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 10

年份

2022 2

2021 3

2018 2

2010 1

2009 1

2008 1

关键词

流形学习 2

Laplacian特征映射 1

低维流形 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

变量选择 1

多元回归方法 1

毫米波 1

特征选择；降维；文本分类；冗余特征；支持向量机；朴素贝叶斯；互信息 1

特征选择；高维；学习技术；微阵列数据集 1

离群数据 1

离群点检测 1

稀疏性 1

维数约减 1

降秩回归 1

降维 1

非线性降维 1

高维数据 1

展开︾

检索范围：

排序：展示方式：

Development trend of urban design in “digital age”: Pan-dimensionality and individual-ubiquity

《结构与土木工程前沿（英文）》 2021年第15卷第3期页码 569-575 doi: 10.1007/s11709-021-0735-7

摘要： The wave of “digital age” featuring digital information is coming. Digital technology is profoundly changing the societal development direction and evolution paths. It also has significant bearing on production modes, social interactions and lifestyles. With regard to urban design, a system of knowledge about the creation and adaptation of material space forms that integrate humanities, art, technology and materials, digital technology has provided it with a brand-new and revolutionary scientific impetus for its evolution. The result of this evolution is “digital urban design paradigm based on human-computer interaction”, i.e., the urban development is moving toward “pan-dimensionality” and “individual ubiquity”. The future of urban design will construct a new approach to urban research and engineering, which is more complex, capable of accommodating and compatible with multiple goals of “instrumental rationality” and “value rationality”. Such a new approach shall be led by the probabilistic theory of “gray scale thinking”, reflecting quaternary synergetic view of “scientific rationality, ecological rationality, cultural rationality and technical rationality” to realize the cognitive progress of “engineering for the benefit of mankind”.

关键词： digital age urban design multiple objectives human-computer interaction pan-dimensionality individual-ubiquity

HTML PDF 收藏

Fuel optimal control of parallel hybrid electric vehicles

PU Jinhuan, YIN Chenliang, ZHANG Jianwu

《机械工程前沿（英文）》 2008年第3卷第3期页码 337-342 doi: 10.1007/s11465-008-0057-7

摘要： A mathematical model for fuel optimal control and its corresponding dynamic programming (DP) recursive equation were established for an existing parallel hybrid electric vehicle (HEV). Two augmented cost functions for gear shifting and engine stop-starting were designed to limit their frequency. To overcome the problem of numerical DP dimensionality, an algorithm to restrict the exploring region was proposed. The algorithm significantly reduced the computational complexity. The system model was converted into real-time simulation code by using MATLAB/RTW to improve computation efficiency. Comparison between the results of a chassis dynamometer test, simulation, and DP proves that the proposed method can compute the performance limitation of the HEV within an acceptable time period and can be used to evaluate and optimize the control strategy.

关键词： mathematical Comparison computational complexity dimensionality corresponding

HTML PDF 收藏

A MATLAB code for the material-field series-expansion topology optimization method

《机械工程前沿（英文）》 2021年第16卷第3期页码 607-622 doi: 10.1007/s11465-021-0637-3

摘要： This paper presents a MATLAB implementation of the material-field series-expansion (MFSE) topo-logy optimization method. The MFSE method uses a bounded material field with specified spatial correlation to represent the structural topology. With the series-expansion method for bounded fields, this material field is described with the characteristic base functions and the corresponding coefficients. Compared with the conventional density-based method, the MFSE method decouples the topological description and the finite element discretization, and greatly reduces the number of design variables after dimensionality reduction. Other features of this method include inherent control on structural topological complexity, crisp structural boundary description, mesh independence, and being free from the checkerboard pattern. With the focus on the implementation of the MFSE method, the present MATLAB code uses the maximum stiffness optimization problems solved with a gradient-based optimizer as examples. The MATLAB code consists of three parts, namely, the main program and two subroutines (one for aggregating the optimization constraints and the other about the method of moving asymptotes optimizer). The implementation of the code and its extensions to topology optimization problems with multiple load cases and passive elements are discussed in detail. The code is intended for researchers who are interested in this method and want to get started with it quickly. It can also be used as a basis for handling complex engineering optimization problems by combining the MFSE topology optimization method with non-gradient optimization algorithms without sensitivity information because only a few design variables are required to describe relatively complex structural topology and smooth structural boundaries using the MFSE method.

关键词： MATLAB implementation topology optimization material-field series-expansion method bounded material field dimensionality reduction

HTML PDF 收藏

扩大多元回归方法在跨组学研究中的范围 Article

Xiaoxi Hu, Yue Ma, Yakun Xu, Peiyao Zhao, Jun Wang

《工程（英文）》 2021年第7卷第12期页码 1725-1731 doi: 10.1016/j.eng.2020.05.028

摘要：

近年来科技的进步和发展使得高维数据急剧增加，研究人员对合适且有效的多元回归方法的需求也随之增长。许多传统的多元分析方法如主成分分析等已广泛应用于投资分析、图像识别和群体遗传结构分析等研究领域。然而，这些常见的方法存在其局限性，即忽略了响应之间的相关性和变量选择效率低的问题。因此，本文引入了降秩回归方法及其扩展形式——稀疏降秩回归和行稀疏的子空间辅助回归，这些方法有望满足上述需求，从而提高回归模型的可解释性。我们通过开展仿真研究来评估它们的效果，并将它们与其他几种变量选择方法进行比较。对于不同的应用场景，我们也提供了基于预测能力和变量选择精度的选择建议。最后，为了证明这些方法在微生物组研究领域的实用价值，我们将所选择的方法应用于实际种群水平的微生物组数据，结果验证了我们方法的有效性。该方法的扩展形式为未来的组学研究特别是多元回归研究提供了有价值的指导，并为微生物组学及其相关研究领域的新发现奠定了基础。

关键词：多元回归方法降秩回归稀疏性降维变量选择

HTML PDF 收藏

Dimensionality reduction and prediction of soil consolidation coefficient using random forest coupling

Hai-Bang LY; Huong-Lan Thi VU; Lanh Si HO; Binh Thai PHAM

《结构与土木工程前沿（英文）》 2022年第16卷第2期页码 224-238 doi: 10.1007/s11709-022-0812-6

摘要： The consolidation coefficient of soil (C_v) is a crucial parameter used for the design of structures leaned on soft soi. In general, the C_v is determined experimentally in the laboratory. However, the experimental tests are time-consuming as well as expensive. Therefore, researchers tried several ways to determine C_v via other simple soil parameters. In this study, we developed a hybrid model of Random Forest coupling with a Relief algorithm (RF-RL) to predict the C_v of soil. To conduct this study, a database of soil parameters collected from a case study region in Vietnam was used for modeling. The performance of the proposed models was assessed via statistical indicators, namely Coefficient of determination (R²), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The proposal models were constructed with four sets of soil variables, including 6, 7, 8, and 13 inputs. The results revealed that all models performed well with a high performance (R² > 0.980). Although the RF-RL model with 13 variables has the highest prediction accuracy ( R² = 0.9869), the difference compared with other models was negligible (i.e., R² = 0.9824, 0.9850, 0.9825 for the cases with 6, 7, 8 inputs, respectively). Thus, it can be concluded that the hybrid model of RF-RL can be employed to predict C_v based on the basic soil parameters.

关键词： soil consolidation coefficient machine learning random forest Relief

HTML PDF 收藏

微阵列数据集的特征选择技术：综合评述、分类和未来方向 Review

Kulanthaivel BALAKRISHNAN, Ramasamy DHANALAKSHMI

《信息与电子工程前沿（英文）》 2022年第23卷第10期页码 1451-1478 doi: 10.1631/FITEE.2100569

摘要：

为获得最佳结果，从微阵列数据集中检索相关特征已成为特征选择（FS）技术的研究热点。本综述旨在全面阐述各种最新特征选择技术，同时介绍了基于微阵列数据集的处理多类分类问题的技术以及提高学习算法性能的不同方法。我们试图理解和解决数据集不平衡问题，以证实研究人员在微阵列数据集上的工作。对文献的分析为理解和强调在通过各种特征选择技术寻找最佳特征子集时存在的众多挑战和问题铺平了道路。同时提供了一个案例说明该方法的实施过程，该方法使用3个微阵列癌症数据集评估一些包装方法和混合方法的分类精度和收敛能力，以确认最优特征子集。

关键词：特征选择；高维；学习技术；微阵列数据集

HTML PDF 收藏

基于Laplacian特征映射的被动毫米波目标识别

罗磊,李跃华,栾英宏

《中国工程科学》 2010年第12卷第3期页码 77-81

摘要：

针对传统被动毫米波金属目标识别方法中特征提取、选择的缺点，采用Laplacian特征映射流形学习算法发现了金属目标回波信号短

关键词：流形学习 Laplacian特征映射非线性降维低维流形毫米波

HTML PDF 收藏

基于流形学习的离群点检测方法

徐雪松,宋东明,张谞,许满武,刘凤玉

《中国工程科学》 2009年第11卷第2期页码 82-87

摘要：

为了提高高维数据集合离群数据挖掘效率，提出了一种基于流形学习的离群点检测算法。局部线性嵌入（ locally linear embedding， LLE）算法是流形学习中有效的非线性降维方法，它的优势在于只定义唯一的参数，即邻域数。根据LLE算法的思想寻找样本数据的内在嵌入分布，并通过邻域数选取和降维后数据点之间的距离调整，提高了数据集中离群点发现效率，同时利用离群点权值判别式进行权值数据判定，根据权值的大小标识出数据集中的离群点，仿真实验的结果表明了该方法能够有效地发现高维数据集中的离群点。与此同时，该算法具有参数估计简单、参数影响不大等优点，该算法为离群点检测问题的机器学习提供了一条新的途径。

关键词：流形学习离群点检测高维数据维数约减离群数据

HTML PDF 收藏

一种用于文本分类的去冗余特征选择新方法 None

You-wei WANG, Li-zhou FENG

《信息与电子工程前沿（英文）》 2018年第19卷第2期页码 221-234 doi: 10.1631/FITEE.1601761

摘要：特征选择是文本分类领域一种重要降维方法。针对传统特征选择方法所选特征集常包含冗余信息的问题，提出一种能够有效去除冗余信息的特征选择新方法。首先，为衡量两个词之间的关系，引入基于词频的相关性和相对冗余词集的概念；接着，选择一种最优特征选择方法并用其获得一个临时特征子集；最后，为提高算法执行效率，结合预设阈值去除临时特征子集中的冗余特征，并将结果存储在链表结构中。实验以支持向量机和朴素贝叶斯作为分类器，并以WebKB、20-Newsgroups和Reuters-21578作为测试数据集。实验结果表明，该方法分类精度高于传统特征选择方法；相对于基于互信息的方法而言，该方法能够在保证分类精度的同时，有效提高运行效率。

关键词：特征选择；降维；文本分类；冗余特征；支持向量机；朴素贝叶斯；互信息

HTML PDF 收藏

基于判别扩散映射分析的内蕴特征提取方法在刀具磨损评估中的应用 None

Yi-xiang HUANG, Xiao LIU, Cheng-liang LIU, Yan-ming LI

《信息与电子工程前沿（英文）》 2018年第19卷第11期页码 1352-1361 doi: 10.1631/FITEE.1601512

摘要：针对铣削加工刀具磨损评估，提出一种基于判别扩散映射分析的方法。判别扩散映射分析（discriminant diffusion maps analysis，DDMA）用于时频域特征提取融合与维度缩减。通过保持内蕴特征空间的扩散距离，耦合时频域特征和判别内核，提取有效信息。该方法包含3个步骤：(1)信号处理与特征提取；(2)内蕴维度估计；(3)基于扩散距离保持的特征融合实现。将该方法应用于数控加工中心主轴驱动电流信号，评估刀具磨损状态。与常见主成分分析方法相比，该方法能更好保持刀具磨损状态相关的有用内蕴信息，大大降低与刀具磨损相关的特征维度，并可直接应用于大多数工业数控加工中心，方便获取电流信号实际情况。

关键词：刀具状态监测；流形学习；降维；扩散映射分析；内蕴特征提取

HTML PDF 收藏

标题作者时间类型操作

Development trend of urban design in “digital age”: Pan-dimensionality and individual-ubiquity

期刊论文

Fuel optimal control of parallel hybrid electric vehicles

PU Jinhuan, YIN Chenliang, ZHANG Jianwu

期刊论文

A MATLAB code for the material-field series-expansion topology optimization method

期刊论文

扩大多元回归方法在跨组学研究中的范围

Xiaoxi Hu, Yue Ma, Yakun Xu, Peiyao Zhao, Jun Wang