Receiver Design for Faster-Than-Nyquist Signaling: Deep-Learning-Based Architectures

Song, Peiyang; Gong, Fengkui; Li, Qiang; Ding, Haiyang

doi:10.1109/access.2020.2986679

Cited by 19 publications

(19 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning also provides promising detection solutions for FTN systems. The papers [19] and [20] both study deep learning based receiver designs, which achieve near-optimal performance. Deep learning also assists FTN in other aspects.…”

Section: A Other Related Workmentioning

confidence: 99%

Faster-than-Nyquist Signaling for MIMO Communications

Zhang¹,

Yüksel²,

Yanıkömeroğlu³

2021

Preprint

View full text Add to dashboard Cite

Faster-than-Nyquist (FTN) signaling is a non-orthogonal transmission technique, which has the potential to provide significant spectral efficiency improvement. This paper studies the capacity of FTN signaling for point-to-point single-input single-output (SISO) and multiple-input multiple-output (MIMO) channels. Although the capacity of SISO FTN was studied previously, due to some incomplete prerequisites, the exact capacity expression was not found. In this paper we resolve these issues for SISO FTN and generalize the result to MIMO FTN. We show that joint waterfilling in time and space is capacity achieving for MIMO FTN.

show abstract

Section: A Other Related Workmentioning

confidence: 99%

Faster-than-Nyquist Signaling for MIMO Communications

Zhang¹,

Yüksel²,

Yanıkömeroğlu³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Yet, on the other hand, as far as our research has uncovered, no or very few scholars use data-driven methods to solve FTN detection algorithms in multipath channels. The existing data-driven related work mainly stays in AWGN channel or special scene channel (similar to AWGN optical communication channel and underwater communication channel) [ 25 , 26 , 27 ]. Preliminary research results show that for FTN signaling with a higher compression rate, the detection algorithm based on deepearning can obtain better performance than the MAP algorithm [ 28 ].…”

Section: Related Workmentioning

confidence: 99%

Data-Driven and Model-Driven Joint Detection Algorithm for Faster-Than-Nyquist Signaling in Multipath Channels

Deng

Bian

2021

Sensors

View full text Add to dashboard Cite

In recent years, Faster-than-Nyquist (FTN) transmission has been regarded as one of the key technologies for future 6G due to its advantages in high spectrum efficiency. However, as a price to improve the spectrum efficiency, the FTN system introduces inter-symbol interference (ISI) at the transmitting end, whicheads to a serious deterioration in the performance of traditional receiving algorithms under high compression rates and harsh channel environments. The data-driven detection algorithm has performance advantages for the detection of high compression rate FTN signaling, but the current related work is mainly focused on the application in the Additive White Gaussian Noise (AWGN) channel. In this article, for FTN signaling in multipath channels, a data and model-driven joint detection algorithm, i.e., DMD-JD algorithm is proposed. This algorithm first uses the traditional MMSE or ZFinear equalizer to complete the channel equalization, and then processes the serious ISI introduced by FTN through the deepearning network based on CNN or LSTM, thereby effectively avoiding the problem of insufficient generalization of the deepearning algorithm in different channel scenarios. The simulation results show that in multipath channels, the performance of the proposed DMD-JD algorithm is better than that of purely model-based or data-driven algorithms; in addition, the deepearning network trained based on a single channel model can be well adapted to FTN signal detection under other channel models, thereby improving the engineering practicability of the FTN signal detection algorithm based on deepearning.

show abstract

“…DC leads to serious ISI and ICI. To eliminate ISI and ICI, the traditional MFTN with the DC usually requires the global iteration and complex equalization algorithm such as the BCJR [7], [15], [31], M-BCJR [8], CS-BCJR [11] [29], SIC [32], GASDRSE [9], MMSE equalization [12], GMP [33], FDE [34], deep learning (DL) technology [13], symbol-bysymbol receiver with SIC [16]- [22]. The LPE converts FTN transmission into orthogonal signaling.…”

Section: Introductionmentioning

confidence: 99%

Multicarrier Faster-Than-Nyquist Based on Efficient Implementation and Probabilistic Shaping

2021

View full text Add to dashboard Cite

The conventional multicarrier faster-than-Nyquist (MFTN) achieves the spectral efficiency (SE) gain by deep compression. However, deep compression leads to severe intersymbol interference (ISI) or intercarrier interference (ICI). We propose the MFTN based on efficient implementation and probabilistic amplitude shaping (PAS) to achieve the SE gain with low complexity. We use mild compression instead of conventional deep compression to achieve the compression gain. The MFTN transceiver with the mild compression can be efficiently implemented by fast Fourier transform (FFT)/inverse FFT (IFFT) and filtering operation. The linear pre-equalization (LPE) method eliminates the ISI for mild compression. The MFTN with efficient implementation employs PAS to achieve extra shaping gain. The theoretical results and simulation results show that our method can achieve better performance than the conventional FTN/MFTN with deep compression. The proposed method does not require a complex equalization algorithm and global turbo iteration so that the total complexity is reduced.INDEX TERMS Multicarrier, faster-than-Nyquist, linear pre-equalization, probabilistic shaping, mild compression.

show abstract

Receiver Design for Faster-Than-Nyquist Signaling: Deep-Learning-Based Architectures

Cited by 19 publications

References 31 publications

Faster-than-Nyquist Signaling for MIMO Communications

Faster-than-Nyquist Signaling for MIMO Communications

Data-Driven and Model-Driven Joint Detection Algorithm for Faster-Than-Nyquist Signaling in Multipath Channels

Multicarrier Faster-Than-Nyquist Based on Efficient Implementation and Probabilistic Shaping

Contact Info

Product

Resources

About