Search | Engineering

订阅投稿

首页学术期刊学术焦点学术视频工程成就工程前沿关于我们 English

资源类型

期刊论文 50

年份

2023 7

2022 3

2021 3

2020 4

2019 4

2018 4

2017 9

2016 6

2015 2

2013 1

2010 1

2008 1

2007 1

2002 2

2000 1

展开︾

关键词

A^*算法 1

不确定性 1

云模型 1

交叉模态 1

低剂量CT；CT成像；全变分；稀疏字典学习 1

信任网络；稀疏学习；同质效应；交互行为 1

动态二叉树 1

协议独立的组播路由一稀疏模式（PIM-SM) 1

固定边界布图规划；修正的模拟退火算法；全局搜索；溢出面积模型；B*-tree表示法 1

图学习；半监督学习；节点分类；注意力机制 1

基于依存关系的上下文；多义词表示；表示学习；句法词向量 1

多会聚点（RPs) 1

多重知识表达；人工智能；大数据 1

大数据知识工程 1

定性概念 1

小阻尼稀疏模态系统 1

层级-方向分解分析；水印框架；轮廓小波嵌入表达；扰码模块；模拟攻击 1

成品率预测；参数扰动；多元参数成品率；性能建模；稀疏表示 1

战场损伤评估；改进的KL散度稀疏自动编码机；结构优化；特征选择 1

展开︾

检索范围：

排序：展示方式：

基于稀疏表示的拉普拉斯稀疏字典图像分类 Article

Fang LI, Jia SHENG, San-yuan ZHANG

《信息与电子工程前沿（英文）》 2017年第18卷第11期页码 1795-1805 doi: 10.1631/FITEE.1600039

摘要：为取得更小且表现更好的字典，本文提出一种基于流形学习及双稀疏理论的拉普拉斯稀疏字典学习方法（Laplacian sparse dictionary, LSD）。

关键词：稀疏表示；拉普拉斯正则子；字典学习；双稀疏；流形

HTML PDF 收藏

基于核稀疏表示的磁共振图像分析及其在脑肿瘤自动分割中的应用 None

Ji-jun TONG, Peng ZHANG, Yu-xiang WENG, Dan-hua ZHU

《信息与电子工程前沿（英文）》 2018年第19卷第4期页码 471-480 doi: 10.1631/FITEE.1620342

摘要：脑肿瘤分割在疾病辅助诊断、治疗方案规划以及手术导航中扮演重要角色。对脑肿瘤精确分割可以帮助临床医生获取肿瘤位置、尺寸和形状信息。提出一种基于核稀疏编码的全自动脑肿瘤分割方法，并在3D多模态磁共振成像图（magnetic resonance imaging, MRI）上验证。首先对MRI图像进行预处理以减少噪声，然后通过核字典学习提取非线性特征，用来构建坏死组织、水肿组织、非增强肿瘤组织、增强肿瘤组织和健康组织5个适应性字典。对从原始MRI图像上肿瘤像素点周边m×m×m的小区域提取的特征向量进行稀疏编码，并通过一种基于字典学习的核聚类方法对像素点进行编码。最后通过形态滤波填充在多个相连部分间的区域，提高分割质量。为评估分割表现，分割结果被上传到在线评估系统中，该评估系统使用dice系数、阳性预测值（positive predictive value, PPV）、灵敏度和kappa值作为评估指标。结果表明，该方法在完整肿瘤区域分割上具有良好表现（dice: 0.83; PPV: 0.84; sensitivity: 0.82），而在肿瘤核心区域（dice: 0.69; PPV: 0.76; sensitivity: 0.80）和增强肿瘤区域（dice: 0.58; PPV: 0.60; sensitivity: 0.65）上表现稍差。相较于脑肿瘤分割（BRATS）挑战中其他团队采用的方法，该方法具有竞争力。该方法在健康组织和病理组织区分上具有一定潜力。

关键词：脑肿瘤分割；核方法；稀疏编码；字典学习

HTML PDF 收藏

基于变分贝叶斯多稀疏成分提取的空间碎片超高速撞击损伤重构方法研究 Research Article

黄雪刚,石安华,罗庆,罗锦阳

《信息与电子工程前沿（英文）》 2022年第23卷第4期页码 530-541 doi: 10.1631/FITEE.2000575

摘要：为提高在轨航天器抵御空间碎片撞击的生存能力，提出一种撞击损伤评估方法。首先，建立一个针对红外热图像序列数据的多区域损伤挖掘模型，用于描述处于不同空间层的撞击损伤。采用变分贝叶斯推理来求解模型参数，从而有效地从红外热图像数据中识别不同类型撞击损伤。然后，提出一种图像处理框架，包括具有能量函数的图像分割算法和具有稀疏表示的图像融合方法，以消除变异贝叶斯误差并比较不同类型损伤的位置。在试验部分，将上述方法用于评估二次碎片云对Whipple防护结构的复杂撞击损伤。实验结果证明本文提出的方法可以对空间碎片超高速撞击造成的不同类型复杂损伤进行有效识别与评估。

关键词：超高速撞击；变分贝叶斯；稀疏表示；损伤评估

HTML PDF 收藏

结构化稀疏学习综述 Review

Lin-bo QIAO, Bo-feng ZHANG, Jin-shu SU, Xi-cheng LU

《信息与电子工程前沿（英文）》 2017年第18卷第4期页码 445-463 doi: 10.1631/FITEE.1601489

摘要：稀疏学习由于其简约特性和计算优势而获得了越来越多的关注，在具有稀疏性的条件下，许多计算问题可以在实践中得到有效的处理。而结构化稀疏学习则进一步将结构信息进行编码，在多个研究领域取得成功。随着各类型结构的发现，人们相继提出了各种结构化正则函数。这些正则函数通过利用特定的结构信息极大提高了稀疏学习算法的性能。在本文中，我们从想法、形式化、算法和应用等方面系统的回顾了结构化稀疏学习。我们将这些算法置于最小化损失函数和惩罚函数的统一框架中，总结了算法的开源软件实现，并比较了典型优化算法解决结构化稀疏学习问题时的计算复杂度。在实验中，我们给出了无监督学习在结构化信号恢复和层次化图像重建中的应用，以及具有图结构引导的逻辑回归的在监督学习中的应用。

关键词：结构化稀疏学习；算法；应用

HTML PDF 收藏

Face recognition based on subset selection via metric learning on manifold

Hong SHAO,Shuang CHEN,Jie-yi ZHAO,Wen-cheng CUI,Tian-shu YU

《信息与电子工程前沿（英文）》 2015年第16卷第12期页码 1046-1058 doi: 10.1631/FITEE.1500085

摘要： With the development of face recognition using sparse representation based classification (SRC), many relevant methods have been proposed and investigated. However, when the dictionary is large and the representation is sparse, only a small proportion of the elements contributes to the 1-minimization. Under this observation, several approaches have been developed to carry out an efficient element selection procedure before SRC. In this paper, we employ a metric learning approach which helps find the active elements correctly by taking into account the interclass/intraclass relationship and manifold structure of face images. After the metric has been learned, a neighborhood graph is constructed in the projected space. A fast marching algorithm is used to rapidly select the subset from the graph, and SRC is implemented for classification. Experimental results show that our method achieves promising performance and significant efficiency enhancement.

关键词： Face recognition Sparse representation Manifold structure Metric learning Subset selection

HTML PDF 收藏

考虑设计参数扰动的芯片多元参数成品率预测算法 Article

Xin LI,Jin SUN,Fu XIAO

《信息与电子工程前沿（英文）》 2016年第17卷第12期页码 1344-1359 doi: 10.1631/FITEE.1601225

摘要：随着芯片制造工艺的进步，工艺参数、供电电压及片上温度（Process, voltage, and temperature, PVT）等设计参数扰动已成为芯片设计过程的棘手问题，其所产生的性能指标间相关性将导致芯片参数成品率显著下降。但是，当前芯片参数成品率预测算法主要局限于单一性能指标成品率预测或对多个单性能指标成品率进行均衡优化，而不能同时针对多个性能指标约束进行多元参数成品率预测，易造成参数成品率精度缺失。基于以上问题，本文将多个性能指标同时作为约束条件，提出一种芯片多元参数成品率预测方法。该方法首先考虑PVT参数扰动，利用自适应弹性网（Adaptive elastic net, AEN）对芯片性能指标进行建模。然后，基于乘法定理及马尔科夫链蒙特卡罗法，通过求解累积分布函数（Cumulative distribution function, CDF）对单一性能指标的芯片参数成品率进行预测。最后，同时考虑多个芯片性能指标约束，根据Copula方法准确预测芯片多元参数成品率。实验结果表明，本文方法可以在指定性能指标约束下对芯片多元参数成品率进行有效预测，并可为芯片设计人员提供任意性能指标约束下的多元参数成品率预测曲面。

关键词：成品率预测；参数扰动；多元参数成品率；性能建模；稀疏表示

HTML PDF 收藏

稀疏快速Clifford傅里叶变换 Article

Rui WANG, Yi-xuan ZHOU, Yan-liang JIN, Wen-ming CAO

《信息与电子工程前沿（英文）》 2017年第18卷第8期页码 1131-1141 doi: 10.1631/FITEE.1500452

摘要：稀疏快速傅里叶变换（sparse fast Fourier transform, sFFT）理论通过选择性地使用输入数据来处理大数据问题。受之启发，我们提出一个称为稀疏快速Clifford傅里叶变换（sparse fast CFT, SFCFT）的算法，该算法能够大幅度提高在标量场和矢量场中的计算性能。

关键词：稀疏快速傅里叶变换（sFFT）；Clifford傅里叶变换（CFT）；稀疏快速Clifford傅里叶变换（SFCFT）；Clifford代数

HTML PDF 收藏

Non-convex sparse optimization-based impact force identification with limited vibration measurements

《机械工程前沿（英文）》 2023年第18卷第3期 doi: 10.1007/s11465-023-0762-2

摘要： Impact force identification is important for structure health monitoring especially in applications involving composite structures. Different from the traditional direct measurement method, the impact force identification technique is more cost effective and feasible because it only requires a few sensors to capture the system response and infer the information about the applied forces. This technique enables the acquisition of impact locations and time histories of forces, aiding in the rapid assessment of potentially damaged areas and the extent of the damage. As a typical inverse problem, impact force reconstruction and localization is a challenging task, which has led to the development of numerous methods aimed at obtaining stable solutions. The classical

ℓ 2

regularization method often struggles to generate sparse solutions. When solving the under-determined problem,

ℓ 2

regularization often identifies false forces in non-loaded regions, interfering with the accurate identification of the true impact locations. The popular

ℓ 1

sparse regularization, while promoting sparsity, underestimates the amplitude of impact forces, resulting in biased estimations. To alleviate such limitations, a novel non-convex sparse regularization method that uses the non-convex

ℓ 1 − 2

penalty, which is the difference of the

ℓ 1

and

ℓ 2

norms, as a regularizer, is proposed in this paper. The principle of alternating direction method of multipliers (ADMM) is introduced to tackle the non-convex model by facilitating the decomposition of the complex original problem into easily solvable subproblems. The proposed method named

ℓ 1 − 2 -ADMM

is applied to solve the impact force identification problem with unknown force locations, which can realize simultaneous impact localization and time history reconstruction with an under-determined, sparse sensor configuration. Simulations and experiments are performed on a composite plate to verify the identification accuracy and robustness with respect to the noise of the

ℓ 1 − 2 -ADMM

method. Results indicate that compared with other existing regularization methods, the

ℓ 1 − 2 -ADMM

method can simultaneously reconstruct and localize impact forces more accurately, facilitating sparser solutions, and yielding more accurate results.

关键词： impact force identification inverse problem sparse regularization under-determined condition alternating direction method of multipliers

HTML PDF 收藏

Standard model of knowledge representation

Wensheng YIN

《机械工程前沿（英文）》 2016年第11卷第3期页码 275-288 doi: 10.1007/s11465-016-0372-3

摘要：

Knowledge representation is the core of artificial intelligence research. Knowledge representation methods include predicate logic, semantic network, computer programming language, database, mathematical model, graphics language, natural language, etc. To establish the intrinsic link between various knowledge representation methods, a unified knowledge representation model is necessary. According to ontology, system theory, and control theory, a standard model of knowledge representation that reflects the change of the objective world is proposed. The model is composed of input, processing, and output. This knowledge representation method is not a contradiction to the traditional knowledge representation method. It can express knowledge in terms of multivariate and multidimensional. It can also express process knowledge, and at the same time, it has a strong ability to solve problems. In addition, the standard model of knowledge representation provides a way to solve problems of non-precision and inconsistent knowledge.

关键词： knowledge representation standard model ontology system theory control theory multidimensional representation

HTML PDF 收藏

Uncertainty propagation analysis by an extended sparse grid technique

X. Y. JIA, C. JIANG, C. M. FU, B. Y. NI, C. S. WANG, M. H. PING

《机械工程前沿（英文）》 2019年第14卷第1期页码 33-46 doi: 10.1007/s11465-018-0514-x

摘要： In this paper, an uncertainty propagation analysis method is developed based on an extended sparse grid technique and maximum entropy principle, aiming at improving the solving accuracy of the high-order moments and hence the fitting accuracy of the probability density function (PDF) of the system response. The proposed method incorporates the extended Gauss integration into the uncertainty propagation analysis. Moreover, assisted by the Rosenblatt transformation, the various types of extended integration points are transformed into the extended Gauss-Hermite integration points, which makes the method suitable for any type of continuous distribution. Subsequently, within the sparse grid numerical integration framework, the statistical moments of the system response are obtained based on the transformed points. Furthermore, based on the maximum entropy principle, the obtained first four-order statistical moments are used to fit the PDF of the system response. Finally, three numerical examples are investigated to demonstrate the effectiveness of the proposed method, which includes two mathematical problems with explicit expressions and an engineering application with a black-box model.

关键词： uncertainty propagation analysis extended sparse grid maximum entropy principle extended Gauss integration Rosenblatt transformation high-order moments analysis

HTML PDF 收藏

Applicability of high dimensional model representation correlations for ignition delay times of n-heptane

Wang LIU, Jiabo ZHANG, Zhen HUANG, Dong HAN

《能源前沿（英文）》 2019年第13卷第2期页码 367-376 doi: 10.1007/s11708-018-0584-9

摘要： It is difficult to predict the ignition delay times for fuels with the two-stage ignition tendency because of the existence of the nonlinear negative temperature coefficient (NTC) phenomenon at low temperature regimes. In this paper, the random sampling-high dimensional model representation (RS-HDMR) methods were employed to predict the ignition delay times of n-heptane/air mixtures, which exhibits the NTC phenomenon, over a range of initial conditions. A detailed n-heptane chemical mechanism was used to calculate the fuel ignition delay times in the adiabatic constant-pressure system, and two HDMR correlations, the global correlation and the stepwise correlations, were then constructed. Besides, the ignition delay times predicted by both types of correlations were validated against those calculated using the detailed chemical mechanism. The results showed that both correlations had a satisfactory prediction accuracy in general for the ignition delay times of the n-heptane/air mixtures and the stepwise correlations exhibited a better performance than the global correlation in each subdomain. Therefore, it is concluded that HDMR correlations are capable of predicting the ignition delay times for fuels with two-stage ignition behaviors at low-to-intermediate temperature conditions.

关键词： ignition delay random sampling high dimensional model representation n-heptane fuel kinetics

HTML PDF 收藏

Home location inference from sparse and noisy data: models and applications

Tian-ran HU,Jie-bo LUO,Henry KAUTZ,Adam SADILEK

《信息与电子工程前沿（英文）》 2016年第17卷第5期页码 389-402 doi: 10.1631/FITEE.1500385

摘要： Accurate home location is increasingly important for urban computing. Existing methods either rely on continuous (and expensive) Global Positioning System (GPS) data or suffer from poor accuracy. In particular, the sparse and noisy nature of social media data poses serious challenges in pinpointing where people live at scale. We revisit this research topic and infer home location within 100 m×100 m squares at 70% accuracy for 76% and 71% of active users in New York City and the Bay Area, respectively. To the best of our knowledge, this is the first time home location has been detected at such a fine granularity using sparse and noisy data. Since people spend a large portion of their time at home, our model enables novel applications. As an example, we focus on modeling people’s health at scale by linking their home locations with publicly available statistics, such as education disparity. Results in multiple geographic regions demonstrate both the effectiveness and added value of our home localization method and reveal insights that eluded earlier studies. In addition, we are able to discover the real buzz in the communities where people live.

关键词： Home location Mobility patterns Healthcare

HTML PDF 收藏

Digital representation of meso-geomaterial spatial distribution and associated numerical analysis of

YUE Zhongqi

《结构与土木工程前沿（英文）》 2007年第1卷第1期页码 80-93 doi: 10.1007/s11709-007-0008-0

摘要： This paper presents the author's efforts in the past decade for the establishment of a practical approach of digital representation of the geomaterial distribution of different minerals, particulars, and components in the meso-scale range (0.1 to 500 mm). The primary goal of the approach is to provide a possible solution to solve the two intrinsic problems associated with the current main-stream methods for geomechanics. The problems are (1) the constitutive models and parameters of soils and rocks cannot be given accurately in geomechanical prediction; and (2) there are numerous constitutive models of soils and rocks in the literature. The problems are possibly caused by the homogenization or averaging method in analyzing laboratory test results for establishing the constitutive models and parameters. The averaging method employs an assumption that the test samples can be represented by a homogeneous medium. Such averaging method ignores the fact that the geomaterial samples are also consisted of a number of materials and components whose properties may have significant differences. In the proposed approach, digital image processing methods are used as measurement tools to construct a digital representation for the actual spatial distribution of the different materials and components in geomaterial samples. The digital data are further processed to automatically generate meshes or grids for numerical analysis. These meshes or grids can be easily incorporated into existing numerical software packages for further mechanical analysis and failure prediction of the geomaterials under external loading. The paper presents case studies to illustrate the proposed approach. Further discussions are also made on how to use the proposed approach to develop the geomechanics by taking into account the geomaterial behavior at micro-scale, meso-scale and macro-scale levels. A literature review of the related developments is given by examining the SCI papers in the database of Science Citation Index Expanded. The results of this review have shown that the proposed approach is one of the latest research and developments in geomechanics where actual spatial distribution and properties of materials and components at the meso-level are taken into account.

关键词： homogeneous numerical analysis Expanded homogenization meso-level

HTML PDF 收藏

知识表示中的不确定性

李德毅

《中国工程科学》 2000年第2卷第10期页码 73-79

摘要：

知识表示一直是人工智能研究中的一个瓶颈，其难点在于知识中隐含有不确定性，即模糊性和随机性。文章提出用云模型3个数字特征（期望值，熵，超熵）来描述一个定性概念，用熵来关联模糊性和随机性。代表定性概念的云的某一次定量值，被称为云滴，可以用它对此概念的贡献度来衡量，许许多多云滴构成云，实现定性和定量之间的随时转换，反映了知识表示中的不确定性。论文以此对我国农历24个节气进行了新的量化解释。云方法已经用于数据开采、智能控制、跳频电台和大系统效能评估中，取得明显的效果。

关键词：知识表示定性概念不确定性云模型数宇特征

HTML PDF 收藏

基于RGBD和稀疏学习的鲁棒目标跟踪 Article

Zi-ang MA, Zhi-yu XIANG

《信息与电子工程前沿（英文）》 2017年第18卷第7期页码 989-1001 doi: 10.1631/FITEE.1601338

摘要：鲁棒目标跟踪近年来成为计算机视觉领域一项重要的且极具挑战性的研究方向。随着深度传感器的普及，深度信息因其对光照变化与遮挡表现出一定的鲁棒性而被广泛应用于视觉目标跟踪算法中。本文提出了一种基于RGBD和稀疏学习的跟踪算法，从三个方面将深度信息应用到稀疏学习跟踪框架。首先将深度图像特征结合现有的基于彩色图像的视觉特征用于目标外观的鲁棒特征描述。为了适应跟踪过程中的各种遮挡情况，我们设计了一种特殊的遮挡物模板用于增广现有的超完备字典。最后，我们进一步提出了一种基于深度信息的遮挡物检测方法用于有效地指示模板更新。基于KITTI和Princeton数据集的大量实验证明了所提出算法的跟踪效果优于时下最先进的多种跟踪器，包括基于稀疏学习的跟踪以及基于RGBD的跟踪。

关键词：目标跟踪；稀疏学习；深度视角；遮挡物模板；深度图像特征

HTML PDF 收藏

标题作者时间类型操作

基于稀疏表示的拉普拉斯稀疏字典图像分类

Fang LI, Jia SHENG, San-yuan ZHANG

期刊论文

基于核稀疏表示的磁共振图像分析及其在脑肿瘤自动分割中的应用

Ji-jun TONG, Peng ZHANG, Yu-xiang WENG, Dan-hua ZHU

期刊论文

基于变分贝叶斯多稀疏成分提取的空间碎片超高速撞击损伤重构方法研究

黄雪刚,石安华,罗庆,罗锦阳

期刊论文