arXiv subjects

Zinan Zhou

Publications and source records attributed to Zinan Zhou.

7 recordsLinked to original sources

arXiv2026

CSPMNet: Pareto-Efficient Automatic Modulation Classification With Learnable Complex Subband Phase Motion

Automatic modulation classification (AMC) is an essential technique for noncooperative spectrum monitoring and intelligent wireless receivers. However, practical AMC models must identify modulation formats from short and noisy I/Q observations while maintaining low computational and storage overhead. Existing deep-learning approaches often improve recognition accuracy by expanding generic neural backbones, which increases deployment cost and weakens their suitability for resource-constrained receivers. To bridge the gap between recognition performance and model efficiency, this letter proposes a Complex Subband Phase-Motion Network, designated as CSPMNet, for lightweight AMC from raw I/Q samples. Specifically, learnable complex subband filters are introduced to adaptively extract frequency-selective baseband responses while preserving the algebraic coupling between in-phase and quadrature components. Then, an amplitude-preserving phase-motion module captures multi-lag temporal rotation dynamics within each subband, and a lightweight temporal classifier performs efficient sequence aggregation. Rigorous experimental evaluations on public RadioML benchmark datasets demonstrate that CSPMNet achieves highly competitive recognition accuracy while requiring substantially lower model complexity than many existing AMC models.

eess.SP↗

arXiv2026

SEI-SHIELD: Robust Specific Emitter Identification Under Label Noise Via Self-Supervised Filtering and Iterative Rescue

Specific Emitter Identification (SEI) provides physical-layer device authentication for wireless communications and Internet of Things (IoT) systems. While deep learning (DL) has significantly advanced SEI performance, label noise severely degrades system reliability in non-cooperative environments. Label noise originates from channel-induced ambiguities, annotation errors, and deliberate data poisoning by intelligent jammers injecting misleading signals. While recent SEI methods attempt to mitigate label noise, they fundamentally rely on corrupted supervised signals to guide sample selection, inevitably leading to confirmation bias and suboptimal feature spaces. To address this challenge, we propose SEI-SHIELD, a robust SEI framework that integrates self-supervised contrastive pre-training with iterative sample selection. Specifically, SEI-SHIELD employs Momentum Contrast (MoCo) with RF-tailored augmentations to extract intrinsically robust, label-independent representations directly from complex-valued I/Q signals. In addition, K-nearest neighbors (KNN)-based noise filtering identifies corrupted samples through neighborhood label consistency analysis in the learned feature space. Furthermore, an iterative rescue mechanism using prediction confidence and prototype cosine similarity progressively recovers correctly labeled hard samples inadvertently discarded during filtering. Comprehensive experiments on the POWDER and ORACLE datasets demonstrate that SEI-SHIELD achieves state-of-the-art (SOTA) accuracy under various noise rates, substantially outperforming existing noise-robust paradigms, including advanced regularization techniques and sample selection frameworks.

eess.SP↗

arXiv2025

Factorized Disentangled Representation Learning for Interpretable Radio Frequency Fingerprint

In response to the rapid growth of Internet of Things (IoT) devices and rising security risks, Radio Frequency Fingerprint (RFF) has become key for device identification and authentication. However, various changing factors - beyond the RFF itself - can be entangled from signal transmission to reception, reducing the effectiveness of RFF Identification (RFFI). Existing RFFI methods mainly rely on domain adaptation techniques, which often lack explicit factor representations, resulting in less robustness and limited controllability for downstream tasks. To tackle this problem, we propose a novel Disentangled Representation Learning (DRL) framework that learns explicit and independent representations of multiple factors, including the RFF. Our framework introduces modules for disentanglement, guided by the principles of explicitness, modularity, and compactness. We design two dedicated modules for factor classification and signal reconstruction, each with tailored loss functions that encourage effective disentanglement and enhance support for downstream tasks. Thus, the framework can extract a set of interpretable vectors that explicitly represent corresponding factors. We evaluate our approach on two public benchmark datasets and a self-collected dataset. Our method achieves impressive performance on multiple DRL metrics. We also analyze the effectiveness of our method on downstream RFFI task and conditional signal generation task. All modules of the framework contribute to improved classification accuracy, and enable precise control over conditional generated signals. These results highlight the potential of our DRL framework for interpretable and explicit RFFs.

eess.SP↗

arXiv2025

Phase retrieval via Zernike phase contrast microscopy with an untrained neural network

Zernike's phase contrast microscopy (PCM) is among the most widely used techniques for observing phase objects, but it lacks quantitative nature, as it cannot directly provide phase information. Current methods for computationally extracting phase distributions from PCM images, however, rely heavily on empirical regularization parameter tuning. In this paper we extend an existing approach by employing an untrained neural network as an image prior, removing the need for manual regularization. We quantitatively demonstrate improved accuracy and robustness in phase retrieval compared to existing methods, using numerical and experimental PCM images. Our results confirm the feasibility of applying deep priors for phase retrieval in incoherent illumination setups.

physics.optics↗

arXiv2024

Snapshotting Quantum Dynamics at Multiple Time Points

Measurement-induced state disturbance is a major challenge in obtaining quantum statistics at multiple time points. We propose a method to extract dynamic information from a quantum system at intermediate time points, namely snapshotting quantum dynamics. To this end, we apply classical post-processing after performing the ancilla-assisted measurements to cancel out the impact of the measurements at each time point. Based on this, we reconstruct a multi-time quasi-probability distribution (QPD) that correctly recovers the probability distributions at the respective time points. Our approach can also be applied to simultaneously extract exponentially many correlation functions with various time-orderings. We provide a proof-of-principle experimental demonstration of the proposed protocol using a dual-species trapped-ion system by employing $^{171}\rm{Yb}^+$ and $^{138}\rm{Ba}^+$ ions as the system and the ancilla, respectively. Multi-time measurements are performed by repeated initialization and detection of the ancilla state without directly measuring the system state. The two- and three-time QPDs and correlation functions are reconstructed reliably from the experiment, negativity and complex values in the QPDs clearly indicate a contribution of the quantum coherence throughout dynamics.

quant-ph↗

arXiv2024

MAMCA -- Optimal on Accuracy and Efficiency for Automatic Modulation Classification with Extended Signal Length

With the rapid growth of the Internet of Things ecosystem, Automatic Modulation Classification (AMC) has become increasingly paramount. However, extended signal lengths offer a bounty of information, yet impede the model's adaptability, introduce more noise interference, extend the training and inference time, and increase storage overhead. To bridge the gap between these requisites, we propose a novel AMC framework, designated as the Mamba-based Automatic Modulation ClassificAtion (MAMCA). Our method adeptly addresses the accuracy and efficiency requirements for long-sequence AMC. Specifically, we introduce the Selective State Space Model as the backbone, enhancing the model efficiency by reducing the dimensions of the state matrices and diminishing the frequency of information exchange across GPU memories. We design a denoising-capable unit to elevate the network's performance under low signal-to-noise radio. Rigorous experimental evaluations on the publicly available dataset RML2016.10, along with our synthetic dataset within multiple quadrature amplitude modulations and lengths, affirm that MAMCA delivers superior recognition accuracy while necessitating minimal computational time and memory occupancy. Codes are available on https://github.com/ZhangYezhuo/MAMCA.

eess.SP↗

arXiv2024

Specific Emitter Identification Handling Modulation Variation with Margin Disparity Discrepancy

In the domain of Specific Emitter Identification (SEI), it is recognized that transmitters can be distinguished through the impairments of their radio frequency front-end, commonly referred to as Radio Frequency Fingerprint (RFF) features. However, modulation schemes can be deliberately coupled into signal-level data to confound RFF information, often resulting in high susceptibility to failure in SEI. In this paper, we propose a domain-invariant feature oriented Margin Disparity Discrepancy (MDD) approach to enhance SEI's robustness in rapidly modulation-varying environments. First, we establish an upper bound for the difference between modulation domains and define the loss function accordingly. Then, we design an adversarial network framework incorporating MDD to align variable modulation features. Finally, We conducted experiments utilizing 7 HackRF-One transmitters, emitting 11 types of signals with analog and digital modulations. Numerical results indicate that our approach achieves an average improvement of over 20\% in accuracy compared to classical SEI methods and outperforms other UDA techniques. Codes are available at https://github.com/ZhangYezhuo/MDD-SEI.

eess.SP↗