期刊文献+
共找到1,222篇文章
< 1 2 62 >
每页显示 20 50 100
MODIFIED INERTIAL SUBGRADIENT EXTRAGRADIENT METHODS FOR SOLVING A SUPPLY CHAIN NETWORK EQUILIBRIUM MODEL
1
作者 Zhuang SHAN 《Acta Mathematica Scientia》 2025年第3期1223-1234,共12页
Using a modified subgradient extragradient algorithm, this paper proposed a novel approach to solving a supply chain network equilibrium model. The method extends the scope of optimisation and improves the accuracy at... Using a modified subgradient extragradient algorithm, this paper proposed a novel approach to solving a supply chain network equilibrium model. The method extends the scope of optimisation and improves the accuracy at each iteration by incorporating adaptive parameter selection and a more general subgradient projection operator. The advantages of the proposed method are highlighted by the proof of strong convergence presented in the paper. Several concrete examples are given to demonstrate the effectiveness of the algorithm, with comparisons illustrating its superior CPU running time compared to alternative techniques. The practical applicability of the algorithm is also demonstrated by applying it to a realistic supply chain network model. 展开更多
关键词 supply chain network equilibrium model subgradient extragradient algorithm Tseng method variational inequalities strong convergence
在线阅读 下载PDF
A Transportation Network Equilibrium Reformulation of Eco-Industry Chain Network
2
作者 Yi-Wen Sun Guo-Shan Liu Shi-Qin Xu 《Journal of Harbin Institute of Technology(New Series)》 EI CAS 2013年第1期107-112,共6页
In this paper, we demonstrate that the eco-industrial network equilibrium model of link flow version previously introduced can be reformulated as a transportation network equilibrium problem of path flow version. Then... In this paper, we demonstrate that the eco-industrial network equilibrium model of link flow version previously introduced can be reformulated as a transportation network equilibrium problem of path flow version. Then, some methodological tools mainly applied in the field of transportation science can be used to discuss the eco-industrial chain network problem. What the highlighted contribution lies in is that the paper not only expands theory of supply chain model with reducing path flow but also generalizes the traditional transportation network equilibrium problem by new applications. 展开更多
关键词 eco-industry chain network transportation network system optimization network equilibrium path flow
在线阅读 下载PDF
Supply Chain Network Equilibrium with Revenue Sharing Contract under Demand Disruptions 被引量:4
3
作者 A-Ting Yang Lin-Du Zhao 《International Journal of Automation and computing》 EI 2011年第2期177-184,共8页
Contract is a common and effective mechanism for supply chain coordination,which has been studied extensively in recent years.For a supply chain network model,contracts can be used to coordinate it because it is too i... Contract is a common and effective mechanism for supply chain coordination,which has been studied extensively in recent years.For a supply chain network model,contracts can be used to coordinate it because it is too ideal to obtain the network equilibrium state in practical market competition.In order to achieve equilibrium,we introduce revenue sharing contract into a supply chain network equilibrium model with random demand in this paper.Then,we investigate the influence on this network equilibrium state from demand disruptions caused by unexpected emergencies.When demand disruptions happen,the supply chain network equilibrium state will be broken and change to a new one,so the decision makers need to adjust the contract parameters to achieve the new coordinated state through bargaining.Finally,a numerical example with a sudden demand increase as a result of emergent event is provided for illustrative purposes. 展开更多
关键词 Supply chain network equilibrium revenue sharing contract demand disruptions coordination.
在线阅读 下载PDF
A closed-loop Supply Chain Network Equilibrium Model with Fuzzy Demand under Production Capacity Constraints and Price Rigidities
4
作者 WU Hai-xiang HU Jin-song 《科技信息》 2013年第7期37-41,共5页
A closed-loop supply chain network equilibrium problem is examined,which consists of mutual competitive manufacturers with production capacity constraints and retailers with fuzzy market demands,mutual competitive col... A closed-loop supply chain network equilibrium problem is examined,which consists of mutual competitive manufacturers with production capacity constraints and retailers with fuzzy market demands,mutual competitive collectors as well as a binding price ceiling of the commodities.By utilizing the credibility measure of fuzzy event,variational inequality and Lagrange dual theory,the optimum behaviors of manufactures,retailers,collectors and consumers are described.Therefore,the supply chain network equilibrium model is established.Numerical examples were given to illustrate the impact of production capacity constraints and price ceiling on the network equilibrium pattern.The results show that the shortage of commodities in consumer market will be more serious,the wholesale price of product and purchase price of waste products rise,the profits of retailers decrease,the profits of manufacturers and collectors increase as the government gradually reduce the binding price ceiling on competitive markets,and the trend will be more obvious in the existence of production capacity constraints at same time. 展开更多
关键词 英语学习 学习方法 阅读知识 阅读材料
在线阅读 下载PDF
Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of AuCu_3-type sublattice system 被引量:3
5
作者 谢佑卿 李小波 +2 位作者 刘心笔 聂耀庄 彭红建 《Transactions of Nonferrous Metals Society of China》 SCIE EI CAS CSCD 2014年第11期3585-3610,共26页
Taking AuCu3-type sublattice system as an example, three discoveries have been presented: First, the third barrier hindering the progress in metal materials science is that researchers have got used to recognizing exp... Taking AuCu3-type sublattice system as an example, three discoveries have been presented: First, the third barrier hindering the progress in metal materials science is that researchers have got used to recognizing experimental phenomena of alloy phase transitions during extremely slow variation in temperature by equilibrium thinking mode and then taking erroneous knowledge of experimental phenomena as selected information for establishing Gibbs energy function and so-called equilibrium phase diagram. Second, the equilibrium holographic network phase diagrams of AuCu3-type sublattice system may be used to describe systematic correlativity of the composition?temperature-dependent alloy gene arranging structures and complete thermodynamic properties, and to be a standard for studying experimental subequilibrium order-disorder transition. Third, the equilibrium transition of each alloy is a homogeneous single-phase rather than a heterogeneous two-phase, and there exists a single-phase boundary curve without two-phase region of the ordered and disordered phases; the composition and temperature of the top point on the phase-boundary curve are far away from the ones of the critical point of the AuCu3 compound. 展开更多
关键词 AuCu3 compound AuCu3-type sublattice system alloy gene Gibbs energy partition function equilibrium holographic network phase diagram systematic metal materials science
在线阅读 下载PDF
Alloy gene Gibbs energy partition function and equilibrium holographic network phase diagrams of Au_3Cu-type sublattice system 被引量:3
6
作者 谢佑卿 聂耀庄 +2 位作者 李小波 彭红建 刘心笔 《Transactions of Nonferrous Metals Society of China》 SCIE EI CAS CSCD 2015年第1期211-240,共30页
Taking Au3Cu-type sublattice system as an example, three discoveries have been presented. First, the fourth barrier to hinder the progress of metal materials science is that today’s researchers do not understand that... Taking Au3Cu-type sublattice system as an example, three discoveries have been presented. First, the fourth barrier to hinder the progress of metal materials science is that today’s researchers do not understand that the Gibbs energy function of an alloy phase should be derived from Gibbs energy partition function constructed of alloy gene sequence and their Gibbs energy sequence. Second, the six rules for establishing alloy gene Gibbs energy partition function have been discovered, and it has been specially proved that the probabilities of structure units occupied at the Gibbs energy levels in the degeneracy factor for calculating configuration entropy should be degenerated as ones of component atoms occupied at the lattice points. Third, the main characteristics unexpected by today’s researchers are as follows. There exists a single-phase boundary curve without two-phase region coexisting by the ordered and disordered phases. The composition and temperature of the top point on the phase-boundary curve are far away from those of the critical point of the Au3Cu compound; At 0 K, the composition of the lowest point on the composition-dependent Gibbs energy curve is notably deviated from that of the Au3Cu compounds. The theoretical limit composition range of long range ordered Au3Cu-type alloys is determined by the first jumping order degree. 展开更多
关键词 Au3Cu compound Au3Cu-type sublattice system alloy gene Gibbs energy partition function equilibrium holographic network phase diagrams systematic metal materials science
在线阅读 下载PDF
ON VECTOR NETWORK EQUILIBRIUM PROBLEMS 被引量:1
7
作者 Guangya CHEN 《Journal of Systems Science and Systems Engineering》 SCIE EI CSCD 2005年第4期454-461,共8页
关键词 network equilibrium problem vector variational inequality weak equilibrium
原文传递
ON RELATIONS BETWEEN MULTICLASS,MULTICRITERIA TRAFFIC NETWORK EQUILIBRIUM MODELS AND VECTOR VARIATIONAL INEQUALITIES 被引量:1
8
作者 Shengjie LI Guangya CHEN 《Journal of Systems Science and Systems Engineering》 SCIE EI CSCD 2006年第3期284-297,共14页
关键词 Traffic network equilibrium model equilibrium principle vector variational inequality
原文传递
Traffic network equilibrium problems with demands uncertainty and capacity constraints of arcs by scalarization approaches 被引量:2
9
作者 CAO JinDe LI RuoXia +2 位作者 HUANG Wei GUO JianHua WEI Yun 《Science China(Technological Sciences)》 SCIE EI CAS CSCD 2018年第11期1642-1653,共12页
This paper focuses on the vector traffic network equilibrium problem with demands uncertainty and capacity constraints of arcs, in which, the demands are not exactly known and assumed as a discrete set that contains f... This paper focuses on the vector traffic network equilibrium problem with demands uncertainty and capacity constraints of arcs, in which, the demands are not exactly known and assumed as a discrete set that contains finite scenarios. For different scenario, the demand may be changed, which seems much more reasonable in practical programming. By using the linear scalarization method,we introduce several definitions of parametric equilibrium flows and reveal their mutual relations. Meanwhile, the relationships between the scalar variational inequality as well as the(weak) vector equilibrium flows are explored, meanwhile, some necessary and sufficient conditions that ensure the(weak) vector equilibrium flows are also considered. Additionally, by means of nonlinear scalarization functionals, two kinds of equilibrium principles are derived. All of the derived conclusions contain the demands uncertainty and capacity constraints of arcs, thus the results proposed in this paper improved some existing works. Finally, some numerical examples are employed to show the merits of the improved conclusions. 展开更多
关键词 TRAFFIC network DEMANDS uncertainty capacity equilibrium flow SCALARIZATION
原文传递
Developing architecture of a traveler information system for dynamic equilibrium in traffic networks 被引量:1
10
作者 Mohammad Hossein Noranian Ahmad Reza Tahsiri 《Journal of Modern Transportation》 2017年第2期106-115,共10页
Having criticized the current architecture of Advanced Traveler Information Systems (ATISs), this work discusses a new base of requirements to develop a new paradigm for traffic information systems. It mainly integr... Having criticized the current architecture of Advanced Traveler Information Systems (ATISs), this work discusses a new base of requirements to develop a new paradigm for traffic information systems. It mainly integrates three dimensions within a traffic system: drivers' pattern of behavior and preferences, urban traffic desires, and capabilities of traffic information service providers. Based on the above, functional segments from several related backgrounds are brought together to structure a new architecture, called Interactive Traveler Information System (ITIS). The main interactive feature of this new architecture is a two-way communication track between drivers and the traffic information system provider-in fact, a decision on choosing a road at a particular time for an individual will be made based on the utility of both sides. This new configuration consists of driver-side smartphone application, centric traffic prediction, and decision-maker units, which will shape a new approach of decision-making processes. These all work together to satisfy the designated goal of ITIS, which is preserving the Wardrop equilibrium condition in the traffic network level. Finally, we concentrate on a comparison study, which shows a differentiation between performance of the proposed ITIS and the current ATIS model in a real situation. This has been done with simulations of analogical scenarios. The most noticeable advantage of the proposed architecture is not being limited to a saturation limit, and the positive effect of increasing system penetration in the performance of the newly introduced information system. In conclusion, new research subjects are suggested to be carried out. 展开更多
关键词 Advanced Traveler Information System (ATIS) System architecture Requirement engineering Mobile network Dynamic equilibrium - Intelligent transportation system
在线阅读 下载PDF
Estimation of plasma equilibrium parameters via a neural network approach
11
作者 Zi-Jian Zhu Yong Guo +2 位作者 Fei Yang Bing-Jia Xiao Jian-Gang Li 《Chinese Physics B》 SCIE EI CAS CSCD 2019年第12期248-254,共7页
Plasma equilibrium parameters such as position, X-point, internal inductance, and poloidal beta are essential information for efficient and safe operation of tokamak. In this work, the artificial neural network is use... Plasma equilibrium parameters such as position, X-point, internal inductance, and poloidal beta are essential information for efficient and safe operation of tokamak. In this work, the artificial neural network is used to establish a non-linear relationship between the measured diagnostic signals and selected equilibrium parameters. The estimation process is split into a preliminary classification of the kind of equilibrium(limiter or divertor) and subsequent inference of the equilibrium parameters. The training and testing datasets are generated by the tokamak simulation code(TSC), which has been benchmarked with the EAST experimental data. The noise immunity of the inference model is tested. Adding noise to model inputs during training process is proved to have a certain ability for maintaining performance. 展开更多
关键词 neural network FUSION plasma equilibrium noise immunity
原文传递
Equilibrium Analysis for Anycast in WDM Networks
12
作者 唐矛宁 王汉兴 《Journal of Shanghai University(English Edition)》 CAS 2005年第1期12-14,共3页
In this paper, the wavelength-routed WDM network was analyzed for the dynamic case where the arrival of anycast requests was modeled by a state-dependent Poisson process. The equilibrium analysis was also given with t... In this paper, the wavelength-routed WDM network was analyzed for the dynamic case where the arrival of anycast requests was modeled by a state-dependent Poisson process. The equilibrium analysis was also given with the UWNC algorithm. 展开更多
关键词 wavelength division multiplexing (WDM) networks anycast requests equilibrium distribution Poisson process.
在线阅读 下载PDF
Modified stochastic user-equilibrium assignment algorithm for urban rail transit under network operation
13
作者 朱炜 胡昊 +1 位作者 徐瑞华 洪玲 《Journal of Central South University》 SCIE EI CAS 2013年第10期2897-2904,共8页
Based on the framework of method of successive averages(MSA), a modified stochastic user-equilibrium assignment algorithm was proposed, which can be used to calculate the passenger flow distribution of urban rail tran... Based on the framework of method of successive averages(MSA), a modified stochastic user-equilibrium assignment algorithm was proposed, which can be used to calculate the passenger flow distribution of urban rail transit(URT) under network operation. In order to describe the congestion's impact to passengers' route choices, a generalized cost function with in-vehicle congestion was set up. Building on the k-th shortest path algorithm, a method for generating choice set with time constraint was embedded, considering the characteristics of network operation. A simple but efficient route choice model, which was derived from travel surveys for URT passengers in China, was introduced to perform the stochastic network loading at each iteration in the algorithm. Initial tests on the URT network in Shanghai City show that the methodology, with rational calculation time, promises to compute more precisely the passenger flow distribution of URT under network operation, compared with those practical algorithms used in today's China. 展开更多
关键词 urban rail TRANSIT STOCHASTIC USER equilibrium ASSIGNMENT ALGORITHM method of successive AVERAGES network operation
在线阅读 下载PDF
Holographic alloy positioning design system and holographic network phase diagrams of Au-Cu system 被引量:4
14
作者 谢佑卿 刘心笔 +2 位作者 李小波 彭红建 聂耀庄 《Transactions of Nonferrous Metals Society of China》 SCIE EI CAS CSCD 2015年第3期885-906,共22页
Taking Au?Cu system as an example, three discoveries and two methods were presented. First, a new way for boosting sustainable progress of systematic metal materials science (SMMS) and alloy gene engineering (AGE) is ... Taking Au?Cu system as an example, three discoveries and two methods were presented. First, a new way for boosting sustainable progress of systematic metal materials science (SMMS) and alloy gene engineering (AGE) is to establish holographic alloy positioning design (HAPD) system, of which the base consists of measurement and calculation center, SMMS center, AGE center, HAPD information center and HAPD cybernation center; Second, the resonance activating-sychro alternating mechanism of atom movement may be divided into the located and oriented diffuse modes; Third, the equilibrium and subequilibrium holographic network phase diagrams are blueprints and operable platform for researchers to discover, design, manufacture and deploy advanced alloys, which are obtained respectively by the equilibrium lever numerical method and cross point numerical method of isothermal Gibbs energy curves. As clicking each network point, the holographic information of three structure levels for the designed alloy may be readily obtained: the phase constitution and fraction, phase arranging structure and properties of organization; the composition, alloy gene arranging structure and properties of each phase and the electronic structures and properties of alloy genes. It will create a new era for network designing advanced alloys. 展开更多
关键词 Au-Cu system holographic alloy positioning design system equilibrium and subequilibrium holographic network phase diagrams systematic metal materials science network designing advanced alloys
在线阅读 下载PDF
基于DCNN-EQLv2的物联网入侵检测模型研究
15
作者 杨雅澜 蒋超 魏文红 《东莞理工学院学报》 2026年第1期32-38,共7页
随着物联网技术的发展,其设备安全问题凸显,特别是物联网环境中隐身和多态性入侵问题面临巨大的挑战。针对此挑战,提出基于DCNN-EQLv2的物联网入侵检测模型用于检测物联网中的隐身和多态性入侵。该模型融合深度神经网络(DCNN)与均衡损... 随着物联网技术的发展,其设备安全问题凸显,特别是物联网环境中隐身和多态性入侵问题面临巨大的挑战。针对此挑战,提出基于DCNN-EQLv2的物联网入侵检测模型用于检测物联网中的隐身和多态性入侵。该模型融合深度神经网络(DCNN)与均衡损失函数(EQLv2),用EQLv2损失函数替代传统交叉熵损失函数,结合SMOTE缓解类别不平衡问题,从而提高检测模型的鲁棒性和准确性。最后在基于IoT的NIDS数据集上对模型进行训练和测试,实验结果表明,与其他检测模型相比,本文模型性能优异,在NF-UNSW-NB15-v2数据集分类精度达到了99.67%。 展开更多
关键词 深度卷积神经网络 均衡损失函数 物联网 入侵检测
在线阅读 下载PDF
基于Moran过程和随机演化博弈模型的网络防御决策方法
16
作者 胡航 冯凯 +1 位作者 谭晶磊 张玉臣 《信息网络安全》 北大核心 2026年第2期291-303,共13页
现有的网络防御决策方法大多基于攻防双方完全理性的假设以及确定性博弈模型,难以模拟实际网络攻防场景,导致实用性较差。为更好地适应有限理性条件下的网络攻防博弈场景,文章提出了基于Moran过程和随机演化博弈模型的网络防御决策方法... 现有的网络防御决策方法大多基于攻防双方完全理性的假设以及确定性博弈模型,难以模拟实际网络攻防场景,导致实用性较差。为更好地适应有限理性条件下的网络攻防博弈场景,文章提出了基于Moran过程和随机演化博弈模型的网络防御决策方法,引入选择强度系数描述攻防双方对优势策略的偏好程度,通过求解攻防策略动态演化方程设计最优防御策略决策算法,并刻画策略选择的演化轨迹。数值仿真实验结果验证了文章所提方法的科学性和有效性,分析探讨了不同网络状态下攻防策略的演变规律。同时,与基于Wright-Fisher和基于复制动态的网络防御决策方法相比,文章所提最优防御策略的收敛速度分别提高了23.1%和17.4%,表明该方法在学习效率和收敛速度方面具有优势。 展开更多
关键词 网络防御 Moran过程 随机演化博弈 演化均衡 最优防御策略
在线阅读 下载PDF
基于BP神经网络预测LNG中二氧化碳液固相平衡
17
作者 徐常安 姜庆华 +3 位作者 张辉 沈鼎 李子禾 朱建鲁 《油气与新能源》 2026年第1期88-97,共10页
随着中国深远海天然气资源的开发,FLNG(浮式液化天然气)被视为关键技术,但因其高昂的造价严重限制了大规模推广。为降低开发成本,埃克森美孚提出了PLNG(带压液化天然气)技术。该技术通过提高液化压力,升高液化温度,从而显著提升了二氧... 随着中国深远海天然气资源的开发,FLNG(浮式液化天然气)被视为关键技术,但因其高昂的造价严重限制了大规模推广。为降低开发成本,埃克森美孚提出了PLNG(带压液化天然气)技术。该技术通过提高液化压力,升高液化温度,从而显著提升了二氧化碳等杂质的溶解度。理论上,这一特性有望简化甚至取消昂贵的预处理装置,其实现的关键在于对PLNG中二氧化碳的液固相平衡数据的准确预测。由于现有理论计算模型预测精度受到固有结构限制,本文基于液固相平衡原理,结合文献实验数据,构建了基于BP神经网络的PLNG中二氧化碳溶解度预测模型。采用最优结构参数时,BP神经网络预测输出与实验值的平均绝对百分比误差为1.71%,总回归系数为0.999 95,均方误差(MSE)为9.495 7×10-6,验证了预测模型的可靠性和准确性。 展开更多
关键词 带压液化天然气 二氧化碳 液固相平衡 BP神经网络
在线阅读 下载PDF
基于结构化神经网络的微电网二次调频控制
18
作者 李锦泽 何晓敏 +1 位作者 吴锦辉 郭方洪 《电力系统自动化》 北大核心 2026年第4期133-141,共9页
随着微电网系统复杂性与不确定性的日益增加,设计兼具稳定性和输出跟踪能力的二次调频控制方法对系统安全可靠运行至关重要。为此,提出一种基于结构化神经网络的微电网二次调频控制方法。首先,基于物理系统中广泛存在的平衡点独立无源性... 随着微电网系统复杂性与不确定性的日益增加,设计兼具稳定性和输出跟踪能力的二次调频控制方法对系统安全可靠运行至关重要。为此,提出一种基于结构化神经网络的微电网二次调频控制方法。首先,基于物理系统中广泛存在的平衡点独立无源性,将微电网的二次调频控制问题建模为严格单调的比例-积分(PI)控制结构,并将PI参数化为严格凸神经网络(SCNN)的梯度。其次,采用带有可调系数的Softplus-β激活函数构建SCNN,在保证其通用逼近能力的同时,有效适应微电网多变的通信约束。此外,将由SCNN构造的严格凸函数的梯度作为Lyapunov函数,进一步给出了系统端到端的稳定性证明。仿真结果表明,相较于其他可能导致系统不稳定的非结构化神经网络控制方法,所提方法不仅可以保证系统稳定性,而且在暂态和稳态性能上均优于传统控制方法。 展开更多
关键词 微电网 二次调频 不确定性 稳定性 神经网络 比例-积分控制 平衡点 独立无源性
在线阅读 下载PDF
面向碳减排与弹性提升的交直流混合配电网协同优化调控方法
19
作者 洪福斌 蔡小辰 +2 位作者 刘贵 陈昊 马兆兴 《电力需求侧管理》 2026年第1期24-32,共9页
在“双碳”目标的指引下,交直流混合配电网络已逐渐成为配电系统未来发展的重要方向。然而,碳减排与提升电力网络弹性这两大需求之间存在一定矛盾,难以高效协同。鉴于此,提出了一种基于近似纳什均衡的交直流混合配电网协同优化方法。首... 在“双碳”目标的指引下,交直流混合配电网络已逐渐成为配电系统未来发展的重要方向。然而,碳减排与提升电力网络弹性这两大需求之间存在一定矛盾,难以高效协同。鉴于此,提出了一种基于近似纳什均衡的交直流混合配电网协同优化方法。首先探讨了不同条件下,碳减排与弹性对交直流配电网络运行的影响;随后,提出了考虑碳减排的协同调控模型,并提出了弹性评估的度量指标,在此基础上设计了优化运行的近似纳什均衡策略。最终,以达成均衡的碳减排、经济性、弹性作为优化目标,构建起交直流混合配电网的优化调控模型。通过改进的IEEE33节点算例和雄安新区某园区算例进行计算分析,验证了所提方法对降低碳排放、提升经济性与弹性的有效性和可行性。 展开更多
关键词 近似纳什均衡 交直流混合配电网 弹性 经济性 碳减排
在线阅读 下载PDF
基于多路径增强与博弈均衡的图像去雾方法
20
作者 黄燕嫄 索煜程 +4 位作者 陈信强 杨睿 张瀚 王梓创 郑金彪 《中国测试》 北大核心 2026年第2期145-152,共8页
针对船舶雾天航行过程中成像特点存在的图像受雾霾影响导致视觉退化、特征模糊等问题,该文提出一种融合多分支结构的循环对抗网络。该网络基于循环对抗神经网络(Cycle-GAN)引入高效多轴特征增强模块(efficient multi-axis aggregation,E... 针对船舶雾天航行过程中成像特点存在的图像受雾霾影响导致视觉退化、特征模糊等问题,该文提出一种融合多分支结构的循环对抗网络。该网络基于循环对抗神经网络(Cycle-GAN)引入高效多轴特征增强模块(efficient multi-axis aggregation,EMA)强化网络对海洋大气光值、海天高对比度背景等重点特征的学习能力,通过多路径融合机制分别从卷积提取特征、多轴空间动态增强维度协同优化图像去雾效果。实验在自建真实船舶雾天航行数据集上验证所提出网络的有效性,对比以往的去雾方法与该文所提方法的去雾效果,并通过峰值信噪比、结构相似性指数等指标对网络鲁棒性进行验证。结果显示在多种航行场景下该方法指标均达到最优,证明该文所提方法可以作为船舶雾天自主感知的重要技术支撑。 展开更多
关键词 图像增强 多轴特征增强 博弈均衡 空间信息建模 去雾网络
在线阅读 下载PDF
上一页 1 2 62 下一页 到第
使用帮助 返回顶部