Search

Graph convolutional networks (GCNs) have been proved successful in the field of semi-supervised node classification by extracting structural information from graph data. However, the random selection of labelled nodes used in GCNs may lead to unstable generalisation performance of GCNs. In this paper, we propose an efficient method for the deterministic selection of labelled nodes: the determinate node selection (DNS) algorithm. The DNS algorithm identifies two categories of representative nodes in the graph through structural analysis of the leading tree information granules: typical nodes and divergent nodes. These labelled nodes are selected by exploring the structure of the graph and determining the ability of the nodes to represent the distribution of data within the graph. The DNS algorithm can be applied quite simply on GCNs, and a wide range of semi-supervised graph neural network models for node classification tasks. Through extensive experimentation, we have demonstrated that the incorporation of the DNS algorithm leads to a remarkable improvement in the average accuracy of the model and a significant decrease in the standard deviation simultaneously, as compared to the vanilla method without a DNS module.

•The prevalence of VRE in our hospital has increased dramatically since 2022.•The ST80 has been the predominant clone until the introduction of ST78 in May 2023.•An ongoing outbreak of ST80 and ST78 VREfm harboring vanAwas uncovered in Shenzhen.

Compositional Zero-Shot Learning (CZSL) has been applied to various scenarios, including scene understanding, visual-language representation, and domain adaptation. Despite numerous endeavours and significant advancements, the crucial issues of fuzzy conceptualization of visual attributes and insufficient inter-class connectivity, have remained insufficiently addressed. To address these issues, we propose Learning Visual Attributes Representation for Compositional Zero-Shot Learning (LVAR-CZSL), which has the ability to learn visual attributes and inter-class dependencies. LVAR-CZSL is mainly composed of two key components: the Visual Attribute Representation Module (VARM) and the Connected Learning Module (CLM). Specifically, VARM extracts detailed attributes and object visual features from global visual features, resolving the issue of fuzzy visual attribute concepts. Moreover, CLM endows LVAR-CZSL with the capability to perceive connectivity between different attributes and objects, effectively enhancing inter-class connectivity. To establish a close connection between VARM and CLM and minimize the gap between image and text features, we introduce the composition-attribute-object Joint Scoring Function (JSF). Additionally, we propose Joint Loss Function (JLF) to optimize the learning process of VARM and CLM. The experiment results on four datasets show that LVAR-CZSL achieves state-of-the-art performance. The code is available at https://github.com/mxjmxj1/LVAR-CZSL.

This paper introduces an enhanced slime mould algorithm (EESMA) designed to address critical challenges in engineering design optimization. The EESMA integrates three novel strategies: the Laplace logistic sine map technique, the adaptive t-distribution elite mutation mechanism, and the ranking-based dynamic learning strategy. These enhancements collectively improve the algorithm’s search efficiency, mitigate convergence to local optima, and bolster robustness in complex optimization tasks. The proposed EESMA demonstrates significant advantages over many conventional optimization algorithms and performs on par with, or even surpasses, several advanced algorithms in benchmark tests. Its superior performance is validated through extensive evaluations on diverse test sets, including IEEE CEC2014, IEEE CEC2020, and IEEE CEC2022, and its successful application in six distinct engineering problems. Notably, EESMA excels in solving economic load dispatch problems, highlighting its capability to tackle challenging optimization scenarios. The results affirm that EESMA is a competitive and effective tool for addressing complex optimization issues, showcasing its potential for widespread application in engineering and beyond.Graphical Abstract

Flight data anomaly detection is crucial for ensuring the flight safety of unmanned aerial vehicles (UAVs). By monitoring and analyzing flight data, anomalies can be detected in time to avoid potential risks. Deep learning can automatically extract complex patterns and features from data and has been widely used in UAV flight data anomaly detection in recent years. Given the lack of a comprehensive survey of research related to deep learning in UAV flight data anomaly detection, this article conducts a systematic and in-depth literature review. First, the basic concepts of UAV flight data are briefly introduced, followed by an analysis and summary of the applications of deep learning methods based on prediction and reconstruction in UAV flight data anomaly detection. Emphasis is placed on the research progress of deep learning methods based on recurrent neural network (RNN), convolutional neural network (CNN), auto-encoder (AE), and variational AE (VAE) for UAV flight data anomaly detection. Second, an in-depth analysis of the threshold calculation methods utilized in existing research is conducted and the advantages and limitations of these thresholds in practical applications are discussed. Finally, some insightful research directions are given based on the shortcomings of existing research. This work aims to provide a reference and insight for future research, inspire further studies, and jointly promote the development of this promising field.

The use of singular value decomposition (SVD) under the Hankel matrix has emerged as a powerful technique for denoising non-stationary signals. The efficacy of the denoising process is significantly influenced by the structure of the Hankel matrix and the selection of subsignals. This article systematically investigates these factors and introduces an analytical signal-based SVD (A-SVD) method. Initially, the analytical signal is introduced. This is based on the observed correlation between subsignals, aiming to reduce this correlation. Subsequently, a parameter unit energy change index (ECI) is introduced for assessing the decomposition’s stability across different Hankel matrices, aiming to optimize the structure of the Hankel matrix. Moreover, the group Gini index (GGI) of the reconstructed signal is utilized to select the optimal denoised signal. Lastly, the envelope spectrum is utilized for the analysis and extraction of relevant fault features. The effectiveness and superiority of the A-SVD method are confirmed through its application to both simulated bearing fault signals and two actual bearing fault cases.

In unmanned aerial vehicle (UAV), flight status monitoring and anomaly detection are effective ways to improve the safety and reliability of UAVs. However, when a UAV is on a mission, any small anomaly can impact the UAV, leading to mission failure. At the same time, most current methods target the detection of a single anomaly type or data and do not consider the occurrence of anomalies in different parameters in the UAV flight data. Therefore, this article proposes a deeply integrated autoencoder anomaly detection method for anomaly detection and critical parameter identification of UAV actuators. First, to reduce the influence of random noise on the model performance, the original data are smoothed using the Savitzky-Golay filter. Second, a hybrid model combining nonlinear mapping, 1-D convolutional neural networks (1DCNNs), and AutoEncoder to exploit the spatiotemporal features in the data fully. Finally, anomaly detection was achieved by comparing the residuals with the anomaly determination threshold, and critical parameter identification was achieved by calculating the anomaly contribution. Experimental results on accurate UAV actuator data injected with anomalies show that the proposed method has obvious advantages over the benchmark method.

Nickel–molybdenum–boron (Ni–Mo–B)-based catalysts with biphasic interfaces are highly advantageous in bifunctional electrocatalytic activity in alkaline water-splitting. However, it remains an ongoing challenge to obtain porous Ni–Mo alloy substrates that provide stable adhesion to catalysts, ensuring the long-term performance of bifunctional self-supporting electrodes at a high current density. Herein, a porous Ni–Mo alloy substrate was effectively obtained by a cost-effective dealloying process on a commercial Ni–Mo alloy with high-energy crystal planes. Subsequently, the Mo2NiB2/Ni3B bifunctional catalyst was in situ synthesized on this substrate via boriding heat treatment, resulting in outstanding catalytic activity and stability. Density functional theory (DFT) calculations reveal that the abundant biphasic interfaces and surface-reconstructed sites of the Mo2NiB2/Ni3B catalyst can decrease the energy barriers for the hydrogen evolution reaction (HER) and oxygen evolution reaction (OER), respectively. Thus, the designed self-supporting electrodes show bifunctional catalytic activity with overpotentials of 151 mV for HER and 260 mV for OER at a current density of 10 mA cm–2. Markedly, the assembled water electrolyzer can be driven up to 10 mA cm–2at 1.64 V and maintain catalytic activity at a high current density of 1000 mA cm–2for 100 h. The new strategy is expected to provide a low-cost scheme for designing self-supporting bifunctional electrodes with high activity and excellent stability and contribute to the development of hydrogen energy technology.

Due to data imbalances and the complexity of data, identifying outliers can be challenging. To address this issue, this paper introduces a new unsupervised model called MMD Fence GAN. An improved loss function is incorporated into the generator to enhance anomaly detection accuracy. In the loss function of the generator, there are three main components: the encirclement loss limits the generated samples to lie at the decision boundary of the normal samples. The central dispersion loss maximizes the decision boundary's range. By measuring the maximum mean discrepancy between the generated samples and the given samples, the sample dispersion loss avoids issues like model collapse and outliers. Two datasets validate the effectiveness of the model: On the 2D synthetic dataset, it converges faster and pinpoints decision boundaries more precisely than Fence GAN. Both F1-score and recall improve over traditional and advanced deep learning methods on the KDD99 dataset.

Flight data anomaly detection is crucial for ensuring the safe operation of unmanned aerial vehicles (UAVs) and has been extensively studied. However, the accurate modeling and analysis of flight data is challenging due to the influence of random noise. Meanwhile, existing methods are often inadequate in parameter selection and feature extraction when dealing with large-scale and high-dimensional flight data. This paper proposes a data-driven multivariate regression-based framework considering spatio-temporal correlation for UAV flight data anomaly detection and recovery, which integrates the techniques of correlation analysis (CA), one-dimensional convolutional neural network and long short-term memory (1D CNN-LSTM), and error filtering (EF), named CA-1DCL-EF. Specifically, CA is first performed on original UAV flight data to select parameters with correlation to reduce the model input and avoid the negative impact of irrelevant parameters on the model. Next, a regression model based on 1D CNN-LSTM is designed to fully extract the spatio-temporal features of UAV flight data and realize parameter mapping. Then, to overcome the effect of random noise, a filtering technique is introduced to smooth the errors to improve the anomaly detection performance. Finally, two common anomaly types are injected into real UAV flight datasets to verify the effectiveness of the proposed method.Graphical Abstract

Fast scanning speed and low-power consumption are becoming progressively more and more important in realizing high-performance chiplet optical phased arrays (OPAs). Here, we successfully demonstrated integrated OPAs with multiple waveguides channels based on thin-film lithium niobate-on-insulator (LNOI) platform. Specifically, two lithium niobate (LN) OPA chips have been implemented with 32 and 48 channels LN waveguides, respectively, enabled by electro-optic modulations, which showcases the low power consumption (1.11 nJ/π) and fast operation speed (14.4 ns), showing obvious advantage of the LNOI platform over others. As results, we experimentally achieved a beam steering with a 62.2° × 8.8° field of view (FOV) and a beam divergence of 2.4° × 1.2° for 32 channels, and a FOV of 40° × 8.8° and a beam divergence of 0.33° × 1.8° for 48 channels. This work also demonstrates the feasibility of LNOI platform in scalable OPA chips.

The wide applications of 3-D sonar measurements are severely limited by factors such as water column interference, acoustic shadows, complex structures, and scattering noise. Outliers in 3-D sonar data are difficult to remove using traditional methods because the inference factors are different from other types of point cloud data. Therefore, this article presents a novel outlier filtering method by analyzing the sequential characteristics of the 3-D sonar data. First, the underwater point cloud is processed by super-voxel clustering method to decompose complex point cloud structures into several super-voxels with simple structures. Then we convert the point cloud data into subsequence data according to the surveying principle of 3-D sonar scanning and super-voxel results. After that, an anomaly score calculation and anomaly region determination method based on the rectangular information granulation of subsequence data is proposed. This method can capture the intrinsic changing characteristics of each subsequence and has a good recognition effect on the abnormal subsequence. Finally, an outlier detection method combining the Grubbs principle and the abnormal score is proposed and applied to the abnormal subsequences, which considers the distortion not only in the vertical direction but also in the horizontal direction. The experimental results show that the proposed comprehensive filtering method has good accuracy for both horizontal and vertical point cloud data. The average overall accuracy of the test results is 99.1%, and the average kappa coefficient is 0.88, which can be effectively applied to the 3-D sonar point cloud data filtering processing in complex underwater areas.

Fixed-wing unmanned aerial vehicles (FW-UAVs) are strategically important in several fields, but are prone to failures during various missions, causing serious damage. Deep learning has brought new opportunities for fault diagnosis techniques for FW-UAVs, but the available fault samples are very limited. In addition, multiple components or multiple modes of faults may occur simultaneously. General methods usually have difficulty dealing with these problems, which poses a significant challenge for FW-UAV fault diagnosis. Therefore, this article proposes a multilevel task knowledge supplement (MTKS) network for FW-UAV fault diagnosis under small samples, enabling simultaneous handling of the faulty component diagnosis (FCD) task (level 1) and the fault severity diagnosis (FSD) task (level 2), while effectively utilizing the common knowledge of the two tasks to improve the model’s performance under small samples. Specifically, we first extract features for the FCD and FSD tasks through two task-specific networks. These features contain abundant shared knowledge. Second, we design a novel adaptive knowledge supplementation strategy, which aims to store the public knowledge of the two tasks in a public knowledge pool (PKP) and supplement additional knowledge to the two task-specific networks when needed to improve the performance of the networks. Moreover, a dynamic weighted average (DWA) approach is used to fully train the two task-specific networks. Finally, extensive experimental results show that the proposed MTKS exhibits an excellent performance and is of significant competitiveness with currently popular methods.

The detection of shipwrecks plays an important role in hydrographic surveying and underwater archaeology. However, traditional 2-D sub-bottom profiler (SBP) data cannot represent the 3-D shape of the buried shipwreck. An automatic shipwreck detection method based on 3-D SBP data is presented in this article. First, the key hull shape parameters are given and analyzed to describe the 3-D geometric characteristics of the shipwreck. Then, geometric contours of reflections were extracted based on 3-D SBP data by using the Enhancement Filtering Method to remove interferences, followed by applying the Global Energy Optimization Method to obtain contour clusters. After that, we elaborated on the main parameters used in hull shape description and presented the definitions of these parameters under a local coordinate system established using principal component analysis. Then, we define the shape index of the shipwreck (SI). To remove the dependence on a shipwreck attitude, we build the local coordinate system. To achieve unsupervised detection, we utilize prior information about the hull shape and determine the threshold for the SI in shipwreck detection. By applying the proposed method to both the real and simulated data, we demonstrate successful detection performance.

Matching multibeam echo sounder (MBES) data and side scan sonar (SSS) data has the potential to obtain high-accuracy seabed topography and geomorphological details simultaneously. However, the position uncertainty as well as radiometric and geometric distortion of SSS images bring serious challenges to the matching process. In this article, we proposed a novel matching method using sea bottom line matching and template matching to solve the above problems. First, we extracted the sea bottom points from the SSS image and calculated the depth series of the sea bottom line as the auxiliary information. Then, coarse matching is employed to this depth series and its corresponding terrain data of the MBES, to remove the coarse position uncertainty between the SSS and MBES images. After that, multiscale local self-similarity (MLSS) is proposed here, which is robust to geometric and radiometric distortion. Based on the coarse-matched SSS image, MLSS descriptor is applied for template matching between SSS and MBES images. Experiments verified the performance of the method. The high-resolution and high-accuracy seabed topography and surface details are eventually obtained.

In this brief, the exhaustive design method for in-line quasi-TEM mode dielectric waveguide filter (DWF) with dispersive coupling is presented. Using the dispersive coupling structure, controllable finite position transmission zeros (TZs) can be implemented without cross-coupling which is commonly used in the quasi-TEM mode DWF, and the coupling coefficient which the filters need can be provided at the center frequency at the same time. The dispersive coupling matrix (CM) including CM $\mathbf {M}_{0}$ at the center frequency and dispersive slope matrix $\mathbf {M}_{d}$ are derived from the synthesized traditional CM, and the procedures of parameter extraction in the DWF are also demonstrated in detail. Three 4–2 filters with different TZs and an 8–4 filter are designed to illustrate the feasibility of the fashion. Eventually, an in-line topology quasi-TEM DWF with dispersive couplings is fabricated, post-processed, and measured.

Feature Selection (FS) is an important data management technique that aims to minimize redundant information in a dataset. This work proposes DENGO, an improved version of the Northern Goshawk Optimization (NGO), to address the FS problem. The NGO is an efficient swarm-based algorithm that takes its inspiration from the predatory actions of the northern goshawk. In order to overcome the disadvantages that NGO is prone to local optimum trap, slow convergence speed and low convergence accuracy, two strategies are introduced in the original NGO to boost the effectiveness of NGO. Firstly, a learning strategy is proposed where search members learn by learning from the information gaps of other members of the population to enhance the algorithm's global search ability while improving the population diversity. Secondly, a hybrid differential strategy is proposed to improve the capability of the algorithm to escape from the trap of the local optimum by perturbing the individuals to improve convergence accuracy and speed. To prove the effectiveness of the suggested DENGO, it is measured against eleven advanced algorithms on the CEC2015 and CEC2017 benchmark functions, and the obtained results demonstrate that the DENGO has a stronger global exploration capability with higher convergence performance and stability. Subsequently, the proposed DENGO is used for FS, and the 29 benchmark datasets from the UCL database prove that the DENGO-based FS method equipped with higher classification accuracy and stability compared with eight other popular FS methods, and therefore, DENGO is considered to be one of the most prospective FS techniques. DENGO's code can be obtained at https://www.mathworks.com/matlabcentral/fileexchange/158811-project1.

Unmanned aerial vehicles (UAVs) have demonstrated remarkable versatility across a spectrum of missions, and their autonomous flight and real-time control heavily rely on onboard sensors. However, UAV sensors are susceptible to external cyberattacks and internal failures in complex environments, and the scarcity of real sensor fault data poses challenges for developing accurate detection models. This article is the first to investigate the zero-shot fault detection (ZSFD) problem for UAV sensors, which considers the most challenging scenario where there are no fault data provided for model training. Therefore, a novel convolutional variational autoencoder-generative adversarial network (CVAE-GAN) is proposed, which is designed with a discriminator, and a generator consisting of two encoders and one decoder. First, a fixed-length sliding window is used on normal data of multiple sensors to construct multidimensional input samples, and the generator first learns the latent distribution of fault-free data in adversarial training. Then, the CVAE-GAN generates large reconstruction errors for unseen fault data in testing, which are used as anomaly scores to be compared with adaptive thresholds to achieve fine-grained detection of different sensor faults. Finally, comprehensive experimental results based on real sensor data from a UAV demonstrate the effectiveness of our method in performing ZSFD tasks with different sensor faults, especially in detecting bias, stuck, and impact faults in magnetometer, where the GM metrics outperform the compared models by approximately 7% on average, and the test time efficiency opens up the possibility of realizing online fault detection.

Inspired by the event-driven nature of biological systems and sparse spiking networks, research on event-driven tactile learning has been stimulated by recent advancements in event-driven tactile sensors and spiking neural networks (SNNs). However, a major challenge in tactile object recognition research lies in addressing the generalization problem caused by the complex spatiotemporal characteristics of high-dimensional event-driven tactile data. Additionally, sparse connections of SNN models are resulted by difficulties in fully utilizing timing information and structural features of tactile nodes, due to the limited representation of tactile information graphs. To address these issues comprehensively, this article proposes a fusing topological graph and Gaussian prior event-driven tactile object recognition SNNs. First, the incorporation of Gaussian prior effectively integrates prior knowledge to alleviate the generalization problem in event-driven tactile object recognition. Furthermore, both topological sorting and R-tree tactile graph construction methods are employed to enhance the connection structure within the tactile graph and resolve the issue of sparse connections. Finally, various approximate leaky integrate-and-fire neuron activation functions are introduced for comprehensive comparison and evaluation regarding their impact on performance in event-driven tactile object recognition. Experimental results using EvTouch-Containers and EvTouch-Objects datasets demonstrate that topological graph and Gaussian prior tactile object recognition (G2T)-SNN achieves superior recognition performance compared to TactileSGNet methods: 7.50% improvement on EvTouch-Containers dataset and 2.23% improvement on EvTouch-Objects dataset.

Catastrophic forgetting in neural networks is a common problem, in which neural networks lose information from previous tasks after training on new tasks. Although adopting a regularization method that preferentially retains the parameters important to the previous task to avoid catastrophic forgetting has a positive effect; existing regularization methods cause the gradient to be near zero because the loss is at the local minimum. To solve this problem, we propose a new continuous learning method with Bayesian parameter updating and weight memory (CL-BPUWM). First, a parameter updating method based on the Bayes criterion is proposed to allow the neural network to gradually obtain new knowledge. The diagonal of the Fisher information matrix is then introduced to significantly minimize computation and increase parameter updating efficiency. Second, we suggest calculating the importance weight by observing how changes in each network parameter affect the model prediction output. In the process of model parameter updating, the Fisher information matrix and the sensitivity of the network are used as the quadratic penalty terms of the loss function. Finally, we apply dropout regularization to reduce model overfitting during training and to improve model generalizability. CL-BPUWM performs very well in continuous learning for classification tasks on CIFAR-100 dataset, CIFAR-10 dataset, and MNIST dataset. On CIFAR-100 dataset, it is 0.8%, 1.03% and 0.75% higher than the best performing regularization method (EWC) in three task partitions. On CIFAR-10 dataset, it is 2.25% higher than the regularization method (EWC) and 0.7% higher than the scaled method (GR). It is 0.66% higher than the regularization method (EWC) on the MNIST dataset. When the CL-BPUWM method was combined with the brain-inspired replay model under the CIFAR-100 and CIFAR-10 datasets, the classification accuracy was 2.35% and 5.38% higher than that of the baseline method, BI-R + SI.

The use of spoilage indicator films has become widespread in food safety due to their ability to detect the freshness of food in real-time through color change. Here, a novel spoilage indicator film was prepared by combining polyvinyl alcohol (PVA)/cassava starch (CS) with neutral red (NR) as a pH-sensitive indicator. The microstructural properties of NR/PVA/CS film indicated that the addition of NR could greatly increase the compatibility of the membrane. The successful mixing of PVA, CS and NR was confirmed by Fourier transform infrared (FTIR). The film was attached to the upper layer of the inner package relying on the stickiness to avoid contacting with meat. Subsequently, the NR/PVA/CS film was successfully applied as a sticker indicator to monitor the spoilage of meat over time. Changes in color of the film from dark red to orange were observed by the naked eye, and quantified using the CIE color difference (ΔE). Finally, polynomial model between ΔE and TVB-N content in pork, mutton, and chicken during storage were successfully constructed with the coefficient of determination (R2) of 0.8286, 0.9426 and 0.9585, respectively. The results demonstrate the potential of the developed system to monitor the freshness of meat in food packaging.

In recent years, event-driven tactile data learning and event-driven spiking neural network (SNN) characteristics have provided new methods for tactile event perception. However, it is difficult to effectively extract tactile information from highly irregular taxel structures; additionally, the step property of spikes leads to nondifferentiability, making it difficult to directly apply the error backpropagation method to the training processes of SNNs. In this context, we propose an adaptive multichannel spiking graph convolutional network (GCN) framework that fully utilizes taxel features and topology information to build tactile topology and feature graphs for irregular taxels, and then extracts specific common tactile event data information from the feature, topology information, and their combinations via adaptive multichannel spiking graph convolution. The temporal spike sequence learning-based backpropagation algorithm is used to accurately calculate the spike gradient loss by analyzing the temporal and spatial dependence of neurons on the activity states of spike neurons. Experimental comparisons are conducted on the EvTouch-Objects tactile event dataset, and the experimental results show that the proposed method can effectively extract and fuse tactile information. Compared with the state-of-the-art methods, the proposed method achieves better classification performance, attaining an accuracy of 91.32% and a high precision rate of 92.43% in tests.

In this brief, a monolithically integrated broadband load modulated balanced amplifier (LMBA) chip without BA pre-matching network is proposed and designed. It is the first time that integrated LMBA operating at sub-6 GHz has been discussed about broadband performance. BA follows with only one inductor and output quadrature coupler, which can effectively reduce loss and improve efficiency. The load modulation behavior of BA is analyzed, indicating that it has an appropriate modulation trajectory. For verification, a LMBA chip was fabricated and measured in the 0.25- $\mu {\mathrm{ m}}$ GaAs pHEMT process. Continuous-wave measurements demonstrate a saturated output power of 30.2–31.8 dBm with drain efficiency (DE) of 34.3–59.2%, and 6-dB back-off DE of 27.7–40.4% in 4.2–5.2 GHz. Modulated signal measurements prove that the linearity of LMBA can be calibrated by digital predistortion.

The modern complicated manufacturing industry and smart manufacturing tendency have imposed new requirements on the scheduling method, such as self-regulation and self-learning capabilities. While traditional scheduling methods cannot meet these needs due to their rigidity. Self-learning is an inherent ability of reinforcement learning (RL) algorithm inhered from its continuous learning and trial-and-error characteristics. Self-regulation of scheduling could be enabled by the emerging digital twin (DT) technology because of its virtual-real mapping and mutual control characteristics. This paper proposed a DT-enabled adaptive scheduling based on the improved proximal policy optimization RL algorithm, which was called explicit exploration and asynchronous update proximal policy optimization algorithm (E2APPO). Firstly, the DT-enabled scheduling system framework was designed to enhance the interaction between the virtual and the physical job shops, strengthening the self-regulation of the scheduling model. Secondly, an innovative action selection strategy and an asynchronous update mechanism were proposed to improve the optimization algorithm to strengthen the self-learning ability of the scheduling model. Lastly, the proposed scheduling model was extensively tested in comparison with heuristic and meta-heuristic algorithms, such as well-known scheduling rules and genetic algorithms, as well as other existing scheduling methods based on reinforcement learning. The comparisons have proved both the effectiveness and advancement of the proposed DT-enabled adaptive scheduling strategy.

Anomaly detection is crucial to the flight safety and maintenance of unmanned aerial vehicles (UAVs) and has attracted extensive attention from scholars. Knowledge-based approaches rely on prior knowledge, while model-based approaches are challenging for constructing accurate and complex physical models of unmanned aerial systems (UASs). Although data-driven methods do not require extensive prior knowledge and accurate physical UAS models, they often lack parameter selection and are limited by the cost of labeling anomalous data. Furthermore, flight data with random noise pose a significant challenge for anomaly detection. This work proposes a spatiotemporal correlation based on long short-term memory and autoencoder (STC-LSTM-AE) neural network data-driven method for unsupervised anomaly detection and recovery of UAV flight data. First, UAV flight data are preprocessed by combining the Savitzky-Golay filter data processing technique to mitigate the effect of noise in the original historical flight data on the model. Correlation-based feature subset selection is subsequently performed to reduce the reliance on expert knowledge. Then, the extracted features are used as the input of the designed LSTM-AE model to achieve the anomaly detection and recovery of UAV flight data in an unsupervised manner. Finally, the method’s effectiveness is validated on real UAV flight data.

Flight data anomaly detection plays an imperative role in the safety and maintenance of unmanned aerial vehicles (UAVs). It has attracted extensive attention from researchers. However, the problems related to the difficulty in obtaining abnormal data, low model accuracy, and high calculation cost have led to severe challenges with respect to its practical applications. Hence, in this study, firstly, several UAV flight data simulation softwares are presented based on a brief presentation of the basic concepts of anomalies, the contents of UAV flight data, and the public datasets for flight data anomaly detection. Then, anomaly detection technologies for UAV flight data are comprehensively reviewed, including knowledge-based, model-based, and data-driven methods. Next, UAV flight data anomaly detection applications are briefly described and analyzed. Finally, the future trends and directions of UAV flight data anomaly detection are summarized and prospected, which aims to provide references for the following research.

This article focuses on dynamic analysis and the fuzzy fixed-time optimal synchronization control problem of unidirectionally coupled fractional-order (FO) permanent magnet synchronous generator (PMSG) system. The synchronization model between FO master and slave PMSGs with capacitive and resistive couplings is built. The dynamic analysis fully reveals its abundant dynamical behaviors including chaotic oscillations and gives stability/instability boundaries with the designed numerical method. In controller design, the hierarchical type-2 fuzzy neural network (HT2FNN) with a transformation is designed to approximate unknown functions, the fixed-time command filter matched up with the compensating signal is proposed to achieve precise estimate and fast convergence, and a fixed-time preconfigured performance function integrated with a smooth and invertible function is built to realize fixed-time convergence and performance constraint. Then a fuzzy fixed-time optimal synchronization control scheme fusing with the HT2FNN, filter, performance function and optimal control is developed under the FO backstepping theory. The stability analysis proves that all signals of the closed-loop system are bounded along with the cost function being minimized. Finally, numerical simulation results verify the feasibility and advantages of our scheme.

Sediment classification based on chirp sonar data is very important in support of marine science and engineering. The traditional adopted spectral-ratio (SR) method is widely applied for its theory of simplicity and easy employment. However, the performance of SR method is heavily degraded by spectrum vibrations introduced by overlapping reflections. To solve this problem, a reflection signal decomposition method is proposed in this article, which decomposes the overlapping reflection into separate reflection subsignals to avoid the spectrum vibration. First, we rederive the overlapping reflection expression from the convolution model and give the initial model for the decomposition of the chirp sonar signal. Then, introducing the spectrum smooth prior into consideration and incorporating it with the fidelity and the bandwidth terms, the decomposition model with constraints is proposed. After that, an iterative algorithm is introduced to solve the model optimization problem. The reflection subsignal can be well-obtained. Finally, through a least-squares linear fitting for the logarithm of the SR (log-SR) of reflection subsignals, quality factor ( ${Q}$ ) which is applied for sediment classification can finally be achieved. Both real and simulated experiments have been conducted to verify the proposed method, and some meaningful discussions are also drawn.

The acquirement of seafloor small target information is one of the most important tasks of a side-scan sonar (SSS) survey. Thus, SSS small target detection becomes fundamental work for SSS applications which holds vital importance for marine engineering, maritime military, and so on. However, existing methods cannot take the prior shadow information into consideration well, which would easily miss small targets. In this article, a novel SSS small target detection method considering shadow characteristics is proposed. First, we give a detailed analysis of the SSS imaging theory as well as the prior information about the characteristics of shadows. Then, considering the prior information of the SSS short-shadow, the second partial derivative of the Gaussian function is specifically introduced for the construction of a weighted item. After that, incorporating the weighted item with the $l_{21}$ -norm, $l_{1}$ -norm, and low-rank constraints on the noise, the target, as well as the background, respectively, a weighted sparse detection model is proposed. To further take the long-shadows into consideration, a long-shadow detection method and its corresponding target detection method are proposed. By combining the two detection results, we get the comprehensive detection result. Experiments based on SSS images in different scenarios proved the validity of the proposed method.

The traditional rule-based congestion control algorithms cannot set congestion window size flexibly, resulting in the inadaptation of the dynamic networks. This article presents a method to model end-to-end TCP congestion control problem using classification techniques. The network status parameters as the input and the type of network status as the output are defined through the analysis of some existing congestion control algorithms. NewReno, CUBIC, and Compound are used as feedback to produce the training data of the XGBoost classifier. The experimental results show that the classifier effectively shapes the strategies of three outstanding congestion control algorithms and almost achieves the same throughput, delay, and fairness. The proposed method makes the congestion control algorithm able to learn from data produced by network.

In this brief, a power amplifier (PA) with excellent integrated filtering characteristics is presented. The designed process is based on a novel impedance transformer (IT) consisting of cascaded coupled-line sections with stubs. The proposed IT generates four transmission zeros (TZs), which not only greatly improves the frequency selectivity, but also improves the second harmonic suppression performance, further enhancing the linearity of the PA. For demonstration, a bandpass filtering PA is designed, fabricated, and measured. The designed PA exhibits both good filtering bandpass response and power amplification. The rejection levels are larger than 59.7 and 69 dB for the lower and higher suppression bands. Meanwhile, the measured drain efficiency (DE) of the constructed PA is 58.5%-73% with a large-signal gain of 8.9-10.2 dB at 1.85-2.1 GHz. Besides, using a 20 MHz long-term evolution signal as the driving signal for the PA, the adjacent channel power ratio is lower than −57.8 dBc.

The singular value decomposition (SVD) based on the Hankel matrix is commonly used in signal processing and fault diagnosis. The noise reduction performance of SVD based on the Hankel matrix is affected by three factors: the reconstruction component(s), the structure of the Hankel matrix, and the point number of the analysis data. In this article, the three influencing factors are systematically studied, and a method based on correlated SVD (C-SVD) is proposed and successfully applied to bearing fault diagnosis. First, perform SVD analysis on the collected original signal. Then, the reconstructed component(s) determination method of SVD based on the combination of singular value ratio (SVR) and correlation coefficient is proposed. Then, based on the SVR, using the envelope kurtosis as the indicator, the optimal structure of the Hankel matrix (number of rows and columns) is studied. Then, the number of data points of the analysis signal is discussed, and the constraint range is given. Finally, the envelope power spectrum analysis is performed on the reconstructed signal to extract the fault features. The proposed C-SVD method is compared with the existing typical methods and applied to the simulated signal and the actual bearing fault signal, and its superiority is verified.

The use of side-scan sonar (SSS) images is limited by radiometric distortion, which is affected by factors such as angle response, beam pattern, and incident energy. Traditional methods have overlooked the impact of sediment-dependent angle response, degrading performance in complex SSS images. In this study, we propose a method for correcting radiometric distortion on SSS images based on the variational Retinex framework and sediment characteristics. First, we analyze the imaging theory of SSS and the angle responses of various sediments. We introduce a mixed Gaussian model to describe the feature of SSS backscatter strength (BS) distribution. After that, a radiometric distortion correction model, incorporating the sediment BS information constraint, low-rank constraint on the incident illumination component, and an anisotropic total variation (ATV) constraint on the albedo, is presented. BS information is obtained through sediment classification based on mixed Gaussian model optimization. A minimization optimization method is used to solve the model, and an SSS image with corrected radiometric distortion is obtained. Experiments with different SSS images demonstrate the effectiveness of the proposed method.

Vanadium diselenide (VSe2) exhibits versatile electronic and magnetic properties in the trigonal prismatic (H-) and octahedral (T-) phases. Compared to the metallic T-phase, the H-phase with a tunable semiconductor property is predicted to be a ferrovalley material with spontaneous valley polarization. Herein we report an epitaxial growth of the monolayer 2D VSe2on a mica substrate via the chemical vapor deposition (CVD) method by introducing salt in the precursor. Our first-principles calculations suggest that the monolayer H-phase VSe2with a large lateral size is thermodynamically favorable. The honeycomb-like structure and the broken symmetry are directly observed by spherical aberration-corrected scanning transmission electron microscopy (STEM) and confirmed by giant second harmonic generation (SHG) intensity. The p-type transport behavior is further evidenced by the temperature-dependent resistance and field-effect device study. The present work introduces a new phase-stable 2D transition metal dichalcogenide, opening the prospect of novel electronic and spintronics device design.

Sarcopenia is defined as an age‐related progressive loss of muscle mass and/or strength. Although different factors can contribute to this disease, the underlying mechanisms remain unclear. We assessed transcriptional heterogeneity in skeletal muscles from sarcopenic and control mice at single‐cell resolution. A mouse model was established to study sarcopenic skeletal muscles. Single‐cell RNA‐seq was performed on tibialis anterior (TA) muscle cells collected from sarcopenic and control mice. A series of bioinformatic analyses were carried out to identify and compare different cell types under different conditions. Immunofluorescence staining and western blotting were used to validate the findings from single‐cell experiments. Tube formation assays were conducted to further evaluate the effects of Gbp2 on endothelial cells during angiogenesis. A murine sarcopenia model was successfully established using a senescence‐accelerated mouse strain (SAMP6, n= 5). Sarcopenia phenotype was induced by administration of dexamethasone (20 mg/kg) and reduced physical activity. Senescence‐resistant mice strain (SAMR1) and SAMP6 strain with similar activity but injected with PBS were recruited as two control groups. As signs of sarcopenia, body weight, muscle cell counts and cross‐sectional fibre area were all significantly decreased in sarcopenic mice (P value = 0.004, 0.03 and 0.035, respectively). After quality control, 13 612 TA muscle single‐cell transcriptomes were retained for analysis. Fourteen cell clusters were identified from the profiled cells. Among them, two distinct endothelial subtypes were found to be dominant in the sarcopenia group (42.2% cells) and in the two control groups (59.1% and 47.9% cells), respectively. 191 differentially expressed genes were detected between the two endothelial subtypes. Sarcopenia‐specific endothelial cell subtype exhibited a dramatic increase in the interferon family genes and the interferon‐inducible guanylate‐binding protein (GBP) family gene expressions. For example, Igtpand Gbp2in sarcopenic endothelial cells were 5.4 and 13.3 times higher than those in the control groups, respectively. We further validated our findings in muscle specimens of sarcopenia patients and observed that GBP2 levels were increased in endothelial cells of a subset of patients (11 of 40 patients, 27.5%), and we identified significantly higher CD31 and GBP2 co‐localization (P value = 0.001128). Finally, we overexpressed Gbp2in human umbilical vein endothelial cells in vitro. The endothelial cells with elevated Gbp2expression displayed compromised tube formation. Our single‐cell‐based results suggested that endothelial cells may play critical roles in sarcopenia development through interferon‐GBP signalling pathways, highlighting new therapeutic directions to slow down or even reverse age‐related sarcopenia.