This letter presents an RS-SPC concatenated code blindrecognition algorithm based on the single-error correction. The algorithm corrects the least reliable bit of the single parity check (SPC) codewords based on the p...
详细信息
This letter presents an RS-SPC concatenated code blindrecognition algorithm based on the single-error correction. The algorithm corrects the least reliable bit of the single parity check (SPC) codewords based on the parity check characteristics, thereby increasing correct Reed-Solomon (RS) codewords and laying the foundation for improving the recognition probability. In addition, this algorithm combines threshold judgement with the matrix recording method, thereby eliminating unnecessary iterative operations under the condition that accurate recognition is possible. At the same time, it employs probability theory as a theoretical basis to quantify the degree of dispersion of the data through sample variance. The experimental results demonstrate that the recognition probability of this algorithm is superior to that of all other algorithms. When the codeword error rate (CER) is 0.5, RS(15,9)-SPC(4,3) still has a recognition probability of 20%. For RS(255,239)-SPC(8,7), the gain of the proposed algorithm exceeds 1.3dB compared to the upper bound of the recognition probability.
In this letter, we propose a novel lightweight X-ray image contraband segmentation network, XSNet, which integrates State Space Models (SSM) with Convolutional Neural Networks (CNNs) to achieve a significant trade-off...
详细信息
In this letter, we propose a novel lightweight X-ray image contraband segmentation network, XSNet, which integrates State Space Models (SSM) with Convolutional Neural Networks (CNNs) to achieve a significant trade-off between segmentation accuracy and lightweight design for computer-aided X-ray security check. The model is built based on the encoder-decoder framework. Specifically, we design an Multi-scale Convolution Fusion (MCF) block for multi-scale information extraction and a Dual-branch State Space Model (DSSM) block to relieve the bias caused by the imbalance of single branch structure in feature extraction and maintain the capabilities of SSM in modeling long range pixel dependencies. In addition, we present two versions of the model in two different sizes called XSNet-s and XSNet-l respectively. The quantitative and qualitative evaluations on the public PIDray and PIXray datasets both show the superiority of two models in terms of mean Intersection over Union (mIoU) and FLOPs.
Graph-based multi-view clustering has garnered considerable attention owing to its effectiveness. Nevertheless, despite the promising performance achieved by previous studies, several limitations remain to be addresse...
详细信息
Graph-based multi-view clustering has garnered considerable attention owing to its effectiveness. Nevertheless, despite the promising performance achieved by previous studies, several limitations remain to be addressed. Most graph-based models employ a two-stage strategy involving relaxation and discretization to derive clustering results, which may lead to deviation from the original problem. Moreover, graph-based methods do not adequately address the challenges of overlapping clusters or ambiguous cluster membership. Additionally, assigning appropriate weights based on the importance of each view is crucial. To address these problems, we propose a self-weighted multi-view fuzzy clustering algorithm that incorporates multiple graph learning. Specifically, we automatically allocate weights corresponding to each view to construct a fused similarity graph matrix. Subsequently, we approximate it as the scaled product of fuzzy membership matrices to directly derive clustering assignments. An iterative optimization algorithm is designed for solving the proposed model. Experiment evaluations conducted on benchmark datasets illustrate that the proposed method outperforms several leading multi-view clustering approaches.
The traditional subspace-based algorithms in the process of coherent direction of arrival (DOA) estimation get in trouble because of the rank loss of the signal covariance matrix. To this end, this paper introduces a ...
详细信息
The traditional subspace-based algorithms in the process of coherent direction of arrival (DOA) estimation get in trouble because of the rank loss of the signal covariance matrix. To this end, this paper introduces a forward/backward convolution kernel (FBCK) method, which not only reconstructs the signal covariance matrix and its diagonal elements, but also efficiently solves the signal coherence problem by utilizing the moving array technique. More precisely, the FBCK operation is applied to the signal space matrix at a given instant and utilizes the forward/backward convolution kernel to recover the rank corresponding to the number of signals without loss of the arrays' aperture. In a comparison evaluation with state-of-the-art spatial smoothing methods (including MSSP, SSP, ESS, ESS-SS, SSS and ASS), the proposed FBCK algorithm demonstrates excellent estimation capabilities in terms of snapshot number and signal-to-noise ratio (SNR), thus providing a robust and effective solution for DOA estimation in coherent signal environments.
The iterative hard thresholding (IHT) algorithm is widely used for recovering sparse signals in compressed sensing. Despite the development of numerous variants of this effective algorithm, its convergence rate and ac...
详细信息
The iterative hard thresholding (IHT) algorithm is widely used for recovering sparse signals in compressed sensing. Despite the development of numerous variants of this effective algorithm, its convergence rate and accuracy in finding the optimal solution still have room for enhancement. Aiming at this issue, we propose a momentum-based iterative hard thresholding (MIHT) algorithm by introducing a new iterative search direction derived from the momentum method, which uses historical iteration information to refine the search direction and thereby accelerate convergence. We establish a sufficient condition, in terms of (3s)-order restricted isometry constant, to guarantee the convergence of MIHT. Excitingly, numerical experiments demonstrate that MIHT possesses an excellent recovery success rate and outperforms a wide range of existing IHT variants.
Scene inference refers to the identification of the scene from a given set of scene representations such as images. A saliency graph of a scene contains scene-defining objects along with semantic information between t...
详细信息
Scene inference refers to the identification of the scene from a given set of scene representations such as images. A saliency graph of a scene contains scene-defining objects along with semantic information between them in the graph representation. Existing methods consider the entire scene with uniform weighting to all semantic information for scene inference, resulting in a suboptimal performance. This letter presents an optimal edge weight estimation using the trust theoretic framework to encode semantic information effectively in saliency graphs. We have utilized the notion of converged global absolute trust in saliency scores of salient objects to compute the weighting of semantic information. Experimental results highlight the efficacy of the proposed method.
As a key technology in radar reconnaissance systems, radar signal sorting aims to separate multiple radar pulses from an interleaved pulse stream. Supervised signal sorting methods based on deep learning depend on a l...
详细信息
As a key technology in radar reconnaissance systems, radar signal sorting aims to separate multiple radar pulses from an interleaved pulse stream. Supervised signal sorting methods based on deep learning depend on a large volume of training data to optimize model parameters. However, acquiring labeled pulses in practice is challenging. In this letter, a semi-supervised learning (SSL) framework is proposed to address this issue. First, a Self-Organizing Map (SOM) is used to learn the spatial distribution of impulse features, and an anchor graph is constructed based on SOM nodes. A pseudo-label set is then generated using the SOM based on pulse discrepancy information. Finally, a three-layer Weighted Residual Graph Convolutional Network (WRGCN) is designed for signal sorting, with its parameters pre-trained on pseudo-labels and fine-tuned with a limited number of true labels. Experiments on a simulated radar pulse dataset demonstrate that this framework outperforms several existing methods for radar signal sorting with limited labeled pulses.
Orthogonal time-frequency space (OTFS) modulation, which exhibits significant advantages in high-speed mobile communication scenarios, holds strong potential in the field of radar applications. The existing state-of-t...
详细信息
Orthogonal time-frequency space (OTFS) modulation, which exhibits significant advantages in high-speed mobile communication scenarios, holds strong potential in the field of radar applications. The existing state-of-the-art target parameter estimation methods for cyclic prefix OTFS (CP-OTFS) based radar systems suffer from inaccuracies in target scattering coefficient (TSC) estimation under conditions of multiple targets, low bandwidth and short duration. In this letter, the equivalent matched filter (EMF) algorithm is designed. Compared to the matched filter (MF) algorithm, EMF intuitively explains the input-output relationship of CP-OTFS based radar, but it remains susceptible to interference from multiple targets. In order to mitigate this impact, the two-stage matched filter-based minimum mean squared error (TS-MF-MMSE) algorithm, a refined TSC estimation algorithm for terrestrial CP-OTFS based radar system is proposed. Simulation results demonstrate the superior performance of proposed algorithm in TSC estimation in comparison with EMF and the state-of-the-art.
Parameter-efficient fine-tuning of pre-trained multilingual speech models can significantly enhance the speech recognition performance of target languages. However, traditional parameter-efficient fine-tuning methods,...
详细信息
Parameter-efficient fine-tuning of pre-trained multilingual speech models can significantly enhance the speech recognition performance of target languages. However, traditional parameter-efficient fine-tuning methods, such as adapter tuning, often face challenges related to random initialization. This can lead to suboptimal performance when adapting to languages with limited resources. To address this issue, this letter introduces TAML-Adapter, which utilizes the Task-Agnostic Meta-Learning algorithm to initialize the parameters of the adapters before fine-tuning in target low-resource languages. Comprehensive experiments conducted on the Common Voice and Fleurs datasets highlight the superior performance of TAML-Adapter in five languages with limited resources. In addition, the TAML-Adapter demonstrates superior generalizability and extensibility compared to similar competing methods.
The Iterative Closest Point (ICP) method, primarily used for transformation estimation, is a crucial technique in 3D signalprocessing, especially for point cloud fine registration. However, traditional ICP is prone t...
详细信息
The Iterative Closest Point (ICP) method, primarily used for transformation estimation, is a crucial technique in 3D signalprocessing, especially for point cloud fine registration. However, traditional ICP is prone to local optima and sensitive to noise, especially when there is no good initialization. Based on the observation that registration errors typically exhibit a multimodal distribution under large rotational offsets and noisy environments, the MultiKernel Correntropy (MKC), which can estimate the registration error distribution, is introduced to provide global information for ICP. Moreover, since MKC consists of multiple Gaussian kernels, it can effectively resist most of the noise. A MultiKernel Correntropy based Iterative Closest Point (MKCICP) is proposed. Extensive experiments on both simulated and real-world datasets show that MKCICP achieves better performance compared to other related methods in challenging scenarios involving large rotational angles, low partial overlap, and high noise levels.
暂无评论