资源类型

期刊论文 8

年份

2022 2

2021 2

2020 1

2019 2

2018 1

关键词

一致性；网络一致性；拉普拉斯能量 1

决策树；多类不平衡学习；节点划分准则；海林格距离；一对多技术 1

学习方法 1

模糊决策树 1

模糊认知图 1

氟化铝添加 1

水下图像压缩；SPIHT压缩；压缩感知；压缩质量预测 1

状态转移优化方法 1

展开 ︾

检索范围：

排序： 展示方式：

A case for assessing

Ian T. RILEY

《农业科学与工程前沿（英文）》 2021年 第8卷 第4期   页码 568-582 doi: 10.15302/J-FASE-2019270

摘要： Agroecosystems in water-limited contexts— Mediterranean, semi-arid and arid climatic zones—are too frequently degraded systems that will not provide the needed ecosystem services to ensure a future of sustainable agricultural production. The processes that have created this situation continue and are being accelerated by anthropogenic climate change. Increasing arboreal vegetation in these areas through agroforestry is an important strategy to conserve and improve their agroecosystems. Actinorhizal trees and shrubs in the Casurinaceae have a unique set of adaptations for heat and water stress, and/or infertile to hostile soils. Central Anatolia, Turkey is particularly at risk of increasing aridity and further degradation. Therefore, species of and have been evaluated for their potential use in agroecosystem improvement in semi-arid areas with a focus on Central Anatolia. Based on a semiquantitative environmental tolerance index and reported plant stature, eight species were identified as being of high ( . and . ) to moderate ( . , . , . , . , . and . ) priority for assessment, with none of these species having been adequately evaluated for agroforestry deployment in semi-arid agroecosystems in any context.

关键词： actinorrhizal trees     agroforestry     climate change     ecosystem restoration    

HTML PDF 收藏

A CASE FOR ASSESSING ALLOCASUARINA AND CASUARINA SPP. FOR USE IN AGROECOSYSTEM IMPROVEMENT IN SEMI-ARID AREAS WITH A FOCUS ON CENTRAL ANATOLIA, TURKEY

《农业科学与工程前沿（英文）》 2021年 第8卷 第4期   页码 568-582 doi: 10.15302/J-FASE -2019270

摘要：

Agroecosystems in water-limited contexts— Mediterranean, semi-arid and arid climatic zones—are too frequently degraded systems that will not provide the needed ecosystem services to ensure a future of sustainable agricultural production. The processes that have created this situation continue and are being accelerated by anthropogenic climate change. Increasing arboreal vegetation in these areas through agroforestry is an important strategy to conserve and improve their agroecosystems. Actinorhizal trees and shrubs in the Casurinaceae have a unique set of adaptations for heat and water stress, and/or infertile to hostile soils. Central Anatolia, Turkey is particularly at risk of increasing aridity and further degradation. Therefore, species of Allocasuarina and Casuarina have been evaluated for their potential use in agroecosystem improvement in semi-arid areas with a focus on Central Anatolia. Based on a semiquantitative environmental tolerance index and reported plant stature, eight species were identified as being of high (A. verticillata and C. pauper) to moderate (A. acutivalvis, A. decaisneana, A. dielsiana, A. huegeliana, C. cristata and C. obesa) priority for assessment, with none of these species having been adequately evaluated for agroforestry deployment in semi-arid agroecosystems in any context.

 

关键词： actinorrhizal trees / agroforestry / climate change / ecosystem restoration    

HTML PDF 收藏

Predicting shear strength of slender beams without reinforcement using hybrid gradient boosting trees

Thuy-Anh NGUYEN; Hai-Bang LY; Van Quan TRAN

《结构与土木工程前沿（英文）》 2022年 第16卷 第10期   页码 1267-1286 doi: 10.1007/s11709-022-0842-0

摘要： Shear failure of slender reinforced concrete beams without stirrups has surely been a complicated occurrence that has proven challenging to adequately understand. The primary purpose of this work is to develop machine learning models capable of reliably predicting the shear strength of non-shear-reinforced slender beams (SB). A database encompassing 1118 experimental findings from the relevant literature was compiled, containing eight distinct factors. Gradient Boosting (GB) technique was developed and evaluated in combination with three different optimization algorithms, namely Particle Swarm Optimization (PSO), Random Annealing Optimization (RA), and Simulated Annealing Optimization (SA). The findings suggested that GB-SA could deliver strong prediction results and effectively generalizes the connection between the input and output variables. Shap values and two-dimensional PDP analysis were then carried out. Engineers may use the findings in this work to define beam's geometrical components and material used to achieve the desired shear strength of SB without reinforcement.

关键词： slender beam     shear strength     gradient boosting     optimization algorithms    

HTML PDF 收藏

irrigation with high irrigation frequency improves root growth and reduces unproductive water loss by apple trees

Shaoqing DU, Ling TONG, Shaozhong KANG, Fusheng LI, Taisheng DU, Sien LI, Risheng DING

《农业科学与工程前沿（英文）》 2018年 第5卷 第2期   页码 188-196 doi: 10.15302/J-FASE-2017176

摘要： Alternate partial root-zone irrigation (APRI) can improve water use efficiency in arid areas. However, the effectiveness and outcomes of different frequencies of APRI on water uptake capacity and physiological water use have not been reported. A two-year field experiment was conducted with two irrigation amounts (400 and 500 mm) and three irrigation methods (conventional irrigation, APRI with high and low frequencies). Root length density, stomatal conductance, photosynthetic rate, transpiration rate, leaf water use efficiency, midday stem and leaf water potentials were measured. The results show that in comparison with conventional irrigation, APRI with high frequency significantly increased root length density and decreased water potentials and stomatal conductance. No differences in the above indicators between the two APRI frequencies were detected. A significantly positive relationship between stomatal conductance and root length density was found under APRI. Overall, alternate partial root-zone irrigation with high frequency has a great potential to promote root growth, expand water uptake capacity and reduce unproductive water loss in the arid apple production area.

关键词： alternate partial root-zone irrigation     apple tree     leaf water use efficiency     root length density     stomatal conductance     water potential    

HTML PDF 收藏

具有受控初始状态递归树的一致性分析及其拉普拉斯能量 Research Articles

洪美都,孙伟刚,刘苏雨,轩腾飞

《信息与电子工程前沿（英文）》 2020年 第21卷 第6期   页码 809-962 doi: 10.1631/FITEE.1900133

摘要： 本文研究一类具有受控初始状态递归树的一致性问题。由拉普拉斯谱定义的网络一致性用于刻画含有噪声线性系统的一致性动力学。基于这类递归树的规则结构，得到拉普拉斯特征值连续两次迭代的递归关系，并由此得到一阶和二阶一致性的精确解。它们由所有非零拉普拉斯特征值的倒数和与平方和来定义。一阶和二阶一致性的幂律关于网络规模N分别为ln N和N。研究表明递归树初始节点数目越少，其一致性表现越好。最后，用数值例子研究一致性和拉普拉斯能量之间的关系，结果表明一阶和二阶一致性分别随拉普拉斯能量以指数和线性速率增长。

关键词： 一致性；网络一致性；拉普拉斯能量    

HTML PDF 收藏

基于质量感知的水下图像自适应压缩方法 Regular Papers

Ya-qiong CAI, Hai-xia ZOU, Fei YUAN

《信息与电子工程前沿（英文）》 2019年 第20卷 第5期   页码 716-730 doi: 10.1631/FITEE.1700737

摘要： 水下图像压缩是水声图像传输系统中必不可少并且至关重要的一个环节，有效的预测感知压缩图像的质量能使系统在压缩过程更好的调整压缩率，提高图像传输通信系统的效率。本文首先分别对压缩感知和嵌入式编码两种压缩策略下的水下压缩图像进行质量感知，然后利用图像活动性IAM（Image Activity Measurement）与BPP-SSIM（Bits Per Pixel and Structural SIMilarity）曲线间的映射进行建模并获得模型参数，从而根据图像的空域活动性、压缩率和压缩策略预测图像的压缩质量。实验结果表明本文所建立的模型能有效拟合水下图像的压缩质量曲线，根据模型中参数所具有的规律性能在小误差范围内预测出水下压缩图像的感知质量。本文所提出的方法能够有效的预测感知水下图像的压缩质量，并有效权衡压缩率与压缩质量之间的关系，减小发送端的数据缓存压力，提高水下图像通信系统的效率。

关键词： 水下图像压缩；SPIHT压缩；压缩感知；压缩质量预测    

HTML PDF 收藏

基于强化模糊认知图实现数据与知识协作的氟化铝添加量决策方法 Article

岳伟超, 桂卫华, 陈晓方, 曾朝晖, 谢永芳

《工程（英文）》 2019年 第5卷 第6期   页码 1060-1076 doi: 10.1016/j.eng.2019.10.005

摘要：

在铝电解过程中，添加氟化铝能降低电解质的初晶温度，从而提高电流效率。氟化铝添加量的决策是一项复杂的知识型工作，需要考虑许多相关的因素，在实际生产中主要依赖于人工经验。由于工艺人员的主观性以及铝电解槽的复杂性，基于知识或者基于数据的决策方法难以保证添加的准确性。现有的决策方法难以囊括复杂的因果关系。本文针对氟化铝添加量的决策提出了一种基于强化模糊认知图的数据与知识协作策略。在这种方法中，改进的模糊k均值和模糊决策树用于提取模糊规则，其中提取的规则用于修正专家提出的初始框架。同时，采用状态转移优化算法（STA）获取强化模糊认知图的权重。将提出的方法与已有方法进行对比，结果表明，强化模糊认知的收敛速度快于基于Hebbian学习方法、粒子群优化方法以及遗传算法。不仅如此，基于所提方法氟化铝添加量的决策准确率高于其他方法。因此，针对氟化铝添加量的决策，本文提出的方法是有效的。

关键词： 氟化铝添加     模糊认知图     学习方法     状态转移优化方法     模糊决策树    

HTML PDF 收藏

面向多类不平衡学习的一对多海林格距离决策树研究 Research Articles

董明刚1,2,刘明1,2,敬超1,2,3

《信息与电子工程前沿（英文）》 2022年 第23卷 第2期   页码 278-290 doi: 10.1631/FITEE.2000417

摘要： 由于传统机器学习方法对偏斜分布很敏感，且未考虑多类不平衡问题的特点，多类偏斜分布对机器学习算法来说是一个巨大挑战。为解决这一问题，提出一种新的基于一对多的海林格距离（OAHD）决策树分割准则。OAHD主要由两部分组成。首先，将一对多思想集成到OAHD的海林格距离计算过程中，从而对海林格距离决策树进行扩展，使其能解决多类不平衡问题。其次，针对多类不平衡问题，考虑了不同类的分布和数量，设计了改进的基尼系数。此外，对OAHD的性质进行理论证明，包括偏斜不敏感性和在决策树中寻找更纯节点的能力。最后，从基于进化学习的知识抽取（KEEL）和加州大学欧文分校（UCI）数据库中收集20个公开的真实不平衡数据集进行实验。实验结果表明，与其他5种常用决策树相比，OAHD在精度、F值，和多类别接收者操作特征曲线下面积（MAUC）上有显著优势。此外，使用了Friedman和Nemenyi检验，统计结果表明OAHD优于其他5种决策树。

关键词： 决策树；多类不平衡学习；节点划分准则；海林格距离；一对多技术    

HTML PDF 收藏

标题 作者 时间 类型 操作

A case for assessing

Ian T. RILEY

期刊论文

A CASE FOR ASSESSING ALLOCASUARINA AND CASUARINA SPP. FOR USE IN AGROECOSYSTEM IMPROVEMENT IN SEMI-ARID AREAS WITH A FOCUS ON CENTRAL ANATOLIA, TURKEY

期刊论文

Predicting shear strength of slender beams without reinforcement using hybrid gradient boosting trees

Thuy-Anh NGUYEN; Hai-Bang LY; Van Quan TRAN

期刊论文

irrigation with high irrigation frequency improves root growth and reduces unproductive water loss by apple trees

Shaoqing DU, Ling TONG, Shaozhong KANG, Fusheng LI, Taisheng DU, Sien LI, Risheng DING

期刊论文

具有受控初始状态递归树的一致性分析及其拉普拉斯能量

洪美都,孙伟刚,刘苏雨,轩腾飞

期刊论文

基于质量感知的水下图像自适应压缩方法

Ya-qiong CAI, Hai-xia ZOU, Fei YUAN

期刊论文

基于强化模糊认知图实现数据与知识协作的氟化铝添加量决策方法

岳伟超, 桂卫华, 陈晓方, 曾朝晖, 谢永芳

期刊论文

面向多类不平衡学习的一对多海林格距离决策树研究

董明刚1,2,刘明1,2,敬超1,2,3

期刊论文