Application of the invariance and robustness principles in the development of demodulation algorithms for wideband communications systems

Bogdanovich, V. A.; Vostretsov, A. G.

doi:10.1134/s1064226909110072

Cited by 13 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, practical wireless communication systems have other imperfections and unknown surrounding effects that cannot be tackled well by accurate channel models; therefore, researchers have developed various channel models that effectively characterise practical channel statistics. By using these channel models, reliable and practical training datasets can be obtained by modelling (Bogdanovich, Vostretsov & Electronics, 2009;Essai Ali, 2021;.…”

Section: Offline DL Of the Dl Bilstm Nn-based Csiementioning

confidence: 99%

“…Thus, a priori uncertainty exists for communication channel statistics. However, the classical theory of detection, recognition, and estimation of signals deals with complete priory certainty for channel statistics, and it is an unreliable and unpractical assumption (Bogdanovich, Vostretsov & Electronics, 2009).…”

Section: Introductionmentioning

confidence: 99%

“…In such conditions, the classical theory allows the synthesis of optimal estimation algorithms, but the structure and quality coefficients of the algorithms depend on the values of the parameters of the signal-noise environment. If the values of the parameters describing the signal-noise environment are slightly different from the parameters for which the optimal algorithm is built, then the quality coefficients will become substantially poor, making the algorithm useless in several cases (Bogdanovich, Vostretsov & Electronics, 2009; O'Shea, Karra & Clancy, 2017). The most frequently used CSIEs are derived from signal and channel statistical models by employing techniques, such as maximum likelihood (ML), least squares (LS), and minimum mean squared error (MMSE) optimisation metrics (Kim, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Channel state information estimation for 5G wireless communication systems: recurrent neural networks approach

Ali

Taha

2021

PeerJ Computer Science

View full text Add to dashboard Cite

In this study, a deep learning bidirectional long short-term memory (BiLSTM) recurrent neural network-based channel state information estimator is proposed for 5G orthogonal frequency-division multiplexing systems. The proposed estimator is a pilot-dependent estimator and follows the online learning approach in the training phase and the offline approach in the practical implementation phase. The estimator does not deal with complete a priori certainty for channels’ statistics and attains superior performance in the presence of a limited number of pilots. A comparative study is conducted using three classification layers that use loss functions: mean absolute error, cross entropy function for kth mutually exclusive classes and sum of squared of the errors. The Adam, RMSProp, SGdm, and Adadelat optimisation algorithms are used to evaluate the performance of the proposed estimator using each classification layer. In terms of symbol error rate and accuracy metrics, the proposed estimator outperforms long short-term memory (LSTM) neural network-based channel state information, least squares and minimum mean square error estimators under different simulation conditions. The computational and training time complexities for deep learning BiLSTM- and LSTM-based estimators are provided. Given that the proposed estimator relies on the deep learning neural network approach, where it can analyse massive data, recognise statistical dependencies and characteristics, develop relationships between features and generalise the accrued knowledge for new datasets that it has not seen before, the approach is promising for any 5G and beyond communication system.

show abstract

Section: Offline DL Of the Dl Bilstm Nn-based Csiementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Channel state information estimation for 5G wireless communication systems: recurrent neural networks approach

Ali

Taha

2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…The proposed detector utilizes Fair criterion, which is one of the robust statistics M-estimators. The proposed detector is compared with the aforementioned detectors at various MIMO configurations (2x2, 4x4, and 8x8), also under the conditions of Gaussian and non-Gaussian channels (uncertain noise environments), were strictly synthesized for the impractical GN distribution hypothesis [4,5,6].…”

Section: Introductionmentioning

confidence: 99%

Fair- M-Estimator Based Mimo Detector and Mimo System Investigation in Non-Gaussian Channels

Essai

2018

JES. Journal of Engineering Sciences

View full text Add to dashboard Cite

The impact of the presence of non-Gaussian noise on the efficiency of OSIC-MMSE and OSIC-ZF detectors for 2x2 SM-MIMO communication systems were investigated. Also, I investigated to what extent, increasing the number of transmitting and receiving antennas in SM-MIMO systems will enhance the efficiency of the investigated detectors against these non-Gaussian noises. Finally, a new M-Estimator based SM-MIMO detector named Fair detector is proposed, in order to achieve robust detection, for non-Gaussian channels. The proposed detector designed for LTE and LTE-advanced wireless communication systems. The proposed detector was compared with aforementioned detectors in terms of bit error rate, and computational complexity. Simulation results show the substantial performance of the proposed detector compared to the investigated detectors.

show abstract

“…With aid of detection techniques that are available in LTE communication networks, such as Zero Forcing -Ordered Sequence Interference Cancelation (ZF-OSIC), Minimum Mean Square Error (MMSE-OSIC), and Maximum likelihood (ML), and SM-MIMO system configuration; we will examine the functionality of these detection techniques (detectors) under an uncertain noise environment, in other words a broad class of noise distributions, where these detectors are strictly optimized for the unrealistic Gaussian noise distribution assumption [4][5][6].…”

Section: Introductionmentioning

confidence: 99%

SM-MIMO effect on the performance of LTE detectors in uncertain noise environments

Essai

2014

2014 12th International Conference on Actual Problems of Electronics Instrument Engineering (APEIE)

View full text Add to dashboard Cite

The effect of Spatial Multiplexing -Multiple Input Multiple Output (SM-MIMO) transmission technique on the performance of commonly used 4G-LTE detection techniques, was investigated. The channel environments used are Additive White Gaussian (AWGN), noise and heavy-tailed noise distributions as an actual noise distribution. The detectors characteristics were obtained by computer simulation for the case of un coded QPSK modulation, and open loop spatial multiplexing.Index Terms -Spatial multiplexing, MIMO, sub-optimal & optimal detectors, uncertain channel noise model.

show abstract

Application of the invariance and robustness principles in the development of demodulation algorithms for wideband communications systems

Cited by 13 publications

References 1 publication

Channel state information estimation for 5G wireless communication systems: recurrent neural networks approach

Channel state information estimation for 5G wireless communication systems: recurrent neural networks approach

Fair- M-Estimator Based Mimo Detector and Mimo System Investigation in Non-Gaussian Channels

SM-MIMO effect on the performance of LTE detectors in uncertain noise environments

Contact Info

Product

Resources

About