检索结果-南通市图书馆

Categorizing methods for integrating machine learning with executable specifications

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第1期67卷 5-19页

作者： David HAREL Raz YERUSHALMI Assaf MARRON Achiya ELYASAF Department of Computer Science and Applied Mathematics Weizmann Institute of Science Department of Software and Information systems engineering Ben-Gurion University of the Negev

Deep learning(DL),which includes deep reinforcement learning(DRL),holds great promise for carrying out real-world tasks that human minds seem to cope with quite *** promise is already delivering extremely impressive results in a variety of ***,while DL-enabled systems achieve excellent performance,they are far from *** has been demonstrated,in several domains,that DL systems can err when they encounter cases they had not hitherto ***,the opacity of the produced agents makes it difficult to explain their behavior and ensure that they adhere to various requirements posed by human *** the other end of the software development spectrum of methods,behavioral programming(BP) facilitates orderly system development using self-standing executable modules aligned with how humans intuitively describe desired system *** this paper,we elaborate on different approaches for combining DRL with BP and,more generally,machine learning(ML) with executable specifications(ES).We begin by defining a framework for studying the various approaches,which can also be used to study new emerging approaches not covered *** then briefly review state-of-the-art approaches to integrating ML with ES,continue with a focus on DRL,and then present the merits of integrating ML with *** conclude with guidelines on how this categorization can be used in decision making in system development,and outline future research challenges.

关键词： machine learning artificial intelligence grey box learning domain knowledge rules behavioral programming deep reinforcement learning survey

MCWOA Scheduler:Modified Chimp-Whale Optimization Algorithm for Task Scheduling in Cloud Computing

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第2期78卷 2593-2616页

作者： Chirag Chandrashekar Pradeep Krishnadoss Vijayakumar Kedalu Poornachary Balasundaram Ananthakrishnan School of Computer Science and engineering Vellore Institute of TechnologyChennai600127India Center for Cyber Physical systems School of Computer Science and EngineeringVellore Institute of TechnologyChennai600127India

Cloud computing provides a diverse and adaptable resource pool over the internet,allowing users to tap into various resources as *** has been seen as a robust solution to relevant challenges.A significant delay can hamper the performance of IoT-enabled cloud ***,efficient task scheduling can lower the cloud infrastructure’s energy consumption,thus maximizing the service provider’s revenue by decreasing user job processing *** proposed Modified Chimp-Whale Optimization Algorithm called Modified Chimp-Whale Optimization Algorithm(MCWOA),combines elements of the Chimp Optimization Algorithm(COA)and the Whale Optimization Algorithm(WOA).To enhance MCWOA’s identification precision,the Sobol sequence is used in the population initialization phase,ensuring an even distribution of the population across the solution ***,the traditional MCWOA’s local search capabilities are augmented by incorporating the whale optimization algorithm’s bubble-net hunting and random search mechanisms into MCWOA’s position-updating *** study demonstrates the effectiveness of the proposed approach using a two-story rigid frame and a simply supported beam *** outcomes reveal that the new method outperforms the original MCWOA,especially in multi-damage detection *** excels in avoiding false positives and enhancing computational speed,making it an optimal choice for structural damage *** efficiency of the proposed MCWOA is assessed against metrics such as energy usage,computational expense,task duration,and *** simulated data indicates that the new MCWOA outpaces other methods across all *** study also references the Whale Optimization Algorithm(WOA),Chimp Algorithm(CA),Ant Lion Optimizer(ALO),Genetic Algorithm(GA)and Grey Wolf Optimizer(GWO).

关键词： Cloud computing scheduling chimp optimization algorithm whale optimization algorithm

MDCN:Modified Dense Convolution Network Based Disease Classification in Mango Leaves

维普期刊数据库评论

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2期78卷 2511-2533页

作者： Chirag Chandrashekar K.P.Vijayakumar K.Pradeep A.Balasundaram School of Computer Science and engineering Vellore Institute of Technology(VIT)ChennaiIndia Center for Cyber Physical systems School of Computer Science and EngineeringVellore Institute of Technology(VIT)ChennaiIndia

The most widely farmed fruit in the world is *** the production and quality of the mangoes are hampered by many *** diseases need to be effectively controlled and ***,a quick and accurate diagnosis of the disorders is *** convolutional neural networks,renowned for their independence in feature extraction,have established their value in numerous detection and classification ***,it requires large training datasets and several parameters that need careful *** proposed Modified Dense Convolutional Network(MDCN)provides a successful classification scheme for plant diseases affecting mango *** model employs the strength of pre-trained networks and modifies them for the particular context of mango leaf diseases by incorporating transfer learning *** data loader also builds mini-batches for training the models to reduce training ***,optimization approaches help increase the overall model’s efficiency and lower computing *** employed on the MangoLeafBD Dataset consists of a total of 4,000 *** the experimental results,the proposed system is compared with existing techniques and it is clear that the proposed algorithm surpasses the existing algorithms by achieving high performance and overall throughput.

关键词： Leaf disease detection deep convolutional neural networks transfer learning optimization MangoLeafBD Dataset

Summer Atmospheric Water Cycle under the Transition Influence of the Westerly and Summer Monsoon over the Yarlung Zangbo River Basin in the Southern Tibetan Plateau

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2024年第5期41卷 830-846页

作者： Qianhui MA Chunyan ZHANG Donghai WANG Zihao PANG School of Atmospheric Sciences Sun Yat-sen UniversityGuangdong Province Key Laboratory for Climate Change and Natural Disaster StudiesKey Laboratory of Tropical Atmosphere-Ocean SystemMinistry of EducationZhuhai 519082China Southern Marine Science and engineering Guangdong Laboratory(Zhuhai) Zhuhai 519082China Guangdong Meteorological Data Center Guangdong Meteorological ServiceGuangzhou 510080China National Observation and Research Station of Coastal Ecological Environments in macao Macao Environmental Research InstituteMacao University of Science and TechnologyMacao SAR 999078China National Meteorological Information Center China Meteorological AdministrationBeijing 100081China

This study compares the summer atmospheric water cycle,including moisture sources and consumption,in the upstream,midstream,and downstream regions of the Yarlung Zangbo River Basin in the southern Tibetan *** evolutions of moisture properties under the influence of the westerly and summer southerly monsoon are examined using 5-yr multi-source measurements and ERA5 reanalysis *** that moisture consumption in this study is associated with clouds,precipitation,and diabatic *** to the midstream and downstream regions,the upstream region has less moisture,clouds,and precipitation,where the moisture is brought by the *** early August,the vertical wet advection over this region becomes enhanced and generates more high clouds and *** midstream region has moisture carried by the westerly in June and by the southerly monsoon from July to *** higher vertical wet advection maximum here forms more high clouds,with a precipitation peak in early *** downstream region is mainly affected by the southerly-driven wet *** rich moisture and strong vertical wet advection here produce the most clouds and precipitation among the three regions,with a precipitation peak in late *** height of the maximum moisture condensation is different between the midstream region(325 hPa)and the other two regions(375 hPa),due to the higher upward motion maximum in the midstream *** diabatic heating structures show that stratiform clouds dominate the upstream region,stratiform clouds and deep convection co-exist in the midstream region,and deep convection systems characterize the downstream region.

关键词： Yarlung Zangbo River Basin atmospheric water cycle constrained variational analysis moisture source and consumption

Three-Wave Mixing of Dipole Solitons in One-Dimensional Quasi-Phase-Matched Nonlinear Crystals

在线全文

学校读者我要写书评

暂无评论

Chinese Physics Letters 2024年第1期41卷 25-33页

作者：郭宇欣徐晓喜陈招拼周延桂刘彬和河向黎永耀谢嘉宁 School of Physics and Optoelectronic engineering Foshan UniversityFoshan 528000China Physics Department and Solid-State institute TechnionHaifa 32000Israel Guangdong-Hong Kong-macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology School of Physics and Optoelectronic EngineeringFoshan UniversityFoshan 528000China

A quasi-phase-matched technique is introduced for soliton transmission in a quadratic[χ^((2))]nonlinear crystal to realize the stable transmission of dipole solitons in a one-dimensional space under three-wave *** report four types of solitons as dipole solitons with distances between their bimodal peaks that can be laid out in different *** study three cases of these solitons:spaced three stripes apart,one stripe apart,and confined to the same *** the case of three stripes apart,all four types have stable results,but for the case of one stripe apart,stable solutions can only be found atω_(1)=ω_(2),and for the condition of dipole solitons confined to one stripe,stable solutions exist only for Type1 and Type3 atω_(1)=ω_(2).The stability of the soliton solution is solved and verified using the imaginary time propagation method and real-time transfer propagation,and soliton solutions are shown to exist in the multistability *** addition,the relations of the transportation characteristics of the dipole soliton and the modulation parameters are numerically ***,possible approaches for the experimental realization of the solitons are outlined.

关键词： soliton solitons dipole

On the convergence of tracking differentiator with multiple stochastic disturbances

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第2期67卷 157-169页

作者： Zehao WU Huacheng ZHOU Baozhu GUO Feiqi DENG School of Mathematics and Big Data Foshan University School of Mathematics and Statistics Central South University Academy of Mathematics and systems Science Chinese Academy of Sciences systems engineering institute South China University of Technology

This paper investigates the convergence, noise-tolerance, and filtering performance of a tracking differentiator in the presence of multiple stochastic disturbances for the first time. We consider a general case wherein the input signal is corrupted by additive colored noise, and the tracking differentiator is disturbed by additive colored noise and white noise. The tracking differentiator is shown to track the input signal and its generalized derivatives in the mean square sense. Further, the almost sure convergence can be achieved when the stochastic noise affecting the input signal is vanishing. Herein, numerical simulations are performed to validate the theoretical results.

关键词： tracking differentiator convergence noise-tolerance filtering performance multiple stochastic disturbances

A GMDA clustering algorithm based on evidential reasoning architecture

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2024年第1期37卷 300-311页

作者： Haibin WANG Xin GUAN Xiao YI Shuangming LI Guidong SUN Naval Aviation University Yantai 264001China Unit 92941 of PLA Huludao 125001China institute of systems engineering Beijing 100082China

The traditional clustering algorithm is difficult to deal with the identification and division of uncertain objects distributed in the overlapping region,and aimed at solving this problem,the Evidential Clustering based on General Mixture Decomposition Algorithm(GMDA-EC)is ***,the belief classification of target cluster is carried out,and the sample category of target distribution overlapping region is ***,on the basis of General Mixture Decomposition Algorithm(GMDA)clustering,the fusion model of evidence credibility and evidence relative entropy is constructed to generate the basic probability assignment of the target and achieve the belief division of the ***,the performance of the algorithm is verified by the synthetic dataset and the measured *** experimental results show that the algorithm can reflect the uncertainty of target clustering results more comprehensively than the traditional probabilistic partition clustering algorithm.

关键词： Evidential clustering Credal partition Evidential reasoning Mixed decomposition Gaussian mixture model

Characterization and prediction of tailpipe ammonia emissions from in-use China 5/6 light-duty gasoline vehicles

在线全文

学校读者我要写书评

暂无评论

Frontiers of Environmental Science & engineering 2024年第1期18卷 71-81页

作者： Lewei Zeng Fengbin Wang Shupei Xiao Xuan Zheng Xintong Li Qiyuan Xie Xiaoyang Yu Cheng Huang Qingyao Hu Yan You Ye Wu College of Chemistry and Environmental engineering Shenzhen UniversityShenzhen 518060China State Key Laboratory of Engines Tianjin UniversityTianjin 300072China China Automotive Technology and Research Center Co.Ltd. Tianjin 300300China CATARC Automotive Test Center(Guangzhou)Co.Ltd. Guangzhou 511300China State Environmental Protection Key Laboratory of Cause and Prevention of Urban Air Pollution Complex Shanghai Academy of Environmental SciencesShanghai 200233China National Observation and Research Station of Coastal Ecological Environments in macao Macao Environmental Research InstituteMacao University of Science and TechnologyMacao SAR 999078China School of Environment State Key Joint Laboratory of Environment Simulation and Pollution ControlTsinghua UniversityBeijing 100084China

On-road tailpipe ammonia (NH3) emissions contribute to urban secondary organic aerosol formation and have direct or indirect adverse impacts on the environment and human health. To understand the tailpipe NH3 emission characteristics, we performed comprehensive chassis dynamometer measurements of NH3 emission from two China 5 and two China 6 light-duty gasoline vehicles (LDGVs) equipped with three-way catalytic converters (TWCs). The results showed that the distance-based emission factors (EFs) were 12.72 ± 2.68 and 3.18 ± 1.37 mg/km for China 5 and China 6 LDGVs, respectively. Upgrades in emission standards were associated with a reduction in tailpipe NH3 emission. In addition, high NH3 EFs were observed during the engine warm-up period in cold-start cases owing to the intensive emissions of incomplete combustion products and suitable catalytic temperature in the TWCs. Notably, based on the instantaneous NH3 emission rate, distinct NH3–emitting events were detected under high/extra high velocity or rapid acceleration. Furthermore, NH3 emission rates correlated well with engine speed, vehicle specific power, and modified combustion efficiency, which were more easily accessible. These strong correlations were applied to reproduce NH3 emissions from China 5/6 LDGVs. The predicted NH3 EFs under different dynamometer and real-world cycles agreed well with existing measurement and prediction results, revealing that the NH3 EFs of LDGVs in urban routes were within 8.55–11.62 mg/km. The results presented here substantially contribute to improving the NH3 emission inventory for LDGVs and predicting on-road NH3 emissions in China.

关键词： NH3 instantaneous emissions Catalytic temperature Vehicle specific power Combustion efficiency Emission prediction

用于含能分子性质预测的分子描述符增强图神经网络

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Materials 2024年第4期67卷 1243-1252页

作者：高天宇纪玉金刘成李有勇 institute of Functional Nano&Soft Materials(FUNSOM) Jiangsu Key Laboratory for Carbon-Based Functional Materials&DevicesSoochow UniversitySuzhou 215123China macao institute of Materials Science and engineering Macao University of Science and TechnologyMacao SAR 999078China

含能分子在军事和民用应用中都发挥着重要作用.传统上,确定含能分子的物理化学参数需要实验工作量且具有风险,而新兴的机器学习方法有望解决这一问题.在这项工作中,我们报道了一种分子描述符增强的图神经网络(MD增强的GNN)模型,该模型... 详细信息

含能分子在军事和民用应用中都发挥着重要作用.传统上,确定含能分子的物理化学参数需要实验工作量且具有风险,而新兴的机器学习方法有望解决这一问题.在这项工作中,我们报道了一种分子描述符增强的图神经网络(MD增强的GNN)模型,该模型可以准确快速地预测含能分子的三个爆轰参数.该模型集成了基于序列的分子描述符和基于结构的图向量,提供了一个不需要自定义描述符的全面框架.因此,我们构建了一个包含18,991个CHNO含能分子的含能分子数据集,并将我们的模型与单一的分子指纹/描述符和GNN方法进行了比较.研究发现,我们提出的MD增强的GNN集成方法通过结合两个不同的互补特征,实现了卓越的精度,R2超过0.93,学习速度提高了20%以上,这突出了我们的模型在重塑含能分子设计格局方面的潜力,并有望在这一关键领域内大幅提高效率和有效性.

关键词：神经网络模型集成分子描述符物理化学参数机器学习方法爆轰参数分子指纹关键领域