检索结果-南通市图书馆

Continual Reinforcement Learning for Intelligent AgriculturalManagement under Climate Changes

Computers, Materials and Continua 2024年第1期81卷 1319-1336页

作者： Wang, Zhaoan Jha, Kishlay xiao, shaoping Department of Mechanical Engineering Iowa Technology Institute University of Iowa Iowa City IA 52242 United States Department of Electrical and Computer Engineering University of Iowa Iowa City IA 52242 United States

Climate change poses significant challenges to agricultural management, particularly in adapting to extreme weather conditions that impact agricultural production. Existing works with traditional Reinforcement Learning (RL) methods often falter under such extreme conditions. To address this challenge, our study introduces a novel approach by integrating Continual Learning (CL) with RL to form Continual Reinforcement Learning (CRL), enhancing the adaptability of agricultural management strategies. Leveraging the Gym-DSSAT simulation environment, our research enables RL agents to learn optimal fertilization strategies based on variable weather conditions. By incorporating CL algorithms, such as Elastic Weight Consolidation (EWC), with established RL techniques like Deep Q-Networks (DQN), we developed a framework in which agents can learn and retain knowledge across diverse weather scenarios. The CRL approach was tested under climate variability to assess the robustness and adaptability of the induced policies, particularly under extreme weather events like severe droughts. Our results showed that continually learned policies exhibited superior adaptability and performance compared to optimal policies learned through the conventional RL methods, especially in challenging conditions of reduced rainfall and increased temperatures. This pioneering work, which combines CL with RL to generate adaptive policies for agricultural management, is expected to make significant advancements in precision agriculture in the era of climate change. © 2024 The Authors. Published by Tech Science Press.

关键词： Deep reinforcement learning

来源：

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

Soil NOx Emission Prediction via Recurrent Neural Networks

引用

Computers, Materials & Continua 2023年第10期77卷 285-297页

作者： Zhaoan Wang shaoping xiao Cheryl Reuben Qiyu Wang Jun Wang Department of Mechanical Engineering Iowa Technology InstituteUniversity of IowaIowa CityIA 52242USA Department of Chemical and Biochemical Engineering Iowa Technology InstituteUniversity of IowaIowa CityIA 52242USA

This paper presents designing sequence-to-sequence recurrent neural network(RNN)architectures for a novel study to predict soil NOx emissions,driven by the imperative of understanding and mitigating environmental *** study utilizes data collected by the Environmental Protection Agency(EPA)to develop two distinct RNN predictive models:one built upon the long-short term memory(LSTM)and the other utilizing the gated recurrent unit(GRU).These models are fed with a combination of historical and anticipated air temperature,air moisture,and NOx emissions as inputs to forecast future NOx *** LSTM and GRU models can capture the intricate pulse patterns inherent in soil NOx ***,the GRU model emerges as the superior performer,surpassing the LSTM model in predictive accuracy while demonstrating efficiency by necessitating less training ***,the investigation into varying input features reveals that relying solely on past NOx emissions as input yields satisfactory performance,highlighting the dominant influence of this *** study also delves into the impact of altering input series lengths and training data sizes,yielding insights into optimal configurations for enhanced model ***,the findings promise to advance our grasp of soil NOx emission dynamics,with implications for environmental management *** ahead,the anticipated availability of additional measurements is poised to bolster machine-learning model ***,the future study will explore physical-based RNNs,a promising avenue for deeper insights into soil NOx emission prediction.

关键词： Soil NOx emission long-short term memory gated recurrent unit sequence-to-sequence

来源：

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

Improvement of the conversion efficiency of Mg_(3)Sb_(2)thermoelectric devices through optimizing the resistivity of the MgSbNi barrier layer

引用

Journal of Materials Science & Technology 2024年第1期168卷 208-214页

作者： Huimin Zhang Yachao Wang Zuhair A.Munir Yongzhong Zhang Wenhao Fan shaoping Chen College of Materials Science and Engineering Taiyuan University of TechnologyTaiyuan030024China Capital Aerospace Machinery Company Beijing100076China Department of Material Science and Engineering University of CaliforniaDavisCalifornia95616United States of America College of Physics and Optoelectronics Taiyuan University of TechnologyTaiyuan030024China Instrumental Analysis Center of Taiyuan University of Technology Taiyuan030024China

Mg_(3)Sb_(2)-based thermoelectric materials have been the focus of widespread investigations as promising candidates for the harvesting of waste *** stability and service performance are key points for the commercial applications of these *** utilized Mg_(4.3)Sb_(3)Ni as a barrier layer to improve the thermal stability of Mg 3 Sb 2-based ***,its intrinsic high resistivity contributed nega-tively to the desired performance of the *** this work,we investigated two other Mg-Sb-Ni ternary phases,MgSbNi and MgSbNi_(2),as new barrier layer materials to connect with Mg_(3.2)Sb_(2)Y_(0.05).The results show that the efficiency of the Mg_(1.2)SbNi/Mg_(3.2)Sb_(2)Y_(0.05)/Mg_(1.2)SbNi joint is increased by 33%relative to the higher Mg-content barriers due to lower *** system exhibited good interfacial compatibility and showed little change with aging at 673 K for 20 days.

关键词： Mg_(3)Sb_(2) Mg_(1.2)SbNi Barrier layer Conversion efficiency

来源：

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

Dynamically updated digital twin for prognostics and health management:Application in permanent magnet synchronous motor

引用

Chinese Journal of Aeronautics 2024年第6期37卷 244-261页

作者： Haoyu GUO shaoping WANG Jian SHI Tengfei MA Giorgio GUGLIERI Rujun JIA Fausto LIZZIO School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China Tianmushan Laboratory Hangzhou 310023China Department of Mechanical and Aerospace Engineering Polytechnic University of TurinTurin 10129Italy Beihang Ningbo Research Institute Ningbo 315800China

Current research on Digital Twin(DT)based Prognostics and Health Management(PHM)focuses on establishment of DT through integration of real-time data from various sources to facilitate comprehensive product monitoring and health ***,there still exist gaps in the seamless integration of DT and PHM,as well as in the development of DT multi-field coupling modeling and its dynamic update *** the product experiences long-period degradation under load spectrum,it is challenging to describe the dynamic evolution of the health status and degradation progression *** addition,DT update algorithms are difficult to be integrated simultaneously by current *** paper proposes an innovative dual loop DT based PHM framework,in which the first loop establishes the basic dynamic DT with multi-filed coupling,and the second loop implements the PHM and the abnormal detection to provide the interaction between the dual loops through updating *** proposed method pays attention to the internal state changes with degradation and interactive mapping with dynamic parameter ***,the Independence Principle for the abnormal detection is proposed to refine the theory of *** at the first loop focus on accurate modeling of multi-field coupling,while the events at the second loop focus on real-time occurrence of anomalies and the product degradation *** interaction and collaboration between different loop models are also ***,the Permanent Magnet Synchronous Motor(PMSM)is used to verify the proposed *** results show that the modeling method proposed can accurately track the lifecycle performance changes of the entity and carry out remaining life prediction and health management effectively.

关键词： Digital Twin(DT) Dynamic Update Independence Principle Multi-field Coupling Permanent Magnet Synchronous Motor(PMSM) Prognostics and Health Management(PHM)

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Adhesive hydrogel interface for enhanced epidermal signal

引用

Science China Technological Sciences 2024年第10期67卷 3136-3151页

作者： SHI XinLei YU Hui TANG ZiQing LU shaoping YOU Min YIN HaiYan CHEN Qiang Wenzhou Institute University of Chinese Academy of Sciences Joint Research Centre on Medicine The Affiliated Xiangshan Hospital of Wenzhou Medical University

This paper presents a discussion on the method, mechanism, and application of adhesive hydrogel in enhancing epidermal signal,focusing on the interface between hydrogel and skin. Due to its excellent conductivity and high adaptability to the skin, the hydrogel is exceptionally suitable for detecting human-machine interfaces, particularly epidermal electromyographic ***, the detection of the high epidermal signal is hindered by the gap and low adhesion between hydrogel and skin. This paper addresses these challenges by introducing approaches to reduce the interface gap and increase interface adhesion, thereby enabling the development of hydrogel-based epidermal signal detection arrays with enhanced resolution and detection performance.

关键词： adhesive hydrogel hydrogel electrodes epidermal signal interfacial adhesion

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

双寡头核心能力发展竞争、学习追随与核心能力均衡

引用

管理评论 2011年第4期23卷 87-96页

作者：肖绍平邓超中南大学商学院长沙410083

寡头是复杂的能力与知识系统,寡头核心能力发展竞争,实质上是独特知识积累的竞争。本文构建的双寡头核心能力发展与学习博弈模型表明,寡头学习类型、学习策略选择、学习努力水平、学习追随与初始知识积累水平,决定双寡头知识积累,进而... 详细信息

寡头是复杂的能力与知识系统,寡头核心能力发展竞争,实质上是独特知识积累的竞争。本文构建的双寡头核心能力发展与学习博弈模型表明,寡头学习类型、学习策略选择、学习努力水平、学习追随与初始知识积累水平,决定双寡头知识积累,进而决定核心能力发展均衡;博弈竞争条件下寡头学习追随可能导致学习无效。

关键词：核心竞争力创新性学习追随模仿性学习博弈均衡

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Effects of Rosa roxburghii&edible fungus fermentation broth on immune response and gut microbiota in immunosuppressed mice

引用

Food Science and Human Wellness 2024年第1期13卷 154-165页

作者： Dechang Xu Jielun Hu Yadong Zhong Yanli Zhang Wenting Liu shaoping Nie Mingyong Xie State Key Laboratory of Food Science and Technology China-Canada Joint Laboratory of Food Science and Technology(Nanchang)Key Laboratory of Bioactive Polysaccharides of Jiangxi ProvinceNanchang UniversityNanchang 330047China

With the rise of probiotics fermentation in food industry,fermented foods have attracted worldwide *** this study,protective effects of Rosa roxburghii&edible fungus fermentation broth(REFB)on immune function and gut health in Cyclophosphamide induced immunosuppressed mice were *** showed that REFB could improve the immune organ index,and promote the proliferation and differentiation of splenic T *** addition,it attenuated intestinal mucosal damage and improved intestinal cellular *** administration also up-regulated the expression of IL-4,INF-γ,TNF-α,T-bet and GATA-3 mRNA in small ***,administration of REFB modulated gut microbiota composition and increased the relative abundance of beneficial genus,such as *** also increased the production of fecal short-chain fatty *** indicate that REFB has the potential to improve immunity,alleviate intestinal injury and regulate gut microbiota in immunosuppressed mice.

关键词： Fermented foods Immunosuppressed mice Immune response Gut microbiota Short-chain fatty acids

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Legumain-triggered aggregable gold nanoparticles for enhanced intratumoral retention

引用

Chinese Chemical Letters 2024年第7期35卷 388-393页

作者： Zhi Li Wenpei Li shaoping Jiang Chuan Hu Yuanyu Huang Maxim Shevtsov Huile Gao Shaobo Ruan Advanced Research Institute of Multidisciplinary Sciences School of Life ScienceBeijing Institute of TechnologyBeijing 100081China Key Laboratory of Drug Targeting and Drug Delivery System West China School of PharmacySichuan UniversityChengdu 610041China Institute of Cytology of Russian Academy of Sciences(RAS) St.Petersburg 194064Russia

Insufficient intratumoral retention of nanomedicines remains the major challenge for broad implementation in clinical ***,we proposed a legumain-triggered aggregable gold nanoparticle(GNP)delivery platform(GNPs-A&C).GNPs-A&C could form intratumoral or intracellular aggregates in response to the overexpressed *** aggregates with size increase not only could reduce back-flow from interstitial space to peripheral bloodstream but also could restrict the cellular exocytosis,leading to enhanced intratumoral *** vitro studies demonstrated that GNPs-A&C possessed an excellent legumain responsiveness and the increased size was closely relevant with legumain *** vivo studies demonstrated GNPs-A&C possessed slower clearance rate and much higher intratumoral retention within legumain-overexpressed tumor compared to non-aggregable NPs,regardless of intravenous or intratumoral *** importantly,this delivery platform significantly improved the chemotherapeutic effect of doxorubicin(DOX)towards subcutaneous xenograft C6 *** effectiveness of this stimulus-responsive aggregable delivery system provides a thinking for designing more intelligent size-tunable nanomedicine that can substantially improve intratumoral retention.

关键词： Legumain Size-tunable Enhanced retention Stimulus-responsive Nanomedicine

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Diverse foraging strategies of breeding Swinhoe's Storm-petrel in the productive marginal sea of the Northwest Pacific

引用

Avian Research 2024年第1期15卷 27-34页

作者： Yachang Cheng Lei Zhu Lin Xue Shisheng Ma Nan Jia shaoping Zang Zhihai Cao Jing Yuan Yang Liu State Key Laboratory of Biocontrol School of EcologySun Yat-sen UniversityShenzhen 518107China Guangxi Mangrove Research Center Guangxi Marine Academy of SciencesNanning 530021China Qingdao Bird Watch Society Qingdao 266121China Jiangsu Provincial Environmental Monitoring Center Nanjing 210019China Marine Science and Engineering Qingdao Agricultural UniversityQingdao 266109China Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering Fudan UniversityShanghai 200433China Qingdao Marine Management and Support Centre Qingdao 266555China Management Committee of Lingshan Island Provincial Nature Reserve Qingdao 266428China

Understanding the foraging behavior is essential for investigating seabird ecology and conservation,as well as monitoring the well-being of the marine *** seabirds adopt diverse foraging strategies to maximize energy gains and cope with the intensified challenges of parenting and *** tradeoff may stem from the heterogeneity of food resources and the constraints of central place ***,abundant marine productivity could alleviate the energy limitation for seabirds,resulting in a consistent foraging ***,we investigated the foraging strategy during the breeding season of a cryptic small-sized seabird,Swinhoe’s Storm-petrel(Hydrobates monorhis),in the Yellow Sea,a productive marginal sea of the Northwest *** GPS tracking,we evaluated habitat preference,quantified the foraging strategy,and tested if environmental conditions and individual traits influence foraging *** found that Swinhoe’s Storm-petrels preferred nearshore areas with shallow water and engaged in primarily short foraging *** southeastward and southwestward strategies emerged when combining trip metrics,including foraging direction,duration,and maximum *** bathymetry,proximity to the coastline,and sea surface temperature differed in two foraging *** strategies exhibited flexibility between individuals,potentially explained by wing morphology,in which longer-winged birds are more likely to embark on longer-distance foraging *** findings highlight the impact of environmental factors and individual traits on seabirds’foraging decisions in productive marginal sea *** study also provides valuable insights into the foraging ecology of this Asian endemic storm-petrel.

关键词： Behavioral strategy Biologging Central place foraging Marine primary productivity Seabird Sea surface temperature

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

爆炸载荷下钢板层裂的二维数值计算

引用

爆炸与冲击 1999年第2期19卷 97-102页

作者：王肖钧刘文韬张刚明肖绍平中国科技大学近代力学系

采用二维有限元方法对爆炸载荷下钢板的层裂问题进行数值模拟计算。计算中引入了一种普适的弹塑性本构方程，并采用了损伤积累准则和半解耦的损伤本构模型。结果表明，二维计算的主裂片厚度略小于一维计算，裂片飞散速度要比一维计算低... 详细信息

采用二维有限元方法对爆炸载荷下钢板的层裂问题进行数值模拟计算。计算中引入了一种普适的弹塑性本构方程，并采用了损伤积累准则和半解耦的损伤本构模型。结果表明，二维计算的主裂片厚度略小于一维计算，裂片飞散速度要比一维计算低得多。

关键词：层裂有限元爆炸载荷弹塑性本构钢板数值解

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：