Convective Storm VIL and Lightning Nowcasting Using Satellite and Weather Radar Measurements Based on Multi-Task Learning Models

Convective storms and lightning are among the most important weather phenomena that are challenging to forecast.In this study,a novel multi-task learning(MTL)encoder-decoder U-net neural network was developed to forecast convective storms and lightning with lead times for up to 90 min,using GOES-16 geostationary satellite infrared brightness temperatures(IRBTs),lightning flashes from Geostationary Lightning Mapper(GLM),and vertically integrated liquid(VIL)from Next Generation Weather Radar(NEXRAD).To cope with the heavily skewed distribution of lightning data,a spatiotemporal exponent-weighted loss function and log-transformed lightning normalization approach were developed.The effects of MTL,single-task learning(STL),and IRBTs as auxiliary input features on convection and lightning nowcasting were investigated.The results showed that normalizing the heavily skew-distributed lightning data along with a log-transformation dramatically outperforms the min-max normalization method for nowcasting an intense lightning event.The MTL model significantly outperformed the STL model for both lightning nowcasting and VIL nowcasting,particularly for intense lightning events.The MTL also helped delay the lightning forecast performance decay with the lead times.Furthermore,incorporating satellite IRBTs as auxiliary input features substantially improved lightning nowcasting,but produced little difference in VIL forecasting.Finally,the MTL model performed better for forecasting both lightning and the VIL of organized convective storms than for isolated cells.

A Multi-Task Motion Generation Model that Fuses a Discriminator and a Generator

The human motion generation model can extract structural features from existing human motion capture data,and the generated data makes animated characters move.The 3D human motion capture sequences contain complex spatial-temporal structures,and the deep learning model can fully describe the potential semantic structure of human motion.To improve the authenticity of the generated human motion sequences,we propose a multi-task motion generation model that consists of a discriminator and a generator.The discriminator classifies motion sequences into different styles according to their similarity to the mean spatial-temporal templates from motion sequences of 17 crucial human joints in three-freedom degrees.And target motion sequences are created with these styles by the generator.Unlike traditional related works,our model can handle multiple tasks,such as identifying styles and generating data.In addition,by extracting 17 crucial joints from 29 human joints,our model avoids data redundancy and improves the accuracy of model recognition.The experimental results show that the discriminator of the model can effectively recognize diversified movements,and the generated data can correctly fit the actual data.The combination of discriminator and generator solves the problem of low reuse rate of motion data,and the generated motion sequences are more suitable for actual movement.

基于多Agent传动关系的股市趋势预测

股市趋势预测是机器学习领域中一个具有挑战性的任务。由于一些因素对于股市的影响是动态且不确定的,导致股市趋势难以预测。针对已有方法在股市预测时存在的灵敏性差、适应力弱等问题,从快变量和慢变量的传动关系出发,利用Agent技术对股市中的快周期和慢周期进行联合建模,提出一种多Agent传动影响图(MATID)股市趋势预测方法。给出股市中快周期和慢周期的划分标准,并引入周期能量的概念;通过对相关趋势指标的特征融合,给出周期能量的量化计算方法;通过分析快周期和慢周期的动态作用过程,给出传动因子的表示方法;将快周期和慢周期分别对应成不同的Agent,利用多Agent影响图模型建模快周期和慢周期的传动过程;利用股市振子模型表示快Agent和慢Agent之间的传动效用,利用联合树的自动推理技术对股市趋势进行预测。在不同样本数量和不同股市趋势下进行实验,结果表明,与门控循环单元、S-LSTM和Hybrid-RNN预测方法相比,MATID方法预测精确率提升1.5%~7.0%,召回率提升5.4%~6.7%,F1值提升3.7%~6.2%,具有良好的灵敏性和适应力。

MDTCNet:Multi-Task Classifications Network and TCNN for Direction of Arrival Estimation

The direction-of-arrival(DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number in millimeter wave system,the multi-task deep residual shrinkage network(MTDRSN) and transfer learning-based convolutional neural network(TCNN), namely MDTCNet, are proposed. The sampling covariance matrix based on the received signal is used as the input to the proposed network. A DRSN-based multi-task classifications model is first introduced to estimate signal sources number and multipath number simultaneously. Then, the DoAs with multi-signal and multipath are estimated by the regression model. The proposed CNN is applied for DoAs estimation with the predicted number of signal sources and paths. Furthermore, the modelbased transfer learning is also introduced into the regression model. The TCNN inherits the partial network parameters of the already formed optimization model obtained by the CNN. A series of experimental results show that the MDTCNet-based DoAs estimation method can accurately predict the signal sources number and multipath number under a range of signal-to-noise ratios. Remarkably, the proposed method achieves the lower root mean square error compared with some existing deep learning-based and traditional methods.

A function-based behavioral modeling method for air combat simulation

Today’s air combat has reached a high level of uncertainty where continuous or discrete variables with crisp values cannot be properly represented using fuzzy sets. With a set of membership functions, fuzzy logic is well-suited to tackle such complex states and actions. However, it is not necessary to fuzzify the variables that have definite discrete semantics.Hence, the aim of this study is to improve the level of model abstraction by proposing multiple levels of cascaded hierarchical structures from the perspective of function, namely, the functional decision tree. This method is developed to represent behavioral modeling of air combat systems, and its metamodel,execution mechanism, and code generation can provide a sound basis for function-based behavioral modeling. As a proof of concept, an air combat simulation is developed to validate this method and the results show that the fighter Alpha built using the proposed framework provides better performance than that using default scripts.

Effect of neutral polymeric bonding agent on tensile mechanical properties and damage evolution of NEPE propellant

Introducing Neutral Polymeric bonding agents(NPBA) into the Nitrate Ester Plasticized Polyether(NEPE)propellant could improve the adhesion between filler/matrix interface, thereby contributing to the development of new generations of the NEPE propellant with better mechanical properties. Therefore,understanding the effects of NPBA on the deformation and damage evolution of the NEPE propellant is fundamental to material design and applications. This paper studies the uniaxial tensile and stress relaxation responses of the NEPE propellant with different amounts of NPBA. The damage evolution in terms of interface debonding is further investigated using a cohesive-zone model(CZM). Experimental results show that the initial modulus and strength of the NEPE propellant increase with the increasing amount of NPBA while the elongation decreases. Meanwhile, the relaxation rate slows down and a higher long-term equilibrium modulus is reached. Experimental and numerical analyses indicate that interface debonding and crack propagation along filler-matrix interface are the dominant damage mechanism for the samples with a low amount of NPBA, while damage localization and crack advancement through the matrix are predominant for the ones with a high amount of NPBA. Finally, crosslinking density tests and simulation results also show that the effect of the bonding agent is interfacial rather than due to the overall crosslinking density change of the binder.

Optimization of Structure of Agricultural Insurance Subsidies:A Multi-task Principal Agent Model

Optimizing the structure of agricultural insurance subsidies is of great significance to increasing the supply of agricultural insurance and strengthening the effects of agricultural insurance policies.This paper optimized the structure of agricultural insurance subsidies.It decomposed insurance activities into three parts:underwriting,claim settlement,and agricultural services.Next,it incorporated adverse selection risks,moral hazards,agricultural production and operation risks,insurance company's behavioral decisions and its risk attitudes into the multi-task principal agent analysis framework.Finally,it discussed how the government designs a subsidy mechanism and adjusts the subsidy structure to increase the insurance supply.

A Cautionary Note on the Application of GIS in Spatial Optimization Modeling

Spatial optimization as part of spatial modeling has been facilitated significantly by integration with GIS techniques. However, for certain research topics, applying standard GIS techniques may create problems which require attention. This paper serves as a cautionary note to demonstrate two problems associated with applying GIS in spatial optimization, using a capacitated p-median facility location optimization problem as an example. The first problem involves errors in interpolating spatial variations of travel costs from using kriging, a common set of techniques for raster files. The second problem is inaccuracy in routing performed on a graph directly created from polyline shapefiles, a common vector file type. While revealing these problems, the paper also suggests remedies. Specifically, interpolation errors can be eliminated by using agent-based spatial modeling while the inaccuracy in routing can be improved through altering the graph topology by splitting the long edges of the shapefile. These issues suggest the need for caution in applying GIS in spatial optimization study.

探析基于公共支撑能力的政务大模型AI+Agent

本文详细探讨了具有公共支撑能力的政务大模型AI+Agent如何为政务应用赋能,点明了创新行政管理和服务方式的重要性,并根据目前省级平台建设情况,描述了系统的特点以及能力输出,最后提出了多模态大模型AI+Agent的应用场景和系统架构。

Multi-agent Based Hierarchy Simulation Models of Carrier-based Aircraft Catapult Launch

With the aid of multi-agent based modeling approach to complex systems, the hierarchy simulation models of carrier-based aircraft catapult launch are developed. Ocean, carrier, aircraft, and atmosphere are treated as aggregation agents, the detailed components like catapult, landing gears, and disturbances are considered as meta-agents, which belong to their aggregation agent. Thus, the model with two layers is formed i.e. the aggregation agent layer and the meta-agent layer. The information communication among all agents is described. The meta-agents within one aggregation agent communicate with each other directly by information sharing, but the meta-agents, which belong to different aggregation agents exchange their information through the aggregation layer first, and then perceive it from the sharing environment, that is the aggregation agent. Thus, not only the hierarchy model is built, but also the environment perceived by each agent is specified. Meanwhile, the problem of balancing the independency of agent and the resource consumption brought by real-time communication within multi-agent system （MAS） is resolved. Each agent involved in carrier-based aircraft catapult launch is depicted, with considering the interaction within disturbed atmospheric environment and multiple motion bodies including carrier, aircraft, and landing gears. The models of reactive agents among them are derived based on tensors, and the perceived messages and inner frameworks of each agent are characterized. Finally, some results of a simulation instance are given. The simulation and modeling of dynamic system based on multi-agent system is of benefit to express physical concepts and logical hierarchy clearly and precisely. The system model can easily draw in kinds of other agents to achieve a precise simulation of more complex system. This modeling technique makes the complex integral dynamic equations of multibodies decompose into parallel operations of single agent, and it is convenient to expand, maintain, and reuse the program codes.

A distributed algorithm for signal coordination of multiple agents with embedded platoon dispersion model

In order to reduce average arterial vehicle delay, a novel distributed and coordinated traffic control algorithm is developed using the multiple agent system and the reinforce learning （RL）. The RL is used to minimize average delay of arterial vehicles by training the interaction ability between agents and exterior environments. The Robertson platoon dispersion model is embedded in the RL algorithm to precisely predict platoon movements on arteries and then the reward function is developed based on the dispersion model and delay equations cited by HCM2000. The performance of the algorithm is evaluated in a Matlab environment and comparisons between the algorithm and the conventional coordination algorithm are conducted in three different traffic load scenarios. Results show that the proposed algorithm outperforms the conventional algorithm in all the scenarios. Moreover, with the increase in saturation degree, the performance is improved more significantly. The results verify the feasibility and efficiency of the established algorithm.

Amelioration of Alzheimer's disease pathology and cognitive deficits by immunomodulatory agents in animal models of Alzheimer's disease

The most common age-related neurodegenerative disease is Alzheimer's disease(AD) characterized by aggregated amyloid-β(Aβ) peptides in extracellular plaques and aggregated hyperphosphorylated tau protein in intraneuronal neurofibrillary tangles,together with loss of cholinergic neurons,synaptic alterations,and chronic inflammation within the brain.These lead to progressive impairment of cognitive function.There is evidence of innate immune activation in AD with microgliosis.Classically-activated microglia(M1 state) secrete inflammatory and neurotoxic mediators,and peripheral immune cells are recruited to inflammation sites in the brain.The few drugs approved by the US FDA for the treatment of AD improve symptoms but do not change the course of disease progression and may cause some undesirable effects.Translation of active and passive immunotherapy targeting Aβ in AD animal model trials had limited success in clinical trials.Treatment with immunomodulatory/anti-inflammatory agents early in the disease process,while not preventive,is able to inhibit the inflammatory consequences of both Aβ and tau aggregation.The studies described in this review have identified several agents with immunomodulatory properties that alleviated AD pathology and cognitive impairment in animal models of AD.The majority of the animal studies reviewed had used transgenic models of early-onset AD.More effort needs to be given to creat models of late-onset AD.The effects of a combinational therapy involving two or more of the tested pharmaceutical agents,or one of these agents given in conjunction with one of the cell-based therapies,in an aged animal model of AD would warrant investigation.

Neuroprotection by immunomodulatory agents in animal models of Parkinson's disease

Parkinson’s disease（PD） is an age-related neurodegenerative disease for which the characteristic motor symptoms emerge after an extensive loss of dopamine containing neurons.The cell bodies of these neurons are present in the substantia nigra,with the nerve terminals being in the striatum.Both innate and adaptive immune responses may contribute to dopaminergic neurodegeneration and disease progression is potentially linked to these.Studies in the last twenty years have indicated an important role for neuroinflammation in PD through degeneration of the nigrostriatal dopaminergic pathway.Characteristic of neuroinflammation is the activation of brain glial cells,principally microglia and astrocytes that release various soluble factors.Many of these factors are proinflammatory and neurotoxic and harmful to nigral dopaminergic neurons.Recent studies have identified several different agents with immunomodulatory properties that protected dopaminergic neurons from degeneration and death in animal models of PD.All of the agents were effective in reducing the motor deficit and alleviating dopaminergic neurotoxicity and,when measured,preventing the decrease of dopamine upon being administered therapeutically after 1-methyl-4-phenyl-1,2,3,6-tetrahydropyridine,6-hydroxydopamine,rotenone-lesioning or delivery of adeno-associated virus-α-synuclein to the ventral midbrain of animals.Some of these agents were shown to exert an anti-inflammatory action,decrease oxidative stress,and reduce lipid peroxidation products.Activation of microglia and astrocytes was also decreased,as well as infiltration of T cells into the substantia nigra.Pretreatment with fingolimod,tanshinoine I,dimethyl fumarate,thalidomide,or cocaine-and amphetamine-regulated transcript peptide as a preventive strategy ameliorated motor deficits and nigral dopaminergic neurotoxicity in brain-lesioned animals.Immunomodulatory agents could be used to treat patients with early clinical signs of the disease or potentially even prior to disease onset in those identified as having pre-disposing risk,including genetic factors.

A Three-Dimensional Model of Transport and Diffusion of Seeding Agents within Stratus

It is essential to learn the temporal and spatial concentration distributions and variations of seeding agents in cloud seeding of precipitation enhancement. A three-dimensional puff trajectory model incorporating a mesoscale nonhydrostatic model has been formulated, and is applied to simulating the transporting and diffusive characteristics of multiple line sources of seeding agents within super-cooled stratus. Several important factors are taken into consideration that affect the diffusion of seeding materials such as effects of topography and vertical wind shear, temporal and spatial variation of seeding parameters and wet deposition. The particles of seeding agents are assumed to be almost inert, they have no interaction with the particles of the cloud or precipitation except that they are washed out by precipitation. The model validity is demonstrated by the analyses and comparisons of model results, and checked by the sensitivity experiments of diffusive coefficients and atmospheric stratification. The advantage of this model includes not only its exact reflection of heterogeneity and unsteadiness of background fields, but also its good simulation of transport and diffusion of multiple line sources. The horizontal diffusion rate and the horizontal transport distance have been proposed that they usually were difficult to obtain in other models. In this simulation the horizontal diffusion rate is 0.82 m s(-1) for average of one hour, and the horizontal average transport distance reaches 65 km after 1 4 which are closely related to the background Fields.

COLLISION AVOIDANCE DECISION-MAKING MODEL OF MULTI-AGENTS IN VIRTUAL DRIVING ENVIRONMENT WITH ANALYTIC HIERARCHY PROCESS

Collision avoidance decision-making models of multiple agents in virtual driving environment are studied. Based on the behavioral characteristics and hierarchical structure of the collision avoidance decision-making in real life driving, delphi approach and mathematical statistics method are introduced to construct pair-wise comparison judgment matrix of collision avoidance decision choices to each collision situation. Analytic hierarchy process （AHP） is adopted to establish the agents＇ collision avoidance decision-making model. To simulate drivers＇ characteristics, driver factors are added to categorize driving modes into impatient mode, normal mode, and the cautious mode. The results show that this model can simulate human＇s thinking process, and the agents in the virtual environment can deal with collision situations and make decisions to avoid collisions without intervention. The model can also reflect diversity and uncertainly of real life driving behaviors, and solves the multi-objective, multi-choice ranking priority problem in multi-vehicle collision scenarios. This collision avoidance model of multi-agents model is feasible and effective, and can provide richer and closer-to-life virtual scene for driving simulator, reflecting real-life traffic environment more truly, this model can also promote the practicality of driving simulator.

Fiscal Policy Effect Analysis Based on Agents Response Equilibrium (ARE) Model

Agents response equilibrium (ARE) model has been taken advantage of to build a multi-agent system for analyzing fiscal policy effect. Through establishing various types of economic entities and endowing them with abilities to react and make decision, the whole system will evolve to new conditions in response to policy change. Compared with different scenarios, it can be concluded that when raising taxation ratio, sectoral scale will shrink to some extent. But supported by government expenditure, certain sectors could be kept in comparatively larger production scale.

面向任务的装备保障体系多Agent建模与评估方法

随着战争形态向着体系化、智能化转变,装备保障体系有了新挑战。同时,动态变化的战场环境要求装备体系要适应战场态势,动态支撑作战任务。目前,装备保障体系建模研究存在与作战任务联系不紧密、与装备体系不匹配,不能充分体现装备保障体系自主性等问题。首先,基于多Agent方法,从结构和流程两个方面对装备保障体系的任务层、基地层、装备层建模,重点考虑保障任务中时间和空间约束问题;其次,提出面向任务的装备保障体系评价指标,构建指标模型;最后,通过对典型作战任务对应保障活动进行仿真,验证模型的合理性和有效性,并完成装备保障体系的效能评估。本研究可为装备保障体系结构优化、流程设计等工作提供参考。

Analysing the behavioural finance impact of ‘fake news’phenomena on financial markets:a representative agent model and empirical validation

This paper proposes an original behavioural finance representative agent model,to explain how fake news’empirical price impacts can persist in finance despite contradicting the efficient-market hypothesis.The model reconciles empirically-observed price overreactions to fake news with empirically-observed price underreactions to real news,and predicts a novel secondary impact of fake news:that fake news in a security amplifies underreactions to subsequent real news for the security.Evaluating the model against a large-sample event study of the 2019 Chinese ADR Delisting Threat fake news and debunking event,this paper finds strong qualitative validation for its model’s dynamics and predictions.

技术创新难度对高科技企业最优创新投入的影响——基于Agent-Based Model的分析

通过Agent-Based Model模拟了高技术企业的发展环境,分析了不同技术创新门槛下企业技术的发展状况。研究发现,高技术创新门槛阻碍了市场最高技术水平的发展,但能提升市场平均技术水平及公司数目。同时,企业研发活动存在能实现最大技术增长的最优创新研发投入比例,并且随着技术创新门槛的提升,企业的研发政策向模仿性投入倾斜。由此可知,针对有高技术创新门槛的高科技企业,政府应提升专利保护强度以影响企业的最优研发政策,保证高新技术产业的健康发展。

Agent Based Multiviews Requirements Model

Based on the current researches of viewpoints oriented requirements engineering and intelligent agent, we present the concept of viewpoint agent and its abstract model based on a recta-language for muhiviews requirements engineering. It provided a basis for consistency checking and integration of different viewpoint requirements, at the same time, these checking and integration works can automatically realized in virtue of intelligent agent＇ s autonomy, proactivenes.s and social ability. Finally, we introduce the practical application of the model by the case study of data flow diagram.