arXiv subjects

Chunyan Feng

Publications and source records attributed to Chunyan Feng.

14 recordsLinked to original sources

arXiv2026

Semantic Communication with an LLM-enabled Knowledge Base

Semantic communication (SC) can achieve superior coding and transmission performance based on the knowledge contained in the semantic knowledge base (KB). However, conventional KBs consist of source KBs and channel KBs, which are often costly to obtain data and limited in data scale. Fortunately, large language models (LLMs) have recently emerged with extensive knowledge and generative capabilities. Therefore, this paper proposes an SC system with LLM-enabled knowledge base (SC-LMKB), which utilizes the generation ability of LLMs to significantly enrich the KB of SC systems. In particular, we first design an LLM-enabled generation mechanism with a prompt engineering strategy for source data generation (SDG) and a cross-attention alignment method for channel data generation (CDG). However, hallucinations from LLMs may cause semantic noise, thus degrading SC performance. To mitigate the hallucination issue, a cross-domain fusion codec (CDFC) framework with a hallucination filtering phase and a cross-domain fusion phase is then proposed for SDG. In particular, the first phase filters out new data generated by the LMKB irrelevant to the original data based on semantic similarity. Then, a cross-domain fusion phase is proposed, which fuses source data with LLM-generated data based on their semantic importance, thereby enhancing task performance. Besides, a joint training objective that combines cross-entropy loss and reconstruction loss is proposed to reduce the impact of hallucination on CDG. Experiment results on three cross-modality retrieval tasks demonstrate that the proposed SC-LMKB can achieve up to 72.6\% and 90.7\% performance gains compared to conventional SC systems and LLM-enabled SC systems, respectively.

eess.SP↗

arXiv2025

Attention-Based Feature Online Conformal Prediction for Time Series

Online conformal prediction (OCP) wraps around any pre-trained predictor to produce prediction sets with coverage guarantees that hold irrespective of temporal dependencies or distribution shifts. However, standard OCP faces two key limitations: it operates in the output space using simple nonconformity (NC) scores, and it treats all historical observations uniformly when estimating quantiles. This paper introduces attention-based feature OCP (AFOCP), which addresses both limitations through two key innovations. First, AFOCP operates in the feature space of pre-trained neural networks, leveraging learned representations to construct more compact prediction sets by concentrating on task-relevant information while suppressing nuisance variation. Second, AFOCP incorporates an attention mechanism that adaptively weights historical observations based on their relevance to the current test point, effectively handling non-stationarity and distribution shifts. We provide theoretical guarantees showing that AFOCP maintains long-term coverage while provably achieving smaller prediction intervals than standard OCP under mild regularity conditions. Extensive experiments on synthetic and real-world time series datasets demonstrate that AFOCP consistently reduces the size of prediction intervals by as much as $88\%$ as compared to OCP, while maintaining target coverage levels, validating the benefits of both feature-space calibration and attention-based adaptive weighting.

cs.LG↗

arXiv2024

Conformal Distributed Remote Inference in Sensor Networks Under Reliability and Communication Constraints

This paper presents communication-constrained distributed conformal risk control (CD-CRC) framework, a novel decision-making framework for sensor networks under communication constraints. Targeting multi-label classification problems, such as segmentation, CD-CRC dynamically adjusts local and global thresholds used to identify significant labels with the goal of ensuring a target false negative rate (FNR), while adhering to communication capacity limits. CD-CRC builds on online exponentiated gradient descent to estimate the relative quality of the observations of different sensors, and on online conformal risk control (CRC) as a mechanism to control local and global thresholds. CD-CRC is proved to offer deterministic worst-case performance guarantees in terms of FNR and communication overhead, while the regret performance in terms of false positive rate (FPR) is characterized as a function of the key hyperparameters. Simulation results highlight the effectiveness of CD-CRC, particularly in communication resource-constrained environments, making it a valuable tool for enhancing the performance and reliability of distributed sensor networks.

eess.SP↗

arXiv2024

On the Impact of Uncertainty and Calibration on Likelihood-Ratio Membership Inference Attacks

In a membership inference attack (MIA), an attacker exploits the overconfidence exhibited by typical machine learning models to determine whether a specific data point was used to train a target model. In this paper, we analyze the performance of the likelihood ratio attack (LiRA) within an information-theoretical framework that allows the investigation of the impact of the aleatoric uncertainty in the true data generation process, of the epistemic uncertainty caused by a limited training data set, and of the calibration level of the target model. We compare three different settings, in which the attacker receives decreasingly informative feedback from the target model: confidence vector (CV) disclosure, in which the output probability vector is released; true label confidence (TLC) disclosure, in which only the probability assigned to the true label is made available by the model; and decision set (DS) disclosure, in which an adaptive prediction set is produced as in conformal prediction. We derive bounds on the advantage of an MIA adversary with the aim of offering insights into the impact of uncertainty and calibration on the effectiveness of MIAs. Simulation results demonstrate that the derived analytical bounds predict well the effectiveness of MIAs.

cs.IT↗

arXiv2023

Boundary-Aware Proposal Generation Method for Temporal Action Localization

The goal of Temporal Action Localization (TAL) is to find the categories and temporal boundaries of actions in an untrimmed video. Most TAL methods rely heavily on action recognition models that are sensitive to action labels rather than temporal boundaries. More importantly, few works consider the background frames that are similar to action frames in pixels but dissimilar in semantics, which also leads to inaccurate temporal boundaries. To address the challenge above, we propose a Boundary-Aware Proposal Generation (BAPG) method with contrastive learning. Specifically, we define the above background frames as hard negative samples. Contrastive learning with hard negative mining is introduced to improve the discrimination of BAPG. BAPG is independent of the existing TAL network architecture, so it can be applied plug-and-play to mainstream TAL models. Extensive experimental results on THUMOS14 and ActivityNet-1.3 demonstrate that BAPG can significantly improve the performance of TAL.

cs.CV↗

arXiv2023

Federated Inference with Reliable Uncertainty Quantification over Wireless Channels via Conformal Prediction

In this paper, we consider a wireless federated inference scenario in which devices and a server share a pre-trained machine learning model. The devices communicate statistical information about their local data to the server over a common wireless channel, aiming to enhance the quality of the inference decision at the server. Recent work has introduced federated conformal prediction (CP), which leverages devices-to-server communication to improve the reliability of the server's decision. With federated CP, devices communicate to the server information about the loss accrued by the shared pre-trained model on the local data, and the server leverages this information to calibrate a decision interval, or set, so that it is guaranteed to contain the correct answer with a pre-defined target reliability level. Previous work assumed noise-free communication, whereby devices can communicate a single real number to the server. In this paper, we study for the first time federated CP in a wireless setting. We introduce a novel protocol, termed wireless federated conformal prediction (WFCP), which builds on type-based multiple access (TBMA) and on a novel quantile correction strategy. WFCP is proved to provide formal reliability guarantees in terms of coverage of the predicted set produced by the server. Using numerical results, we demonstrate the significant advantages of WFCP against digital implementations of existing federated CP schemes, especially in regimes with limited communication resources and/or large number of devices.

cs.IT↗

arXiv2023

Information Bottleneck-Inspired Type Based Multiple Access for Remote Estimation in IoT Systems

Type-based multiple access (TBMA) is a semantics-aware multiple access protocol for remote inference. In TBMA, codewords are reused across transmitting sensors, with each codeword being assigned to a different observation value. Existing TBMA protocols are based on fixed shared codebooks and on conventional maximum-likelihood or Bayesian decoders, which require knowledge of the distributions of observations and channels. In this letter, we propose a novel design principle for TBMA based on the information bottleneck (IB). In the proposed IB-TBMA protocol, the shared codebook is jointly optimized with a decoder based on artificial neural networks (ANNs), so as to adapt to source, observations, and channel statistics based on data only. We also introduce the Compressed IB-TBMA (CIB-TBMA) protocol, which improves IB-TBMA by enabling a reduction in the number of codewords via an IB-inspired clustering phase. Numerical results demonstrate the importance of a joint design of codebook and neural decoder, and validate the benefits of codebook compression.

eess.SP↗

arXiv2021

Joint LED Selection and Precoding Optimization for Multiple-User Multiple-Cell VLC Systems

This paper proposes a hybrid dimming scheme based on joint LED selection and precoding design (TASP-HD) for multiple-user (MU) multiple-cell (MC) visible light communications (VLC) systems. In TASP-HD, both the LED selection and the precoding of each cell can be dynamically adjusted to reduce the intra- and inter-cell interferences while satisfying illumination constraints. First, a MU-MC-VLC system model is established, and then a sum-rate maximization problem under dimming level and illumination uniformity constraints is formulated. In this studied problem, the indices of activated LEDs and precoding matrices are optimized, which result in a complex non-convex mixed integer problem. To solve this problem, the original problem is separated into two subproblems. The first subproblem, which maximizes the sum-rate of users via optimizing the LED selection with a given precoding matrix, is a mixed integer problem solved by the penalty method. With the optimized LED selection matrix, the second subproblem which focuses on the maximization of the sum-rate via optimizing the precoding matrix is solved by the Lagrangian dual method. Finally, these two subproblems are iteratively solved to obtain a convergent solution. Simulation results verify that in a typical indoor scenario under a dimming level of 70%, the mean bandwidth efficiency of TASP-HD is 4.8 bit/s/Hz and 7.13 bit/s/Hz greater than AD and DD, respectively.

eess.SY↗

arXiv2020

A Content Driven Resource Allocation Scheme for Video Transmission in Vehicular Networks

With the growing computer vision applications, lots of videos are transmitted for content analysis, the way to allocate resources can affect the performance of video content analysis. For this purpose, the traditional resource allocation schemes for video transmission in vehicular networks, such as qualityof-service (QoS) based or quality-of-experience (QoE) based schemes, are no longer optimal anymore. In this paper, we propose an efficient content driven resource allocation scheme for vehicles equipped with cameras under bandwidth constraints in order to improve the video content analysis performance. The proposed resource allocation scheme is based on maximizing the quality-of-content (QoC), which is related to the content analysis performance. A QoC based assessment model is first proposed. Then, the resource allocation problem is converted to a solvable convex optimization problem. Finally, simulation results show the better performance of our proposed scheme than the existing schemes like QoE based schemes.

cs.NI↗

arXiv2020

Power Efficient LED Placement Algorithm for Indoor Visible Light Communication

This paper proposes a novel power-efficient light-emitting diode (LED) placement algorithm for indoor visible light communication (VLC). In the considered model, the LEDs can be designedly placed for high power efficiency while satisfying the indoor communication and illumination requirements. This design problem is formulated as a power minimization problem under both communication and illumination level constraints. Due to the interactions among LEDs and the illumination uniformity constraint, the formulated problem is complex and non-convex. To solve the problem, we first transform the complex uniformity constraint into a series of linear constraints. Then an iterative algorithm is proposed to decouple the interactions among LEDs and transforms the original problem into a series of convex sub-problems. Then, we use Lagrange dual method to solve the sub-problem and obtain a convergent solution of the original problem. Simulation results show that the proposed LED placement algorithm can harvest 22.86% power consumption gain when compared with the baseline scheme with centrally placed LEDs.

eess.SP↗

arXiv2020

A Novel Received Signal Strength Assisted Perspective-three-Point Algorithm for Indoor Visible Light Positioning

In this paper, a received signal strength assisted Perspective-three-Point positioning algorithm (R-P3P) is proposed for visible light positioning (VLP) systems. The basic idea of R-P3P is to joint visual and strength information to estimate the receiver position using 3 LEDs regardless of the LEDs' orientations. R-P3P first utilizes visual information captured by the camera to estimate the incidence angles of visible lights. Then, R-P3P calculates the candidate distances between the LEDs and the receiver based on the law of cosines and the Wu-Ritt's zero decomposition method. Based on the incidence angles, the candidate distances and the physical characteristics of the LEDs, R-P3P can select the exact distances from all the candidate distances. Finally, the linear least square (LLS) method is employed to estimate the position of the receiver. Due to the combination of visual and strength information of visible light signals, R-P3P can achieve high accuracy using 3 LEDs regardless of the LEDs' orientations. Simulation results show that R-P3P can achieve positioning accuracy within 10 cm over 70% indoor area with low complexity regardless of LEDs orientations.

eess.SP↗

arXiv2020

A Generalized Dimming Control Scheme for Visible Light Communications

A novel dimming control scheme, termed as generalized dimming control (GDC), is proposed for visible light communication (VLC) systems. The proposed GDC scheme achieves dimming control by simultaneously adjusting the intensity of transmitted symbols and the number of active elements in a space-time matrix. Both the indices of the active elements in each space-time matrix and the modulated constellation symbols are used to carry information. Since illumination is deemed as the prior task of VLC, an incremental algorithm for index mapping is proposed for achieving target optical power and uniform illumination. Next, GDC having the optimal activation pattern is investigated to further improve the bit-error rate (BER) performance. In particular, the BER performance of GDC is analyzed using the union bound technique. Based on the analytical BER bound, the optimal activation pattern of GDC scheme with the minimum BER criterion (GDC-MBER) is obtained by exhaustively searching all conditional pairwise error probabilities. However, since GDC-MBER requires high search complexity, two low-complexity GDC schemes having the maximum free distance criterion (GDCMFD) are proposed. The first GDC-MFD scheme, coined as GDC-MFD1, reduces the computational complexity by deriving a lower bound of the free distance based on Rayleigh-Ritz theorem. Based on the time-invariance characteristics of the VLC channel, GDC-MFD2 is proposed to further reduce the required computation efforts. Simulation and numerical results show that GDC-MBER, GDC-MFD1 and GDC-MFD2 have similar BER performance, and they can achieve 2 dB performance gains over conventional hybrid dimming control scheme and 7 dB performance gains over digital dimming control schemes.

cs.IT↗

arXiv2020

A High Coverage Camera Assisted Received Signal Strength Ratio Algorithm for Indoor Visible Light Positioning

In this paper, a high coverage algorithm termed enhanced camera assisted received signal strength ratio (eCA-RSSR) positioning algorithm is proposed for visible light positioning (VLP) systems. The basic idea of eCA-RSSR is to utilize visual information captured by the camera to estimate the incidence angles of visible lights first. Based on the incidence angles, eCA-RSSR utilizes the received signal strength ratio (RSSR) calculated by the photodiode (PD) to estimate the ratios of the distances between the LEDs and the receiver. Based on an Euclidean plane geometry theorem, eCA-RSSR transforms the ratios of the distances into the absolute values. In this way, eCA-RSSR only requires 3 LEDs for both orientation-free 2D and 3D positioning, implying that eCA-RSSR can achieve high coverage. Based on the absolute values of the distances, the linear least square method is employed to estimate the position of the receiver. Therefore, for the receiver having a small distance between the PD and the camera, the accuracy of eCA-RSSR does not depend on the starting values of the non-linear least square method and the complexity of eCA-RSSR is low. Furthermore, since the distance between the PD and camera can significantly affect the performance of eCA-RSSR, we further propose a compensation algorithm for eCA-RSSR based on the single-view geometry. Simulation results show that eCA-RSSR can achieve centimeter-level accuracy over 80% indoor area for both the receivers having a small and a large distance between the PD and the camera.

eess.SP↗

arXiv2019

Power Efficient Visible Light Communication (VLC) with Unmanned Aerial Vehicles (UAVs)

A novel approach that combines visible light communication (VLC) with unmanned aerial vehicles (UAVs) to simultaneously provide flexible communication and illumination is proposed. To minimize the power consumption, the locations of UAVs and the cell associations are optimized under illumination and communication constraints. An efficient sub-optimal solution that divides the original problem into two sub-problems is proposed. The first sub-problem is modeled as a classical smallest enclosing disk problem to obtain the optimal locations of UAVs, given the cell association. Then, assuming fixed UAV locations, the second sub-problem is modeled as a min-size clustering problem to obtain the optimized cell association. In addition, the obtained UAV locations and cell associations are iteratively optimized multiple times to reduce the power consumption. Numerical results show that the proposed approach can reduce the total transmit power consumption by at least 53.8% compared to two baseline algorithms with fixed UAV locations.

eess.SP↗