Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 89

年份

2023 11

2022 7

2021 5

2020 8

2019 8

2018 6

2017 10

2016 6

2015 4

2013 1

2011 2

2010 5

2009 2

2007 5

2006 2

2005 2

2004 2

2001 2

2000 1

展开︾

关键词

人脸识别 2

特征抽取 2

Pd局域环境 1

Powell法 1

YAG激光淬火 1

三峡电站 1

不同性能探测模块 1

丙烯 1

乙炔半加氢 1

二维线性鉴别分析 1

人为地形变化 1

以太网连接的嵌入 1

公共无线局域网 1

农村能源革命 1

刀具状态监测；流形学习；降维；扩散映射分析；内蕴特征提取 1

分布式优化 1

分布式系统 1

分布式能源 1

区块链 1

展开︾

检索范围：

排序：展示方式：

Xiao-hu MA,Meng YANG,Zhao ZHANG

《信息与电子工程前沿（英文）》 2016年第17卷第3期页码 212-223 doi: 10.1631/FITEE.1500255

摘要： The feature extraction algorithm plays an important role in face recognition. However, the extracted features also have overlapping discriminant information. A property of the statistical uncorrelated criterion is that it eliminates the redundancy among the extracted discriminant features, while many algorithms generally ignore this property. In this paper, we introduce a novel feature extraction method called local uncorrelated local discriminant embedding (LULDE). The proposed approach can be seen as an extension of a local discriminant embedding (LDE) framework in three ways. First, a new local statistical uncorrelated criterion is proposed, which effectively captures the local information of interclass and intraclass. Second, we reconstruct the affinity matrices of an intrinsic graph and a penalty graph, which are mentioned in LDE to enhance the discriminant property. Finally, it overcomes the small-sample-size problem without using principal component analysis to preprocess the original data, which avoids losing some discriminant information. Experimental results on Yale, ORL, Extended Yale B, and FERET databases demonstrate that LULDE outperforms LDE and other representative uncorrelated feature extraction methods.

关键词： Feature extraction Local discriminant embedding Local uncorrelated criterion Face recognition

HTML PDF 收藏

一种局部二次嵌入学习算法及其在软测量中的应用 Article

包垚垚, 朱远明, 钱峰

《工程（英文）》 2022年第18卷第11期页码 186-196 doi: 10.1016/j.eng.2022.04.025

摘要：

鉴于元学习在众多领域取得的巨大成就，本文针对数据回归问题提出了融合度量学习和神经网络（NN）的局部二次嵌入学习（LQEL）算法。首先，通过优化输入输出空间里样本间度量的全局一致性来改进马氏度量（Mahalanobis metric）学习算法；同时，通过引入松弛约束进一步证明了改进的度量学习问题等价于一个凸规划问题。然后，基于局部二次插值假设原理，引入了两个轻量级的神经网络，其一用于学习局部二次模型中的系数矩阵，另一个则用于对从不同局部近邻获得的预测结果进行权重分配。最后，将两个子模型嵌入统一的回归框架中，并通过随机梯度下降（SGD）算法学习模型参数。所提出的算法优势在于可充分利用目标标签中隐含的信息找到更可靠的参考样本。并且，使用LQEL算法对变量进行差分建模，避免了因传感器漂移或不可测量变量导致的模型退化问题。多个基准数据集和两个实际工业应用数据集的计算结果表明，所提出的方法优于几种典型的回归方法。

关键词：局部二次嵌入度量学习回归机软测量

HTML PDF 收藏

A novel multimode process monitoring method integrating LDRSKM with Bayesian inference

Shi-jin REN,Yin LIANG,Xiang-jun ZHAO,Mao-yun YANG

《信息与电子工程前沿（英文）》 2015年第16卷第8期页码 617-633 doi: 10.1631/FITEE.1400263

摘要： A local discriminant regularized soft -means (LDRSKM) method with Bayesian inference is proposed for multimode process monitoring. LDRSKM extends the regularized soft -means algorithm by exploiting the local and non-local geometric information of the data and generalized linear discriminant analysis to provide a better and more meaningful data partition. LDRSKM can perform clustering and subspace selection simultaneously, enhancing the separability of data residing in different clusters. With the data partition obtained, kernel support vector data description (KSVDD) is used to establish the monitoring statistics and control limits. Two Bayesian inference based global fault detection indicators are then developed using the local monitoring results associated with principal and residual subspaces. Based on clustering analysis, Bayesian inference and manifold learning methods, the within and cross-mode correlations, and local geometric information can be exploited to enhance monitoring performances for nonlinear and non-Gaussian processes. The effectiveness and efficiency of the proposed method are evaluated using the Tennessee Eastman benchmark process.

关键词： Multimode process monitoring Local discriminant regularized soft k-means clustering Kernel support vector data description Bayesian inference Tennessee Eastman process

HTML PDF 收藏

Virtual network embedding based on real-time topological attributes

Jian DING,Tao HUANG,Jiang LIU,Yun-jie LIU

《信息与电子工程前沿（英文）》 2015年第16卷第2期页码 109-118 doi: 10.1631/FITEE.1400147

摘要： As a great challenge of network virtualization, virtual network embedding/mapping is increasingly important. It aims to successfully and efficiently assign the nodes and links of a virtual network (VN) onto a shared substrate network. The problem has been proved to be NP-hard and some heuristic algorithms have been proposed. However, most of the algorithms use only the local information of a node, such as CPU capacity and bandwidth, to determine how to map a VN, without considering the topological attributes which may pose significant impact on the performance of the embedding. In this paper, a new embedding algorithm is proposed based on real-time topological attributes. The concept of betweenness centrality in graph theory is borrowed to sort the nodes of VNs, and the nodes of the substrate network are sorted according to the correlation properties between the former selected and unselected nodes. In this way, node mapping and link mapping can be well coupled. A simulator is built to evaluate the performance of the proposed virtual network embedding (VNE) algorithm. The results show that the new algorithm significantly increases the revenue/cost (R/C) ratio and acceptance ratio as well as reduces the runtime.

关键词： Virtual network embedding (VNE) Real-time topological attributes Betweenness centrality Correlation properties Network virtualization

HTML PDF 收藏

An approach for mechanical fault classification based on generalized discriminant analysis

LI Wei-hua, SHI Tie-lin, YANG Shu-zi

《机械工程前沿（英文）》 2006年第1卷第3期页码 292-298 doi: 10.1007/s11465-006-0022-2

摘要： To deal with pattern classification of complicated mechanical faults, an approach to multi-faults classification based on generalized discriminant analysis is presented. Compared with linear discriminant analysis (LDA), generalized discriminant analysis (GDA), one of nonlinear discriminant analysis methods, is more suitable for classifying the linear non-separable problem. The connection and difference between KPCA (Kernel Principal Component Analysis) and GDA is discussed. KPCA is good at detection of machine abnormality while GDA performs well in multi-faults classification based on the collection of historical faults symptoms. When the proposed method is applied to air compressor condition classification and gear fault classification, an excellent performance in complicated multi-faults classification is presented.

关键词： generalized discriminant non-separable abnormality classification multi-faults classification

HTML PDF 收藏

基于代价敏感学习的实体-关系联合知识嵌入 Article

Sheng-kang YU, Xue-yi ZHAO, Xi LI, Zhong-fei ZHANG

《信息与电子工程前沿（英文）》 2017年第18卷第11期页码 1867-1873 doi: 10.1631/FITEE.1601255

摘要：我们将实体嵌入问题看作同时完成两个不同但相关的嵌入任务（实体嵌入和关系嵌入）的联合优化问题，并在联合嵌入框架下求解该问题。在该嵌入框架下，我们设计了联合评分函数，用以对实体和关系间的相关性实例进行量化评价，并将评分函数融入最大间隔学习方法中，使用知识库中的上下文信息学习实体与关系的嵌入向量。通过求解联合优化问题，我们的设计有效地表达了嵌入空间的固有拓扑结构。实验结果证实了我们的嵌入框架在表达不同关系的语义相关性和进行知识推理中的关系预测时的有效性。

关键词：知识嵌入；联合嵌入；代价敏感学习

HTML PDF 收藏

High-order phase-field model with the local and second-order max-entropy approximants

Fatemeh AMIRI

《结构与土木工程前沿（英文）》 2019年第13卷第2期页码 406-416 doi: 10.1007/s11709-018-0475-5

摘要： We approximate the fracture surface energy functional based on phase-field method with smooth local maximum entropy (LME) and second-order maximum entropy (SME) approximants. The higher-order continuity of the meshfree methods such as LME and SME approximants allows to directly solve the fourth-order phase-field equations without splitting the fourth-order differential equation into two second-order differential equations. We will first show that the crack surface functional can be captured more accurately in the fourth-order model with smooth approximants such as LME, SME and B-spline. Furthermore, smaller length scale parameter is needed for the fourth-order model to approximate the energy functional. We also study SME approximants and drive the formulations. The proposed meshfree fourth-order phase-field formulation show more stable results for SME compared to LME meshfree methods.

关键词： second-order maximum entropy local maximum entropy second- and fourth-order phase-field models B-spline

HTML PDF 收藏

Making central-local relations work: Comparing America and China environmental governance systems

Dan GUTTMAN, SONG Yaqin

《环境科学与工程前沿（英文）》 2007年第1卷第4期页码 418-433 doi: 10.1007/s11783-007-0068-3

摘要： The challenge of making central requirements work at local levels is a common problem for environmental governance throughout the world. Countries can learn from one another s approaches, but must understand the local context in w

HTML PDF 收藏

EXPLORING THE RELATIVE ADVANTAGES OF LOCAL INNOVATION IN AGROFORESTRY

《农业科学与工程前沿（英文）》 2023年第10卷第1期页码 61-72 doi: 10.15302/J-FASE-2022476

摘要：

● Promotion of local sustainable innovation developed by forest farmers.

关键词： agroforestry forest farmers local innovation relative advantage social forestry

HTML PDF 收藏

Preparation and characterization of a novel microorganism embedding material for simultaneous nitrification

Ming Zeng, Ping Li, Nan Wu, Xiaofang Li, Chang Wang

《环境科学与工程前沿（英文）》 2017年第11卷第6期 doi: 10.1007/s11783-017-0961-3

摘要： A novel microorganism embedding material was prepared to enhance the biological nitrogen removal through simultaneous nitrification and denitrification. Polyvinyl alcohol (PVA), sodium alginate (SA) and cyclodextrin (CD) were used to compose gel bead with embedded activated sludge. The effects of temperature, CD addition and concentrations of PVA and SA on nitrogen removal were evaluated. Results show that the gel bead with CD addition at 30°C contributed to the highest nitrogen removal efficiency and nitrogen removal rate of 85.4% and 2.08 mg·(L·h)?1, respectively. Meanwhile, negligible NO3? and NO2? were observed, proving the occurrence of simultaneous nitrification and denitrification. The High-Throughput Sequencing confirms that the microbial community mainly contained Comamonadaceae in the proportion of 61.3%. Overall, CD increased gel bead’s porosity and resulted in the high specific endogenous respiration rate and high nitrogen removal efficiency, which is a favorable additional agent to the traditional embedding material.

关键词： Immobilization technology Nitrogen removal Cyclodextrin Microbial community Wastewater treatment

HTML PDF 收藏

Role of local governments in fostering the development of an emerging industry: A market-oriented policy

Jun JIN, Maureen McKELVEY, Ying DONG

《工程管理前沿（英文）》 2020年第7卷第3期页码 447-458 doi: 10.1007/s42524-020-0104-6

摘要： This research investigates the role of local governments in stimulating an emerging industry and focuses on the specific growth of the new energy vehicle industry in Hangzhou, China. This research confirms that enabling firms to access emerging technology, acquire financial support, and touch customers and/or suppliers are critical to foster the emergence and development of industries. Moreover, the primary contribution of this study is to emphasize the support of the local government in the development of emerging industries on the perspective of the creation of a large-scale market demand. The creation of large-scale market demand may inspire actors to be proactive in responding to these incentives; thus, public and private actions may help increase the accessibility to technology, infrastructure, and finances. Hence, a market-oriented policy that incentivizes the creation and expansion of market demand among diverse public and private actors should be seen as the key issue for the emergence and growth of emerging industries. Policies should also be adopted promptly with the development of the market.

关键词： market demand local government new energy vehicles

HTML PDF 收藏

Understand the local and regional contributions on air pollution from the view of human health impacts

《环境科学与工程前沿（英文）》 2021年第15卷第5期 doi: 10.1007/s11783-020-1382-2

摘要：

• PM_2.5-related deaths were estimated to be 227 thousand in BTH & surrounding regions.

关键词： PM_2.5 Regional transport Local emissions Health impact Environmental inequality

HTML PDF 收藏

基于模糊集理论的二维线性鉴别分析新方法

郑宇杰,杨静宇,吴小俊,李勇智

《中国工程科学》 2007年第9卷第2期页码 49-53

摘要：

二维线性鉴别分析（２DLDA）是一种直接基于矩阵的特征提取方法，跳过传统的基于Fisher鉴别准则的线性鉴别分析方法中必须先将二维矩阵转化成一维矢量的过程，有效地提高了特征提取速度且避免了小样本问题，其识别率优于传统的Fisherface方法。结合模糊集理论，提出了一种新的２DLDA算法——模糊２DLDA （F１DLDA）算法。首先采用FKNN算法得到相应的样本分布信息，并按其对最后得到的特征向量所作的贡献融入到特征抽取过程中，得到有效的样本特征向量集。实验表明，F２DLDA算法的性能优于传统的２DLDA算法和Fisherface算法。

关键词：二维线性鉴别分析模糊二维线性鉴别分析模糊集理论特征提取模糊k近邻

HTML PDF 收藏

Improvement of impact resistance of plain-woven composite by embedding superelastic shape memory alloy

Xiaojun GU, Xiuzhong SU, Jun WANG, Yingjie XU, Jihong ZHU, Weihong ZHANG

《机械工程前沿（英文）》 2020年第15卷第4期页码 547-557 doi: 10.1007/s11465-020-0595-1

摘要： Carbon fiber reinforced polymer (CFRP) composites have excellent mechanical properties, specifically, high specific stiffness and strength. However, most CFRP composites exhibit poor impact resistance. To overcome this limitation, this study presents a new plain-woven CFRP composite embedded with superelastic shape memory alloy (SMA) wires. Composite specimens are fabricated using the vacuum-assisted resin injection method. Drop-weight impact tests are conducted on composite specimens with and without SMA wires to evaluate the improvement of impact resistance. The material models of the CFRP composite and superelastic SMA wire are introduced and implemented into a finite element (FE) software by the explicit user-defined material subroutine. FE simulations of the drop-weight impact tests are performed to reveal the superelastic deformation and debonding failure of the SMA inserts. Improvement of the energy absorption capacity and toughness of the SMA-CFRP composite is confirmed by the comparison results.

关键词： carbon fiber reinforced polymer composite shape memory alloy wire impact resistance drop-weight test finite element simulation

HTML PDF 收藏

统计不相关最佳鉴别矢量集的本质研究

吴小俊,杨静宇,王士同,刘同明,Josef Kittler

《中国工程科学》 2004年第6卷第2期页码 44-47

摘要：

对统计不相关最佳鉴别矢量集的本质进行研究，在基于总体散布矩阵特征分解的基础上，构造了一种白化变换，使得变换后的样本空间中的总体散布矩阵为单位矩阵，这样使得传统的最佳鉴别矢量集算法得到的均是具有统计不相关的最佳鉴别矢量集，从而揭示了统计不相关最佳鉴别变换的本质——白化变换加普通的线性鉴别变换。该方法的最大优点在于所获得的最优鉴别矢量同时具有正交性和统计不相关性。该方法对代数特征抽取具有普遍适用性。用ORL人脸数据库的数值实验，验证了该方法的有效性。

关键词：模式识别特征抽取鉴别分析广义最佳鉴别矢量集人脸识别