Search

In the recent advancements of recommendation systems, the integration of deep learning models has significantly enhanced prediction accuracy and user experience. This paper introduces a novel model called GRATB, which enhances the existing BERT4Rec framework by incorporating a self-attention mechanism based on time-mixing attention mechanism and dynamic head fusion. Additionally, it introduces a new ’comment tower’ to integrate user review information. By employing a hybrid approach, our model is able to incorporate both the interaction sequence between users and items, as well as sentiment-rich review data. This enables us to obtain a more comprehensive understanding of user preferences. Empirical evidence derived from extensive experimentation demonstrates that GRATB exhibits substantial performance improvements over existing state-of-the-art models across multiple evaluation metrics. GRATB achieves significant enhancements in two critical performance indicators: Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG), with average increases of 2.41% and 3.25%, respectively.

Via is an essential component in the design of an Electromagnetic Band Gap (EBG) structure. This paper investigates the effects of the via in a mushroom-like EBG structure and proposes an equivalent circuit model of the via. It is revealed that when the via in the mushroom-like structure is offset, the element reflection phase will vary within 720 degrees instead of 360 degrees phase range in a conventional design. This phenomenon can be explained by a new circuit model that introduces a mutual inductance, and the corresponding electromagnetic properties of mushroom-like EBG structure can be quantitatively analyzed by this model. In addition, the applicability and error analysis of the model are discussed in this paper. The theoretical modeling and analysis enable an efficient and in-depth exploration of the via functions in similar EBG structures, and also provide more theoretical guidance and assistance for the design of reflection and transmission units based on EBG structure.

In high-dimensional scenarios, path planning is a challenging and computationally complex optimization task that requires finding optimal paths within complex domains. Metaheuristic (MH) algorithms offer a practical approach to addressing this issue. The Dung Beetle Optimizer (DBO), categorized as a MH algorithm, takes inspiration from the biological behaviors exhibited by dung beetles. However, DBO exhibits limitations, including inadequate global search capabilities and a tendency to converge on local optima. To address these challenges, this paper proposes a multi-strategy Improved Dung Beetle Optimization algorithm (IDBO) for UAV 3D path planning. Initially, cubic chaos mapping is applied for population initialization, enhancing diversity. Subsequently, a novel global exploration strategy replaces the DBO’s original rolling phase, improving information exchange and minimizing parameter dependence. Third, an adaptive t-distribution is introduced to adjust dung beetle positions, balancing exploration and exploitation. Finally, an enhanced population update strategy is proposed, utilizing varied behavioral logic at different algorithm stages to improve solution quality and search efficiency. Additionally, performance comparisons with six advanced algorithms on the CEC2017 test suite, and the validation of IDBO’s effectiveness via the Wilcoxon rank-sum and Friedman mean rank test. Meanwhile, in UAV 3D path planning experiment, IDBO achieves the best cost index, which is 1.34% higher than the best cost of original DBO, and is also significantly better than the most advanced algorithms such as WOA, GSA, HHO, COA, and the standard deviation is reduced by 99.93% compared with DBO algorithm, which proves the effectiveness and robustness of IDBO in UAV 3D path planning.

Regional surface deformation resulting from the development and utilization of underground space resources poses a significant threat to the safety of urban areas, and the combination of Synthetic Aperture Radar and Gravity Recovery and Climate Experiment (GRACE) satellite data has become a new means to study the impact of underground space evolution on surface deformation. We combine the Interferometric Synthetic Aperture Radar (InSAR) technology and gravity satellite data to extract information on regional surface deformation and groundwater storage changes in Shanxi Province, to explore the patterns of their temporal and spatial variations, to discover their links with seasonal climate change, to re-conceptualize the laws of the regional water cycle, and to quantify the contribution of multiple fields to the evolution of the surface. Furthermore, we propose a novel multi-source neural network prediction model (LSTM/BP) based on signal decomposition (VMD) and algorithm optimization to handle the complex time series characteristics of groundwater storage. Our findings reveal that groundwater storage in Shanxi Province has been consistently declining, with a monthly deficit rate of approximately 1.05 mm. Additionally, there is a notable spatial variation in the annual rate of change, ranging from −21 to 4 mm/year from north to south. Furthermore, we observe a close relationship between inter-annual and seasonal groundwater storage changes and local rainfall patterns, and we find that regional surface deformation is influenced by these groundwater storage changes. The new prediction model outperforms other models, with a root mean square error of 1.56 mm and a correlation coefficient of more than 0.98 on the test set. The model improves the prediction accuracy of the groundwater reserves in the basin, and it can be used to provide a reference for the comprehensive management of the groundwater in Shanxi Province, the rational development of mineral resources, and other major national needs.

In short-term load forecasting, deep learning models with recurrent units are widely used. For Long Short-term Memory (LSTM) models, in terms of the input features at one particular time-step, there is a weight series for each input feature. Hence, an input feature with a larger value of weight can be regarded as more important to the final forecasting result. Since the weights of the features are time-invariant, the model considers the input features as equally important at each time step, thus lack of the capability of reflecting the importance fluctuation through the time span. To tackle this issue, this paper proposes a forecasting scheme, which integrates mutual information (MI) into bi-directional long short-term memory (BILSTM) network. The MI method is used to extract the importance value of input features at different time-steps, and constitute the fluctuation matrix of the importance values for input features, which is used as coefficients to correct the original input feature. The corrected features are substituted into the BILSTM network, which further improves the forecasting accuracy. Numerical experiments have been carried out based on real-world load data. The results demonstrate the superior performance of the proposed scheme compared with a series of state-of-the-art methods and thus indicate the importance and effectiveness of capturing the fluctuation of the importance value.

Sketch-based image retrieval (SBIR) utilizes sketches to search for images containing similar objects or scenes. Due to the proliferation of touch-screen devices, sketching has become more accessible and therefore has received increasing attention. Deep learning has emerged as a potential tool for SBIR, allowing models to automatically extract image features and learn from large amounts of data. To the best of our knowledge, there is currently no systematic literature review (SLR) of SBIR with deep learning. Therefore, the aim of this review is to incorporate related works into a systematic study, highlighting the main contributions of individual researchers over the years, with a focus on past, present and future trends. To achieve the purpose of this study, 90 studies from 2016 to June 2023 in 4 databases were collected and analyzed using the Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) framework. The specific models, datasets, evaluation metrics, and applications of deep learning in SBIR are discussed in detail. This study found that Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN) are the most widely used deep learning methods for SBIR. A commonly used dataset is Sketchy, especially in the latest Zero-shot sketch-based image retrieval (ZS-SBIR) task. The results show that Mean Average Precision (mAP) is the most commonly used metric for quantitative evaluation of SBIR. Finally, we provide some future directions and guidance for researchers based on the results of this review.

In this article, a variance-constrained $H_{\infty }$ state estimation issue is dealt with for a type of nonlinear time-varying complex networks affected by dynamical bias under binary encoding schemes (BESs). The BESs are used during signal transmission in view of the security of binary bit strings. The stochastic bias is involved using a dynamical equation, and stochastic nonlinearity is characterized by statistical property. The purpose of this article is to construct a finite-horizon state estimator, such that the estimation error dynamics satisfies performance requirements of both the prescribed upper bound constraint on the error variance and the $H_{\infty }$ noise rejection. By employing the matrix inequality approach and random analysis, sufficient conditions are established for the presence of the state estimator. Subsequently, the gain parameters of the constructed estimator are acquired by solving some recursive matrix inequalities. Ultimately, the correctness of the developed estimation algorithm is testified via a numerical simulation example.

This paper focuses on the secure path tracking control of wireless self-driving vehicles (SDVs). To address the challenges of network security and limited network bandwidth in the design of wireless SDVs, a co-modeling approach considering denial-of-service (DoS) attack and event trigger mechanism (ETM) is introduced for path tracking control of SDVs. To achieve a high level of tracking control performance, the threshold of the proposed adaptive ETM is designed to adjust dynamically based on the state information of the SDVs, resulting in better tracking performance. Additionally, a novel distributed control strategy is developed for SDVs using a leader-following approach, and the parameters of the distributed controllers and adaptive ETMs are obtained to meet the path tracking performance requirements and ensure effective communication through the use of Lyapunov stability theory and linear matrix inequality (LMI) techniques. The proposed method is verified through a numerical simulation of SDVs subjected to DoS attacks, demonstrating its effectiveness.

With the rapid increase in demand for fresh products, cold chain logistics has become an important mode of transportation. Logistics enterprises are faced with the problem of cost control and improving of customer satisfaction. In light of this, we present a bi-objective optimization vehicle routing problem model in cold chain logistics, which aims to reduce the total costs and improve customer satisfaction. To solve the intricate model, we propose a hybrid algorithm called the Simulated Annealing Non-dominated Sorting Genetic Algorithm II (SA-NSGA-II) algorithm, which amalgamates the simulated annealing algorithm with the NSGA-II algorithm, enabling efficient resolution of the bi-objective problem. Extensive numerical experiments validate the effectiveness of the proposed model and algorithm by exhibiting solutions with lower costs and higher satisfaction levels. Furthermore, we conduct a sensitivity analysis to explore the impact of vehicle speed on both costs and satisfaction, shedding light on the trade-offs between various optimization objectives.

Line break faults commonly occur in distribution networks and pose the risk of electric shocks to nearby individuals and animals. This study aims to address the challenge of identifying the direction of a line break fault. Specifically, we develop a model for a single-phase line break fault in a small current grounding system and focus on analyzing the steady-state voltage changes on both sides of the fault point. The voltage characteristics of the ungrounded system and the resonant grounding system are compared and summarized. Based on these characteristics, a more reliable method is proposed to identify the single-phase line break fault direction by utilizing two types of local voltage information: the magnitude of the line-to-line voltage and the sequence of phase-to-earth voltage. Additionally, we analyze the effects of V/V wired potential transformer (PT) and distributed generation (DG). The proposed method can accommodate the high utilization rate of V/V wired PT in distribution networks and its practicality is unaffected by the connection of DG to the distribution network. The above analysis is verified through simulations. The findings of this study demonstrate that the direction of a single-phase line break fault can be reliably detected using local voltage information and can be further localized with the assistance of communication, thereby improving the level of relay protection in distribution networks.

The microgrid under VSG control is conducive to the security and stability of the microgrid system. However, it still belongs to the primary regulation of frequency, and the microgrid in islanding mode has the problem that the frequency cannot be stabilised at the rated value after the load change. To address this problem, in order to eliminate the steady state error caused by the primary frequency regulation structure of the traditional VSG control technique and keep the load-induced frequency offset near the rated value, this paper proposes a fractional-order self-resilient-based secondary frequency regulation control strategy. Firstly, a three-phase circuit topology based on VSG is established, and the mechanism of primary frequency regulation is analysed with it as the research object. Then, the proposed fractional-order self-resilient control algorithm is applied to the rotor equations of the active frequency regulation characteristics of the VSG, so as to achieve the quadratic non-differential regulation of the frequency, and to eliminate the frequency error caused by frequency fluctuation of the virtual synchronous generator in the islanding mode. Finally, for the case of sudden load change, the VSG-based islanded microgrid model is constructed in Matlab/Simulink and compared with other control strategies, which verifies the effectiveness of the control strategy proposed in this paper. The control strategy in this paper can effectively eliminate the steady state error caused by the primary frequency modulation and improve the response speed.

Beyond 5G (B5G) networks rapidly growing to connect billions of Internet of Things (IoT) devices and the dense deployment of IoT devices leads the large-scale network conflict and obstacles the resource-efficient, which brings a great challenge for network resource management (NRM). To tackle this problem, hypergraph based resource-efficient collaborative reinforcement learning (CRL) was proposed for B5G massive IoT. Firstly, the hypergraph theory based network conflict model was formulated to quantify the conflict degree of the B5G massive IoT. Then, since the conflict-free resource management problem is a combinatorial optimization problem with NP-hard, the resource management based Markov decision process (MDP) model was built for NRM in B5G massive IoT. To reduce the computational load by distributing the training overhead throughout the entire B5G massive IoT and achieve distributed collaborative learning, the federated averaging advantage Actor-Critic (FedAvg-A2C) based resource management is proposed to handle the network conflict-free resource management problem and accelerate the training process. Simulation results show the proposed scheme has high network throughput and the resource-efficient in B5G massive IoT.

Oceanic eddies are ubiquitous phenomena carrying large amounts of energy, thus of great importance for marine ecology and sea–air exchange. As an all-weather, high-resolution sensor, synthetic aperture radar (SAR) could provide valuable observations for oceanic eddies. However, there are few well-established methods for eddy detection on SAR images except for manual seeking, which is laborious and time-consuming. In combination with deep learning, this study is among the earliest in the literature that attempts end-to-end eddy detection on SAR images. Due to obscure pictures and indistinct eddy boundaries, ordinary deep learning models are not adaptable to the objective. Therefore, an customized model, stacked attention network (SANet), is designed to recognize the unique eddy pattern presented on radar images automatically. SANet is a two-unit stacking architecture, with each an hourglass structure for bottom–up, top–down reference and the overall stacking network for iterative extractions of eddy textures contained in shallow layers of each unit. Besides, SANet has included the inner-hourglass attention gates and the outer-hourglass GCblock for the extracted features to be more concentrated on the interested areas. Using SANet, we have identified 87.75% of eddies in the constructed dataset collected from ESA-2 and ENVISAT SAR products. The result is much better than the no-stacking counterpart U-net, as well as state-of-the-art deep learning models DeepLabV3+ and SegFomer, thus verifying the superiority of the proposed method. The generalization ability of the algorithm has also been tested. The code and the constructed SAR dataset have been made public for broader use.

In order to establish a photovoltaic(PV) grid-connected system model that is suitable for studying faults in medium-voltage distribution networks, it is advisable to conduct linearized and simplified equivalent research on each component of the PV grid-connected system according to specific fault scenarios. The primary focus should be on linearizing and simplifying the modeling research of the PV array, which serves as the energy supply link. The impact of medium voltage distribution network faults on the PV array output is analyzed, and the maximum power point(MPP), short circuit current point, and open circuit voltage point are identified as key parameters. The output equation of the non-ideal PV array is used to derive the equivalent formula for these parameters. By statistically analyzing the equivalent curve under different PV parameters, a linear relationship is established between the intersection point of the linear equivalent curve and the voltage and current of the MPP, based on statistical analysis of the equivalent curve under different PV parameters. Based on this relationship, a simplified calculation method for the equivalent curve parameters is proposed. Finally, the limitations of traditional equivalent methods are analyzed using examples, simulations and RTDS experiment, and the accuracy of the proposed calculation method is validated. Compared to existing modeling methods, the proposed method is specifically designed for medium-voltage fault scenarios. While ensuring the simulation output, it greatly simplifies the PV array model and its parameter calculation method, reduces the difficulty and calculation of theoretical and simulation research, laying the foundation for further simplifying the PV grid-connected system model.

Researchers typically leverage side information, such as social networks or the knowledge graph, to overcome the sparsity and cold start problem in collaborative filtering. To tackle the limitations of existing user interest modeling, we propose a knowledge-enhanced user multi-interest modeling for recommender systems (KEMIM). First, we utilize the user-item historical interaction as the knowledge graph’s head entity to create a user’s explicit interests and leverage the relationship path to expand the user’s potential interests through connections in the knowledge graph. Second, considering the diversity of a user’s interests, we adopt an attention mechanism to learn the user’s attention to each historical interaction and each potential interest. Third, we combine the user’s attribute features with interests to solve the cold start problem effectively. With the knowledge graph’s structural data, KEMIM could describe the features of users at a fine granularity and provide explainable recommendation results to users. In this study, we conduct an in-depth empirical evaluation across three open datasets for two different recommendation tasks: Click-Through rate (CTR) prediction and Top-K recommendation. The experimental findings demonstrate that KEMIM outperforms several state-of-the-art baselines.

A thorough analysis of the system model for complex-valued optical double-sideband (DSB) transmission with carrier-assisted differential detection (CADD) receiver under the influence of laser phase noise and fiber chromatic dispersion (CD) is presented. It is shown that the interaction of laser phase noise and CD leads to the phenomenon of phase-to-amplitude (P2A) noise and equalization-enhanced phase noise (EEPN). The achievable performance of the complex-valued optical DSB transmission with CADD receiver under the influence of EEPN and P2A noise is estimated by a closed-form expression, and it is verified by simulation that the results show an inaccuracy of less than 1 dB for a wide range of system parameters. In addition, in order to mitigate the EEPN and P2A noise, we propose a pre-decision aid-based simplified blind phase search (BPS) algorithm, commonly referred to as PDA-BPS algorithm. The PDA-BPS algorithm allows for reduced complexity by decreasing the number of symbols entering the BPS algorithm. Theoretical derivation and simulation verification illustrate that the PDA-BPS algorithm can achieve similar mitigation performance to the BPS algorithm with lower complexity. Specifically, under the condition that classification decision threshold $R$ is equal to 0.25, the complexity can be reduced by 40%/16.6% with 1 MHz/7 MHz linewidth for 16-QAM and 29%/10.9% with 0.5 MHz/3 MHz linewidth for 64-QAM.

Insomnia is a common public health problem and an open biomedical research topic. Insomnia results in various health problems, including memory decline, decreases concentration and weakens problem-solving ability. The insufficient sleep also leads to skin ageing, heart disease, high blood pressure, arrhythmia and stroke. While it remains as a global health concern, sleep quality improvement using modern technologies, such as machine learning, classification technologies, virtual reality (VR), becomes an open and hot research problem. These modern technologies offer new curing solutions under certain conditions. In this paper, we present a sleeping-aid system with a single-channel electroencephalogram (EEG) sleep stage classification algorithm to improve the sleep quality. The sleeping-aid system promotes machine learning integrated VR and multimedia technology for sleep improvement. Ninety participants were invited to test on three different systems with 3D VR, 2D video, and music only. An adequate stimulus of audio-vision can be a complement of the drug treatment. The experimental results showed that the proposed method demonstrated superior performance over existing methods.

Localizing and interpreting human actions in videos require understanding the spatial and temporal context of the scenes. Aside from accurate detection, vast sensing scenarios in the real-world also mandate incremental, instantaneous processing of scenes under restricted computational budgets. However, state-of-the-art detectors fail to meet the above criteria. The main challenge lies in their heavy architectural designs and detection pipelines to reason pertinent spatiotemporal information, such as incorporating 3D Convolutoinal Neural Networks (CNN) or extracting optical flow. With this insight, we propose a lightweight action tubelet detector coined TEDdet which unifies complementary feature aggregation and motion modeling modules. Specifically, our Temporal Feature Exchange module induces feature interaction by adaptively aggregating 2D CNN features over successive frames. To address actors’ location shift in the sequence, our Temporal Feature Difference module accumulates approximated pair-wise motion among target frames as trajectory cues. These modules can be easily integrated with an existing anchor-free detector to cooperatively model action instances’ categories, sizes, and movement for precise tubelet generation. TEDdet exploits larger temporal strides to efficiently infer actions in a coarse-to-fine and online manner. Without relying on 3D CNN or optical flow models, our detector demonstrates competitive accuracy at an unprecedented speed (89 FPS) that is more compliant with realistic applications. Codes will be available at https://github.com/alphadadajuju/TEDdet.

BPMN process models have been widely used in software designs. The BPMN process models are characterized by a static graph-oriented modeling language and a lack of analytical capabilities as well as dynamic behavior verification capabilities, which not only leads to inconsistencies in the semantics of the BPMN process models, but also leads to a lack of model error detection capabilities for the BPMN process models, which also hinders the correctness verification and error correction efforts of the models. In this study, we propose an executable modeling approach for CPN-based data flow well-structured BPMN (dw-BPMN) process models, and consider both control-flow and data-flow perspectives. First, we present a formal definition of the dw-BPMN process model, which is formally mapped into a CPN executable model in three steps: splitting, mapping and combining. Then, we discuss four types of data flow errors that can occur in the model: missing, lost, redundant, and inconsistent data error. To detect these four data flow errors, we propose a detection method based on the execution results of the CPN model. Subsequently, we propose correction strategies for these four data flow errors. Finally, a dw-BPMN process model of a robot’s temperature detection system for COVID-19 prevention and control in a kindergarten was used as an example to verify the validity of the method.

Bird sounds recognition is of great significance in bird protection. With appropriate sound classification, research can automatically predict the quality of life in the area. Nowadays, the deep learning model is used to classify bird sound data with high classification accuracy. However, the generalization ability of most existing bird sound recognition models is poor, and the complicated algorithm is applied to extract bird sound features. To address these problems, a large data set containing 264 kinds of birds is constructed in this paper to enhance the generalization ability of the model, and then a lightweight bird sound recognition model is proposed to build a lightweight feature extraction and recognition network with MobileNetV3 as the backbone. By adjusting the depthwise separable convolution in the model, the recognition ability of the model is improved. A multi-scale feature fusion structure is designed, and the Pyramid Split Attention (PSA) module is added to the multi-scale feature fusion structure to improve the adaptability of the network to scale extraction of spatial information and channel information. To improve the refinement ability of the model towards the global information, the channel attention mechanism and ordinary convolution are introduced into Bneck module which makes the Bneck module become the Bnecks module. The experimental results show that the accuracy of Top-1 and Top-5 of the model in identifying 264 kinds of birds on the self-built data set is 95.12% and 100%, which are higher than that of MobileNetV1, MobileNetV2, MobileNetV3 respectively. Although the accuracy is lower than ResNet50, the number of parameters and floating-point operations (FLOPs) of the model is only 2.6M and 127M respectively. The accuracy is only reduced by 2.25% while saving costs.

This paper proposes a novel asymmetrical permanent magnet assisted synchronous reluctance machine (APMA-SynRM) with high cost performance, namely it has the advantages of high torque performance and low cost. This machine has an asymmetrical rotor configuration featured by low-cost ferrite and expensive NdFeB, and two kinds of material are placed asymmetrically on both sides of the “U”-shaped barriers, which causes the magnet-axis-shift (MAS) effect. Consequently, the proposed APMA-SynRM improves the utilization of the reluctance torque and permanent magnet torque. The influences of permanent magnet volume ratio and hybrid permanent magnet on torque performance are further investigated, and the optimal topologies are designed through a multi-objective genetic algorithm. Moreover, the machine performance of APMA-SynRM is analyzed and compared with that of the conventional permanent magnet assisted synchronous reluctance machine (PMA-SynRM), which confirms that the proposed APMA-SynRM can reduce the cost of permanent magnets but still achieve similar torque and wider constant power speed range performance.

This paper addresses a security control issue of connected vehicle systems subject to denial-of-service (DoS) attacks. To deal with the bandwidth constraint, a novel dynamic event-triggered mechanism (DETM) is proposed. Compared with static ETMs, attack intensity is introduced into the design of triggering parameters, which strikes a better balance between the data releasing amount and system performance. To withstand the negative impact of DoS attacks, an extended tracking error model is constructed, which integrates a modified bidirectional information topology, intermittent DoS attacks, DETM into a unified scheme. By using a piecewise Lyapunov function, a co-design method of controllers and communication parameters is developed. Different from string stability or asymptotic stability analysis methods, finite-time boundedness of the concerned system is investigated to provide an evaluation of system performance with respect to time. Finally, simulation results verify the effectiveness of the proposed methods.

In this paper, a 94 GHz dual-polarization high-isolation cassegrain antenna feed by a diagonal horn antenna is designed. The antenna consists of a D = 540 mm main reflector, sub-reflector, and dual-port dual-polarization diagonal horn feed antenna. To obtain similar feed horn E-H radiation patterns, gain, high polarization, and port isolation, a dual-port diagonal horn was designed in the feed. The measured antenna gains are 50.85 dBi and the side-lobe levels are −24.5 dB at E-H radiation patterns of two ports at 94 GHz, respectively. The VSWRs of port 1 and port 2 are less than 1.5:1 in the range 93.2–95.3 GHz, which meets the working requirements of frequency modulated continuous wave and pulse cloud radars. And the isolation between the two ports is above −50 dB, whereas the polarization isolation of each port is above 40 dB. The proposed W-band antenna is a suitable candidate for the dual-polarization cloud radars.

The collaborative mission capability of multi-UAV has received more and more attention in recent years as the research on multi-UAV theories and applications has intensified. The artificial intelligence technology integrated into the multi-UAV collaborative decision-making system can effectively improve the collaborative mission capability of multi-UAV. We propose a multi-agent reinforcement learning algorithm for multi-UAV collaborative decision-making. Our approach is based on the actor-critic algorithm, where each UAV is treated as an actor that collects data decentralized in the environment. A centralized critic provides evaluation information for each training step during the centralized training of these actors. We introduce a gate recurrent unit in the actor to enable the UAV to make reasonable decisions concerning historical decision information. Moreover, we use an attention mechanism to design the centralized critic, which can achieve better learning in a complex environment. Finally, the algorithm is trained and experimented in a multi-UAV air combat scenario developed in the collaborative decision-making environment. The experimental results show that our approach can learn collaborative decision-making strategies with excellent performance, while convergence performance is better compared to other algorithms.

Aiming at improving the torque density of the motor and the utilization rate of permanent magnets (PMs), a dual rotor consequent-pole vernier motor (DRCPVM) is proposed in this article. The stator of the motor has a double-sided structure with two sets of independent windings on each side. Therefore, the proposed motor has different working modes according to the on/off state of the two sets of windings. In the design process, DRCPVM is used as a basic model and optimization is performed on it. The optimization includes the slot width and height of the stator teeth and the radian ratio occupied by the PMs. Moreover, the Halbach array is introduced into the consequent-pole structure to establish the dual rotor consequent-pole vernier motor with Halbach array (DRCPVM-HA). Halbach array reduces flux leakage and improves the magnetic circuit. And Halbach array is employed to discuss the design of the magnetization angle. The rule of the electromagnetic performance changing with the magnetization angle is studied to find the optimal magnetization angle in the Halbach array. When the magnetization angle is 45° in DRCPVM-HA, the torque is significantly improved, the torque ripple is reduced, and the utilization rate of PMs is improved.

In the field of human-machine interaction, gesture recognition using sparse multichannel surface electromyography (sEMG) remains a challenge. Based on the Hilbert filling curve, a dual-view multi-scale convolutional neural network (DVMSCNN) is designed to enhance gesture recognition performance in this paper. The network consists of two parts. In the first part, sEMG is filled using Hilbert filling curve, and the obtained images in the time and electrode domain are used as inputs to the block. In the second part, the depth features learned by block are fused and classified by a “layer fusion” based view aggregation network. The evaluation of the architecture in the four databases of Ninapro-DB1, DB2, DB3 and DB4 shows that DVMSCNN is more than 7% more accurate than other state-of-the-art methods. When validated using a home-grown dataset, DVMSCNN was able to achieve a recognition rate of 0.8848.

A low-profile transmissive metasurface is proposed to synthesize contour beam pattern for a European region. A slot array feed is used to illuminate same size metasurface aperture with a plane wave at a near field distance of 24 mm. A two step optimization process is proposed to solve asymmetric and complicated pattern synthesis problem for transformation of plane wave to contour beam pattern using modified Alternating Projection Method (APM). A new subwavelength 4-arm spiral element is proposed to achieve desired performance for contour beam pattern synthesis in $Ku$ band centered at 12.5 GHz. A prototype of low profile transmissive metasurface is also fabricated and measured to verify its gain and bandwidth performance for contour beam pattern synthesis for the European region.

State-of-health (SOH) assessment for aero-engine can effectively reduce maintenance cost and operational risk, and is also a significant part of the prognostics and health management (PHM) system. However, the current SOH assessment is usually closely coordinated with other parts of PHM to achieve specific functions. This is not conducive to generalizing the function of SOH assessment. Therefore, this paper proposes a data-driven framework of SOH assessment that mainly includes data preprocessing, pseudo label generation, weight assignment and feature selection, and assessment, which enhances the systematicness of SOH assessment. A combination model based on density-distance clustering and fuzzy Bayesian risk models is designed to generate a pseudo label, select optimal parameter subset, and assign weight. Then, two assessment indicators including state membership degree and health degree are produced based on two fuzzy models for horizontal and vertical comparisons. These two indicators expand the dimensions and perspectives of SOH measurement, which can more comprehensively characterize the health state of the engine. Finally, the correctness and effectiveness of the proposed methodology are verified by the widely used Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) dataset.

In view of the difficulties in optimal dispatch caused by diverse energy and various types of equipment in the regional integrated energy system(RIES), this paper established a generalized energy storage model by extracting the flexibility characteristics of cooling, heat, and electrical load based on abstract equivalence. Instead of reducing the accuracy of regulation, this modeling method can greatly simplify the information interaction between the energy dispatching center and energy consumers, thus cutting down the time of collaborative analysis calculations. With the scheduling characteristics of multiple types of flexible loads in day-ahead and intra-day time scales considered comprehensively, a multi-time-scale optimization scheduling model of RIES is established, which takes into account the economy of system operation and the demand response. The simulation results show that the proposed optimization model can fully tap the load-side scheduling potential, along with effectively reducing the computational complexity. Through the coordination of resources with different characteristics, the pressure of balancing energy supply and demand can be relieved, and the operating cost of the system can be minimized.

In this study, a high-performance orbital angular momentum (OAM) beam is designed, analyzed and experimented using a 1-bit programmable metasurface. OAM as a novel technology is investigated systematically in this paper. Moreover, this study is motivated by the application requirements of real-time controllable communication. The proposed programmable metasurface comprises 1-bit phase modulation units with only two phase states, which is evolved from an electromagnetic surface composed of 360° continuous phase units based on the principle of 1-bit phase quantization. First, the necessity and feasibility of developing the OAM beam based on 1-bit programmable metasurface are studied. Then, qualitative analysis of OAM beams is conducted on different OAM modes and phase modulation elements. Next, the quantitative indexes of OAM beams such as the peak gain in far-field, the divergence angle of main lobe, and circumferential symmetry in azimuth planes are systematically analyzed through a survey of key factors. It is noteworthy that this analysis provides a powerful research basis to achieve an excellent OAM beam with the adjustable function. Thereafter, an active reflective programmable metasurface with 48×48 elements is fabricated to verify the feasibility of developing an OAM beam using a 1-bit element. The experimental and simulation results are in good agreement. Furthermore, a high gain OAM beam with a narrow divergence angle is realized by using the large-scale 1-bit programmable metasurface. Notably, a high-gain beam and an OAM beam can be both generated and can converted into each other, which lays the foundation to achieve the OAM beam with the function of real time dynamic control in future.

The dynamic properties of one kind of Inter-Connected Hydro-Pneumatic Struts (IC HPS), which is designed based on the developed double-gas-chamber compacted Hydro-Pneumatic Struts (HPS) integrating double inner gas chambers, will be investigated in this research. Comparing with the traditional IC HPS designs based on single gas chamber compacted HPS, the proposed IC HPS can postpone the force distortion, and then increase the working envelop, provide good stiffness performance and be stable in both In-Phase and Out-of-Phase working condition. The equation of motion of the proposed IC HPS will be derived firstly. And then based on the established dynamic model, the related simulating model will be established utilizing the AMEsim software, and the validity of the established simulating model will be verified on the basis of experimental data and available literatures. The validity and performance of the proposed IC HPS will be verified and investigated through comprehensive comparison with traditional IC HPS designs. Finally, the detailed sensitivity analysis of the essential design parameter of the proposed IC HPS will be presented to illustrate the advantage of the proposed IC HPS design.

Object detection in remote sensing images is challenging due to the dense distribution and arbitrary angle of the objects. It is a consensus that the oriented bounding box (OBB) is more suitable to represent the aerial objects. However, there are some extreme cases in regression-based OBB detection that make the regression target discontinuous, resulting in the poor performance. In this article, an analysis of the formats of OBB and the problems in its regression is presented, following with an exploration of transform localization from regression to keypoint estimation, which could be applied to avoid the problem of discontinuous regression target. Our novel method is called Object-wise Point-guided Localization Detector (OPLD). Continuously, a new prediction of center-point is introduced to refine the results, as the truncation problem caused by the cut graph. Lastly, in order to figure the problem of inconsistency between the localization quality and the classification score, both the endpoint scores and the classification score are adopted weighting as a result score. Experimental results are based on two widely used datasets, i.e., DOTA and HRSC2016. OPLD achieve 76.43% mAP and 78.35% mAP in OBB and horizontal bounding boxes tasks of DOTA-v1.0, which achieves state-of-the-art performance, respectively. Project page at https://github.com/yf19970118/OPLD-Pytorch.

In grid-tied power converters, the grid parameters such as the frequency, phase angle of the fundamental component, and the harmonics are essential to the control of power converters, the fast and accurate estimation of the grid parameters is a challenge especially for high-order harmonics. This paper proposes a one-step-prediction (OSP) discrete observer (OSPDO) to observe the fundamental and harmonic sequence components of the grid voltage. Based on the proposed OSPDO, a frequency locked loop (FLL) is designed. The proposed OSPDO-FLL has a good robustness to sampling frequency on dynamic response and high precision for frequency estimation. The proposed algorithm can estimate up to maximum 50th harmonic with a low sampling frequency thanks to the robust properties. Finally, the good characteristics of the proposed synchronization algorithm are verified by simulations and laboratory experiments.

This article noticed that the feature of the block in human body image is noticeable, some algorithms in pedestrian re-identification are based on partitioning the human body to calculate the similarity between pedestrians images. However, it is not easy to find a proper method to partition the pedestrian image. This article proposes a method partition adaptive network structure (PANS) to automatically determine the partition scheme. This method can save much work to find a suitable partitioning scheme, and the effect of the automatic partitioning scheme is better than that of the manual partitioning scheme. In addition, this paper proposes a pedestrian re-recognition method based on channel partition weight adaptive (CPWA). We obtained better results on three public pedestrian re-identification data sets compared with the baseline. This method, combined with the automatic partitioning scheme proposed in this article, can improve results. We have done experiments on the three public data sets of market-1501, DukeMTMC-Reid, and CUHK03, proving the superiority of the two methods proposed in this article.

NDN (Named Data Networking) is one of the most popular future network architecture, a “clean slate” design for replacing the traditional TCP/IP network. However, the lookup algorithm of FIB entry in NDN is the bottleneck of the current NDN. Owing to the unique identifier of content name, whose length is variable, the size of FIB entries is proliferating, and the effectiveness of lookup algorithms is low. This paper proposed an entropy-oriented name processing mechanism, compressing the content names effectively by bringing in an encoding scheme. This mechanism can be split into two parts: name compression and lookup. The first part compressed the content names and converted them into a kind of code with a smaller size by considering the information redundancies of content names; the second part built a compact structure to minimize the memory footprint of FIB entries with keeping the high lookup performance. This mechanism outperformed many traditional name lookup algorithms, had better flexibility and cost less memory footprint.

Information-Centric Networking (ICN) has drawn considerable attention as a new network architecture recently. However, the lack of experimental environments brings about the inconvenience of evolving ICN. As forwarding devices need to be updated once the protocols evolve, researchers spend a large amount of time developing forwarding engines rather than improving protocols. In this paper, we propose a flexible forwarding system called Content-oriented Experimental Forwarding System (CEFS) for experiments in ICN, aiming at alleviating the inconvenience of evolving ICN protocols. Combined with Software Defined Networking, CEFS uses southbound messages to manage the protocol, routing, and content in the forwarding system. Moreover, we design a generic packet processing module to forward ICN packets in CEFS, using Open vSwitch as the basis to implement it and verifying its feasibility. Evaluation data show that CEFS is better than Named Data Networking Forwarding Daemon and Protocol-Independent Packet Processors behavioral-model. The applications show that researchers can use simple messages to manage the protocol, routing, and content of ICN without updating the forwarding system, which significantly improves the efficiency of evolving ICN protocols.

In this study, a target tracking algorithm based on the flower pollination algorithm (FPA) is proposed. This method solves the problem of robust visual target tracking in different complex tracking scenes with the good global and local optimisation ability of the FPA. Meanwhile, with the aim of solving the problem of invalid background feature interference and the loss of effective features caused by the fixed scale of tracking frame in traditional tracking methods, a scale adaptive adjustment model of tracking frame is proposed. Considering that the FPA has good global and local optimization ability at simultaneously, the position update equation of the FPA is introduced as the main optimization method of target tracking. In addition, considering that the traditional FPA is similar to classical swarm intelligence algorithm (such as the particle swarm optimization algorithm), it also faces the problems of a high probability of falling into local extrema, a low efficiency of late convergence speed and a high probability of early maturity. Therefore, this work proposes the GTFPA, an advanced FPA based on the gravitational search algorithm (GSA) and mutation mechanism via a trigonometric function. We qualitatively, quantitatively and statistically compare the proposed method with other classical general tracking methods through two datasets, OTB2015 and VOT2018, which contain hundreds of video sequences and more than ten tracking scenes and can effectively test the success rate, accuracy and stability of the trackers. The results of a large number of tracking experiments in a variety of complex tracking scenarios prove that the proposed GTFPA tracker performs well with regards to efficiency, accuracy and robustness.

In SDN architecture, the control channel between the control and data planes is extremely significant, which has two connection modes: out-of-band mode and in-band mode. For in-band mode, the key to the establishment of SDN control channel is how to forward in-band control traffic in the data plane (control traffic: traffic between controllers and switches). In almost all the existing implementation of the in-band SDN networks, the forwarding of in-band control traffic in the data plane depends on distributed Layer 2 switching that cannot respond to the network state change immediately. In this article, we propose a Centralized Trust-based In-Band (CTIB) control mechanism for SDN in-band control channel. Then based on CTIB control mechanism, we design CTIB routing algorithm to select the most trusted control path for each data plane switch in order to improve the QoS (Quality of Service) of in-band control traffic. Furthermore, we implement CTIB control mechanism in an in-band SDN network and carry out several experiments to test the QoS of the in-band control traffic. The results indicate that there is a huge improvement of in-band control traffic QoS when using CTIB control mechanism compared to the distributed Layer 2 switching.

In order to improve network performance, including reducing computation delay, transmission delay and bandwidth consumption, edge computing and caching technologies are introduced to the fifth-generation wireless network (5G). However, the volume of edge resources is limited, while the number and complexity of tasks in the network are increasing sharply. Therefore, how to provide the most efficient service for network users with limited resources is an urgent problem to be solved. Thus, improving the utilization rate of communication, computing and caching resources in the network is an important issue. The diversification of network resources brings difficulties to network management. The joint resource allocation problem is difficult to be solved by traditional approaches. With the development of Artificial Intelligence (AI) technology, these AI algorithms have been applied to joint resource allocation problems to solve complex decision-making problems. In this paper, we first summarize the AI-based joint resources allocation schemes. Then, an AI-assisted intelligent wireless network architecture is proposed. Finally, based on the proposed architecture, we use deep Q-network (DQN) algorithm to figure out the complex and high-dimensional joint resource allocation problem. Simulation results show that the algorithm has good convergence characteristics, proposed architecture and the joint resource allocation scheme achieve better performance compared to other resource allocation schemes.

Single pixel imaging (SPI) combined with compressed sensing techniques can provide solutions for special optical imaging to avoid array detectors and raster scanning. However, the imaging speed should be further improved for real-time SPI and the challenge is to reduce the sampling time and post-processing time. This paper proposes a deep compressive and super-fast single pixel imaging protocol based on reordering Hadamard basis patterns and Fourier domain regularization inversion (FDRI) algorithm. Two reordered Hadamard basis patterns in terms of the improvement in the compressing ratio and reconstruction quality are proposed and compared to other methods. The deterministic Hadamard basis are reordered through their total variation (TV) in ascending order and total wavelet transformed coefficients (TW) in ascending order to have the best performance. Numerical simulation shows that this protocol can reconstruct a 128 × 128 pixels natural image at the sampling ratio of 5% with the peak-signal-to-noise ratio (PSNR) of 25.56 dB in 0.00039s. Terahertz near-field imaging experiment also verifies the proposed protocol. The inherent advantage and mechanism of reordering approaches are discussed and then revealed by comparing the coherent area generated by these reordered patterns. The TV order and TW order Hadamard basis patterns can be deterministically described mathematically and easily constructed. Meanwhile, it results in a significant improvement both in the compression ratio and image reconstruction quality. Finally, the realization this protocol in real SPI system in the future will bring the real-time SPI closer to practical applications.

Serious challenges for to drive agricultural sustainability combined with climate crisis issues have induced an urgent need to decarbonise agriculture. In this paper, we briefly introduce a novel concept of the Photovoltaic Agricultural Internet of Things (PAIoT). This system approach fuses agricultural production with renewable power generation and control via an IoT platform. We discuss PAIoT applications and potential to realize the next generation of smart farming. In addition, we provide a review of key issues on the feasibility of PAIoT and further propose novel techniques to mitigate these key issues.

Oil-paper insulation is the main insulating medium of converter transformers. Space charge can result in the distortion of electric field in oil-paper insulation, hence it's necessary to analyze the space charge transport characteristic and its influence on the oil-paper insulation. In the paper, the space charge transport characteristic considering the electric field is investigated, and an upstream finite element method is presented to calculate the space charge distribution in oil insulation of converter transformer considering the influence of injection barrier, ion mobility, trapped coefficient and carrier recombination coefficient. Finally, the insulation state of tortuous oil-path is evaluated. Experiments were conducted to analyze the relationship between ion mobility and electric field intensity, the results indicate that the influence of space charge on the electric field intensity in the tortuous oil-path can not be ignored for the design of converter transformer.

Paraconsistent soft sets can address issues involving incomplete and inconsistent information simultaneously. In this paper, paraconsistent soft sets are furtherly extended to dynamic paraconsistent soft sets by introducing time factors. We define some basic operations, such as dynamic paraconsistent soft subsets, complement, “AND”, restricted intersection, relaxed intersection, restricted cross and relaxed cross. Subsequently, we also propose the definitions of dynamic paraconsistent soft decision system, compound time choice value, compound time decision value, compound time weighting vector and final decision value. Additionally, we construct a decision making algorithm for dynamic paraconsistent soft sets, which can address issues involving both dynamic incomplete and inconsistent information. Furthermore, we apply the proposed algorithm to a practical loan problem for small and micro enterprises. Finally, we perform a sensitivity analysis and a comparative analysis to prove the effectiveness and feasibility of the proposed algorithm.

Shore power system that powers berthing ships is gradually becoming widely used worldwide because it helps reduce air and noise pollution. However, due to the bad environment of the port, the influence of the port tide on the temperature distribution and the ampacity of the shore power cable connecting the ship and shore can't be ignored. Therefore, in this paper, a thermal field calculation model of shore power cable based on electromagnetic-thermal-flow coupling field is presented, in which the impact of tide has been considered. And the validity of the coupling model is verified by thermal circuit method base on IEC(International Electrotechnical Commission) 60287 standard. Then, the influence of cable immersion depth, water velocity and temperature, wind speed and air temperature on the temperature distribution of shore power cable was analyzed based on the multi-field coupling model. Finally, the ampacity of shore power cable in different environments is calculated by the combined Newton iterative and numerical simulation method. The results indicate that the conductor temperature firstly decreases and then increases with the immersion depth. And when the immersion depth is small, the wind speed dominates the temperature of the conductor. While the water flow speed plays a leading role in the conductor temperature when the immersion depth is deeper. In addition, the relationship between ambient temperature and capacity of shore power cable is approximately linear.

The salp swarm algorithm (SSA) is a bio-heuristic optimization algorithm proposed in 2017. It has been proved that SSA has competitive results compared to several other well-known meta-heuristic algorithms on various optimization problem. However, like most meta-heuristic algorithms, SSA is prone to problems such as local optimal solution and a slow convergence rate. To solve these problems, a chaotic salp swarm algorithm based on opposition-based learning (OCSSA) is proposed. The application of opposition-based learning (OBL) guarantees a better convergence speed and better develops the search space. The chaotic local search (CLS) method is also introduced, which can improve the performance of the algorithm to obtain the global optimal solution. The performance of OCSSA is compared with that of the original SSA and some other meta-heuristic algorithms on 28 benchmark functions with unimodal or multimodal characteristics. The experimental results show that the performance of OCSSA, with an appropriate chaotic map, is better than or comparable with the SSA and other meta-heuristic algorithms.

The grounding grid is the cornerstone for maintaining the safe operation of the power system. The grounding network acts as a concealed project, and its invisible characteristics make the defects difficult to be detected, which causes major safety hazards in the system. Thus accurate diagnosis of grounding grid corrosion is vital in electrical engineering. A diagnosis method for grounding grid corrosion based on branch voltage disturbance is proposed in this paper, which can judge the location and degree of corrosion through branch voltage disturbance before and after corrosion. Firstly, the sensitivity of branch voltage to branch resistance of the grounding grid is analyzed. Secondly, a diagnostic model based on branch voltage disturbance is established, and the corresponding regularity between peak voltage disturbance and the corrosion state of the grounding grid branch is developed. Finally, it is verified by experiments that this method can effectively diagnose the corrosion of the grounding grid.