QLQinghua Liu

Qinghua Liu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Qinghua Liu has a total of 43 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Few-Shot Active Radar Jamming Recognition Using Adaptive Confidence Dual-Branch Fusion Network with Full-Information Time–Frequency Features

    by Bao Chen, Qinghua Liu, Ming Li

    Active radar jamming recognition is an important technology in modern electronic warfare (EW). With the increasingly widespread application of Digital Radio Frequency Memory (DRFM) technology, the types of jamming have become more diverse. Meanwhile, in most non-cooperative confrontation scenarios, it is difficult to obtain large-scale labeled jamming samples. The commonly used methods for radar jamming signal recognition have some limitations. One is that they require a large number of jamming samples; the other is that their recognition performance degrades severely in few-shot scenarios. To address these limitations, an Adaptive Confidence Dual-Branch Fusion Network (ACDF-Net) is proposed for few-shot jamming recognition. The Short-Time Fourier Transform (STFT) is firstly used to obtain four-channel time–frequency features of the jamming signal, which fully retains the real part, imaginary part, amplitude, and phase information of jamming. Secondly, a dual-branch complementary representation learning network is well designed to extract jamming modulation characteristics and energy-phase characteristics. Finally, an adaptive confidence fusion method controlled by learnable parameters and a multi-task supervised learning paradigm are introduced, which improve recognition accuracy and make the network more robust. A mixed dataset containing 15 types of radar active jamming (including 8 single jamming types, 3 composite jamming types, and 4 real measured jamming types) is established to verify the proposed method. Multi-dimensional validation experiments are conducted, including few-shot performance comparison under different training set proportions (3~11%), per-class recognition performance analysis, measured data generalization validation, and ablation studies of core modules. In few-shot scenarios, the OA of ACDF-Net reaches 92.81% under 3% training data proportion, which is better than the comparison algorithms. More comparative experiments show that the proposed method is better than the comparison methods. The proposed method provides an effective solution for radar active jamming recognition in few-shot and complex electromagnetic environments, which exhibits high feasibility for practical engineering applications.

  • Open Access

    Heteroscedastic Bias-Robust Projected Gradient Descent for UWB Localization in Complex Indoor Environments

    by Zhongyang Yu, Qinghua Liu, Yong Qian

    Ultra-wideband (UWB) localization is widely used in indoor positioning because it provides high temporal resolution and direct geometric range constraints. In complex indoor environments, however, UWB ranging is affected by non-line-of-sight propagation, multipath reflection, heterogeneous measurement quality, and link-dependent persistent bias, producing long-tailed errors and trajectory drift. This paper proposes HBR-PGD, a heteroscedastic bias-robust projected gradient descent framework for UWB-only indoor localization. Its central idea is a role-separated error-source formulation that assigns packet-level quality degradation, anchor-channel persistent bias, and sparse instantaneous NLOS anomalies to different roles in a unified constrained residual model. Packet-level quality features are mapped to heteroscedastic uncertainty scales, robust loss shape parameters, and non-negative NLOS correction priors; anchor-channel soft gating limits residual-correction freedom; and target trajectories and bounded structural bias states are jointly estimated in overlapping sliding windows. Experiments on a public indoor UWB dataset show that HBR-PGD achieves RMSE values of 0.107 m, 0.068 m, and 0.204 m in residential-apartment, small-apartment, and workshop/industrial environments, respectively. Compared with WLS, MCC-VC-TOA, SR-MCC, and AR-PNN, HBR-PGD consistently improves overall accuracy and high-percentile robustness, with the largest gain in the workshop/industrial environment. Ablation results verify the contributions of heteroscedastic weighting, structural-bias estimation, gated correction, and information-weighted fusion. These results suggest that HBR-PGD is a practical UWB-only localization framework for complex indoor environments with heterogeneous measurement quality, persistent link bias, and sparse NLOS anomalies.

  • Open Access

    A UWB Underground Mine Positioning Algorithm Based on Graph Neural Network

    by Zhongyang Yu, Qinghua Liu, Yong Qian

    Ultra-Wideband (UWB) positioning is a promising technique for underground mine localization, but its accuracy is strongly affected by complex tunnel topology, multipath propagation, and non-line-of-sight (NLOS) ranging errors. To address these challenges, this paper proposes a three-dimensional UWB positioning algorithm based on a Multi-head Attention Feature Fusion Graph Neural Network (MAFF-GNN). The localization problem is formulated as a graph-based node position regression task, where anchors and tags are represented as nodes and UWB ranging links are represented as edges. The proposed model integrates graph message passing, multi-head attention-based feature fusion, global skip connections, and geometry-constrained regularization to learn reliability-aware spatial representations from noisy ranging measurements. A physics-guided simulated underground mine environment is constructed by considering tunnel geometry, wall roughness, coal dust concentration, humidity attenuation, and controlled NLOS conditions. Three mine-like corridor topologies are generated, with 10,500 localization samples in total. Experimental results under controlled simulation conditions show that MAFF-GNN achieves an RMSE of 0.323 ± 0.093 m, an MAE of 0.274 ± 0.024 m, and a P90 error of 0.480 ± 0.038 m. Compared with weighted least squares and support vector regression, the proposed method reduces RMSE by 74.16% and 40.30%, respectively. Robustness tests under different simulated NLOS ratios further indicate that the proposed graph-attention framework maintains a gradual error-growth trend as NLOS severity increases. These results indicate the potential of attention-enhanced graph learning for UWB localization in a challenging mine-like environment.

  • Open Access

    Integrating evolutionary and compositional features with ML and DL for robust and interpretable druggable protein prediction

    by Mujeebu Rehman, Qinghua Liu, Muhammad Javed, Ali Ghulam, Teerath Kumar

    Druggable proteins are essential targets in contemporary therapeutic discovery, and their precise identification is necessary for the progression of rational drug design. Traditional biochemical screening techniques are costly, laborious, and protracted, whereas current computational models typically attain only moderate efficacy and seldom offer robust statistical validation or biological interpretability. To mitigate these limitations, we offer a hybrid computational approach that integrates evolutionary and compositional information by merging Average Block-based Position-Specific Scoring Matrix (AB-PSSM) characteristics with Dipeptide Composition (DPC) into a 600-dimensional representation. The hybrid feature space was assessed utilizing three machine learning algorithms (support vector machine, random forest, and XGBoost) alongside three deep learning architectures (CapsBiLSTM, ResCapsNetPlus, and ResNet1D) following a rigorous five-fold out-of-fold cross-validation protocol to guarantee fairness and reproducibility. A thorough assessment revealed that the hybrid attributes significantly surpassed individual descriptors, with the SVM and CapsBiLSTM classifiers attaining classification accuracies of 90% and ROC-AUC and PR-AUC values surpassing 95%. By integrating complementary evolutionary and compositional descriptors within a rigorously controlled out-of-fold validation framework, the proposed method improves predictive stability compared with previously reported sequence-based and ensemble learning predictors. Furthermore, unlike many existing approaches that primarily rely on accuracy-based evaluation, this study incorporates statistical significance testing and interpretable feature attribution, enabling both reliable generalization performance and biological interpretability. The robustness and reliability were further validated by statistical analyses, including DeLong’s test, McNemar’s test, and bootstrap confidence intervals, demonstrating that the observed enhancements were substantial and consistent. Furthermore, interpretability investigations employing SHAP feature attribution and t-SNE visualization underscored biologically significant sequence descriptors as pivotal factors influencing druggability, thus mitigating the “black box” constraint inherent in numerous deep learning methodologies. This study presents a statistically validated, interpretable, and high-performing framework for predicting druggable proteins, demonstrating competitive performance compared with existing machine learning and ensemble-based predictors while providing improved statistical reliability and interpretability, thereby establishing a clear basis for future applications in precision medicine and drug discovery.

  • Open Access

    GPR-Based Leakage Reconstruction of Shallow-Buried Water Supply Pipelines Using an Improved UNet++ Network

    by Qingqi Xu, Qinghua Liu, Shan Ouyang

    Ground-penetrating radar (GPR) plays a critical role in detecting underground targets, particularly locating and characterizing leaks in buried pipelines. However, the complex nature of GPR images related to pipeline leaks, combined with the limitations of existing neural network-based inversion methods, such as insufficient feature extraction and low inversion accuracy, poses significant challenges for effective leakage reconstruction. To address these challenges, this paper proposes an enhanced UNet++-based model: the Multi-Scale Directional Network PlusPlus (MSDNet++). The network employs an encoder–decoder architecture, in which the encoder incorporates multi-scale directional convolutions with coordinate attention to extract and compress features across different scales effectively. The decoder fuses multi-level features through dense skip connections and further enhances the representation of critical information via coordinate attention, enabling the accurate inversion of dielectric constant images. Experimental results on both simulated and real-world data demonstrate that MSDNet++ can accurately invert the location and extent of buried pipeline leaks from GPR B-scan images.


  • Open Access

    Research on a Broadband Digital Receiver Based on Envelope Differentiation

    by Bao Chen, Ming Li, Qinghua Liu

    In modern electronic reconnaissance systems, digital receivers play an important role in receiving a variety of complex signals, in which signal-to-time extraction is a key issue, but traditional methods often rely on the signal envelope, which is easily affected by the value of the threshold setting and the signal-to-noise ratio (SNR) of the signal. In fact, the pulse envelope front has a large derivative, which leads the envelope differentiation to show sharp peaks. In this paper, a time of arrival (TOA) extraction method based on first-order envelope differentiation of the signal is proposed. The method realizes the normalized extraction of different modulated signals by estimating the location where the sharp peaks appear, and it is not easily affected by the threshold setting. The processing flow of the digital receiver is as follows: the signal is first processed by digital channelization, and, after channelization, it passes through the signal detection module; then, after envelope differentiation, the useful signal is filtered out according to the result, and, finally, the pulse descriptor word consisting of the pulse arrival time, pulse width, signal frequency, and signal amplitude is formed, which is convenient for the subsequent processing. The experimental results verify the effectiveness and reliability of the signal arrival time extraction method.

  • Open Access

    Two-Stage GPR Image Inversion Method Based on Multi-Scale Dilated Convolution and Hybrid Attention Gate

    by Mingze Wu, Qinghua Liu, Shan Ouyang

    Ground penetrating radar (GPR) image inversion is of great significance for interpreting GPR data. In practical applications, the complexity and nonuniformity of underground structures bring noise and clutter interference, making GPR inversion problems more challenging. To address these issues, this study proposes a two-stage GPR image inversion network called MHInvNet based on multi-scale dilated convolution (MSDC) and hybrid attention gate (HAG). This method first denoises the B-scan through the first network MHInvNet1, then combines the denoised B-scan from MHInvNet1 with the undenoised B-scan as input to the second network MHInvNet2 for inversion to reconstruct the distribution of the permittivity of underground targets. To further enhance network performance, the MSDC and HAG modules are simultaneously introduced to both networks. Experimental results from simulated and actual measurement data show that MHInvNet can accurately invert the position, shape, size, and permittivity of underground targets. A comparison with existing methods demonstrates the superior inversion performance of MHInvNet.


  • Open Access

    A Cross-Modal Semantic Alignment and Feature Fusion Method for Bionic Drone and Bird Recognition

    by Hehao Liu, Dong Li, Ming Zhang, Jun Wan, Shuang Liu, Hanying Zhu, Qinghua Liu

    With the continuous progress in drone and materials technology, numerous bionic drones have been developed and employed in various fields. These bionic drones are designed to mimic the shape of birds, seamlessly blending into the natural environment and reducing the likelihood of detection. However, such a high degree of similarity also poses significant challenges in accurately distinguishing between real birds and bionic drones. Existing methods attempt to recognize both using optical images, but the visual similarity often results in poor recognition accuracy. To alleviate this problem, in this paper, we propose a cross-modal semantic alignment and feature fusion (CSAFF) network to improve the recognition accuracy of bionic drones. CSAFF aims to introduce motion behavior information as an auxiliary cue to improve discriminability. Specifically, a semantic alignment module (SAM) was designed to explore the consistent semantic information between cross-modal data and provide more semantic cues for the recognition of bionic drones and birds. Then, a feature fusion module (FFM) was developed to fully integrate cross-modal information, which effectively enhances the representability of these features. Extensive experiments were performed on datasets containing bionic drones and birds, and the experimental results consistently show the effectiveness of the proposed CSAFF method in identifying bionic drones and birds.


  • Knowledge-Guided Rotated Network for Power Line Detection in Infrared Images

    by Dong Li, Renjie Jiang, Tianqi Mao, Shuang Liu, Jun Wan, Qinghua Liu

    Detecting power lines accurately remains a challenging task for low-altitude aircraft due to their low radiation and complex background, making them one of the most perilous impediments for such aircraft. To overcome this issue, in this letter, a knowledge-guided rotated network (KRNet) is proposed for power line detection in complex infrared scenes. The proposed method consists of the following main three steps. First, we develop a linear-distribution perception module (LDPM), which enhances feature representation by extracting and exploiting important linear and spatial distributional prior knowledge. Second, to more accurately locate the power line, we design a novel loss function rotation-aware complete intersection-over-union (RACIoU), which utilizes the prior knowledge of power line non-directionality to guide model learning. Finally, using this prior knowledge of the power line, we obtain good detection results and verify the effectiveness and advantages of the proposed method using the power line rotation detection dataset (PRDD) that we built. Our method outperforms other state-of-the-art benchmarks for power line detection.