Deep Transfer Learning for Site-Specific Channel Estimation in Low-Resolution mmWave MIMO

Alves, Wesin; Correa, Ilan; González–Prelcic, Nuria; Klautau, Aldebaro

doi:10.1109/lwc.2021.3069199

Cited by 21 publications

(22 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the offline training can be made more efficient by first pretraining the model on a realistic system simulator, and then extending the training with an additional, usually smaller, set of training samples collected from a real-world environment [14]. This process can be further improved by techniques of deep transfer learning, which can speed up the model design, as suggested in [30]. Also, authors in [31] propose effective combining of the trained models using the concept of federated learning in order to arrive at more robust and efficient models.…”

Section: Numerical Resultsmentioning

confidence: 99%

Deep Learning-Based Packet Detection and Carrier Frequency Offset Estimation in IEEE 802.11ah

Ninković

Valka²,

Dumic³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Wi-Fi systems based on the IEEE 802.11 standards are the most popular wireless interfaces that use Listen Before Talk (LBT) method for channel access. The distinctive feature of a majority of LBTbased systems is that the transmitters use preambles that precede the data to allow the receivers to perform packet detection and carrier frequency offset (CFO) estimation. Preambles usually contain repetitions of training symbols with good correlation properties, while conventional digital receivers apply correlationbased methods for both packet detection and CFO estimation. However, in recent years, data-based machine learning methods are disrupting physical layer research. Promising results have been presented, in particular, in the domain of deep learning (DL)-based channel estimation. In this paper, we present a performance and complexity analysis of packet detection and CFO estimation using both the conventional and the DL-based approaches. The goal of the study is to investigate under which conditions the performance of the DLbased methods approach or even surpass the conventional methods, but also, under which conditions their performance is inferior. Focusing on the emerging IEEE 802.11ah standard, our investigation uses both the standard-based simulated environment, and a real-world testbed based on Software Defined Radios.

show abstract

Section: Numerical Resultsmentioning

confidence: 99%

Deep Learning-Based Packet Detection and Carrier Frequency Offset Estimation in IEEE 802.11ah

Ninković

Valka²,

Dumic³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…4 depicts the results of channel estimation using MIMO systems adopting analog to digital converters with resolution of a single bit. For this task, we used convolutional NNs as described in [18] and the companion source code. ULAs with N tx = 64 and N rx = 8 antennas were adopted.…”

Section: Numerical Resultsmentioning

confidence: 99%

“…ULAs with N tx = 64 and N rx = 8 antennas were adopted. The normalized mean-squared error (NMSE) [18] is the figure of merit. We first compared SISO-RT-GET with (CO) and without (FO) orientation correction, and both led to similar results.…”

Section: Numerical Resultsmentioning

confidence: 99%

Generating MIMO Channels For 6G Virtual Worlds Using Ray-tracing Simulations

Klautau¹,

Oliveira²,

Trindade³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Some 6G use cases include augmented reality and highfidelity holograms, with this information flowing through the network. Hence, it is expected that 6G systems can feed machine learning algorithms with such context information to optimize communication performance. This paper focuses on the simulation of 6G MIMO systems that rely on a 3-D representation of the environment as captured by cameras and eventually other sensors. We present new and improved Raymobtime datasets, which consist of paired MIMO channels and multimodal data. We also discuss tradeoffs between speed and accuracy when generating channels via ray-tracing. We finally provide results of beam selection and channel estimation to assess the impact of the improvements in the ray-tracing simulation methodology.

show abstract

“…Nevertheless, these DL-based CEs still face many challenges, such as low generalization with the environment change [44], long training time, complex parameter tuning, and large memory requirements [45], etc. Relative to the general DL method, the TL features many advantages [24], [46], e.g., huge amount of data is not required, the training time is short, and the network effectively adapts to the new environment without network retraining, etc. In [24], the TL approach was exploited to speed up new environment adaptation in lowresolution multiple-input multiple-output systems.…”

Section: A Related Workmentioning

confidence: 99%

“…Relative to the general DL method, the TL features many advantages [24], [46], e.g., huge amount of data is not required, the training time is short, and the network effectively adapts to the new environment without network retraining, etc. In [24], the TL approach was exploited to speed up new environment adaptation in lowresolution multiple-input multiple-output systems. By using direct transfer, the TL-based CE was designed in [24] to adapt the migration from one environment to another, while still encountering high computational complexity.…”

Section: A Related Workmentioning

confidence: 99%

Transfer Learning-based Channel Estimation in Orthogonal Frequency Division Multiplexing Systems Using Data-nulling Superimposed Pilots

Qing,

Dong,

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Data-nulling superimposed pilot (DNSP) effectively alleviates the superimposed interference of superimposed training (ST)-based channel estimation (CE) in orthogonal frequency division multiplexing (OFDM) systems, while facing the challenges of the estimation accuracy and computational complexity. By developing the promising solutions of deep learning (DL) in the physical layer of wireless communication, we fuse the DNSP and DL to tackle these challenges in this paper. Nevertheless, due to the changes of wireless scenarios, the model mismatch of DL leads to the performance degradation of CE, and thus faces the issue of network retraining. To address this issue, a lightweight transfer learning (TL) network is further proposed for the DL-based DNSP scheme, and thus structures a TL-based CE in OFDM systems. Specifically, based on the linear receiver, the least squares estimation is first employed to extract the initial features of CE. With the extracted features, we develop a convolutional neural network (CNN) to fuse the solutions of DLbased CE and the CE of DNSP. Finally, a lightweight TL network is constructed to address the model mismatch. To this end, a novel CE network for the DNSP scheme in OFDM systems is structured, which improves its estimation accuracy and alleviates the model mismatch. The experimental results show that in all signal-to-noise-ratio (SNR) regions, the proposed method achieves lower normalized mean squared error (NMSE) than the existing DNSP schemes with minimum mean square error (MMSE)-based CE. For example, when the SNR is 0 decibel (dB), the proposed scheme achieves similar NMSE as that of the MMSE-based CE scheme at 20 dB, thereby significantly improving the estimation accuracy of CE. In addition, relative to the existing schemes, the improvement of the proposed scheme presents its robustness against the impacts of parameter variations.Index Terms-Transfer learning (TL), channel estimation (CE), orthogonal frequency division multiplexing (OFDM), data-nulling superimposed pilot (DNSP) I. INTRODUCTIONO RTHOGONAL frequency division multiplexing (OFDM) has been widely applied in wireless communication systems, due to its attractive solution to combat multipath fading [1]. To guarantee the reliable communication in OFDM systems, channel estimation (CE) plays a critical role [2] to eliminate the impact of wireless channels, and thus inspires many CE methods, e.g., non-pilotaided CE [3], [4] and pilot-aided CE [5]. Without employing the pilot sequence (PS), the non-pilot-aided CE saves the valuable bandwidth resources [6]. Yet the high computational

show abstract

Deep Transfer Learning for Site-Specific Channel Estimation in Low-Resolution mmWave MIMO

Cited by 21 publications

References 20 publications

Deep Learning-Based Packet Detection and Carrier Frequency Offset Estimation in IEEE 802.11ah

Deep Learning-Based Packet Detection and Carrier Frequency Offset Estimation in IEEE 802.11ah

Generating MIMO Channels For 6G Virtual Worlds Using Ray-tracing Simulations

Transfer Learning-based Channel Estimation in Orthogonal Frequency Division Multiplexing Systems Using Data-nulling Superimposed Pilots

Contact Info

Product

Resources

About