In multi-intersection traffic signal timing (TST) the use of a uniform cycle time reduces efficiency at low-volume intersections and signal changes which can alter vehicle flows and degrade communication quality. This paper presents a solution to this problem introducing a Twin-Timescale model whereby a multi-intersection TST method is jointly considered with communication resource allocation (CRA) strategies. For each intersection, a Twin-Timescale Reinforcement Learning (RL) algorithm is proposed, by considering both CRA and TST as the Short- and the Long- Timescale models, respectively, and jointly formulating their rewards. Based on the characteristics of this Twin-Timescale model, the reward function is constructed as a singularly perturbed model (SPM), and a state feedback controller that can ensure asymptotic stability is designed. Furthermore, a novel asynchronous time Multi-Agent Coordinated RL algorithm is proposed, which allows each intersection to generate each own joint parameters for its decision strategy which are based upon information obtained from neighboring intersections at asynchronous time. In addition, the use of Federated Learning (FL) in conjunction with the proposed algorithms is investigated, and its advantages in enhancing the resistance to malicious attacks are discussed. Using real traffic data, various performance evaluation results obtained by means of extensive computer simulation experiments have confirmed that the proposed TST-CRA joint optimization approach significantly improves traffic indicators and maintains the quality of the overall communication performance. Through numerical calculations, the state feedback controller coefficients have been determined.

In simulating synthetic aperture radar (SAR) ship wakes, dynamic wake modeling often uses the linear superposition of sea waves and Kelvin wakes. This method, however, overlooks the alterations in sea surface roughness caused by the nonlinear interaction between waves and wakes, thus failing to accurately capture real sea surface variations. In this letter, we introduce a rapid SAR image simulation technique for ship wakes that incorporates sea waves using fluid velocity potential. Firstly, the computational domain and ship grid are constructed, with the grid scale tailored to the ship's surface structure to satisfy boundary conditions for efficient fluid velocity potential calculations. Next, to enhance boundary calculation accuracy, we employ the Taylor expansion boundary element method to swiftly resolve both steady and unsteady velocity potential components. Additionally, our approach not only depicts the interaction between sea waves and ship wakes but also facilitates the simulation analysis of various sea condition parameters. By treating the ship wake as noise and comparing images containing only background sea waves with the simulation images, the results show that the accuracy of the proposed approach is 0.2 SSIM higher than that of the linear superposition method, and the speed is 3 hours faster than that of CFD method.

Infrared imaging possesses characteristics such as long visual distance and strong anti-interference capabilities, enabling it to provide clear target images in low light conditions. However, due to the difficulty in obtaining a large amount of labeled data, recognizing infrared targets under few-shot conditions remains a challenge. To address these challenges, this paper proposes an infrared time-sensitive target recognition method based on model-agnostic meta-learning (MAML). We utilize the lightweight network Lite-HRNet as the backbone, and incorporate the scale-aware squeeze-and-excitation (SASE) module to achieve multi-scale feature extraction and fusion. Simultaneously, the MAML algorithm is used to optimize the parameter update process, enabling the model to quickly obtain optimal parameters through fine-tuning on few-shot datasets in the target domain. The experiments were conducted on a public dataset of time-sensitive targets. The results demonstrate that the proposed method outperforms other comparative algorithms in terms of recognition precision, achieving a precision of 72.58%.

Heterogeneous image change detection involves identifying changes on the Earth’s surface using different imaging data from satellites. In this paper, we propose a multilayer convolutional adversarial network model based on transfer learning for detecting changes in heterogeneous images under unsupervised conditions. Firstly, we construct an adversarial network consisting of generators and discriminators, which is used to build a heterogeneous image transformation network and an approximate network that introduces change recognition factors. The generator is designed with a feedback-connected multi-convolutional layer structure to repair and reuse image features. Additionally, based on the idea of transfer learning, the transformation and approximate networks are alternately trained to strengthen the network’s ability to capture potential changes between images. Finally, the algorithm is validated on a public heterogeneous dataset to enhance the accuracy of image change detection, particularly for detecting small changes in images.

The wake target has garnered increasing attention due to its length, which can be up to ten times that of the ship, and its inclusion of critical navigation information such as heading and speed. However, deep learning methods used in synthetic aperture radar (SAR) image wake detection tasks are limited to analyzing the features of the image itself, overlooking the characteristics of ship wakes in the frequency domain. This letter proposes a network called pseudo-siamese and multidomain feature fusion network (PSMDNet) that is composed of two parallel feature extraction branches. The feature extraction in the frequency domain uses the frequency channel attention network (FcaNet) as the backbone, incorporating an adjacent scale space attention module (ASSAM) to fuse high-level features into low-level features. The time domain uses the residual network (ResNet) as the backbone, incorporating a bidirectional feature channel module (BFCM) to enhance the representation of low-level spatial information. These two parallel branches extract the time- and frequency-domain features from the image to better capture the wake feature information. The proposed ASSAM module calculates weighted coding with context information, thereby selectively aggregating the unique linear spatial features of the wake into the low-level feature map. Verification experiments were conducted on the SAR-WAKE dataset, and the results demonstrate that the proposed method excels in detection accuracy compared with other algorithms, achieving excellent results of 92.71%. Particularly noteworthy is that the positioning and visualization of wake vertex and Kelvin arms are realized by the loss function designed for the wake.

Change detection based on synthetic aperture radar (SAR) images is a challenging task in the field of remote sensing image analysis due to the influence of noise and the lack of labeled data. In this paper, we propose a new unsupervised change detection algorithm based on deep learning, which explores the spatial and frequency domain features of SAR images in parallel to improve detection performance. Our proposed method first obtains pseudo-labels by clustering and then combines them with neural networks for unsupervised detection. To reduce the impact of noise and improve sensitivity to changes, we integrate an attention mechanism (AM) into the network. We also use complementary features to integrate the spatial and frequency domain features. These complementary features include a multi-regional feature weighted by channel-spatial AM and a deep feature filtered out by a gated linear unit (GLU). Experimental results demonstrate that the proposed method improves the detection accuracy.

Remote sensing change detection (CD) has been widely studied, and the CD of heterogeneous images based on cross-sensor acquisition has significant research significance. However, the scarcity of heterogeneous data and the difficulty in obtaining high-quality change maps remain significant challenges. To address these issues, we propose a deep image translation-based feature refinement-aggregation change detection network (FRAN) designed for heterogeneous images, such as optics and SAR images. First, we use data augmentation to increase the number of available images and a no-independent-component-for-encoding GAN (NICE-GAN) to translate the features from the optical domain to the SAR image domain, enabling direct comparison of images from different domains. Finally, we introduce feature refinement module and feature aggregation module to extract more accurate change information and obtain an accurate change region. Our experiments on two public datasets demonstrate that the proposed FRAN’s re-detection accuracy is superior to that of four other heterogeneous detection methods.

Conducting research on electromagnetic (EM) modeling and simulation for ship wakes is crucial due to the lack of available Synthetic Aperture Radar (SAR) ship wake datasets for analysis. In this study, we have created a quick simulation model of wake SAR imaging under complex sea circumstances based on the EM scattering theory of random rough surfaces, the theory of ship wave resistance, and the influence of three modulations on radar echo. Using this model, we generated wake SAR images with varying parameters for two separate ship models and two different wave spectra. We evaluated these images using four standard image evaluation indexes to assess the impact of two significant parameters, namely the Froude number and the range-to-velocity ratio. We also investigated the effects of hydrodynamic and SAR parameters on sea surface imaging. Our findings suggest that a design with a higher Froude number and a lower R/V value can result in superior visualization effects. This study contributes to the development of EM modeling and simulation for SAR imaging of ship wakes, which can provide valuable insights for a range of applications.

Recently, deep learning methods have been applied to detect ships in synthetic aperture radar (SAR) images. However, detecting ships in SAR images with low resolution and complex background, especially ports that are closely distributed and arbitrarily oriented, remains a challenge. To address these issues, this paper proposes a novel SAR image rotation target detection module based on multi-scale attention for inshore ship detection. The network focuses on the frequency domain features of the image and integrates the global multi-scale features with an attention mechanism. The proposed method is verified on the public data set RSDD-SAR, and the results demonstrate its superiority over all comparison methods.

The categorization of synthetic aperture radar (SAR) ships primarily focuses on large ships with distinct features, but accurately identifying SAR ships remains challenging due to limited samples in certain ship categories. In this study, we propose a compressed and excited Vision Transformer model based on local feature fusion. This model leverages local feature fusion and channel modeling through the squeezing-and-excitation (SE) mechanism to effectively balance the contributions of each feature. By incorporating better local information, we are able to extract deeper features even from small datasets. To evaluate the efficacy of our model, we trained it on the three-category OpenSARShip 2.0 dataset and conducted experiments. The results demonstrate that our proposed model achieves superior classification accuracy compared to existing methods.

Change detection based on synthetic aperture radar (SAR) images is an important application in the remote-sensing technology field. However, the lack of labeled data has been a difficult problem in SAR image detection, especially for pixel-level change detection. In this letter, we propose a novel unsupervised change detection algorithm, which improves the detection accuracy by exploring features from both spatial and frequency domains of SAR images. In particular, first clustering is used as preclassification to obtain pseudo-labels and then by incorporating classifiers and pseudo-labels in terms of feature learning, a novel unsupervised detection algorithm is proposed. To improve the sensitivity of the algorithm to changed details and enhance the antinoise ability of the change detection network, the attention mechanism (AM) is integrated into the network to fully extract important spatial structure information. Moreover, a multidomain fusion module is proposed to integrate spatial and frequency domain features into complementary feature representations. This module contains multiregion features weighted by the channel-spatial AM and deep features filtered out by the gated linear units (GLUs) in the frequency domain. To verify the effectiveness of the proposed algorithm, it is compared against the other four SAR image change detection algorithms using three real datasets. The experimental results show that the proposed method outperforms the other four algorithms in terms of percent correct classification (PCC) and Kappa coefficient (KC).

Fetal heart rate monitoring is an enormous challenge since the observed fetal electrocardiography (ECG) signal is typically characterized by a very low signal-to-noise ratio (SNR). In this letter, we aim to improve the accuracy of heartbeat detection by proposing an adaptive template for removing the maternal cycle. The template is formed by a matrix, each row of which consists of an abdominal recorded signal (ADS). It can be updated by integrating the incoming cycle while removing the contribution of the previous recording. This process is conducted by considering a discriminator to adapt the non-stationarity of each incoming cycle. Furthermore, to suppress the morphological change caused by noise, we propose a novel multi-layer hybrid network to reconstruct the chest maternal ECG (chest mECG) morphology from a set of templates. The approach has a deep structure of each layer consisting of a reservoir layer and an encoder layer. The reservoir layer explores multi-scale dynamics by transforming the input series into a high-dimensional space. The encoder layer achieves the collection of the encoder features from the output of the reservoir layer. Once the model is built, the output weight of a direct connection is trained by solving a regression problem. Experimental results show that the proposed method has a better performance compared with some classical approaches.

Similar to the deep architectures, a novel multi-layer architecture is used to extend the linear blind source separation (BSS) method to the nonlinear case in this paper. The approach approximates the nonlinearities based on a polynomial network, where the layer of our network begins with the polynomial of degree 1, up to build an output layer that can represent data with a small bias by a good approximate basis. Relying on several transformations of the input data, with higher-level representation from lower-level ones, the networks are to fulfill a mapping implicitly to the high-dimensional space. Once the polynomial networks are built, the coefficient matrix can be estimated by solving an l1-regularization on the coding coefficient vector. The experiment shows that the proposed approach exhibits a higher separation accuracy than the comparison algorithms.

Blind source separation (BSS) is a technique to recognize the multiple talkers from the multiple observations received by some sensors without any prior knowledge information. The problem is that the mixing is always complex, i.e., nonlinear, underdetermined mixture, such as the case where sources are mixed with some direction angles, or where the number of sensors is less than that of sources. In this paper, we propose a multi-subspace representation based BSS approach that allows the mixing process to be nonlinear and underdetermined. The approach relies on a multi-layer representation and sparse representation in time-frequency (TF) domain. By parameterizing such subspaces, we can map the observed signals in the feature space with the coefficient matrix from the parameter space. We then exploit the linear mixture in the feature space that corresponds to the nonlinear mixture in the input space. Once such subspaces are built, the coefficient matrix can be constructed by solving an l1-regularization on the coding coefficient vector. Relying on the TF representation, the target matrix can be constructed in a sparse mixture TF vectors with a fewer computational cost. The experiments are run on the observations that are generated from nonlinear functions, and that are collected with some direction angles in a virtual room environment. The proposed approach exhibits a higher separation accuracy than that of the conventional algorithms.

Signal restoration involves the removal or minimization of degradation such as attenuation, interference, and noise. Blind signal restoration is the process of estimating either the original signals or mixture functions from the degraded signals, without any prior information about original sources. In this paper, we present a novel approach to tackle the ill-posedness of the nonlinear blind source separation problem. The derivation of our algorithm is inspired by the idea of an efficient layer-by-layer representation to approximate the nonlinearity. Once such representations are built, a final output layer is constructed by solving a convex optimization problem. Thus, the projected data can break a nonlinear problem down into the version of generalized joint diagonalization problem in the feature space. Importantly, the parameters and forms of polynomials depend solely on the input data, which guarantee the robustness of the structure. We thus address the general problem without being restricted to any specific mixture or parametric model. Experimental results show that the proposed algorithm is able to recover the nonlinear mixture with higher separation accuracy on audio datasets from the real world.