Yeong-Luh Ueng

Yeong-Luh Ueng

Auto-generated profile, based on publicly available information

Yeong-Luh Ueng

Department of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 June 2020 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
CZChuan Zhang
Chuan Zhang
YUYeong-Luh Ueng
Yeong-Luh Ueng
CSChristoph Studer
Christoph Studer
ABAndreas Burg
Andreas Burg
The communication industry is rapidly advancing towards 5G and beyond 5G (B5G) wireless technologies in order to fulfill the ever-growing needs for higher data rates and improved quality-of-service (QoS). Emerging applications require wireless connectivity with tremendously increased data rates, substantially reduced latency, and growing support for a large number of devices. These requirements pose new challenges that can no longer be efficiently addressed by conventional approaches. Artificial intelligence (AI) is considered as one of the most promising solutions to improve the performance and robustness of 5G and B5G systems, fueled by the massive amount of data generated in 5G and B5G networks and the availability of powerful data processing fabrics. As a consequence, a plethora of research on AI-based communication technologies has emerged recently, promising higher data rates and improved QoS with affordable implementation overhead. In this overview paper, we summarize the state-of-the-art of AI-based 5G and B5G techniques on the algorithm, implementation, and optimization levels. We shed light on the advantages and limitations of AI-based solutions, and we provide a summary of emerging techniques and open research problems.

26 June 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
XTXiaosi Tan
Xiaosi Tan
YUYeong-Luh Ueng
Yeong-Luh Ueng
ZZZaichen Zhang
Zaichen Zhang
XYXiaohu You
Xiaohu You
CZChuan Zhang
Chuan Zhang
Among various massive multiple-input multiple-output (MIMO) signal detection schemes, expectation propagation (EP) achieves superior performance in high-dimensional systems with high-order modulations and flexible antenna configurations. However, the inevitable matrix inversion in each iteration of EP brings unbearable computational burden, which hinders the efficient implementation. Several reduced-complexity variants of EP are proposed recently, which effectively alleviate the computational cost but at the expense of unacceptable performance loss. In this paper, a low-complexity massive MIMO detection is first proposed based on approximate EP, which relieves the computational complexity of the exact EP while maintaining the good performance. Particularly, the EP moment matching equations are reformulated to simplify the sequential updating procedure. In addition, an approximation based on the channel-hardening phenomenon is proposed to eliminate the matrix inversion at each iteration. Numerical results show that, for high-dimensional MIMO the proposed detector approaches the exact EP in term of bit-error-rate (BER) by a small number of iterations. No matter with symmetric or asymmetric antenna configuration, it outperforms other EP variants, Gaussian tree approximation (GTA), and channel-hardening exploiting message passing (CHEMP). An analysis of computational complexity reveals the high efficiency of the proposed detection compared to the state-of-the-art (SOA) with flexible antenna configurations.

20 May 2020 in IEEE Journal on Emerging and Selected Topics in Circuits and Systems
Verified
Journal Article
Closed access
WXWeihong Xu
Weihong Xu
XTXiaosi Tan
Xiaosi Tan
YBYair Be'ery
Yair Be'ery
YUYeong-Luh Ueng
Yeong-Luh Ueng
YHYongming Huang
Yongming Huang
CZChuan Zhang
Chuan Zhang
This paper presents deep learning (DL) methods to optimize polar belief propagation (BP) decoding and concatenated LDPC-polar codes. First, two-dimensional offset Min- Sum (2-D OMS) decoding is proposed to improve the errorcorrection performance of existing normalized Min-Sum (NMS) decoding. Two optimization methods used in DL, namely backpropagation and stochastic gradient descent, are exploited to derive the parameters of proposed algorithms. Numerical results demonstrate that there is no performance gap between 2-D OMS and exact BP on various code lengths. Then the concatenated OMS algorithms with low complexity are presented for concatenated LDPC-polar codes. As a result, the optimized concatenated OMS decoding yields error-correction performance with CRCaided successive cancellation list (CA-SCL) decoder of list size 2 on length-1024 polar codes. In addition, the efficient hardware architectures of scalable polar OMS decoder are described and the proposed decoder is reconfigurable to support three code lengths (N = 256, 512, 1024) and two decoding algorithms (2- D OMS and concatenated OMS). The polar OMS decoder implemented on 65 nm CMOS technology achieves a maximum coded throughput of 5.4 Gb/s at Eb/N0 = 4 dB for code length 1024 and 7.5 Gb/s at Eb/N0 = 3.5 dB for code length 256, which are comparable to the state-of-the-art polar BP decoders. Moreover, a 5.1 Gb/s throughput at Eb/N0 = 4 dB is achieved under concatenated OMS decoding mode for code length 1024 with a latency of 200 ns, which is superior to existing CA-SCL decoders that have similar error-correction performance.

19 February 2020 in IEEE Transactions on Emerging Topics in Computational Intelligence
Verified
Journal Article
Closed access
YLYu-Fei Lin
Yu-Fei Lin
THTzu-Ming Huang
Tzu-Ming Huang
WCWei-Ho Chung
Wei-Ho Chung
YUYeong-Luh Ueng
Yeong-Luh Ueng
Profits can be made from a trading strategy where long or short positions are placed in advance, based on the ability to forecast a future stock price or index, such as the closing or opening price. In addition to predicting stock index values, a prediction of the sign for the difference between closing and opening prices is important in order to earn a profit. This article presents an approach based on a Recurrent Neural Network (RNN) to forecast the opening price, the closing price, and the difference between them. Compared to previously reported approaches that were based on machine learning, the method proposed here emphasizes the pre-processing of the data, including the normalized first order difference method, as well as the focusing on the characteristics of the stock data, such as the zero-crossing rate (ZCR), which denotes the ratio of changes in the sign within a specific time interval. We propose a decision-making approach that is based on an estimate of both the ZCR and the cross-validation data so as to enhance the ability to forecast the difference between the opening and closing prices. We apply our technique to the S&P500 (Standard & Poor's 500) and the Dow Jones stock indices. As indicated by the results, our method can achieve a better performance compared to previous work.

18 July 2019 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
WSWei-Cheng Sun
Wei-Cheng Sun
YSYu-Chieh Su
Yu-Chieh Su
YUYeong-Luh Ueng
Yeong-Luh Ueng
CYChia-Hsiang Yang
Chia-Hsiang Yang
This paper presents the first low-complexity realization of an LDPC-code sparse code multiple access (SCMA) receiver with a high-throughput LDPC decoder and a multi-mode SCMA detector. The minimum mean-square error with parallel interference cancellation (MMSE-PIC) algorithm is adopted in the SCMA detection. The modified user-node operations in the MMSE-PIC-based message-passing detector improve the convergence rate in error performance. The proposed receiver also supports multi-user iterative detection and decoding (MU-IDD) to improve the error rate performance. The proposed receiver supports both $4\times 6$ and $8\times 12$ SCMA systems. The proposed MU LDPC decoder has a 57.1% lower hardware complexity than the direct-mapped design that is achieved through hardware sharing and memory access scheduling. Designed in a 40-nm CMOS technology, the SCMA receiver integrates 10.9M logic gates in an area of $3.382\times 3.382$ mm 2 . The proposed design achieves a gross throughput of 1.198 Gb/s and 599 Mb/s for $8\times 12$ and $4\times 6$ SCMA systems, respectively, under a practical situation. It dissipates 813 mW at a clock frequency of 300 MHz from a 0.9-V supply.

29 November 2018 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
YCYan-Tong Chen
Yan-Tong Chen
WSWei-Cheng Sun
Wei-Cheng Sun
CCChung-Chao Cheng
Chung-Chao Cheng
TTTsung-Lin Tsai
Tsung-Lin Tsai
YUYeong-Luh Ueng
Yeong-Luh Ueng
CYChia-Hsiang Yang
Chia-Hsiang Yang
For a coded massive multi-user multiple-input multiple-output (MIMO) system, a soft-output MIMO detector is essential since it can provide a significant coding gain, e.g., 3 dB, compared with a hard-output detector. However, the computational complexity of the soft-output MIMO detector is usually much greater than that of the hard-output detector. This paper presents the first soft-output message-passing detector (MPD), which is also integrated with a high-throughput polar decoder. The algorithm and architecture are designed concurrently to improve the hardware performance. The proposed techniques, including the adaptive variance estimation and reliable symbol detection, reduce the complexity of the MPD by 98.3%, and enable soft output for the outer polar decoder. Compared to the state-of-the-art hard-output design, the proposed MPD achieves a 5.86× higher throughput-to-area ratio (TAR) with 54.3% lower energy dissipation, despite the soft output. The proposed bidirectional-propagation belief propagation decoder is devised to reduce the critical path and to increase the throughput. The proposed polar decoder can improve the TAR by 35% with a comparable area and energy compared with the state-of-the-art polar decoder. A polar-coded massive MIMO receiver that supports a length-1024 rate-1/2 polar code, 128 receive antennas, and eight users is designed and implemented, and delivers a throughput of 7.61 Gb/s.