arXiv subjects

Yansha Deng

Publications and source records attributed to Yansha Deng.

At least 37 records · Page 2Linked to original sources

arXiv2025

CNN-Based Detection of Mixed-Molecule Concentrations in Molecular Communication

Molecular communication (MC) is a promising paradigm for applications where traditional electromagnetic communications are impractical. However, decoding chemical signals, especially in multi-transmitter systems, remains a key challenge due to interference and complex propagation dynamics. In this paper, we develop a one-dimensional fractal convolutional neural network (fCNN) to detect the concentrations of multiple types of molecules based on the absorbance spectra measured at a receiver. Our model is trained by both experimental and simulated datasets, with the latter enhanced by noise modeling to mimic real-world measurements. We demonstrate that a noiseaugmented simulated dataset can effectively be a substitute for experimental data, achieving similar decoding accuracy. Our approach successfully detects bit sequences in both binary and quadruple concentration shift keying (BCSK and QCSK) scenarios, even when transmitters are desynchronized, highlighting the potential of machine learning for robust MC signal detection.

eess.SP↗

arXiv2025

Communication-Aware Knowledge Distillation for Federated LLM Fine-Tuning over Wireless Networks

Federated learning (FL) for large language models (LLMs) offers a privacy-preserving scheme, enabling clients to collaboratively fine-tune locally deployed LLMs or smaller language models (SLMs) without exchanging raw data. While parameter-sharing methods in traditional FL models solves number of technical challenges, they still incur high communication overhead and struggle with adapting to heterogeneous model architectures. Federated distillation, a framework for mutual knowledge transfer via shared logits, typically offers lower communication overhead than parameter-sharing methods. However, transmitting logits from LLMs remains challenging for bandwidth-limited clients due to their high dimensionality. In this work, we focus on a federated LLM distillation with efficient communication overhead. To achieve this, we first propose an adaptive Top-k logit selection mechanism, dynamically sparsifying logits according to real-time communication conditions. Then to tackle the dimensional inconsistency introduced by the adaptive sparsification, we design an adaptive logits aggregation scheme, effectively alleviating the artificial and uninformative inputs introduced by conventional zero-padding methods. Finally, to enhance the distillation effect, we incorporate LoRA-adapted hidden-layer projection from LLM into the distillation loss, reducing the communication overhead further while providing richer representation. Experimental results demonstrate that our scheme achieves superior performance compared to baseline methods while effectively reducing communication overhead by approximately 50%.

cs.LG↗

arXiv2025

Molecule Mixture Detection and Alphabet Design for Non-linear, Cross-reactive Receiver Arrays in MC

Air-based molecular communication (MC) has the potential to be one of the first MC systems to be deployed in real-world applications, enabled by existing sensor technologies such as metal-oxide semi-conductor (MOS) sensors. However, commercially available sensors usually exhibit non-linear and cross-reactive behavior, contrary to the idealizing assumptions about linear and perfectly molecule type-specific sensing often made in the MC literature. To address this gap, we propose a detector for molecule mixture communication with a general non-linear, cross-reactive receiver (RX) array that performs approximate maximum likelihood detection on the sensor outputs. Additionally, we introduce an algorithm for the design of mixture alphabets that accounts for the RX characteristics. We evaluate our detector and alphabet design algorithm through simulations that are based on measurements reported for two commercial MOS sensors. Our simulations demonstrate that the proposed detector achieves similar symbol error rates as data-driven methods without requiring large numbers of training samples and that the alphabet design algorithm outperforms methods that do not account for the RX characteristics. Since the proposed detector and alphabet design algorithm are also applicable to other chemical sensors, they pave the way for reliable air-based MC.

eess.SP↗

arXiv2025

HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization

Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy. However, challenges such as high computational and memory demands, heterogeneous client resources, bandwidth constraints, and ineffective global aggregation hinder its efficiency. To address these issues, we propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable federated fine-tuning of LLMs in heterogeneous environments. To reduce memory and computation demands, we propose a salience-driven adaptive LLM quantization framework that evaluates the importance of transformer blocks using a salience metric and applies adaptive block-wise quantization accordingly. To handle heterogeneous computational capabilities, we propose an importance-based parameter truncation and freezing scheme. To address communication bottlenecks, we propose an importance-aware bandwidth-adaptive quantization method, which dynamically adjusts parameter precision based on importance and bandwidth constraints. To improve global model aggregation, we propose an adaptive rank-1 matrix-level aggregation strategy, which prevents information dilution and accelerates convergence by aggregating only updated rank-1 matrices from clients. Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.

cs.LG↗

arXiv2025

PWC-MoE: Privacy-Aware Wireless Collaborative Mixture of Experts

Large language models (LLMs) hosted on cloud servers alleviate the computational and storage burdens on local devices but raise privacy concerns due to sensitive data transmission and require substantial communication bandwidth, which is challenging in constrained environments. In contrast, small language models (SLMs) running locally enhance privacy but suffer from limited performance on complex tasks. To balance computational cost, performance, and privacy protection under bandwidth constraints, we propose a privacy-aware wireless collaborative mixture of experts (PWC-MoE) framework. Specifically, PWC-MoE employs a sparse privacy-aware gating network to dynamically route sensitive tokens to privacy experts located on local clients, while non-sensitive tokens are routed to non-privacy experts located at the remote base station. To achieve computational efficiency, the gating network ensures that each token is dynamically routed to and processed by only one expert. To enhance scalability and prevent overloading of specific experts, we introduce a group-wise load-balancing mechanism for the gating network that evenly distributes sensitive tokens among privacy experts and non-sensitive tokens among non-privacy experts. To adapt to bandwidth constraints while preserving model performance, we propose a bandwidth-adaptive and importance-aware token offloading scheme. This scheme incorporates an importance predictor to evaluate the importance scores of non-sensitive tokens, prioritizing the most important tokens for transmission to the base station based on their predicted importance and the available bandwidth. Experiments demonstrate that the PWC-MoE framework effectively preserves privacy and maintains high performance even in bandwidth-constrained environments, offering a practical solution for deploying LLMs in privacy-sensitive and bandwidth-limited scenarios.

cs.LG↗

arXiv2025

Exhaled Breath Analysis Through the Lens of Molecular Communication: A Survey

Molecular Communication (MC) has long been envisioned to enable an Internet of Bio-Nano Things (IoBNT) with medical applications, where nanomachines within the human body conduct monitoring, diagnosis, and therapy at micro- and nanoscale levels. MC involves information transfer via molecules and is supported by well-established theoretical models. However, practically achieving reliable, energy-efficient, and bio-compatible communication at these scales still remains a challenge. Air-Based Molecular Communication (ABMC) is a type of MC that operates over larger, meter-scale distances and extends even outside the human body. Therefore, devices and techniques to realize ABMC are readily accessible, and associated use cases can be very promising in the near future. Exhaled breath analysis has previously been proposed. It provides a non-invasive approach for health monitoring, leveraging existing commercial sensor technologies and reducing deployment barriers. The breath contains a diverse range of molecules and particles that serve as biomarkers linked to various physiological and pathological conditions. The plethora of proven methods, models, and optimization approaches in MC enable macroscale breath analysis, treating human as the transmitter, the breath as the information carrier, and macroscale sensors as the receiver. Using ABMC to interface with the inherent dynamic networks of cells, tissues, and organs could create a novel Internet of Bio Things (IoBT), a preliminary macroscale stage of the IoBNT. This survey extensively reviews exhaled breath modeling and analysis through the lens of MC, offering insights into theoretical frameworks and practical implementations from ABMC, bringing the IoBT a step closer to real-world use.

cs.ET↗

arXiv2025

Goal-oriented Semantic Communications for Metaverse Construction via Generative AI and Optimal Transport

The emergence of the metaverse has boosted productivity and creativity, driving real-time updates and personalized content, which will substantially increase data traffic. However, current bit-oriented communication networks struggle to manage this high volume of dynamic information, restricting metaverse applications interactivity. To address this research gap, we propose a goal-oriented semantic communication (GSC) framework for metaverse. Building on an existing metaverse wireless construction task, our proposed GSC framework includes an hourglass network-based (HgNet) encoder to extract semantic information of objects in the metaverse; and a semantic decoder that uses this extracted information to reconstruct the metaverse content after wireless transmission, enabling efficient communication and real-time object behaviour updates to the scenery for metaverse construction task. To overcome the wireless channel noise at the receiver, we design an optimal transport (OT)-enabled semantic denoiser, which enhances the accuracy of metaverse scenery through wireless communication. Experimental results show that compared to the conventional metaverse construction, our proposed GSC framework significantly reduces wireless metaverse construction latency by 92.6\%, while improving metaverse object status accuracy and viewing experience by 45.6\% and 44.7\%, respectively.

eess.SY↗

arXiv2025

Goal-Oriented Semantic Communication for Wireless Image Transmission via Stable Diffusion

Efficient image transmission is essential for seamless communication and collaboration within the visually-driven digital landscape. To achieve low latency and high-quality image reconstruction over a bandwidth-constrained noisy wireless channel, we propose a stable diffusion (SD)-based goal-oriented semantic communication (GSC) framework. In this framework, we design a semantic autoencoder that effectively extracts semantic information (SI) from images to reduce the transmission data size while ensuring high-quality reconstruction. Recognizing the impact of wireless channel noise on SI transmission, we propose an SD-based denoiser for GSC (SD-GSC) conditional on an instantaneous channel gain to remove the channel noise from the received noisy SI under known channel. For scenarios with unknown channel, we further propose a parallel SD denoiser for GSC (PSD-GSC) to jointly learn the distribution of channel gains and denoise the received SI. It is shown that, with the known channel, our SD-GSC outperforms state-of-the-art ADJSCC and Latent-Diff DNSC, improving Peak Signal-to-Noise Ratio (PSNR) by 32% and 21%, and reducing Fréchet Inception Distance (FID) by 40% and 35%, respectively. With the unknown channel, our PSD-GSC improves PSNR by 8% and reduces FID by 17% compared to MMSE equalizer-enhanced SD-GSC.

eess.IV↗

arXiv2025

Goal-Oriented Semantic Communication for Wireless Video Transmission via Generative AI

Efficient video transmission is essential for seamless communication and collaboration within the visually-driven digital landscape. To achieve low latency and high-quality video transmission over a bandwidth-constrained noisy wireless channel, we propose a stable diffusion (SD)-based goal-oriented semantic communication (GSC) framework. In this framework, we first design a semantic encoder that effectively identify the keyframes from video and extract the relevant semantic information (SI) to reduce the transmission data size. We then develop a semantic decoder to reconstruct the keyframes from the received SI and further generate the full video from the reconstructed keyframes using frame interpolation to ensure high-quality reconstruction. Recognizing the impact of wireless channel noise on SI transmission, we also propose an SD-based denoiser for GSC (SD-GSC) condition on an instantaneous channel gain to remove the channel noise from the received noisy SI under a known channel. For scenarios with an unknown channel, we further propose a parallel SD denoiser for GSC (PSD-GSC) to jointly learn the distribution of channel gains and denoise the received SI. It is shown that, with the known channel, our proposed SD-GSC outperforms state-of-the-art ADJSCC, Latent-Diff DNSC, DeepWiVe and DVST, improving Peak Signal-to-Noise Ratio (PSNR) by 69%, 58%, 33% and 38%, reducing mean squared error (MSE) by 52%, 50%, 41% and 45%, and reducing Fréchet Video Distance (FVD) by 38%, 32%, 22% and 24%, respectively. With the unknown channel, our PSD-GSC achieves a 17% improvement in PSNR, a 29% reduction in MSE, and a 19% reduction in FVD compared to MMSE equalizer-enhanced SD-GSC. These significant performance improvements demonstrate the robustness and superiority of our proposed methods in enhancing video transmission quality and efficiency under various channel conditions.

eess.IV↗

arXiv2025

Modeling and Optimization of Insulin Injection for Type-1 Diabetes Mellitus Management

Diabetes mellitus is a global health crisis characterized by poor blood sugar regulation, impacting millions of people worldwide and leading to severe complications and mortality. Although Type 1 Diabetes Mellitus (T1DM) has a lower number of cases compared to other forms of diabetes, it is often diagnosed at a young age and requires lifelong exogenous insulin administration. In this paper, we focus on understanding the interaction of insulin and glucose molecules within the subcutaneous layer, which is crucial for blood sugar control in T1DM patients. Specifically, we propose a comprehensive model to characterize the insulin-glucose system within the subcutaneous layer, incorporating a multicellular molecular communication system. We then divide the T1DM system into insulin and glucose subsystems and derive the end-to-end expression for insulin-glucose interaction in the subcutaneous layer. We further validate the insulin-glucose interaction analysis with an agent-based simulator. As effectively managing postprandial glucose levels is crucial for individuals with T1DM to safeguard their overall health and avert short-term and long-term complications, we also derive the optimal insulin administration time based on the derived glucose response via the Lagrange multiplier and gradient descent ascent method. This allows us to explore the impact of different types of insulin and dietary management on blood sugar levels. Simulation results confirm the correctness of our proposed model and the effectiveness of our optimized effective time window for injecting insulin in individuals with T1DM.

q-bio.OT↗

arXiv2025

When xURLLC Meets NOMA: A Stochastic Network Calculus Perspective

The advent of next-generation ultra-reliable and low-latency communications (xURLLC) presents stringent and unprecedented requirements for key performance indicators (KPIs). As a disruptive technology, non-orthogonal multiple access (NOMA) harbors the potential to fulfill these stringent KPIs essential for xURLLC. However, the immaturity of research on the tail distributions of these KPIs significantly impedes the application of NOMA to xURLLC. Stochastic network calculus (SNC), as a potent methodology, is leveraged to provide dependable theoretical insights into tail distribution analysis and statistical QoS provisioning (SQP). In this article, we develop a NOMA-assisted uplink xURLLC network architecture that incorporates an SNC-based SQP theoretical framework (SNC-SQP) to support tail distribution analysis in terms of delay, age-of-information (AoI), and reliability. Based on SNC-SQP, an SQP-driven power optimization problem is proposed to minimize transmit power while guaranteeing xURLLC's KPIs on delay, AoI, reliability, and power consumption. Extensive simulations validate our proposed theoretical framework and demonstrate that the proposed power allocation scheme significantly reduces uplink transmit power and outperforms conventional schemes in terms of SQP performance.

eess.SP↗

arXiv2025

Federated Fine-Tuning of LLMs: Framework Comparison and Research Directions

Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy. However, fine-tuning the extensive parameters in LLMs is particularly challenging in resource-constrained federated scenarios due to the significant communication and computational costs. To gain a deeper understanding of how these challenges can be addressed, this article conducts a comparative analysis three advanced federated LLM (FedLLM) frameworks that integrate knowledge distillation (KD) and split learning (SL) to mitigate these issues: 1) FedLLMs, where clients upload model parameters or gradients to enable straightforward and effective fine-tuning; 2) KD-FedLLMs, which leverage KD for efficient knowledge sharing via logits; and 3) Split-FedLLMs, which split the LLMs into two parts, with one part executed on the client and the other one on the server, to balance the computational load. Each framework is evaluated based on key performance metrics, including model accuracy, communication overhead, and client-side computational load, offering insights into their effectiveness for various federated fine-tuning scenarios. Through this analysis, we identify framework-specific optimization opportunities to enhance the efficiency of FedLLMs and discuss broader research directions, highlighting open opportunities to better adapt FedLLMs for real-world applications. A use case is presented to demonstrate the performance comparison of these three frameworks under varying configurations and settings.

cs.LG↗

arXiv2024

Goal-Oriented Semantic Communication for Wireless Visual Question Answering

The rapid progress of artificial intelligence (AI) and computer vision (CV) has facilitated the development of computation-intensive applications like Visual Question Answering (VQA), which integrates visual perception and natural language processing to generate answers. To overcome the limitations of traditional VQA constrained by local computation resources, edge computing has been incorporated to provide extra computation capability at the edge side. Meanwhile, this brings new communication challenges between the local and edge, including limited bandwidth, channel noise, and multipath effects, which degrade VQA performance and user quality of experience (QoE), particularly during the transmission of large high-resolution images. To overcome these bottlenecks, we propose a goal-oriented semantic communication (GSC) framework that focuses on effectively extracting and transmitting semantic information most relevant to the VQA goals, improving the answering accuracy and enhancing the effectiveness and efficiency. The objective is to maximize the answering accuracy, and we propose a bounding box (BBox)-based image semantic extraction and ranking approach to prioritize the semantic information based on the goal of questions. We then extend it by incorporating a scene graphs (SG)-based approach to handle questions with complex relationships. Experimental results demonstrate that our GSC framework improves answering accuracy by up to 49% under AWGN channels and 59% under Rayleigh channels while reducing total latency by up to 65% compared to traditional bit-oriented transmission.

cs.CV↗

arXiv2024

Goal-oriented Semantic Communications for Robotic Waypoint Transmission: The Value and Age of Information Approach

The ultra-reliable and low-latency communication (URLLC) service of the fifth-generation (5G) mobile communication network struggles to support safe robot operation. Nowadays, the sixth-generation (6G) mobile communication network is proposed to provide hyper-reliable and low-latency communication to enable safer control for robots. However, current 5G/ 6G research mainly focused on improving communication performance, while the robotics community mostly assumed communication to be ideal. To jointly consider communication and robotic control with a focus on the specific robotic task, we propose goal-oriented semantic communication in robotic control (GSRC) to exploit the context of data and its importance in achieving the task at both transmitter and receiver. At the transmitter, we propose a deep reinforcement learning algorithm to generate optimal control and command (C&C) data and a proactive repetition scheme (DeepPro) to increase the successful transmission probability. At the receiver, we design the value of information (VoI) and age of information (AoI) based queue ordering mechanism (VA-QOM) to rank the queue based on the semantic information extracted from AoI and VoI. The simulation results validate that our proposed GSRC framework achieves a 91.5% improvement in the mean square error compared to the traditional unmanned aerial vehicle control framework.

cs.RO↗

arXiv2024

Goal-Oriented UAV Communication Design and Optimization for Target Tracking: A MachineLearning Approach

To accomplish various tasks, safe and smooth control of unmanned aerial vehicles (UAVs) needs to be guaranteed, which cannot be met by existing ultra-reliable low latency communications (URLLC). This has attracted the attention of the communication field, where most existing work mainly focused on optimizing communication performance (i.e., delay) and ignored the performance of the task (i.e., tracking accuracy). To explore the effectiveness of communication in completing a task, in this letter, we propose a goal-oriented communication framework adopting a deep reinforcement learning (DRL) algorithm with a proactive repetition scheme (DeepP) to optimize C&C data selection and the maximum number of repetitions in a real-time target tracking task, where a base station (BS) controls a UAV to track a mobile target. The effectiveness of our proposed approach is validated by comparing it with the traditional proportional integral derivative (PID) algorithm.

eess.SY↗

arXiv2024

Goal-oriented Semantic Communication for the Metaverse Application

With the emergence of the metaverse and its role in enabling real-time simulation and analysis of real-world counterparts, an increasing number of personalized metaverse scenarios are being created to influence entertainment experiences and social behaviors. However, compared to traditional image and video entertainment applications, the exact transmission of the vast amount of metaverse-associated information significantly challenges the capacity of existing bit-oriented communication networks. Moreover, the current metaverse also witnesses a growing goal shift for transmitting the meaning behind custom-designed content, such as user-designed buildings and avatars, rather than exact copies of physical objects. To meet this growing goal shift and bandwidth challenge, this paper proposes a goal-oriented semantic communication framework for metaverse application (GSCM) to explore and define semantic information through the goal levels. Specifically, we first analyze the traditional image communication framework in metaverse construction and then detail our proposed semantic information along with the end-to-end wireless communication. We then describe the designed modules of the GSCM framework, including goal-oriented semantic information extraction, base knowledge definition, and neural radiance field (NeRF) based metaverse construction. Finally, numerous experiments have been conducted to demonstrate that, compared to image communication, our proposed GSCM framework decreases transmission latency by up to 92.6% and enhances the virtual object operation accuracy and metaverse construction clearance by up to 45.6% and 44.7%, respectively.

eess.SY↗

arXiv2024

Joint Model Pruning and Resource Allocation for Wireless Time-triggered Federated Learning

Time-triggered federated learning, in contrast to conventional event-based federated learning, organizes users into tiers based on fixed time intervals. However, this network still faces challenges due to a growing number of devices and limited wireless bandwidth, increasing issues like stragglers and communication overhead. In this paper, we apply model pruning to wireless Time-triggered systems and jointly study the problem of optimizing the pruning ratio and bandwidth allocation to minimize training loss under communication latency constraints. To solve this joint optimization problem, we perform a convergence analysis on the gradient $l_2$-norm of the asynchronous multi-tier federated learning (FL) model with adaptive model pruning. The convergence upper bound is derived and a joint optimization problem of pruning ratio and wireless bandwidth is defined to minimize the model training loss under a given communication latency constraint. The closed-form solutions for wireless bandwidth and pruning ratio by using KKT conditions are then formulated. As indicated in the simulation experiments, our proposed TT-Prune demonstrates a 40% reduction in communication cost, compared with the asynchronous multi-tier FL without model pruning, while maintaining the model convergence at the same level.

cs.LG↗

arXiv2024

Task-oriented and Semantics-aware Communications for Augmented Reality

Upon the advent of the emerging metaverse and its related applications in Augmented Reality (AR), the current bit-oriented network struggles to support real-time changes for the vast amount of associated information, creating a significant bottleneck in its development. To address the above problem, we present a novel task-oriented and semantics-aware communication framework for augmented reality (TSAR) to enhance communication efficiency and effectiveness significantly. We first present an analysis of the traditional wireless AR point cloud communication framework, followed by a detailed summary of our proposed semantic information extraction within the end-to-end communication. Then, we detail the components of the TSAR framework, incorporating semantics extraction with deep learning, task-oriented base knowledge selection, and avatar pose recovery. Through rigorous experimentation, we demonstrate that our proposed TSAR framework considerably outperforms traditional point cloud communication framework, reducing wireless AR application transmission latency by 95.6% and improving communication effectiveness in geometry and color aspects by up to 82.4% and 20.4%, respectively.

eess.SY↗