检索结果-南通市图书馆

MADDPG-D2: An Intelligent Dynamic Task Allocation Algorithm Based on Multi-Agent Architecture Driven by Prior Knowledge

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第9期140卷 2559-2586页

作者： Tengda Li Gang wang qiang fu College of Air and Missile Defense Air Force Engineering UniversityXi’an710051China

Aiming at the problems of low solution accuracy and high decision pressure when facing large-scale dynamic task allocation(DTA)and high-dimensional decision space with single agent,this paper combines the deep reinforce-ment learning(DRL)theory and an improved Multi-Agent Deep Deterministic Policy Gradient(MADDPG-D2)algorithm with a dual experience replay pool and a dual noise based on multi-agent architecture is proposed to improve the efficiency of *** algorithm is based on the traditional Multi-Agent Deep Deterministic Policy Gradient(MADDPG)algorithm,and considers the introduction of a double noise mechanism to increase the action exploration space in the early stage of the algorithm,and the introduction of a double experience pool to improve the data utilization rate;at the same time,in order to accelerate the training speed and efficiency of the agents,and to solve the cold-start problem of the training,the a priori knowledge technology is applied to the training of the ***,the MADDPG-D2 algorithm is compared and analyzed based on the digital battlefield of ground and air *** experimental results show that the agents trained by the MADDPG-D2 algorithm have higher win rates and average rewards,can utilize the resources more reasonably,and better solve the problem of the traditional single agent algorithms facing the difficulty of solving the problem in the high-dimensional decision *** MADDPG-D2 algorithm based on multi-agent architecture proposed in this paper has certain superiority and rationality in DTA.

关键词： Deep reinforcement learning dynamic task allocation intelligent decision-making multi-agent system MADDPG-D2 algorithm

A New Industrial Intrusion Detection Method Based on CNN-BiLSTM

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第6期79卷 4297-4318页

作者： Jun wang Changfu Si Zhen wang qiang fu College of Computer Science and Technology Shenyang University of Chemical TechnologyShenyang110142China

Nowadays,with the rapid development of industrial Internet technology,on the one hand,advanced industrial control systems(ICS)have improved industrial production ***,there are more and more cyber-attacks targeting industrial control *** ensure the security of industrial networks,intrusion detection systems have been widely used in industrial control systems,and deep neural networks have always been an effective method for identifying cyber *** intrusion detection methods still suffer from low accuracy and a high false alarm ***,it is important to build a more efficient intrusion detection *** paper proposes a hybrid deep learning intrusion detection method based on convolutional neural networks and bidirectional long short-term memory neural networks(CNN-BiLSTM).To address the issue of imbalanced data within the dataset and improve the model’s detection capabilities,the Synthetic Minority Over-sampling Technique-Edited Nearest Neighbors(SMOTE-ENN)algorithm is applied in the preprocessing *** algorithm is employed to generate synthetic instances for the minority class,simultaneously mitigating the impact of noise in the majority *** approach aims to create a more equitable distribution of classes,thereby enhancing the model’s ability to effectively identify patterns in both minority and majority *** the experimental phase,the detection performance of the method is verified using two data *** results show that the accuracy rate on the CICIDS-2017 data set reaches 97.7%.On the natural gas pipeline dataset collected by Lan Turnipseed from Mississippi State University in the United States,the accuracy rate also reaches 85.5%.

关键词： Intrusion detection convolutional neural network bidirectional long short-term memory neural network multi-head self-attention mechanism

Enhancing Dense Small Object Detection in UAV Images Based on Hybrid Transformer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第3期78卷 3993-4013页

作者： Changfeng Feng Chunping wang Dongdong Zhang Renke Kou qiang fu Shijiazhuang Campus People Liberation Army Engineering UniversityShijiazhuang050003China School of Information and Intelligent Engineering Sanya UniversitySanya572000China

Transformer-based models have facilitated significant advances in object ***,their extensive computational consumption and suboptimal detection of dense small objects curtail their applicability in unmanned aerial vehicle(UAV)*** these limitations,we propose a hybrid transformer-based detector,H-DETR,and enhance it for dense small objects,leading to an accurate and efficient ***,we introduce a hybrid transformer encoder,which integrates a convolutional neural network-based cross-scale fusion module with the original encoder to handle multi-scale feature sequences more ***,we propose two novel strategies to enhance detection performance without incurring additional inference *** filter is designed to cope with the dense clustering inherent in drone-captured images by counteracting similar queries with a training-aware non-maximum *** denoising learning is a novel enhancement method inspired by adversarial learning,which improves the detection of numerous small targets by counteracting the effects of artificial spatial and semantic *** experiments on the VisDrone and UAVDT datasets substantiate the effectiveness of our approach,achieving a significant improvement in accuracy with a reduction in computational *** method achieves 31.9%and 21.1%AP on the VisDrone and UAVDT datasets,respectively,and has a faster inference speed,making it a competitive model in UAV image object detection.

关键词： UAV images transformer dense small object detection

Numerical Analysis of PRISM-PY Calculations for Hard-and Soft-Core Generic Polymer Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第4期42卷 532-543页

作者： qiang wang Department of Chemical and Biological Engineering Colorado State University1370 Campus DeliveryFort CollinsCO80523-1370USA

Generic polymer models capturing the chain connectivity and excluded-volume interactions between polymer segments can be classified, according to whether or not the 3D integral of the latter diverges, into hard- and soft-core models. Taking homogeneous systems of compressible homopolymer melts (or equivalently homopolymer solutions in an implicit, good solvent) in the continuum as an example, we recently compared the correlation effects on the structural and thermodynamic properties of the hard- and soft-core models given by the polymer reference interaction site model (PRISM) theory with the Percus-Yevick (PY) closure (Polymers 2023, 15, 1180). Here we analyzed in detail the numerical errors and behavior of the interchain pair correlation functions (PCFs) given by the PRISM-PY calculations of these models using an efficient numerical approach that we proposed. Our numerical approach has the least number of independent variables to be iteratively solved, analytically treats the discontinuities caused by the non-bonded pair potential (such as that of the hard spheres) and takes only the inverse Fourier transform of the interchain indirect PCF between polymer segments (which is continuous and decays towards 0 with increasing wavenumber much faster than both the interchain direct and total PCFs), and is essential for us to accurately solve the PRISM-PY theory for chain length N as large as 106. To capture the correlation-hole effect, the real-space cut-off in the PRISM calculations should be proportional to the square root of N.

关键词： Generic polymer models Soft potentials Polymer reference interaction site model theory

Preparation of Self-limiting Heating Cables with Excellent Processability, Mechanical Properties and PTC Effect via Thermal and Electrical Treatments

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Polymer Science 2024年第4期42卷 511-520页

作者： Tian-Hao Yang Tong Wu qiang fu State Key Laboratory of Polymer Materials Engineering College of Polymer Science and EngineeringSichuan UniversityChengdu610065China State Key Laboratory of Polymer Materials Engineering Polymer Research Institute of Sichuan UniversityChengdu610065China

Polymer/conductive filler composites have been widely used for the preparation of self-limiting heating cables with the positive temperature coefficient (PTC) effect. The control of conductive filler distribution and network in polymer matrix is the most critical for performance of PTC materials. In order to compensate for the destruction of the filler network structure caused by strong shearing during processing, an excessive conductive filler content is usually added into the polymer matrix, which in turn sacrifices its processability and mechanical properties. In this work, a facile post-treatment of the as-extruded cable, including thermal and electrical treatment to produce high-density polyethylene (HDPE)/carbon black (CB) cable with excellent PTC effect, is developed. It is found for the as-extruded sample, the strong shearing makes the CB particles disperse uniformly in HDPE matrix, and 25 wt% CB is needed for the formation of conductive paths. For the thermal-treated sample, a gradually aggregated CB filler structure is observed, which leads to the improvement of PTC effect and the notable reduction of CB content to 20 wt%. It is very interesting to see that for the sample with combined thermal and electrical treatment, CB particles are agglomerated and oriented along the electric field direction to create substantial conductive paths, which leads to a further decrease of CB content down to 15 wt%. In this way, self-limiting heating cables with excellent processability, mechanical properties and PTC effect have simultaneously been achieved.

关键词： Self-limiting heating cables Positive temperature coefficient Thermal treatment Electrical treatment

Search for the chiral magnetic effect in heavy ion collisions

在线全文

学校读者我要写书评

暂无评论

Nuclear Science and Techniques 2018年第12期29卷 71-80页

作者： fu-qiang wang Jie Zhao School of Science Huzhou University Department of Physics and Astronomy Purdue University

Quark interactions with topological gluon fields in quantum chromodynamics can yield local P and CP violations that could explain the matter–antimatter asymmetry in our universe. Effects of P and CP violations can lead to charge separation under a strong magnetic field, a phenomenon called the chiral magnetic effect(CME).Early measurements of the CME-induced charge separation in heavy ion collisions are dominated by physics backgrounds. This report discusses the recent innovative efforts in eliminating those backgrounds, namely by eventshape engineering, invariant mass dependence, and reaction and participant plane comparison. The backgroundfree CME measurements using these novel methods are presented.

关键词：重离子碰撞磁性不对称现象相互作用能物理背景 CME 反物质 CP

Hybrid Estimation of State and Input for Linear Discrete Time-varying Systems： A Game Theory Approach

在线全文

学校读者我要写书评

暂无评论

自动化学报 2008年第6期34卷 665-669页

作者： YOU fu-qiang wang fu-Li GUAN Shou-Ping Key Laboratory of Integrated Automation Process Industry Ministry of Education Northeastern University Shenyang 110004 P. R. China

为线性分离变化时间的系统的 H 混合评价问题在这份报纸被调查，在估计的信号是状态和输入的线性联合的地方。设计目的从骚乱要求最坏的精力获得到是的评价错误不到规定水平。混合评价问题的最佳的答案是僵绳点一二播放器零和微分游戏... 详细信息

为线性分离变化时间的系统的 H 混合评价问题在这份报纸被调查，在估计的信号是状态和输入的线性联合的地方。设计目的从骚乱要求最坏的精力获得到是的评价错误不到规定水平。混合评价问题的最佳的答案是僵绳点一二播放器零和微分游戏。根据微分比赛途径，为混合评价问题的必要、足够的可解决的条件以一个 Riccati 微分方程的答案被提供。而且，如果可解决的条件满足，一个可能的评估者被建议。评估者被印射矩阵的一个获得矩阵和产量描绘，在后者反映在未知输入和输出评价错误之间的内部关系的地方。最后，一个数字例子被提供说明建议途径。

关键词：博奕论线性离散系统时间变化系统智能化系统

Efficacy and predictive factors of transarterial chemoembolization combined with lenvatinib plus programmed cell death protein-1 inhibition for unresectable hepatocellular carcinoma

在线全文

学校读者我要写书评

暂无评论

World Journal of Gastrointestinal Oncology 2024年第4期16卷 1236-1247页

作者： Kun-Peng Ma Jin-Xin fu Feng Duan Mao-qiang wang Department of Interventional Radiology The Fifth Medical Center of Chinese People's Liberation Army General HospitalBeijing 100853China Chinese People's Liberation Army Medical School Beijing 100853China

BACKGROUND The efficacy and safety of transarterial chemoembolization(TACE)combined with lenvatinib plus programmed cell death protein-1(PD-1)for unresectable hepato-cellular carcinoma(HCC)have rarely been evaluated and it is unknown which factors are related to *** To evaluate the efficacy and independent predictive factors of TACE combined with lenvatinib plus PD-1 inhibitors for unresectable *** This study retrospectively enrolled patients with unresectable HCC who received TACE/lenvatinib/PD-1 treatment between March 2019 and April *** survival(OS)and progression-free survival(PFS)were *** objective response rate(ORR)and disease control rate(DCR)were evaluated in accordance with the modified Response Evaluation Criteria in Solid ***,the prognostic factors affecting the clinical outcome were *** One hundred and two patients were enrolled with a median follow-up duration of 12.63 *** median OS was 26.43 months(95%CI:17.00-35.87),and the median PFS was 10.07 months(95%CI:8.50-11.65).The ORR and DCR were 61.76%and 81.37%,*** patients with Barcelona Clinic Liver Cancer Classification(BCLC)B stage,early neutrophil-to-lymphocyte ratio(NLR)response(decrease),or early alpha-fetoprotein(AFP)response(decrease>20%)had superior OS and PFS than their *** This study showed that TACE/lenvatinib/PD-1 treatment was well tolerated with encouraging efficacy in patients with unresectable *** patients with BCLC B-stage disease with early NLR response(decrease)and early AFP response(decrease>20%)may achieve better clinical outcomes with this triple therapy.

关键词： Transarterial chemoembolization Efficacy Lenvatinib Programmed cell death protein-1 inhibitors Unresectable hepatocellular carcinoma

Spatial compartmentalization and temporal stability of associated microbiota in Pacific oyster Crassostrea gigas

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Oceanology and Limnology 2024年第4期42卷 1348-1358页

作者： qiang fu Zichao YU Junyan ZHAO Lei GAO Ning KONG Lingling wang Linsheng SONG Liaoning Key Laboratory of Marine Animal Immunology and Disease Control Dalian Ocean UniversityDalian 116023China functional Laboratory of Marine Fisheries Science and Food Production Processes Qingdao National Laboratory for Marine Science and TechnologyQingdao 266237China Southern Marine Science and Engineering Guangdong Laboratory(Zhuhai) Zhuhai 519000China Dalian Key Laboratory of Aquatic Animal Disease Prevention and Control Dalian Ocean UniversityDalian 116023China

The Pacific oyster Crassostrea gigas,one of the most exploited molluscs in the world,has suffered from massive mortality in recent decades,and the occurrence mechanisms have not been well *** this study,to reveal the relationship of associated microbiota to the fitness of oysters,temporal dynamics of microbiota in the gill,hemolymph,and hepatopancreas of *** during April 2018-January 2019 were investigated by 16 S rRNA gene *** microbiota in *** exhibited tissue heterogeneity,of which Spirochaetaceae was dominant in the gill and hemolymph while Mycoplasmataceae enriched in the ***-occurrence network demonstrated that the gill microbiota exhibited higher inter-taxon connectivity while the hemolymph microbiota had more *** richness(Chao 1 index)and diversity(Shannon index)of microbial community in each tissue showed no significant seasonal variations,except for the hepatopancreas having a higher richness in the ***,beta diversity analysis indicated a relatively stable microbiota in each tissue during the sampling period,showing relative abundance of the dominant taxa exhibiting temporal *** indicate that the microbial community in *** showed a tissue-specific stability with temporal dynamics in the composition,which might be essential for the tissue functioning and environmental adaption in *** work provides a baseline microbiota in *** and is helpful for the understanding of host-microbiota interaction in oysters.

关键词： Pacific oyster associated microbiota spatial compartmentalization temporal stability