Deep learning‐based pilot‐assisted channel state estimator for OFDM systems

Ali, Mohamed Hassan Essai

doi:10.1049/cmu2.12051

Cited by 20 publications

(19 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Four classes are specified by considering the size 4 fully connected (FC) layer, followed by a softmax layer and ended by a classification layer. Figure 3 illustrates the structure of the proposed estimator (Essai Ali, 2021;Ye, Li & Juang, 2018).…”

Section: Dlnn-based Csiementioning

confidence: 99%

“…The channel can be considered stationary during a certain frame, but it can change between different frames. The proposed DL BiLSTM NN-based CSIE receives the arrived data at its input terminal and extracts the transmitted data at its output terminal (Essai Ali, 2021;Ye, Li & Juang, 2018).…”

Section: Bilstm Nn-based Csie For 5g-ofdm Wireless Communication Systemsmentioning

confidence: 99%

“…Training should be done offline due to the long training time of the proposed CSIE and the large number of BILSTM-NN's parameters, such as biases and weights, that should be tuned during training. The trained CSIE is then used in online implementation to extract the transmitted data (Ye, Li & Juang, 2018;Essai Ali, 2021).…”

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

confidence: 99%

“…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%

See 3 more Smart Citations

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

Ali

Taha

2021

PeerJ Computer Science

Self Cite

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: Dlnn-based Csiementioning

confidence: 99%

Section: Bilstm Nn-based Csie For 5g-ofdm Wireless Communication Systemsmentioning

confidence: 99%

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

confidence: 99%

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

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…The most important advantages of deep learning neural networks are their learning capabilities, flexible solutions in solving nonlinear problems, easing the hardware load by using few parameters, and parallel processing capabilities. To address the issues of channel estimation and symbol detection for wireless communication platform, many types of deep learning neural networks have been proposed in the literature [4][5][6][7][8][9][10][11][12][13]. For instance, in [5], the performance of the signal detector created with convolutional neural networks has been compared with the SIC and then better symbol error rate was obtained.…”

Section: Introductionmentioning

confidence: 99%

Convolutional fuzzy neural network based symbol detection in MIMO NOMA systems

Seyman

2023

Journal of Electrical Engineering

View full text Add to dashboard Cite

One of the most important tasks to be considered in wireless communication systems, especially in multi-carrier systems such as Multi-Input Multi Output Non-Orthogonal (MIMO-NOMA), is to correctly estimate the channel state information for coherent detection at the receiver. A hybrid deep learning model, called convolutional fuzzy deep neural networks, is proposed in this study for accurately estimating channel state information and detecting symbols in MIMO-NOMA systems. The performance of this proposal has been compared to traditional algorithms like Least Square Error- Successive Interference Cancelation (LS-SIC) and linear minimum mean square (LMMSE-SIC), as well as to other deep learning methods such as convolutional neural networks. With this proposed scheme, significantly less bit error rate is obtained in both Rician and Rayleigh channel environment compared to other algorithms. In addition to the high performance of this scheme, the fact that it does not need channel statistics is another important advantage.

show abstract

ML‐IDSDN: Machine learning based intrusion detection system for software‐defined network

Alzahrani

Alenazi

2022

Concurrency and Computation

View full text Add to dashboard Cite

Software-defined networking (SDN) has been developed to separate network control plane from forwarding plane which can decrease operational costs and the time it takes to deploy new services compared to traditional networks. Despite these advantages, this technology brings threats and vulnerabilities. Consequently, developing high-performance real-time intrusion detection systems (IDSs) to classify malicious activities is a vital part of SDN architecture. This article introduces two created datasets generated from SDN using Mininet and Ryu controller with different feature extraction tools that contain normal traffic and different types of attacks (Fin flood, UDP flood, ICMP flood, OS probe scan, port probe scan, TCP bandwidth flood, and TCP syn flood) that is used for training a number of supervised binary classification machine learning algorithms such as k-nearest neighbor, AdaBoost, decision tree (DT), random forest, naive Bayes, multilayer perceptron, support vector machine, and XGBoost. The DT algorithm has achieved high scores to fit a real-time application achieving F1 score on attack class of 0.9995, F1 score on normal class of 0.9983, and throughput score of 6,737,147.275 samples per second with a total number of three features. In addition, using data preprocessing to reduce the model complexity, thereby increasing the overall throughput to fit a real-time system.

show abstract

Deep learning‐based pilot‐assisted channel state estimator for OFDM systems

Cited by 20 publications

References 16 publications

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

Convolutional fuzzy neural network based symbol detection in MIMO NOMA systems

ML‐IDSDN: Machine learning based intrusion detection system for software‐defined network

Contact Info

Product

Resources

About