Abstract
Conventional frame synchronization detection algorithms in the communication system, such as correlation and maximum likelihood, either fails to deal with frequency deviation problem or requires great efforts to be implemented on the hardware platform. Therefore, we parallel the frame synchronization detection problem with the Multi-instance Learning (MIL) in the field of machine learning, and propose a novel Learning to Detect Frame Synchronization algorithm (LDFS). This algorithm is mainly conducted offline to learn preamble signal detectors, which can then be efficiently implemented on the hardware platform to accomplish the synchronous detection task. In this paper, we first solve frame synchronization detection problem from the point of machine learning, and thus our algorithm displays some advantages over the existing algorithms. First, the resulted detector is simple and efficiently realized on the hardware platform. Second, the learned detector is adaptive to work under different communication frequencies straightforwardly without extra modifications. Experimental results demonstrate the effectiveness and promise of the proposed LDFS algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Mengali, U., D’Andrea, A.N.: Synchronization techniques for digital receivers. Springer (1997)
Barker, R.H.: Group synchronizing of binary digital systems. Communication Theory, 273–287 (1953)
Sklar, B.: Digital Communications. Prentice-Hall, Englewood Cliffs (1988)
Scholtz, R.: Frame synchronization techniques. IEEE Transactions on Communications 28(8), 1204–1213 (1980)
Massey, J.: Optimum frame synchronization. IEEE Transactions on Communications 20(2), 115–119 (1972)
Chiani, M., Martini, M.G.: Optimum synchronization of frames with unknown, variable lengths on Gaussian channels. In: IEEE Global Telecommunications Conference, GLOBECOM 2004, vol. 6, pp. 4087–4091. IEEE (2004)
Chiani, M., Martini, M.G.: Practical frame synchronization for data with unknown distribution on AWGN channels. IEEE Communications Letters 9(5), 456–458 (2005)
Foulds, J., Frank, E.: A review of multi-instance learning assumptions. Knowledge Engineering Review 25(1), 1 (2010)
Zhou, Z.H., Zhang, M.L., Huang, S.J., et al.: Multi-instance multi-label learning. Artificial Intelligence 176(1), 2291–2320 (2012)
Andrews, S., Tsochantaridis, I., Hofmann, T.: Support vector machines for multiple-instance learning. In: Advances in Neural Information Processing Systems, pp. 561–568 (2002)
Zhang, Q., Goldman, S.A., Yu, W., et al.: Content-based image retrieval using multiple-instance learning. In: Machine Learning-International Workshop then Conference, pp. 682–689 (2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, Y., Zhang, C., Peng, Q., Wang, Z. (2013). Learning to Detect Frame Synchronization. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8227. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42042-9_71
Download citation
DOI: https://doi.org/10.1007/978-3-642-42042-9_71
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42041-2
Online ISBN: 978-3-642-42042-9
eBook Packages: Computer ScienceComputer Science (R0)