arXiv subjects

Tzu-Hsuan Chou

Publications and source records attributed to Tzu-Hsuan Chou.

8 recordsLinked to original sources

arXiv2026

Distribution-Aware GMD Transceiver Design for Probabilistic Shaping in MIMO

Multiple-input multiple-output (MIMO) transceiver and probabilistic shaping (PS) are key enablers for high spectral efficiency in 6G wireless networks. This work proposes a distribution-aware MIMO transceiver optimized for PS constellation symbols, including a Bayesian geometric mean decomposition (BGMD) precoder and a maximum a posteriori VBLAST (MAP-VBLAST) detector. The BGMD precoder uses PS priors in the derivation and equalizes layer gains to facilitate a single modulation and coding scheme for low-complexity transmissions while preserving channel capacity. MAP-VBLAST leverages these PS priors for optimal MAP detection within a successive interference cancellation (SIC) framework. Furthermore, a new codeword-to-layer mapping scheme, termed layer-contained MIMO (LC-MIMO), is proposed. By containing each codeblock (CB) within a single layer, LC-MIMO enables SIC at the CB level, allowing the receiver to exploit the error-correction capability of channel coding to mitigate error propagation. Numerical results show that the BGMD transceiver with LC-MIMO achieves notable performance gains over state-of-the-art methods.

eess.SP↗

arXiv2025

LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data

Large language models (LLMs) have shown a remarkable ability to generalize beyond their pre-training data, and fine-tuning LLMs can elevate performance to human-level and beyond. However, in real-world scenarios, lacking labeled data often prevents practitioners from obtaining well-performing models, thereby forcing practitioners to highly rely on prompt-based approaches that are often tedious, inefficient, and driven by trial and error. To alleviate this issue of lacking labeled data, we present a learning framework integrating LLMs with active learning for unlabeled dataset (LAUD). LAUD mitigates the cold-start problem by constructing an initial label set with zero-shot learning. Experimental results show that LLMs derived from LAUD outperform LLMs with zero-shot or few-shot learning on commodity name classification tasks, demonstrating the effectiveness of LAUD.

cs.LG↗

arXiv2025

Joint UAV Placement and Transceiver Design in Multi-User Wireless Relay Networks

In this paper, a novel approach is proposed to improve the minimum signal-to-interference-plus-noise-ratio (SINR) among users in non-orthogonal multi-user wireless relay networks, by optimizing the placement of unmanned aerial vehicle (UAV) relays, relay beamforming, and receive combining. The design is separated into two problems: beamforming-aware UAV placement optimization and transceiver design for minimum SINR maximization. A significant challenge in beamforming-aware UAV placement optimization is the lack of instantaneous channel state information (CSI) prior to deploying UAV relays, making it difficult to derive the beamforming SINR in non-orthogonal multi-user transmission. To address this issue, an approximation of the expected beamforming SINR is derived using the narrow beam property of a massive MIMO base station. Based on this, a UAV placement algorithm is proposed to provide UAV positions that improve the minimum expected beamforming SINR among users, using a difference-of-convex framework. Subsequently, after deploying the UAV relays to the optimized positions, and with estimated CSI available, a joint relay beamforming and receive combining (JRBC) algorithm is proposed to optimize the transceiver to improve the minimum beamforming SINR among users, using a block-coordinate descent approach. Numerical results show that the UAV placement algorithm combined with the JRBC algorithm provides a 4.6 dB SINR improvement over state-of-the-art schemes.

eess.SP↗

arXiv2025

Distributed Machine Learning Approach for Low-Latency Localization in Cell-Free Massive MIMO Systems

Low-latency localization is critical in cellular networks to support real-time applications requiring precise positioning. In this paper, we propose a distributed machine learning (ML) framework for fingerprint-based localization tailored to cell-free massive multiple-input multiple-output (MIMO) systems, an emerging architecture for 6G networks. The proposed framework enables each access point (AP) to independently train a Gaussian process regression model using local angle-of-arrival and received signal strength fingerprints. These models provide probabilistic position estimates for the user equipment (UE), which are then fused by the UE with minimal computational overhead to derive a final location estimate. This decentralized approach eliminates the need for fronthaul communication between the APs and the central processing unit (CPU), thereby reducing latency. Additionally, distributing computational tasks across the APs alleviates the processing burden on the CPU compared to traditional centralized localization schemes. Simulation results demonstrate that the proposed distributed framework achieves localization accuracy comparable to centralized methods, despite lacking the benefits of centralized data aggregation. Moreover, it effectively reduces uncertainty of the location estimates, as evidenced by the 95\% covariance ellipse. The results highlight the potential of distributed ML for enabling low-latency, high-accuracy localization in future 6G networks.

eess.SP↗

arXiv2025

Hybrid Fingerprint-based Positioning in Cell-Free Massive MIMO Systems

Recently, there has been an increasing interest in 6G technology for integrated sensing and communications, where positioning stands out as a key application. In the realm of 6G, cell-free massive multiple-input multiple-output (MIMO) systems, featuring distributed base stations equipped with a large number of antennas, present an abundant source of angle-of-arrival (AOA) information that could be exploited for positioning applications. In this paper we leverage this AOA information at the base stations using the multiple signal classification (MUSIC) algorithm, in conjunction with received signal strength (RSS) for positioning through Gaussian process regression (GPR). An AOA fingerprint database is constructed by capturing the angle data from multiple locations across the network area and is combined with RSS data from the same locations to form a hybrid fingerprint which is then used to train a GPR model employing a squared exponential kernel. The trained regression model is subsequently utilized to estimate the location of a user equipment. Simulations demonstrate that the GPR model with hybrid input achieves better positioning accuracy than traditional GPR models utilizing RSS-only and AOA-only inputs.

eess.SP↗

arXiv2023

Compressed Training for Dual-Wideband Time-Varying Sub-Terahertz Massive MIMO

6G operators may use millimeter wave (mmWave) and sub-terahertz (sub-THz) bands to meet the ever-increasing demand for wireless access. Sub-THz communication comes with many existing challenges of mmWave communication and adds new challenges associated with the wider bandwidths, more antennas, and harsher propagations. Notably, the frequency- and spatial-wideband (dual-wideband) effects are significant at sub-THz. This paper presents a compressed training framework to estimate the time-varying sub-THz MIMO-OFDM channels. A set of frequency-dependent array response matrices are constructed, enabling channel recovery from multiple observations across subcarriers via multiple measurement vectors (MMV). Using the temporal correlation, MMV least squares (LS) is designed to estimate the channel based on the previous beam support, and MMV compressed sensing (CS) is applied to the residual signal. We refer to this as the MMV-LS-CS framework. Two-stage (TS) and MMV FISTA-based (M-FISTA) algorithms are proposed for the MMV-LS-CS framework. Leveraging the spreading loss structure, a channel refinement algorithm is proposed to estimate the path coefficients and time delays of the dominant paths. To reduce the computational complexity and enhance the beam resolution, a sequential search method using hierarchical codebooks is developed. Numerical results demonstrate the improved channel estimation accuracy of MMV-LS-CS over state-of-the-art techniques.

eess.SP↗

arXiv2020

Fast Position-Aided MIMO Beam Training via Noisy Tensor Completion

In this paper, a data-driven position-aided approach is proposed to reduce the training overhead in MIMO systems, by leveraging side information and on-the-field measurements. A data tensor is constructed by collecting beam-training measurements on a subset of positions and beams, and a hybrid noisy tensor completion (HNTC) algorithm is proposed to predict the received power across the coverage area, which exploits both the spatial smoothness and the low-rank property of MIMO channels. A recommendation algorithm based on the completed tensor, beam subset selection (BSS), is proposed to achieve fast and accurate beam-training. Besides, a grouping-based BSS algorithm is proposed to combat the detrimental effect of noisy positional information. Numerical results evaluated with the Quadriga channel simulator at 60 GHz millimeter-wave channels show that the proposed BSS recommendation algorithm in combination with HNTC achieve accurate received power predictions, enabling beam-alignment with small overhead: given power measurements on 40% of possible discretized positions, HNTC-based BSS attains a probability of correct alignment of 91%, with only 2% of trained beams, as opposed to a state-of-the-art position-aided beam-alignment scheme which achieves 54% correct alignment in the same configuration. Finally, an online HNTC method via warm-start is proposed, that alleviates the computational complexity by 50%, with no degradation in prediction accuracy.

eess.SP↗

arXiv2020

Millimeter Wave Beam Recommendation via Tensor Completion

Accurate and fast beam-alignment is essential to cope with the fast-varying environment in millimeter-wave communications. A data-driven approach is a promising solution to reduce the training overhead by leveraging side information and on-the-field measurements. In this work, a two-stage tensor completion algorithm is proposed to predict the received power on a set of possible users' positions, given received power measurements on a small subset of positions. Based on these predictions and on positional side information, a small subset of beams is recommended to reduce the training overhead of beam-alignment. Numerical results evaluated with the Quadriga channel simulator demonstrate that the proposed algorithm achieves correct alignment with high probability using small training overhead: given power measurement on only 20% of the possible positions when using a discrete coverage area, our algorithm attains a probability of correct alignment of 80%, with only 2% of trained beams, as opposed to a state-of-the-art scheme which achieves 50% correct alignment in the same configuration. To the best of our knowledge, this is the first work to consider the beam recommendation problem based on measurements collected on a small subset of positions.

eess.SP↗