Continual Learning-Based Channel Estimation for 5G Millimeter-Wave Systems

Kumar, Swaraj; Vankayala, Satya Kumar; Sahoo, Biswa P. S.; Yoon, Seungil

doi:10.1109/ccnc49032.2021.9369645

Cited by 11 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other related studies focusing on continual learning (CL) benchmarked the performance of CL-based methods for MIMO channels estimation by varying the SNR and the coherence time of the channel [124]. A continual learning minimum mean-square error (CL-MMSE) method has also been proposed in [125] where the DNN adapts to different numbers of receive antennas between 8 and 128 to generate tasks with different difficulties.…”

Section: B Channel Estimationmentioning

confidence: 99%

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

Akrout

Shyianov

Bellili

et al. 2023

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

Data-driven machine learning (ML) is promoted as one potential technology to be used in next-generations wireless systems. This led to a large body of research work that applies ML techniques to solve problems in different layers of the wireless transmission link. However, most of these applications rely on supervised learning which assumes that the source (training) and target (test) data are independent and identically distributed (i.i.d). This assumption is often violated in the real world due to domain or distribution shifts between the source and the target data. Thus, it is important to ensure that these algorithms generalize to out-of-distribution (OOD) data. In this context, domain generalization (DG) tackles the OODrelated issues by learning models on different and distinct source domains/datasets with generalization capabilities to unseen new domains without additional finetuning. Motivated by the importance of DG requirements for wireless applications, we present a comprehensive overview of the recent developments in DG and the different sources of domain shift. We also summarize the existing DG methods and review their applications in selected wireless communication problems, and conclude with insights and open questions.

show abstract

Section: B Channel Estimationmentioning

confidence: 99%

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

Akrout

Shyianov

Bellili

et al. 2023

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

“…The transmitted reference signal and the received reference signal values are already known. The channel coefficient can be calculated in accordance with the equation (4). By knowing all these values, the noise parameter can be calculated.…”

Section: Estimation Of Noise Parametersmentioning

confidence: 99%

“…Compared to Orthogonal Frequency-Division Multiplexing (OFDM) antenna, arrays that divide wide band elevated signals into sub-channels [3]. Moreover, the MIMO antenna systems significantly improve the reliability and diversity characters of the wireless link [4]. Using OFDM-MIMO in a radio receiver can dramatically reduce the impacts of inter-symbol interference and frequency-selective fading to measurable levels [5].…”

Section: Introductionmentioning

confidence: 99%

A Novel Intelligent Channel Estimation Strategy for the 5G Wireless Communication Systems

Lakshmi

Vijayalakshmi

Naveena

2023

Wireless Pers Commun

View full text Add to dashboard Cite

Nowadays, the Multiple Input Multiple Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) is an important method used in wireless communications, especially in 5G cellular communications. As in a wireless network, the input signals pass through a channel, and the input signal undergoes phase shift, attenuation, and interference. So, the password from the user side and the received signals are not the same. Thus, an effective channel estimator is essential to make cellular communication better. Hence, a novel hybrid technique called Chimp-based CatBoost channel estimation (CbCBCE) was proposed. This technique is the combination of the Chimp optimization algorithm and CatBoost algorithm. The channel parameters are estimated and then reduced using the Chimp optimization algorithm. Finally, the proposed model is validated with the case study. Then, the result of the proposed model was estimated, and it was compared with other existing techniques. It is observed that the outcome of the proposed design is more compared with the other conventional methods. The presented model is executed in the MATLAB platform, and it is proved that the proposed model has high throughput, high energy efficiency, less BER, and a high data transfer rate.

show abstract

“…However, SE cannot be calculated in the same way with an ELM method, since there is no estimated channel with this strategy [10], [32]. Therefore, the SINR can also be computed as (14) where PAPR is given per modulation scheme, i.e., the PAPR value corresponds to 0 dB, 2.6 dB, 3.7 dB, and 4.2 dB for the quadrature phase shift keying (QPSK) modulation, 16-quadrature amplitude modulation (16-QAM), 64-QAM, and 256-QAM, respectively, [32]. The error vector magnitude (EVM) of the s th subcarrier of the user k, (EVM k [s]), is calculated with the combined symbols in the receiver based on the Euclidean distance between the combined symbols and their perfect constellation points.…”

Section: E Spectral Efficiencymentioning

confidence: 99%

“…Since channel estimation is relevant in conventional receiver designs, ML and DL algorithms are used to improve channel estimation efficiency and communication quality [12]- [14]. In addition, many studies have investigated the issue of joint channel estimation and signal detection [15].…”

Section: Introductionmentioning

confidence: 99%

Novel Multilayer Extreme Learning Machine as a Massive MIMO Receiver for Millimeter Wave Communications

et al. 2022

View full text Add to dashboard Cite

Nowadays he is pursuing his Ph.D. degree at Tecnológico de Monterrey, México. His current research interest includes the use of techniques of artificial intelligence to automate different tasks on new generation networks, such as traffic modelling, Intrusion Detection Systems, and network resources optimization. CESAR A. AZURDIA-MEZA (Member IEEE) received the B.Sc. degree in Electronics Engineering from Universidad del Valle de Guatemala, Guatemala in 2005, and the M.Sc.

show abstract

Continual Learning-Based Channel Estimation for 5G Millimeter-Wave Systems

Cited by 11 publications

References 12 publications

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

Achievable Rate of Near-Field Communications Based on Physically Consistent Models

A Novel Intelligent Channel Estimation Strategy for the 5G Wireless Communication Systems

Novel Multilayer Extreme Learning Machine as a Massive MIMO Receiver for Millimeter Wave Communications

Contact Info

Product

Resources

About