arXiv subjects

Zhuangkun Wei

Publications and source records attributed to Zhuangkun Wei.

18 recordsLinked to original sources

arXiv2026

Coop-WD: Cooperative Perception with Weighting and Denoising for Robust V2V Communication

Cooperative perception, leveraging shared information from multiple vehicles via vehicle-to-vehicle (V2V) communication, plays a vital role in autonomous driving to alleviate the limitation of single-vehicle perception. Existing works have explored the effects of V2V communication impairments on perception precision, but they lack generalization to different levels of impairments. In this work, we propose a joint weighting and denoising framework, Coop-WD, to enhance cooperative perception subject to V2V channel impairments. In this framework, the self-supervised contrastive model and the conditional diffusion probabilistic model are adopted hierarchically for vehicle-level and pixel-level feature enhancement. An efficient variant model, Coop-WD-eco, is proposed to selectively deactivate denoising to reduce processing overhead. Rician fading, non-stationarity, and time-varying distortion are considered. Simulation results demonstrate that the proposed Coop-WD outperforms conventional benchmarks in all types of channels. Qualitative analysis with visual examples further proves the superiority of our proposed method. The proposed Coop-WD-eco achieves up to 50% reduction in computational cost under severe distortion while maintaining comparable accuracy as channel conditions improve.

cs.CV↗

arXiv2025

Mixed-Precision Federated Learning via Multi-Precision Over-The-Air Aggregation

Over-the-Air Federated Learning (OTA-FL) is a privacy-preserving distributed learning mechanism, by aggregating updates in the electromagnetic channel rather than at the server. A critical research gap in existing OTA-FL research is the assumption of homogeneous client computational bit precision. While in real world application, clients with varying hardware resources may exploit approximate computing (AxC) to operate at different bit precisions optimized for energy and computational efficiency. And model updates of various precisions amongst clients poses an open challenge for OTA-FL, as it is incompatible in the wireless modulation superposition. Here, we propose an mixed-precision OTA-FL framework of clients with multiple bit precisions, demonstrating the following innovations: (i) the superior trade-off for both server and clients within the constraints of varying edge computing capabilities, energy efficiency, and learning accuracy requirements comparing to homogeneous client bit precision, and (ii) a multi-precision gradient modulation scheme to ensure compatibility with OTA aggregation and eliminate the overheads of precision conversion. Through case study with real world data, we validate our modulation scheme that enables AxC based mixed-precision OTA-FL. In comparison to homogeneous standard precision of 32-bit and 16-bit, our framework presents more than 10% in 4-bit ultra low precision client performance and over 65%and 13% of energy savings respectively. This demonstrates the great potential of our mixed-precision OTA-FL approach in heterogeneous edge computing environments.

cs.LG↗

arXiv2025

Integrated Sensing, Communication, and Over-The-Air Control of UAV Swarm Dynamics

Coordinated controlling a large UAV swarm requires significant spectrum resources due to the need for bandwidth allocation per UAV, posing a challenge in resource-limited environments. Over-the-air (OTA) control has emerged as a spectrum-efficient approach, leveraging electromagnetic superposition to form control signals at a base station (BS). However, existing OTA controllers lack sufficient optimization variables to meet UAV swarm control objectives and fail to integrate control with other BS functions like sensing. This work proposes an integrated sensing and OTA control framework (ISAC-OTA) for UAV swarm. The BS performs OTA signal construction (uplink) and dispatch (downlink) while simultaneously sensing objects. Two uplink post-processing methods are developed: a control-centric approach generating closed-form control signals via a feedback-looped OTA control problem, and a sensing-centric method mitigating transmission-induced interference for accurate object sensing. For the downlink, a non-convex problem is formulated and solved to minimize control signal dispatch (transmission) error while maintaining a minimum sensing signal-to-noise ratio (SNR). Simulation results show that the proposed ISAC-OTA controller achieves control performance comparable to the benchmark optimal control algorithm while maintaining high sensing accuracy, despite OTA transmission interference. Moreover, it eliminates the need for per-UAV bandwidth allocation, showcasing a spectrum-efficient method for cooperative control in future wireless systems.

eess.SP↗

arXiv2025

How to Find Opinion Leader on the Online Social Network?

Online social networks (OSNs) provide a platform for individuals to share information, exchange ideas, and build social connections beyond in-person interactions. For a specific topic or community, opinion leaders are individuals who have a significant influence on others' opinions. Detecting opinion leaders and modeling influence dynamics is crucial as they play a vital role in shaping public opinion and driving conversations. Existing research have extensively explored various graph-based and psychology-based methods for detecting opinion leaders, but there is a lack of cross-disciplinary consensus between definitions and methods. For example, node centrality in graph theory does not necessarily align with the opinion leader concepts in social psychology. This review paper aims to address this multi-disciplinary research area by introducing and connecting the diverse methodologies for identifying influential nodes. The key novelty is to review connections and cross-compare different multi-disciplinary approaches that have origins in: social theory, graph theory, compressed sensing theory, and control theory. Our first contribution is to develop cross-disciplinary discussion on how they tell a different tale of networked influence. Our second contribution is to propose trans-disciplinary research method on embedding socio-physical influence models into graph signal analysis. We showcase inter- and trans-disciplinary methods through a Twitter case study to compare their performance and elucidate the research progression with relation to psychology theory. We hope the comparative analysis can inspire further research in this cross-disciplinary area.

cs.SI↗

arXiv2024

Explainable Adversarial Learning Framework on Physical Layer Secret Keys Combating Malicious Reconfigurable Intelligent Surface

Reconfigurable intelligent surfaces (RIS) can both help and hinder the physical layer secret key generation (PL-SKG) of communications systems. Whilst a legitimate RIS can yield beneficial impacts, including increased channel randomness to enhance PL-SKG, a malicious RIS can poison legitimate channels and crack almost all existing PL-SKGs. In this work, we propose an adversarial learning framework that addresses Man-in-the-middle RIS (MITM-RIS) eavesdropping which can exist between legitimate parties, namely Alice and Bob. First, the theoretical mutual information gap between legitimate pairs and MITM-RIS is deduced. From this, Alice and Bob leverage adversarial learning to learn a common feature space that assures no mutual information overlap with MITM-RIS. Next, to explain the trained legitimate common feature generator, we aid signal processing interpretation of black-box neural networks using a symbolic explainable AI (xAI) representation. These symbolic terms of dominant neurons aid the engineering of feature designs and the validation of the learned common feature space. Simulation results show that our proposed adversarial learning- and symbolic-based PL-SKGs can achieve high key agreement rates between legitimate users, and is further resistant to an MITM-RIS Eve with the full knowledge of legitimate feature generation (NNs or formulas). This therefore paves the way to secure wireless communications with untrusted reflective devices in future 6G.

cs.CR↗

arXiv2023

Securing IoT Communication using Physical Sensor Data -- Graph Layer Security with Federated Multi-Agent Deep Reinforcement Learning

Internet-of-Things (IoT) devices are often used to transmit physical sensor data over digital wireless channels. Traditional Physical Layer Security (PLS)-based cryptography approaches rely on accurate channel estimation and information exchange for key generation, which irrevocably ties key quality with digital channel estimation quality. Recently, we proposed a new concept called Graph Layer Security (GLS), where digital keys are derived from physical sensor readings. The sensor readings between legitimate users are correlated through a common background infrastructure environment (e.g., a common water distribution network or electric grid). The challenge for GLS has been how to achieve distributed key generation. This paper presents a Federated multi-agent Deep reinforcement learning-assisted Distributed Key generation scheme (FD2K), which fully exploits the common features of physical dynamics to establish secret key between legitimate users. We present for the first time initial experimental results of GLS with federated learning, achieving considerable security performance in terms of key agreement rate (KAR), and key randomness.

cs.AI↗

arXiv2022

Adversarial Reconfigurable Intelligent Surface Against Physical Layer Key Generation

The development of reconfigurable intelligent surfaces (RIS) has recently advanced the research of physical layer security (PLS). Beneficial impacts of RIS include but are not limited to offering a new degree-of-freedom (DoF) for key-less PLS optimization, and increasing channel randomness for physical layer secret key generation (PL-SKG). However, there is a lack of research studying how adversarial RIS can be used to attack and obtain legitimate secret keys generated by PL-SKG. In this work, we show an Eve-controlled adversarial RIS (Eve-RIS), by inserting into the legitimate channel a random and reciprocal channel, can partially reconstruct the secret keys from the legitimate PL-SKG process. To operationalize this concept, we design Eve-RIS schemes against two PL-SKG techniques used: (i) the CSI-based PL-SKG, and (ii) the two-way cross multiplication based PL-SKG. The channel probing at Eve-RIS is realized by compressed sensing designs with a small number of radio-frequency (RF) chains. Then, the optimal RIS phase is obtained by maximizing the Eve-RIS inserted deceiving channel. Our analysis and results show that even with a passive RIS, our proposed Eve-RIS can achieve a high key match rate with legitimate users, and is resistant to most of the current defensive approaches. This means the novel Eve-RIS provides a new eavesdropping threat on PL-SKG, which can spur new research areas to counter adversarial RIS attacks.

eess.SP↗

arXiv2022

Graph Layer Security: Encrypting Information via Common Networked Physics

The proliferation of low-cost Internet of Things (IoT) devices has led to a race between wireless security and channel attacks. Traditional cryptography requires high-computational power and is not suitable for low-power IoT scenarios. Whist, recently developed physical layer security (PLS) can exploit common wireless channel state information (CSI), its sensitivity to channel estimation makes them vulnerable from attacks. In this work, we exploit an alternative common physics shared between IoT transceivers: the monitored channel-irrelevant physical networked dynamics (e.g., water/oil/gas/electrical signal-flows). Leveraging this, we propose for the first time, graph layer security (GLS), by exploiting the dependency in physical dynamics among network nodes for information encryption and decryption. A graph Fourier transform (GFT) operator is used to characterize such dependency into a graph-bandlimted subspace, which allows the generations of channel-irrelevant cipher keys by maximizing the secrecy rate. We evaluate our GLS against designed active and passive attackers, using IEEE 39-Bus system. Results demonstrate that, GLS is not reliant on wireless CSI, and can combat attackers that have partial networked dynamic knowledge (realistic access to full dynamic and critical nodes remains challenging). We believe this novel GLS has widespread applicability in secure health monitoring and for Digital Twins in adversarial radio environments.

eess.SP↗

arXiv2022

Scarce Data Driven Deep Learning of Drones via Generalized Data Distribution Space

Increased drone proliferation in civilian and professional settings has created new threat vectors for airports and national infrastructures. The economic damage for a single major airport from drone incursions is estimated to be millions per day. Due to the lack of diverse drone training data, accurate training of deep learning detection algorithms under scarce data is an open challenge. Existing methods largely rely on collecting diverse and comprehensive experimental drone footage data, artificially induced data augmentation, transfer and meta-learning, as well as physics-informed learning. However, these methods cannot guarantee capturing diverse drone designs and fully understanding the deep feature space of drones. Here, we show how understanding the general distribution of the drone data via a Generative Adversarial Network (GAN) and explaining the missing features using Topological Data Analysis (TDA) - can allow us to acquire missing data to achieve rapid and more accurate learning. We demonstrate our results on a drone image dataset, which contains both real drone images as well as simulated images from computer-aided design. When compared to random data collection (usual practice - discriminator accuracy of 94.67\% after 200 epochs), our proposed GAN-TDA informed data collection method offers a significant 4\% improvement (99.42\% after 200 epochs). We believe that this approach of exploiting general data distribution knowledge form neural networks can be applied to a wide range of scarce data open challenges.

cs.CV↗

arXiv2022

Revealing the Excitation Causality between Climate and Political Violence via a Neural Forward-Intensity Poisson Process

The causal mechanism between climate and political violence is fraught with complex mechanisms. Current quantitative causal models rely on one or more assumptions: (1) the climate drivers persistently generate conflict, (2) the causal mechanisms have a linear relationship with the conflict generation parameter, and/or (3) there is sufficient data to inform the prior distribution. Yet, we know conflict drivers often excite a social transformation process which leads to violence (e.g., drought forces agricultural producers to join urban militia), but further climate effects do not necessarily contribute to further violence. Therefore, not only is this bifurcation relationship highly non-linear, there is also often a lack of data to support prior assumptions for high resolution modeling. Here, we aim to overcome the aforementioned causal modeling challenges by proposing a neural forward-intensity Poisson process (NFIPP) model. The NFIPP is designed to capture the potential non-linear causal mechanism in climate induced political violence, whilst being robust to sparse and timing-uncertain data. Our results span 20 recent years and reveal an excitation-based causal link between extreme climate events and political violence across diverse countries. Our climate-induced conflict model results are cross-validated against qualitative climate vulnerability indices. Furthermore, we label historical events that either improve or reduce our predictability gain, demonstrating the importance of domain expertise in informing interpretation.

cs.LG↗

arXiv2021

Random Matrix based Physical Layer Secret Key Generation in Static Channels

Physical layer secret key generation exploits the reciprocal channel randomness for key generation and has proven to be an effective addition security layer in wireless communications. However, static or scarcely random channels require artificially induced dynamics to improve the secrecy performance, e.g., using intelligent reflecting surface (IRS). One key challenge is that the induced random phase from IRS is also reflected in the direction to eavesdroppers (Eve). This leakage enables Eve nodes to estimate the legitimate channels and secret key via a globally known pilot sequence. To mitigate the secret key leakage issue, we propose to exploit random matrix theory to inform the design of a new physical layer secret key generation (PL-SKG) algorithm. We prove that, when sending appropriate random Gaussian matrices, the singular values of Alice's and Bob's received signals follow a similar probability distribution. Leveraging these common singular values, we propose a random Gaussian matrix based PL-SKG (RGM PL-SKG), which avoids the usages of the globally known pilot and thereby prevents the aforementioned leakage issue. Our results show the following: (i) high noise resistance which leads to superior secret key rate (SKR) improvement (up to 300%) in low SNR regime, and (ii) general improved SKR performance against multiple colluded Eves. We believe our combination of random matrix theory and PL-SKG shows a new paradigm to secure the wireless communication channels.

cs.IT↗

arXiv2020

Sampling and Inference of Networked Dynamics using Log-Koopman Nonlinear Graph Fourier Transform

Networked nonlinear dynamics underpin the complex functionality of many engineering, social, biological, and ecological systems. Monitoring the networked dynamics via the minimum subset of nodes is essential for a variety of scientific and operational purposes. When there is a lack of a explicit model and networked signal space, traditional evolution analysis and non-convex methods are insufficient. An important data-driven state-of-the-art method use the Koopman operator to generate a linear evolution model for a vector-valued observable of original state-space. As a result, one can derive a sampling strategy via the linear evolution property of observable. However, current polynomial Koopman operators result in a large sampling space due to: (i) the large size of polynomial based observables ($O(N^2)$, $N$ number of nodes in network), and (ii) not factoring in the nonlinear dependency between observables. In this work, to achieve linear scaling ($O(N)$) and a small set of sampling nodes, we propose to combine a novel Log-Koopman operator and nonlinear Graph Fourier Transform (NL-GFT) scheme. First, the Log-Koopman operator is able to reduce the size of observables by transforming multiplicative poly-observable to logarithm summation. Second, a nonlinear GFT concept and sampling theory are provided to exploit the nonlinear dependence of observables for Koopman linearized evolution analysis. Combined, the sampling and reconstruction algorithms are designed and demonstrated on two established application areas. The results demonstrate that the proposed Log-Koopman NL-GFT scheme can (i) linearize unknown nonlinear dynamics using $O(N)$ observables, and (ii) achieve lower number of sampling nodes, compared with the state-of-the art polynomial Koopman linear evolution analysis.

cs.IT↗

arXiv2020

Scalable Partial Explainability in Neural Networks via Flexible Activation Functions

Achieving transparency in black-box deep learning algorithms is still an open challenge. High dimensional features and decisions given by deep neural networks (NN) require new algorithms and methods to expose its mechanisms. Current state-of-the-art NN interpretation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself. In current deep NN operations, there is uncertainty over the exact role played by neurons with fixed activation functions. In this paper, we achieve partially explainable learning model by symbolically explaining the role of activation functions (AF) under a scalable topology. This is carried out by modeling the AFs as adaptive Gaussian Processes (GP), which sit within a novel scalable NN topology, based on the Kolmogorov-Arnold Superposition Theorem (KST). In this scalable NN architecture, the AFs are generated by GP interpolation between control points and can thus be tuned during the back-propagation procedure via gradient descent. The control points act as the core enabler to both local and global adjustability of AF, where the GP interpolation constrains the intrinsic autocorrelation to avoid over-fitting. We show that there exists a trade-off between the NN's expressive power and interpretation complexity, under linear KST topology scaling. To demonstrate this, we perform a case study on a binary classification dataset of banknote authentication. By quantitatively and qualitatively investigating the mapping relationship between inputs and output, our explainable model can provide interpretation over each of the one-dimensional attributes. These early results suggest that our model has the potential to act as the final interpretation layer for deep neural networks.

cs.LG↗

arXiv2020

Neural Network Approximation of Graph Fourier Transforms for Sparse Sampling of Networked Flow Dynamics

Infrastructure monitoring is critical for safe operations and sustainability. Water distribution networks (WDNs) are large-scale networked critical systems with complex cascade dynamics which are difficult to predict. Ubiquitous monitoring is expensive and a key challenge is to infer the contaminant dynamics from partial sparse monitoring data. Existing approaches use multi-objective optimisation to find the minimum set of essential monitoring points, but lack performance guarantees and a theoretical framework. Here, we first develop Graph Fourier Transform (GFT) operators to compress networked contamination spreading dynamics to identify the essential principle data collection points with inference performance guarantees. We then build autoencoder (AE) inspired neural networks (NN) to generalize the GFT sampling process and under-sample further from the initial sampling set, allowing a very small set of data points to largely reconstruct the contamination dynamics over real and artificial WDNs. Various sources of the contamination are tested and we obtain high accuracy reconstruction using around 5-10% of the sample set. This general approach of compression and under-sampled recovery via neural networks can be applied to a wide range of networked infrastructures to enable digital twins.

cs.LG↗

arXiv2019

Optimal Sampling for Dynamic Complex Networks with Graph-Bandlimited Initialization

Many engineering, social, and biological complex systems consist of dynamical elements connected via a large-scale network. Monitoring the network's dynamics is essential for a variety of maintenance and scientific purposes. Whilst we understand how to optimally sample a single dynamic element or a non-dynamic graph, we do not possess a theory on how to optimally sample networked dynamical elements. Here, we study nonlinear dynamic graph signals on a fixed complex network. We define the necessary conditions for optimal sampling in the combining time- and graph-domain to fully recover the networked dynamics. We firstly interpret the networked dynamics into a linearized matrix. Then, we prove that the dynamic signals can be sampled and fully recovered if the networked dynamics is stable and their initialization is bandlimited in the graph spectral domain. This new theory directly maps optimal sampling locations and rates to the graph properties and governing nonlinear dynamics. This can inform the optimal placement of experimental probes and sensors on dynamical networks as well as inform the design of each sensor's optimal sampling rate. We motivate the reader with two examples of recovering the networked dynamics for: social population growth and networked protein biochemical interactions with both bandlimited and arbitrary initialization.

eess.SP↗

arXiv2019

Optimal Sampling of Water Distribution Network Dynamics using Graph Fourier Transform

Water Distribution Networks (WDNs) are critical infrastructures that ensure safe drinking water. One of the major threats is the accidental or intentional injection of pollutants. Data collection remains challenging in underground WDNs and in order to quantify its threat to end users, modeling pollutant spread with minimal sensor data is can important open challenge. Existing approaches using numerical optimisation suffer from scalability issues and lack detailed insight and performance guarantees. Applying general data-driven approaches such as compressed sensing (CS) offer limited improvements in sample node reduction. Graph theoretic approaches link topology (e.g. Laplacian spectra) to optimal sensing locations, it neglects the complex dynamics. In this work, we introduce a novel Graph Fourier Transform (GFT) that exploits the low-rank property to optimally sample junction nodes in WDNs. The proposed GFT allows us to fully recover the full network dynamics using a subset of data sampled at the identified nodes. The proposed GFT technique offers attractive improvements over existing numerical optimisation, compressed sensing, and graph theoretic approaches. Our results show that, on average, with nearly 30-40\% of the junctions monitored, we are able to fully recover the dynamics of the whole network. The framework is useful beyond the application of WDNs and can be applied to a variety of infrastructure sensing for digital twin modeling.

cs.IT↗

arXiv2019

Sequential Bayesian Detection of Spike Activities from Fluorescence Observations

Extracting and detecting spike activities from the fluorescence observations is an important step in understanding how neuron systems work. The main challenge lies in that the combination of the ambient noise with dynamic baseline fluctuation, often contaminates the observations, thereby deteriorating the reliability of spike detection. This may be even worse in the face of the nonlinear biological process, the coupling interactions between spikes and baseline, and the unknown critical parameters of an underlying physiological model, in which erroneous estimations of parameters will affect the detection of spikes causing further error propagation. In this paper, we propose a random finite set (RFS) based Bayesian approach. The dynamic behaviors of spike sequence, fluctuated baseline and unknown parameters are formulated as one RFS. This RFS state is capable of distinguishing the hidden active/silent states induced by spike and non-spike activities respectively, thereby \emph{negating the interaction role} played by spikes and other factors. Then, premised on the RFS states, a Bayesian inference scheme is designed to simultaneously estimate the model parameters, baseline, and crucial spike activities. Our results demonstrate that the proposed scheme can gain an extra $12\%$ detection accuracy in comparison with the state-of-the-art MLSpike method.

q-bio.NC↗

arXiv2019

High-dimensional Metric Combining for Non-coherent Molecular Signal Detection

In emerging Internet-of-Nano-Thing (IoNT), information will be embedded and conveyed in the form of molecules through complex and diffusive medias. One main challenge lies in the long-tail nature of the channel response causing inter-symbol-interference (ISI), which deteriorates the detection performance. If the channel is unknown, we cannot easily achieve traditional coherent channel estimation and cancellation, and the impact of ISI will be more severe. In this paper, we develop a novel high-dimensional non-coherent scheme for blind detection of molecular signals. We achieve this in a higher-dimensional metric space by combining different non-coherent metrics that exploit the transient features of the signals. By deducing the theoretical bit error rate (BER) for any constructed high-dimensional non-coherent metric, we prove that, higher dimensionality always achieves a lower BER in the same sample space. Then, we design a generalised blind detection algorithm that utilizes the Parzen approximation and its probabilistic neural network (Parzen-PNN) to detect information bits. Taking advantages of its fast convergence and parallel implementation, our proposed scheme can meet the needs of detection accuracy and real-time computing. Numerical simulations demonstrate that our proposed scheme can gain 10dB BER compared with other state of the art methods.

cs.LG↗