ML-Based Iterative Sequence Estimation Without Symbol Timing Recovery

Shen, Zhixiang; Yu, Hongyi; Shen, Caiyao; Hu, Yunpeng

doi:10.1109/lcomm.2013.082613.131532

Cited by 3 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12], EM-based technique integrated with code property can provide a reliable timing estimate for scenarios where conventional schemes' performance deteriorates. Furthermore, [13] proposed a framework for direct sequence detection without explicit timing recovery based on the EM algorithm. Recently, research considering synchronization integrated with deep learning gradually appeared in academia.…”

Section: Introductionmentioning

confidence: 99%

End‐to‐end waveform level receiver with deep learning

Zhu

Shen

2022

IET Communications

Self Cite

View full text Add to dashboard Cite

Numerous researches on communication receiver design with deep learning algorithms have been implemented effectively recently. In this paper, an innovative scheme is proposed to construct an end‐to‐end neural network (NN) receiver to directly recover information bits from unsynchronized waveform sequences. Considering the correlation between samples, multiple bidirectional long‐short term memory (BiLSTM) layers to process oversampled signals. Then, shifted binary cross‐entropy (SBCE) function is devised to tackle the overfitting issue and eliminate instances with abnormal bit error rate (BER), which originate from standard binary cross‐entropy (BCE) loss function. Substantial simulation results demonstrate that the trained NN receiver can achieve theory BER values under excellent conditions for transceivers. Compared with traditional synchronization algorithms, the proposed method can obtain significant BER performance gain under harsh conditions, such as low oversample rate, small roll‐off factor, short frame length.

show abstract

Section: Introductionmentioning

confidence: 99%

End‐to‐end waveform level receiver with deep learning

Zhu

Shen

2022

IET Communications

Self Cite

View full text Add to dashboard Cite

show abstract

“…The STO estimation is widely categorized into two basic groups. The first group belongs to the data‐aided group , which is not bandwidth efficient, as it uses a pilot signal or training sequences for the STO estimation. The second approach is the non‐data–aided structure, which exploits the statistics of the received signal for the estimation, and is also known as blind estimation .…”

Section: Introductionmentioning

confidence: 99%

“…The first group belongs to the data‐aided group , which is not bandwidth efficient, as it uses a pilot signal or training sequences for the STO estimation. The second approach is the non‐data–aided structure, which exploits the statistics of the received signal for the estimation, and is also known as blind estimation . Some of the non‐data–aided classical STO estimations are the early‐late gate algorithm , Mueller and Muller algorithm , and Gardner algorithm .…”

Section: Introductionmentioning

confidence: 99%

Blind symbol timing offset estimation for offset‐QPSK modulated signals

Kumar

Majhi

2019

ETRI Journal

View full text Add to dashboard Cite

In this paper, a blind symbol timing offset (STO) estimation method is proposed for offset quadrature phase‐shift keying (OQPSK) modulated signals, which also works for other linearly modulated signals (LMS) such as binary‐PSK, QPSK, π/4‐QPSK, and minimum‐shift keying. There are various methods available for blind STO estimation of LMS; however, none work in the case of OQPSK modulated signals. The popular cyclic correlation method fails to estimate STO for OQPSK signals, as the offset present between the in‐phase (I) and quadrature (Q) components causes the cyclic peak to disappear at the symbol rate frequency. In the proposed method, a set of close and approximate offsets is used to compensate the offset between the I and Q components of the received OQPSK signal. The STO in the time domain is represented as a phase in the cyclic frequency domain. The STO is therefore calculated by obtaining the phase of the cyclic peak at the symbol rate frequency. The method is validated through extensive theoretical study, simulation, and testbed implementation. The proposed estimation method exhibits robust performance in the presence of unknown carrier phase offset and frequency offset.

show abstract

“…Another approach is presented in [10]: based on a coarse estimate of timing, the detection is performed by combining soft bits obtained by the turbo decoder. Recently in [11], with an assumption of perfect carrier synchronization, a numerical integration of timing is applied instead of the conventional symbol timing recovery.…”

Section: Introductionmentioning

confidence: 99%

Iterative ML Symbol Detection without Timing and Phase Synchronization

Shen

Zhang

et al. 2014

AMR

View full text Add to dashboard Cite

This paper deals with maximum-likelihood (ML) detection of symbol sequence in the absence of synchronization information. A novel iterative scheme is proposed to obtain the ML estimates of the symbols without an estimation of synchronization parameters. Instead of the optimal sampling point recovery and explicit carrier phase compensation, the detection of symbols employs the direct calculation of the matched filter output, eliminating the need for a separate synchronizer. The detection problem is treated as ML estimation from incomplete data, which is solved by means of an iterative scheme based on the expectation-maximization algorithm. The proposed scheme is compared with conventional non-data-aided and iterative ML synchronizers. Accordingly, the simulation results indicate that the proposed detector enables improvements on both the bit error rate and convergence property.

show abstract

ML-Based Iterative Sequence Estimation Without Symbol Timing Recovery

Cited by 3 publications

References 14 publications

End‐to‐end waveform level receiver with deep learning

End‐to‐end waveform level receiver with deep learning

Blind symbol timing offset estimation for offset‐QPSK modulated signals

Iterative ML Symbol Detection without Timing and Phase Synchronization

Contact Info

Product

Resources

About