arXiv subjects

Wenjin Wang

Publications and source records attributed to Wenjin Wang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Low-Coherence Sequence Design Under PAPR Constraints

Low-coherence sequences with low peak-to-average power ratio (PAPR) are crucial for multi-carrier wireless communication systems and are used for pilots, spreading sequences, and so on. This letter proposes an efficient low-coherence sequence design algorithm (LOCEDA) that can generate any number of sequences of any length that satisfy user-defined PAPR constraints while supporting flexible subcarrier assignments in orthogonal frequency-division multiple access (OFDMA) systems. We first visualize the low-coherence sequence design problem under PAPR constraints as resolving collisions between hyperspheres. By iteratively adjusting the radii and positions of these hyperspheres, we effectively generate low-coherence sequences that strictly satisfy the imposed PAPR constraints. Simulation results (i) confirm that LOCEDA outperforms existing methods, (ii) demonstrate its flexibility, and (iii) highlight its potential for various applications.

eess.SP↗

arXiv2024

An AI-Enabled Framework Within Reach for Enhancing Healthcare Sustainability and Fairness

Good health and well-being is among key issues in the United Nations 2030 Sustainable Development Goals. The rising prevalence of large-scale infectious diseases and the accelerated aging of the global population are driving the transformation of healthcare technologies. In this context, establishing large-scale public health datasets, developing medical models, and creating decision-making systems with a human-centric approach are of strategic significance. Recently, by leveraging the extraordinary number of accessible cameras, groundbreaking advancements have emerged in AI methods for physiological signal monitoring and disease diagnosis using camera sensors. These approaches, requiring no specialized medical equipment, offer convenient manners of collecting large-scale medical data in response to public health events. Therefore, we outline a prospective framework and heuristic vision for a camera-based public health (CBPH) framework utilizing visual physiological monitoring technology. The CBPH can be considered as a convenient and universal framework for public health, advancing the United Nations Sustainable Development Goals, particularly in promoting the universality, sustainability, and equity of healthcare in low- and middle-income countries or regions. Furthermore, CBPH provides a comprehensive solution for building a large-scale and human-centric medical database, and a multi-task large medical model for public health and medical scientific discoveries. It has a significant potential to revolutionize personal monitoring technologies, digital medicine, telemedicine, and primary health care in public health. Therefore, it can be deemed that the outcomes of this paper will contribute to the establishment of a sustainable and fair framework for public health, which serves as a crucial bridge for advancing scientific discoveries in the realm of AI for medicine (AI4Medicine).

cs.CY↗

arXiv2024

CRUD-RAG: A Comprehensive Chinese Benchmark for Retrieval-Augmented Generation of Large Language Models

Retrieval-Augmented Generation (RAG) is a technique that enhances the capabilities of large language models (LLMs) by incorporating external knowledge sources. This method addresses common LLM limitations, including outdated information and the tendency to produce inaccurate "hallucinated" content. However, the evaluation of RAG systems is challenging, as existing benchmarks are limited in scope and diversity. Most of the current benchmarks predominantly assess question-answering applications, overlooking the broader spectrum of situations where RAG could prove advantageous. Moreover, they only evaluate the performance of the LLM component of the RAG pipeline in the experiments, and neglect the influence of the retrieval component and the external knowledge database. To address these issues, this paper constructs a large-scale and more comprehensive benchmark, and evaluates all the components of RAG systems in various RAG application scenarios. Specifically, we have categorized the range of RAG applications into four distinct types-Create, Read, Update, and Delete (CRUD), each representing a unique use case. "Create" refers to scenarios requiring the generation of original, varied content. "Read" involves responding to intricate questions in knowledge-intensive situations. "Update" focuses on revising and rectifying inaccuracies or inconsistencies in pre-existing texts. "Delete" pertains to the task of summarizing extensive texts into more concise forms. For each of these CRUD categories, we have developed comprehensive datasets to evaluate the performance of RAG systems. We also analyze the effects of various components of the RAG system, such as the retriever, the context length, the knowledge base construction, and the LLM. Finally, we provide useful insights for optimizing the RAG technology for different scenarios.

cs.CL↗

arXiv2024

Ubiquitous Integrated Sensing and Communications for Massive MIMO LEO Satellite Systems

The next sixth generation (6G) networks are envisioned to integrate sensing and communications in a single system, thus greatly improving spectrum utilization and reducing hardware costs. Low earth orbit (LEO) satellite communications combined with massive multiple-input multiple-output (MIMO) technology holds significant promise in offering ubiquitous and seamless connectivity with high data rates. Existing integrated sensing and communications (ISAC) studies mainly focus on terrestrial systems, while operating ISAC in massive MIMO LEO satellite systems is promising to provide high-capacity communication and flexible sensing ubiquitously. In this paper, we first give an overview of LEO satellite systems and ISAC and consider adopting ISAC in the massive MIMO LEO satellite systems. Then, the recent research advances are presented. A discussion on related challenges and key enabling technologies follows. Finally, we point out some open issues and promising research directions.

eess.SP↗

arXiv2024

$\text{Memory}^3$: Language Modeling with Explicit Memory

The training and inference of large language models (LLMs) are together a costly process that transports knowledge from raw data to meaningful computation. Inspired by the memory hierarchy of the human brain, we reduce this cost by equipping LLMs with explicit memory, a memory format cheaper than model parameters and text retrieval-augmented generation (RAG). Conceptually, with most of its knowledge externalized to explicit memories, the LLM can enjoy a smaller parameter size, training cost, and inference cost, all proportional to the amount of remaining "abstract knowledge". As a preliminary proof of concept, we train from scratch a 2.4B LLM, which achieves better performance than much larger LLMs as well as RAG models, and maintains higher decoding speed than RAG. The model is named $\text{Memory}^3$, since explicit memory is the third form of memory in LLMs after implicit memory (model parameters) and working memory (context key-values). We introduce a memory circuitry theory to support the externalization of knowledge, and present novel techniques including a memory sparsification mechanism that makes storage tractable and a two-stage pretraining scheme that facilitates memory formation.

cs.CL↗

arXiv2024

Polar-Coded Tensor-Based Unsourced Random Access with Soft Decoding

The unsourced random access (URA) has emerged as a viable scheme for supporting the massive machine-type communications (mMTC) in the sixth generation (6G) wireless networks. Notably, the tensor-based URA (TURA), with its inherent tensor structure, stands out by simultaneously enhancing performance and reducing computational complexity for the multi-user separation, especially in mMTC networks with a large numer of active devices. However, current TURA scheme lacks the soft decoder, thus precluding the incorporation of existing advanced coding techniques. In order to fully explore the potential of the TURA, this paper investigates the Polarcoded TURA (PTURA) scheme and develops the corresponding iterative Bayesian receiver with feedback (IBR-FB). Specifically, in the IBR-FB, we propose the Grassmannian modulation-aided Bayesian tensor decomposition (GM-BTD) algorithm under the variational Bayesian learning (VBL) framework, which leverages the property of the Grassmannian modulation to facilitate the convergence of the VBL process, and has the ability to generate the required soft information without the knowledge of the number of active devices. Furthermore, based on the soft information produced by the GM-BTD, we design the soft Grassmannian demodulator in the IBR-FB. Extensive simulation results demonstrate that the proposed PTURA in conjunction with the IBR-FB surpasses the existing state-of-the-art unsourced random access scheme in terms of accuracy and computational complexity.

eess.SP↗

arXiv2024

Joint Channel Estimation and Prediction for Massive MIMO with Frequency Hopping Sounding

In massive multiple-input multiple-output (MIMO) systems, the downlink transmission performance heavily relies on accurate channel state information (CSI). Constrained by the transmitted power, user equipment always transmits sounding reference signals (SRSs) to the base station through frequency hopping, which will be leveraged to estimate uplink CSI and subsequently predict downlink CSI. This paper aims to investigate joint channel estimation and prediction (JCEP) for massive MIMO with frequency hopping sounding (FHS). Specifically, we present a multiple-subband (MS) delay-angle-Doppler (DAD) domain channel model with off-grid basis to tackle the energy leakage problem. Furthermore, we formulate the JCEP problem with FHS as a multiple measurement vector (MMV) problem, facilitating the sharing of common CSI across different subbands. To solve this problem, we propose an efficient Off-Grid-MS hybrid message passing (HMP) algorithm under the constrained Bethe free energy (BFE) framework. Aiming to address the lack of prior CSI in practical scenarios, the proposed algorithm can adaptively learn the hyper-parameters of the channel by minimizing the corresponding terms in the BFE expression. To alleviate the complexity of channel hyper-parameter learning, we leverage the approximations of the off-grid matrices to simplify the off-grid hyper-parameter estimation. Numerical results illustrate that the proposed algorithm can effectively mitigate the energy leakage issue and exploit the common CSI across different subbands, acquiring more accurate CSI compared to state-of-the-art counterparts.

eess.SP↗

arXiv2024

Integrated Communications and Localization for Massive MIMO LEO Satellite Systems

Integrated communications and localization (ICAL) will play an important part in future sixth generation (6G) networks for the realization of Internet of Everything (IoE) to support both global communications and seamless localization. Massive multiple-input multiple-output (MIMO) low earth orbit (LEO) satellite systems have great potential in providing wide coverage with enhanced gains, and thus are strong candidates for realizing ubiquitous ICAL. In this paper, we develop a wideband massive MIMO LEO satellite system to simultaneously support wireless communications and localization operations in the downlink. In particular, we first characterize the signal propagation properties and derive a localization performance bound. Based on these analyses, we focus on the hybrid analog/digital precoding design to achieve high communication capability and localization precision. Numerical results demonstrate that the proposed ICAL scheme supports both the wireless communication and localization operations for typical system setups.

cs.IT↗

arXiv2024

Deep-Unfolded Joint Activity and Data Detection for Grant-Free Transmission in Cell-Free Systems

Massive grant-free transmission and cell-free wireless communication systems have emerged as pivotal enablers for massive machine-type communication. This paper proposes a deep-unfolding-based joint activity and data detection (DU-JAD) algorithm for massive grant-free transmission in cell-free systems. We first formulate a joint activity and data detection optimization problem, which we solve approximately using forward-backward splitting (FBS). We then apply deep unfolding to FBS to optimize algorithm parameters using machine learning. In order to improve data detection (DD) performance, reduce algorithm complexity, and enhance active user detection (AUD), we employ a momentum strategy, an approximate posterior mean estimator, and a novel soft-output AUD module, respectively. Simulation results confirm the efficacy of DU-JAD for AUD and DD.

cs.IT↗

arXiv2024

Robust Symbol-Level Precoding for Massive MIMO Communication Under Channel Aging

This paper investigates the robust design of symbol-level precoding (SLP) for multiuser multiple-input multiple-output (MIMO) downlink transmission with imperfect channel state information (CSI) caused by channel aging. By utilizing the a posteriori channel model based on the widely adopted jointly correlated channel model, the imperfect CSI is modeled as the statistical CSI incorporating the channel mean and channel variance information with spatial correlation. With the signal model in the presence of channel aging, we formulate the signal-to-noise-plus-interference ratio (SINR) balancing and minimum mean square error (MMSE) problems for robust SLP design. The former targets to maximize the minimum SINR across users, while the latter minimizes the mean square error between the received signal and the target constellation point. When it comes to massive MIMO scenarios, the increment in the number of antennas poses a computational complexity challenge, limiting the deployment of SLP schemes. To address such a challenge, we simplify the objective function of the SINR balancing problem and further derive a closed-form SLP scheme. Besides, by approximating the matrix involved in the computation, we modify the proposed algorithm and develop an MMSE-based SLP scheme with lower computation complexity. Simulation results confirm the superiority of the proposed schemes over the state-of-the-art SLP schemes.

eess.SP↗

arXiv2024

2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data

In medical-data driven learning, 3D convolutional neural networks (CNNs) have started to show superior performance to 2D CNNs in numerous deep learning tasks, proving the added value of 3D spatial information in feature representation. However, the difficulty in collecting more training samples to converge, more computational resources and longer execution time make this approach less applied. Also, applying transfer learning on 3D CNN is challenging due to a lack of publicly available pre-trained 3D models. To tackle these issues, we proposed a novel 2D strategical representation of volumetric data, namely 2.75D. In this work, the spatial information of 3D images is captured in a single 2D view by a spiral-spinning technique. As a result, 2D CNN networks can also be used to learn volumetric information. Besides, we can fully leverage pre-trained 2D CNNs for downstream vision problems. We also explore a multi-view 2.75D strategy, 2.75D 3 channels (2.75Dx3), to boost the advantage of 2.75D. We evaluated the proposed methods on three public datasets with different modalities or organs (Lung CT, Breast MRI, and Prostate MRI), against their 2D, 2.5D, and 3D counterparts in classification tasks. Results show that the proposed methods significantly outperform other counterparts when all methods were trained from scratch on the lung dataset. Such performance gain is more pronounced with transfer learning or in the case of limited training data. Our methods also achieved comparable performance on other datasets. In addition, our methods achieved a substantial reduction in time consumption of training and inference compared with the 2.5D or 3D method.

eess.IV↗

arXiv2024

Privacy Protected Contactless Cardio-respiratory Monitoring using Defocused Cameras during Sleep

The monitoring of vital signs such as heart rate (HR) and respiratory rate (RR) during sleep is important for the assessment of sleep quality and detection of sleep disorders. Camera-based HR and RR monitoring gained popularity in sleep monitoring in recent years. However, they are all facing with serious privacy issues when using a video camera in the sleeping scenario. In this paper, we propose to use the defocused camera to measure vital signs from optically blurred images, which can fundamentally eliminate the privacy invasion as face is difficult to be identified in obtained blurry images. A spatial-redundant framework involving living-skin detection is used to extract HR and RR from the defocused camera in NIR, and a motion metric is designed to exclude outliers caused by body motions. In the benchmark, the overall Mean Absolute Error (MAE) for HR measurement is 4.4 bpm, for RR measurement is 5.9 bpm. Both have quality drops as compared to the measurement using a focused camera, but the degradation in HR is much less, i.e. HR measurement has strong correlation with the reference ($R \geq 0.90$). Preliminary experiments suggest that it is feasible to use a defocused camera for cardio-respiratory monitoring while protecting the privacy. Further improvement is needed for robust RR measurement, such as by PPG-modulation based RR extraction.

eess.SP↗

arXiv2024

Grimoire is All You Need for Enhancing Large Language Models

In-context Learning (ICL) is one of the key methods for enhancing the performance of large language models on specific tasks by providing a set of few-shot examples. However, the ICL capability of different types of models shows significant variation due to factors such as model architecture, volume of learning data, and the size of parameters. Generally, the larger the model's parameter size and the more extensive the learning data, the stronger its ICL capability. In this paper, we propose a method SLEICL that involves learning from examples using strong language models and then summarizing and transferring these learned skills to weak language models for inference and application. This ensures the stability and effectiveness of ICL. Compared to directly enabling weak language models to learn from prompt examples, SLEICL reduces the difficulty of ICL for these models. Our experiments, conducted on up to eight datasets with five language models, demonstrate that weak language models achieve consistent improvement over their own zero-shot or few-shot capabilities using the SLEICL method. Some weak language models even surpass the performance of GPT4-1106-preview (zero-shot) with the aid of SLEICL.

cs.CL↗

arXiv2023

Beam-Delay Domain Channel Estimation for mmWave XL-MIMO Systems

This paper investigates the uplink channel estimation of the millimeter-wave (mmWave) extremely large-scale multiple-input-multiple-output (XL-MIMO) communication system in the beam-delay domain, taking into account the near-field and beam-squint effects due to the transmission bandwidth and array aperture growth. Specifically, we model the sparsity in the delay domain to explore inter-subcarrier correlations and propose the beam-delay domain sparse representation of spatial-frequency domain channels. The independent and non-identically distributed Bernoulli-Gaussian models with unknown prior hyperparameters are employed to capture the sparsity in the beam-delay domain, posing a challenge for channel estimation. Under the constrained Bethe free energy minimization framework, we design different structures on the beliefs to develop hybrid message passing (HMP) algorithms, thus achieving efficient joint estimation of beam-delay domain channel and prior hyperparameters. To further improve the model accuracy, the multidimensional grid point perturbation (MDGPP)-based representation is presented, which assigns individual perturbation parameters to each multidimensional discrete grid. By treating the MDGPP parameters as unknown hyperparameters, we propose the two-stage HMP algorithm for MDGPP-based channel estimation, where the output of the initial estimation stage is pruned for the refinement stage for the computational complexity reduction. Numerical simulations demonstrate the significant superiority of the proposed algorithms over benchmarks with both near-field and beam-squint effects.

eess.SP↗

arXiv2023

Soft Demodulator for Symbol-Level Precoding in Coded Multiuser MISO Systems

In this paper, we consider symbol-level precoding (SLP) in channel-coded multiuser multi-input single-output (MISO) systems. It is observed that the received SLP signals do not always follow Gaussian distribution, rendering the conventional soft demodulation with the Gaussian assumption unsuitable for the coded SLP systems. It, therefore, calls for novel soft demodulator designs for non-Gaussian distributed SLP signals with accurate log-likelihood ratio (LLR) calculation. To this end, we first investigate the non-Gaussian characteristics of both phase-shift keying (PSK) and quadrature amplitude modulation (QAM) received signals with existing SLP schemes and categorize the signals into two distinct types. The first type exhibits an approximate-Gaussian distribution with the outliers extending along the constructive interference region (CIR). In contrast, the second type follows some distribution that significantly deviates from the Gaussian distribution. To obtain accurate LLR, we propose the modified Gaussian soft demodulator and Gaussian mixture model (GMM) soft demodulators to deal with two types of signals respectively. Subsequently, to further reduce the computational complexity and pilot overhead, we put forward a novel neural soft demodulator, named pilot feature extraction network (PFEN), leveraging the transformer mechanism in deep learning. Simulation results show that the proposed soft demodulators dramatically improve the throughput of existing SLPs for both PSK and QAM transmission in coded systems.

eess.SP↗

arXiv2023

Symbol-Level Precoding for Average SER Minimization in Multiuser MISO Systems

This paper investigates symbol-level precoding (SLP) for high-order quadrature amplitude modulation (QAM) aimed at minimizing the average symbol error rate (SER), leveraging both constructive interference (CI) and noise power to gain superiority in full signal-to-noise ratio (SNR) ranges. We first construct the SER expression with respect to the transmitted signal and the rescaling factor, based on which the problem of average SER minimization subject to total transmit power constraint is further formulated. Given the non-convex nature of the objective, solving the above problem becomes challenging. Due to the differences in constraints between the transmit signal and the rescaling factor, we propose the double-space alternating optimization (DSAO) algorithm to optimize the two variables on orthogonal Stiefel manifold and Euclidean spaces, respectively. To facilitate QAM demodulation instead of affording impractical signaling overhead, we further develop a block transmission scheme to keep the rescaling factor constant within a block. Simulation results demonstrate that the proposed SLP scheme exhibits a significant performance advantage over existing state-of-the-art SLP schemes.

eess.SP↗

arXiv2023

Layout and Task Aware Instruction Prompt for Zero-shot Document Image Question Answering

Layout-aware pre-trained models has achieved significant progress on document image question answering. They introduce extra learnable modules into existing language models to capture layout information within document images from text bounding box coordinates obtained by OCR tools. However, extra modules necessitate pre-training on extensive document images. This prevents these methods from directly utilizing off-the-shelf instruction-tuning language foundation models, which have recently shown promising potential in zero-shot learning. Instead, in this paper, we find that instruction-tuning language models like Claude and ChatGPT can understand layout by spaces and line breaks. Based on this observation, we propose the LAyout and Task aware Instruction Prompt (LATIN-Prompt), which consists of layout-aware document content and task-aware instruction. Specifically, the former uses appropriate spaces and line breaks to recover the layout information among text segments obtained by OCR tools, and the latter ensures that generated answers adhere to formatting requirements. Moreover, we propose the LAyout and Task aware Instruction Tuning (LATIN-Tuning) to improve the performance of small instruction-tuning models like Alpaca. Experimental results show that LATIN-Prompt enables zero-shot performance of Claude and ChatGPT to be comparable to the fine-tuning performance of SOTAs on document image question answering, and LATIN-Tuning enhances the zero-shot performance of Alpaca significantly. For example, LATIN-Prompt improves the performance of Claude and ChatGPT on DocVQA by 263% and 20% respectively. LATIN-Tuning improves the performance of Alpaca on DocVQA by 87.7%. Quantitative and qualitative analyses demonstrate the effectiveness of LATIN-Prompt and LATIN-Tuning. We provide the code in supplementary and will release it to facilitate future research.

cs.CL↗

arXiv2023

Joint Active User Detection, Channel Estimation, and Data Detection for Massive Grant-Free Transmission in Cell-Free Systems

Cell-free communication has the potential to significantly improve grant-free transmission in massive machine-type communication, wherein multiple access points jointly serve a large number of user equipments to improve coverage and spectral efficiency. In this paper, we propose a novel framework for joint active user detection (AUD), channel estimation (CE), and data detection (DD) for massive grant-free transmission in cell-free systems. We formulate an optimization problem for joint AUD, CE, and DD by considering both the sparsity of the data matrix, which arises from intermittent user activity, and the sparsity of the effective channel matrix, which arises from intermittent user activity and large-scale fading. We approximately solve this optimization problem with a box-constrained forward-backward splitting algorithm, which significantly improves AUD, CE, and DD performance. We demonstrate the effectiveness of the proposed framework through simulation experiments.

cs.IT↗