The scale of ground-to-air confrontation task assignments is large and needs to deal with many concurrent random events. Aiming at the problems where existing assignment methods are applied confrontation, there low efficiency in dealing complex tasks, interactive conflicts multiagent systems. This study proposes a architecture based on one-general agent multiple narrow agents (OGMN) reduce conflicts. Considering slow speed traditional dynamic algorithms, this paper proximal policy...

Over 3 billion people live in rural, unincorporated areas globally, which are vital for habitation and production. The perceived safety of these landscapes significantly impacts health well-being. However, rural areas, as natural environments urban populations to connect with nature, have not been sufficiently addressed terms concerns. Negative factors often outweigh those promoting safety, limiting the restorative potential landscapes. This study collected audio–visual samples through...

We study a new design objective for "Internet in space" terrestrial users: To align logical network topology, address, and route the virtual cyberspace with movements of satellite mega-constellations earth's rotations real physical world. explain why this is particularly desirable by recent low-earth-orbit (LEO) mega-constellations, how it welcomes mobility to streamline stability, efficiency, scalability an unstable space-ground environment. showcase its feasibility common fixed sub-point...

The multi-agent system is the optimal solution to complex intelligent problems. In accordance with game theory, concept of loyalty introduced analyze relationship between agents' individual income and global benefits build logical architecture system. Besides, verify feasibility method, cyclic neural network optimized, bi-directional coordination built as training for deep learning, specific scenes are simulated background. After a certain number iterations, model can learn simple strategies...

Deep Reinforcement Learning (DRL) methods are inefficient in the initial strategy exploration process large-scale complex scenarios. This is becoming one of bottlenecks their application to game adversarial paper proposes a Safe reinforcement learning combined with Imitation for Task Assignment (SITA) method representative red-blue confrontation scenario. Aiming at problem difficult sampling (IL), this combines human knowledge rules build rule base; We propose Decoupled Network (ILDN)...

With the rapid development of information technology, network-centric warfare (NCW) has become main operational style now and even in future, destruction resistance networks one most important issues field. Based on complex theory, command control (C2) network is constructed, topology characteristics are analyzed. Aiming at deliberate attack random attack, C2 analyzed optimized. The simulation results show that conforms to small-world free-scale characteristics, it sensitive attack. strategy...

As military technology continues to evolve and the amount of situational information available on battlefield increase, data-driven deep learning methods are becoming primary method for air target intention recognition. Deep is based a large high quality data; however, in field recognition, it often faces key problems such as low data volume unbalanced datasets due insufficient real-world scenarios. To address these problems, we propose new called time-series conditional generative...

In order to generate cross sections for fast reactor calculation, a code named TXMAT based on object–oriented programming and allocate memory technology has been developed. It the capability macroscopic transport or diffusion calculation microscopic burnup can also deal with ultrafine group (more than 2000 groups P5 Legendre order) which TRANSX 2.15 can’t do. works together generalized section data library called MATXS give users easier access appropriate nuclear capabilities are difficult...

Abstract Under the premise of many types and large numbers targets, how to solve problem rational allocation dynamic multi-objectives has always been a hot issue for experts scholars. In this paper, distributed target method based on auction algorithm is used kind problem. This paper establishes mathematical model air defense combat, uses Finally, effectiveness real-time performance are proved by simulation.

Spatial crowdsourcing is a mode that uses distributed artificial computing power to solve specific function sets through Internet outsourcing. It has broad application value in the networked command and control of current joint air defense operations. In this paper, we introduce spatial theory into field target allocation for operations establish weapon-target assignment model based on mode, which more appropriate real situation highlights system cooperation capability To model, propose...

Abstract Facial expression recognition (FER) is one of the popular research topics in computer vision. Most deep learning methods perform well on a single dataset, but may struggle cross‐domain FER applications when applied to different datasets. under cross‐dataset also suffers from difficulties such as feature distribution deviation and discriminator degradation. To address these issues, we propose prototype‐oriented similarity transfer framework (POST) for FER. The bidirectional...

Microplastics (MPs) generated from daily life are commonly collected by urban sewage pipe network, and then transfer to sludge in wastewater treatment plants. Conventional biochemical processes cannot degrade MPs effectively, causing an ecological risk via land use. Wet air oxidation (WAO) is a promising technology with strong ability decompose complex organic matter, but its potential on the removal of was unclear. In this study, three common (polyethylene, polystyrene polyethylene...

The full neutron spectrum code for advanced reactor simulation named FSAR has recently been developed at Nuclear Power Institute of China in order to meet the requirements with large energy range. Based on two-step calculation scheme, consists two-dimensional lattice and core code. In calculation, subgroup method ultrafine groups was implemented resonance self-shielding by incorporating MOC get accurate self-shielded cross-section. For better consideration strong space coupling different...

Abstract Aiming at the problem of coherent speckle noise in SAR image processing, this paper improves network based on convolutional neural method, adjusts hierarchical relationship hierarchy, and introduces principles batch normalization residual to eliminate. The gradient disappears when level is too deep. loss function improved by using multiple convolution kernels different sizes which are used extract a variety levels feature information. Finally, peak signal-to-noise ratio (PSNR) edge...

We present F-Rosette, a stable space-ground network structure for low-earth orbit (LEO) satellite mega-constellations at scale. Due to the dynamic many-to-many mapping in high mobility, existing LEO with IP protocol stack suffer from frequent user address changes (every 133~510s per user) and routing re-convergence (<20% usability). To provably stabilize under mobility dynamics, F-Rosette adopts recursive over Rosette constellation, derives hierarchical time-invariant space new geographical...

Under the background of great changes in military science and technology theory, order to solve problem massive high-dimensional situation knowledge processing process battlefield assessment.The current dimensionality reduction methods often ignore influence algorithm complexity model representation ability on when solving knowledge. In balance this problem, paper proposes a dimension method based Sparse Autoencoder, which has good performance achieving information obtaining its abstract...

Modern air defense battlefield situations are complex and varied, requiring high-speed computing capabilities real-time situational processing for task assignment. Current methods struggle to balance the quality speed of assignment strategies. This paper proposes a hierarchical reinforcement learning architecture ground-to-air confrontation (HRL-GC) an algorithm combining model predictive control with proximal policy optimization (MPC-PPO), which effectively combines advantages centralized...

In view of the problems such as low efficiency, difficulty in resolving local conflicts and lack practical application scenarios, existing interaction model multi-agent systems a distributed environment, multi-master multi-slave was designed based on Stackelberg game, which is applied to game problem between controller participant command control process. Through optimizing multi-attribute decision-making, multi-master, multi-slave, system designed, closed loop under solved for dimension...

This paper briefly analyzed the operational background and characteristics of regional joint air defense, summarized requirements mission planning for defense operations, pointed out deficiencies current research. Finally, it is suggested that command level should be adjusted, charging mode optimized, target allocation model solving algorithm improved, evaluation system operation improved in future development operation.

The fast reactor is gradually being paid attention to in nuclear power due a better breeding effect, and its economy also directly followed. Due the restriction of core density, level related volume active area. When increase, mass uranium 235U at beginning life will increase on basis critical inventory. At same time, gradual utilization rate resources end increase. characteristics large high low cannot be further reduced because lifetime should extended use wealthy reactivity improvement...

A multi-robot vision collaborative SLAM system based on the updated ORB algorithm was provided to respond needs of large error and poor sensitivity in system. Firstly, histogram equalization is carried out collected image, which improves overall contrast image. Shi-Tomasi corner detection used supplement loss feature points during camera rotation. Second, Lucas-Kanade (LK) sparse optical flow employed enhance algorithm's matching process. Finally, improved applied CCMSLAM cooperative The...