0011-x

Key words

Navigation