Abstract
This article presents the concept of future 5th generation (5G) wireless communications as an existing beyond 4G systems like long term evolution (LTE) which means the indicate of 5G scenarios can be introduced in near future. Therefore, this paper deals of a future 5G mobile terminal for applications to uplink transmission in a multiuser LTE scheme. Unfortunately, LTE-uplink inherently generates significant inter-symbol interference especially high bandwidth scenarios. The result is a rise to mutual interference among active users with an increased error rate. This incidence eventually causes non-orthogonal user spreading codes. Moreover, this drawback is known as the multiple access interference episodes which demonstrate high computational complexity and enhances symbol error rate at the receiving end and degrades the communication quality. Most of the related work has been claimed iterative linear minimum mean square error (LMMSE) detection requires a matrix inversion role which has a high computational complexity and contains a combinatorial optimization problem. Consequently, the LMMSE does not meet the requirement to implement real-time detection with low complexity and thus limiting its application. Therefore, we propose an acceptable bio-inspired neural network (NN) in the case of single and multilayer NNs with supervised learning particularly Levenberg–Marquardt backpropagation learning algorithm to improve the convergence speed. Simulation results performed with highest approaches highlights a better act for the proposed system.
Similar content being viewed by others
Abbreviations
- 3GPP:
-
Third generation partnership project
- 4G:
-
Fourth generation
- LTE:
-
Long term evolution
- 5G:
-
Fifth generation
- ISI:
-
Inter-symbol interference
- MIMO:
-
Multiple input and multiple output
- OFDM:
-
Orthogonal frequency division multiplexing
- DFT:
-
Discrete Fourier transform
- IDFT:
-
Inverse discrete Fourier transform
- SC-FDMA:
-
Single carrier-frequency division multiple access
- NNs:
-
Neural networks
- LMMSE:
-
Linear minimum mean square error
- LMB:
-
Levenberg–Marquardt backpropagation
- ARQ:
-
Automatic repeat request
- DFE:
-
Decision feedback equalizer
- M-RAT:
-
Multi-radio access technology
References
Prasad, R. (2013). Global ICT standardization forum for India (GISFI) and 5G standardization. Journal of ICT Standardization, 1(2), 123–136.
Prasad, R. (2014). 5G: 2020 and beyond. Aalborg: The River Publisher.
Dahlman, E., Parkvall, S., Skold, J., & Beming, P. (2008). 3G evolation HSPA and LTE for mobile broadband (2nd ed.). London: Academic Press.
Toskala, A. (2012). 3GPP TSG RAN workshop on Rel-12 and onwards. RWS-120002 Samsung, Ljubljana, Slovenia.
Farooq, K. (2009). LTE for 4G mobile broadband. Cambridge: Cambridge University Press.
Dahlman, E., & Parkvall, S. (2011). LTE/LTE-advanced for mobile broadband. London: Academic Press.
Harri, H., & Antti, T. (2012). LTE-advanced 3GPP solution for IMT-advanced. London: Wiley.
Nam, W., Bai, D., Lee, J., & Kang, I. (2014). 5G wireless communications systems: Prospects and challenges advanced interference management for 5G cellular networks. IEEE Communications Magazine, 52(5), 52–60.
Rusek, F., Daniel, P., Kiong, B. L., Erik, L. G., Marzetta, T. L., Edfors, O., & Tufvesson, F. (2013). Scaling up MIMO: Opportunities and challenges with very large arrays. IEEE Signal Processing Magazine, 30(1), 40–60.
Marzetta, T. L. (2010). Beyond LTE: Hundreds of base station antennas! IEEE Communication Theory Workshop, Bell Laboratories. Alcatel-Lucent.
Yang, H. (2005). A road to future broadband wireless access: MIMO–OFDM based wireless access. IEEE Communication Magazine, 43(1), 53–60.
Bolcski, H., & Zurich, E. (2006). MIMO–OFDMA wireless systems: Basics, perspectives and challenges. IEEE Wireless Communications, 13(4), 31–37.
Jiang, M., & Hanzo, L. (2007). Multiuser MIMO–OFDM for next generation wireless systems. Proceeding of the IEEE, 95(7), 1430–1469.
Telatar, E. (1999). Capacity of multi-antenna Gaussien channel. European Transaction on Telecommnications, 10(6), 585–595.
Alamouti, S. (1998). A simple transmit diversity technique for wireless communications. IEEE Journal on Selected Areas in Communications, 16(8), 1451–1458.
Tarokh, V., Jafarkhani, H., & Calderbank, R. (1999). Space-time block codes from orthogonal designs. IEEE Transactions on Information Theory, 45(5), 1456–1467.
Weinstein, S. B., & Ebert, P. M. (1971). Data transmission by frequency-division multiplexing using discreet Fourier transform. IEEE Transactions on Communications, 19(2), 628–634.
Riichi, K., Armour, S., McGeehan, J., & Mizoguchi, M. (2013). A channel state information feedback method for massive MIMO–OFDM. Journal of Communication and Networks, 15(4), 352–361.
Myung, H., Lim, J., & Goodman, D. (2006). Single carrier FDMA for uplink wireless transmission. IEEE Vehicular Technology Magazine, 1(3), 30–38.
Raleigh, G. C., & John, M. C. (1998). Spatio-temporal coding for wireless communication. IEEE Transactions on Communications, 46(3), 357–366.
Madhow, U., & Honig, M. L. (1994). MMSE interference suppression for direct-sequence spread-spectrum CDMA. IEEE Transactions on Communications, 42, 3178–3188.
Rapajic, P. B., & Vucetic, B. S. (1994). Adaptive receiver structures for asynchronous CDMA systems. IEEE Journal on Selected Areas in Communications, 12, 685–697.
Miller, S. L. (1995). An adaptive direct-sequence code-division multiple-access receiver for multiuser interference rejection. IEEE Transactions on Communications, 43, 1746–1755.
Abdulrahman, M., Sheikh, A. U. H., & Falconer, D. D. (1994). Decision feedback equalization for CDMA in indoor wireless communications. IEEE Journal on Selected Areas in Communications, 12, 698–706.
Yuan, X., Chongbin, X., Ping, L., & Xiaokang, L. (2009). Precoder design for multiuser MIMO ISI channels based on iterative LMMSE detection. IEEE Journal of Selected Topics in Signal Processing, 3(6), 1118–1128.
Frings, H. (1977). Animal communications, 2nd edn. University of Oklahoma Press. ISBN: 0806113936.
Dressler, F., & Akan, F. B. (2010). Bio-inspired networking: From theory to practice. IEEE Communication Magazine, 48(11), 173–183.
Zurada, J. M. (1995). Introduction to artificial neural systems. Boston, MA: PWS-Kent.
Hagan, T. M., & Menhaj, M. (1994). Training feed-forward networks with the Marquardt algorithm. IEEE Transactions on Neural Networks, 5(6), 989–993.
Kollis, S., & Anastassiou, D. (1989). An adaptive squares algorithm for the efficient training of artificial neural networks. IEEE Transactions on Neural Networks, 36, 1092–1101.
Razavi, S., & Tolson, A. B. (2011). A new formulation for feedforward neural networks. IEEE Transaction on Neural Networks, 22(10), 1588–1598.
Osseiran, A., Boccardi, F., Braun, V., Kasume, K., Marsch, P., Maternia, M., et al. (2014). 5G wireless communications systems: Prospects and challenges, scenarios for 5G mobile wireless communications: The vision of the METIS project. IEEE Communications Magazine, 52(5), 26–35.
Wang, Z., & Giannakis, G. B. (2000). Wireless multicarrier communications: Where Fourier meets Shannon. IEEE Signal Processing Magazine, 47(3), 29–48.
Yuan, X., Guo, Q., Wang, X., & Ping, L. (2008). Low-complexity iterative detection in multi-user MIMO ISI channels. IEEE Signal Processing Letter, 15, 25–28.
Yuan, X., Guo, Q., Wang, X., & Ping, L. (2008). Evolution analysis of low cost iterative equalization in coded linear systems with cyclic prefixes. IEEE Journal on Selected Areas in Communications, 26(2), 301–310.
Falconer, D., Ariyavisitakul, S. L., Benyamin, S. A., & Eldson, B. (2002). Frequency domain equalization for single-carrier broadband wireless systems. IEEE Communications Magazine, 40(4), 58–66.
Palomar, D. P., Cioffi, J. M., & Lagunas, M. A. (2003). Joint Tx–Rx beamforming design for multicarrier MIMO channels: A unified framework for convex optimization. IEEE Transactions on Signal Processing, 51(9), 2381–2401.
Verdù, S. (1998). Multiuser detection. New York: Cambridge University Press.
Li, J., & Zhang, X.-D. (2005). Blind adaptive multiuser detection based on affine projection algorithm. IEEE Signal Processing Letters, 12(10), 673–676.
Fantacci, R., Forti, M., Marini, M., Tarchi, D., & Vannuccini, G. (2003). A neural network for constrained optimization with applications to CDMA communication systems. IEEE Transaction on Circuits Systems II, 50(8), 484–487.
Fantacci, R., Tarchi, D., Marini, M., & Rabbini, A. (2006). A neural network approach to MMSE receivers in a DS-CDMA multipath fading environment. IEEE Transaction on Communications, 54(5), 778–782.
Hopfield, J. J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences, 81, 3088–3092.
Kennedy, M. P., & Chua, L. O. (1988). Neural networks for nonlinear programming. IEEE Transaction on Circuits Systems, 35(5), 554–562.
Choi, J. (2010). Optimal combining and detection: Statistical signal processing for communication (pp. 132–134). Cambridge: Cambridge University Press.
Henri, P. G. (2013). The Levenberg–Marquardt method for nonlinear least squares curve-fitting problems. Duke University Press. http://people.duke.edu/~hpgavin/ce281/lm.pdf
Jose, J., Ashikhmin, A., Marzetta, T. L., & Vishwanath, S. (2009). Pilot contamination problem in multi-cell TDD systems. Seoul Korea: ISIT.
Ashikhmin, A., & Marzetta, T. (2012). Pilot contamination precoding in multi-cell large scale antenna systems. Cambridge, MA: ISIT.
Cover, T. M., & Thomas, J. A. (2006). Element of information theory (pp. 183–240). London: Wiley.
Heath, R. W., Sandhu, S., & Paulraj, A. (2001). Antenna selection for spatial multiplexing systems with linear receivers. IEEE Communications Letters, 5(4), 142–144.
Antonio, F., et al. (2007). Adaptive MIMO transmission for exploiting the capacity of spatially correlated channels. IEEE Transaction on Vehicular Tecnology, 56(2), 619–630.
Roajs, R. (1996). Neural networks. Berlin: Springer.
Klema, V. C., & Alan J. L., Member, IEEE. (1980). The singular value decomposition: Its computation and some applications. IEEE Transactions on Automatic Control, 25(2), 164–176.
Young, S. C., Kim, J., Yang, W. Y., & Kang, C. G. (2010). MIMO–OFDM wireless communications with MatLab (pp. 263–265). London: Wiley.
Marquardt, D. W. (1963). An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics, 11(2), 431–441.
Acknowledgments
This work was supported by MEST-2012-002521 and Brain Korea 21 (BK21)-2015 National Research Foundation (NRF), Republic of Korea.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1
A multilayer NNs model is a very useful for a neuromodeling application and based on linear or nonlinear models which are proposed by Mcculloch and Pitts, 1943 and Rosenblatt, 1958 as cited in Haykin, 1999. There are three main steps in multilayer perceptions—(1) outline; (2) weights update or learning rule; (3) generalized test. In this model, neurons are signal processing units composed by a linear combiner and an activation function that can be linear or nonlinear [51]. Usually a linear channel estimator that is a single computing element with estimated network weights \( w_{i} = w_{0} ,w_{1} ,\text{w}_{2} , \ldots ,\text{w}_{q} \) and which for the input produces \( w_{1} x_{1} + w_{2} x_{2} + \cdots + w_{q} x_{q} \). The neuron output signal is the value of the activation function f(·) in response to the neuron activation potential from j network net j as follows
The final output of the linear NNs is given by
Similarly, x 0 = ±1 is the polarization potential (or threshold) applied to the neurons. The non-liner NNs is given by
and the final output of non-linear NNs is given by
We can represent the threshold detection using Eqs. (54–56) as follows
In multilayer NNs, a collection of neuron connected together in a network can be represented by a direction graph in Fig. 10.
In Fig. 10, nodes represented neurons and arrows represent the links between them and each node has its number and a link connecting two nodes will have a pair (connecting nodes 1 and 4). The network without cycle (feedback loops) are called feed-forward network or perception. The input nodes of the network such as node 1, 2 and 3 are associated with the input variables \( (x_{i} = x_{1} ,x_{2} , \ldots ,x_{q} ) \). They do not compute anything but simply pass the value to the processing nodes. The output nodes (4 and 5) are associated with the output variables \( (y_{j} = y_{1} ,y_{2} , \ldots ,y_{p} ) \). NNs can have several hidden layers. Each j-th node in a network has a set of weights w ij and the activation functions, f of all the nodes. For example of two layers feed-forward NN in Fig. 11.
Let the input variables x 1 = 1 and x 2 = 0. Node 3, 4 and 5 has weights w 13 = 2, w 23 = −3, w 14 = 1, w 24 = 4, w 35 = 2 and w 45 = −1, respectively. The output of final node 5 is obtain
Now we calculate weighted sum in the first hidden layer
After activation function in Eqs. (59) and (60) and given by
and
The weighted sum of node 5 is
The output of final node 5 is given by
Appendix 2
The SVD decomposition [52] Theorem 1 as follows
Theorem 1
Let \( {\mathbf{H}} \in {\mathbf{R}}^{{M_{R}\times M_{T}}} \) or \( {\mathbf{H}} \in {\mathbf{C}}^{{M_{R}\times M_{T}}} \) , then there exist orthogonal or unitary matrices such as \( U \in {\mathbf{R}}^{{M_{R}\times M_{R}}} \) or \( U \in {\mathbf{C}}^{{M_{R}\times M_{R}}} \) and \( V \in {\mathbf{R}}^{{M_{T}\times M_{T}}} \) or \( V \in {\mathbf{C}}^{{M_{T}\times M_{T}}} \) and \( \Sigma \in {\mathbf{R}}^{{M_{R}\times M_{T}}} \) or \( \Sigma\in {\mathbf{C}}^{{M_{R}\times M_{T}}} \) is a rectangular matrix whose diagonal elements are non-negative real numbers and whose off-diagonal elements are zero whereas the matrix H has the SVD as follows:
or,
where \( \Sigma = \left[{\begin{array}{*{20}l} S & 0\\ 0 & 0\\ \end{array}}\right] \) and S = diag{σ 1 , σ 2 ,…,σ k } since σ 1 ≥ σ 2 ≥ ···>σ k .
Proof
Let \( {\mathbf{H}}^{T} {\mathbf{H}} \ge 0 \) we have \( \sigma \left( {{\mathbf{H}}^{T} {\mathbf{H}}} \right) \le \left[ {0,\infty}\right] \) where operator {·}T represent the transpose. Denoting \( \sigma \left( {{\mathbf{H}}^{T} {\mathbf{H}}} \right) \) by \( \left\{ {\sigma_{i}^{2} ,i = 1,2, \ldots ,n} \right\} \), we can arrange that,
Suppose \( V_{1} ,\text{V}_{2}, \ldots ,\text{V}_{n} \) be a corresponding set of orthogonal eigenvectors and let,
then if S = diag{σ 1, σ 2,…,σ k } we have:
where \( S^{-1} V_{1}^{T} {\mathbf{H}}^{T} {\mathbf{H}}V_{1} S^{-1} = I \).
Also \( {\mathbf{H}}^{T} {\mathbf{H}}V_{2} = V_{2} 0 \), So that, \( V_{2}^{T} {\mathbf{H}}^{T} {\mathbf{H}}V_{2} = 0 \), thus H V 2 = 0.
Let \( U_{1} = {\mathbf{H}}V_{1} S^{-1} \) we have \( U_{1}^{T} U_{1} = I \) choose any U 2 such that U = (U 1, U 2) is orthogonal then:
So H = UΣV T as desired.
For an example in [53], If the matrix product H = UΛV H and M min = min(M T , M R ) can be expressed when M min = M T as follows:
where \( U_{{M_{\min}}}\in {\mathbf{C}}^{{M_{R}\times M_{\min}}} \) is composed of M min left singular vectors corresponding to the maximum possible singular values and \( \Sigma_{{M_{\min}}}\in {\mathbf{C}}^{{M_{\min}\times M_{\min}}} \) square matrix.
Similarly if M min = M R then we can be written as:
where \( V_{{M_{\min}}}\in {\mathbf{C}}^{{M_{T}\times M_{\min}}} \) is composed of M min right singular vectors.
Therefore, the eigenvalue decomposition as below:
where \( \Lambda \in {\mathbf{C}}^{{M_{R} \times M_{R} }} \) a diagonal matrix is whose diagonal elements is given by:
where \( \{ \lambda_{i} \}_{i = 1}^{{M_{R} }} \) is the eigenvalues of Λ and the unitary matrix U = Q and \( QQ^{H} = I_{{M_{R} }} \).
The squared Frobenius norm of the MIMO channel becomes:
Using Eq. (70) in Eq. (71) and we have:
Rights and permissions
About this article
Cite this article
Sarker, M.A.L., Lee, M.H. & Chung, J.G. ISI Free Channel Equalization for Future 5G Mobile Terminal Using Bio-inspired Neural Networks. Wireless Pers Commun 83, 2899–2923 (2015). https://doi.org/10.1007/s11277-015-2573-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-015-2573-1