资源类型

期刊论文 481

会议视频 7

年份

2023 76

2022 84

2021 57

2020 53

2019 38

2018 27

2017 41

2016 17

2015 16

2014 5

2013 7

2012 5

2011 3

2010 4

2009 2

2008 9

2007 10

2006 4

2005 3

2003 2

展开 ︾

关键词

机器学习 27

深度学习 15

人工智能 12

2022全球十大工程成就 2

人工神经网络 2

代理模型 2

多输入多输出 2

工程管理 2

强化学习 2

材料设计 2

结构健康监测 2

高层建筑 2

2016年熊本地震 1

2D—3D配准 1

3D打印 1

6G 1

ALOS-2 PALSAR-2 1

ARM 1

BFT 1

展开 ︾

检索范围：

排序： 展示方式：

An assessment of surrogate fuel using Bayesian multiple kernel learning model in sight of sooting tendency

《能源前沿（英文）》 2022年 第16卷 第2期   页码 277-291 doi: 10.1007/s11708-021-0731-6

摘要： An integrated and systematic database of sooting tendency with more than 190 kinds of fuels was obtained through a series of experimental investigations. The laser-induced incandescence (LII) method was used to acquire the 2D distribution of soot volume fraction, and an apparatus-independent yield sooting index (YSI) was experimentally obtained. Based on the database, a novel predicting model of YSI values for surrogate fuels was proposed with the application of a machine learning method, named the Bayesian multiple kernel learning (BMKL) model. A high correlation coefficient (0.986) between measured YSIs and predicted values with the BMKL model was obtained, indicating that the BMKL model had a reliable and accurate predictive capacity for YSI values of surrogate fuels. The BMKL model provides an accurate and low-cost approach to assess surrogate performances of diesel, jet fuel, and biodiesel in terms of sooting tendency. Particularly, this model is one of the first attempts to predict the sooting tendencies of surrogate fuels that concurrently contain hydrocarbon and oxygenated components and shows a satisfying matching level. During surrogate formulation, the BMKL model can be used to shrink the surrogate candidate list in terms of sooting tendency and ensure the optimal surrogate has a satisfying matching level of soot behaviors. Due to the high accuracy and resolution of YSI prediction, the BMKL model is also capable of providing distinguishing information of sooting tendency for surrogate design.

关键词： sooting tendency     yield sooting index     Bayesian multiple kernel learning     surrogate assessment     surrogate formulation    

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

Multiple fault separation and detection by joint subspace learning for the health assessment of wind

Zhaohui DU, Xuefeng CHEN, Han ZHANG, Yanyang ZI, Ruqiang YAN

《机械工程前沿（英文）》 2017年 第12卷 第3期   页码 333-347 doi: 10.1007/s11465-017-0435-0

摘要：

The gearbox of a wind turbine (WT) has dominant failure rates and highest downtime loss among all WT subsystems. Thus, gearbox health assessment for maintenance cost reduction is of paramount importance. The concurrence of multiple faults in gearbox components is a common phenomenon due to fault induction mechanism. This problem should be considered before planning to replace the components of the WT gearbox. Therefore, the key fault patterns should be reliably identified from noisy observation data for the development of an effective maintenance strategy. However, most of the existing studies focusing on multiple fault diagnosis always suffer from inappropriate division of fault information in order to satisfy various rigorous decomposition principles or statistical assumptions, such as the smooth envelope principle of ensemble empirical mode decomposition and the mutual independence assumption of independent component analysis. Thus, this paper presents a joint subspace learning-based multiple fault detection (JSL-MFD) technique to construct different subspaces adaptively for different fault patterns. Its main advantage is its capability to learn multiple fault subspaces directly from the observation signal itself. It can also sparsely concentrate the feature information into a few dominant subspace coefficients. Furthermore, it can eliminate noise by simply performing coefficient shrinkage operations. Consequently, multiple fault patterns are reliably identified by utilizing the maximum fault information criterion. The superiority of JSL-MFD in multiple fault separation and detection is comprehensively investigated and verified by the analysis of a data set of a 750 kW WT gearbox. Results show that JSL-MFD is superior to a state-of-the-art technique in detecting hidden fault patterns and enhancing detection accuracy.

关键词： joint subspace learning     multiple fault diagnosis     sparse decomposition theory     coupling feature separation     wind turbine gearbox    

HTML PDF 收藏

Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD, Wen-Jing GU

《结构与土木工程前沿（英文）》 2021年 第15卷 第2期   页码 490-505 doi: 10.1007/s11709-020-0669-5

摘要： This study investigates the performance of four machine learning (ML) algorithms to evaluate the earthquake-induced liquefaction potential of soil based on the cone penetration test field case history records using the Bayesian belief network (BBN) learning software Netica. The BBN structures that were developed by ML algorithms-K2, hill climbing (HC), tree augmented naive (TAN) Bayes, and Tabu search were adopted to perform parameter learning in Netica, thereby fixing the BBN models. The performance measure indexes, namely, overall accuracy ( ), precision, recall, , and area under the receiver operating characteristic curve, were used to evaluate the training and testing BBN models’ performance and highlight the capability of the K2 and TAN Bayes models over the Tabu search and HC models. The sensitivity analysis results showed that the cone tip resistance and vertical effective stress are the most sensitive factors, whereas the mean grain size is the least sensitive factor in the prediction of seismic soil liquefaction potential. The results of this study can provide theoretical support for researchers in selecting appropriate ML algorithms and improving the predictive performance of seismic soil liquefaction potential models.

关键词： seismic soil liquefaction     Bayesian belief network     cone penetration test     parameter learning     structural learning    

HTML PDF 收藏

基于带约束最大间隔的贝叶斯分类器判别学习方法 None

Ke GUO, Xia-bi LIU, Lun-hao GUO, Zong-jie LI, Zeng-min GENG

《信息与电子工程前沿（英文）》 2018年 第19卷 第5期   页码 639-650 doi: 10.1631/FITEE.1700007

摘要： 提出一种新的面向贝叶斯模式分类的判别学习方法，称作“带约束的最大间隔（CMM）方法”。通过计算正样本最小决策值和负样本最大决策值的差异，定义类别之间的类别间隔。基于该类别间隔和正确分类的约束，将间隔函数学习问题转化为最大化类别间隔问题。利用序列无约束最小化技术解决该非线性规划问题。运用CMM方法得到基于高斯混合模型的贝叶斯分类器，并在10个UCI数据集上进行实验。结果表明，利用CMM方法得到的分类器分类性能，明显优于代表性的生成式学习方法期望最大化（EM）和判别式学习方法支持向量机（SVM），并且在多个数据集上取得了相比之前最优结果更好的效果。分类实验和分类器对比实验证明，CMM方法有效，具有一定应用前景。

关键词： 判别学习；统计建模；贝叶斯分类器；高斯混合模型；UCI数据集    

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

裂缝性储层数据驱动模型证伪与不确定性量化 Article

方军龄, 龚斌, Jef Caers

《工程（英文）》 2022年 第18卷 第11期   页码 116-128 doi: 10.1016/j.eng.2022.04.015

摘要：

天然裂缝的许多特性是不确定的，如裂缝的空间分布、岩石物理特性和流体流动性能。贝叶斯定理提供了一个框架来量化地质建模和流动模拟的不确定性，从而支持储层物性预测。贝叶斯方法在裂缝性储层中的应用大多局限于合成案例。然而，在现场应用中，一个主要问题是贝叶斯先验是被证伪的，因为它不能预测油气藏的生产历史。在本文中，我们展示了如何利用全局敏感性分析（GSA）来确定先验被证伪的原因。然后，我们采用近似贝叶斯计算（ABC）方法，结合基于决策树的代理模型来拟合生产历史。我们将这两种方法应用于一个复杂的裂缝性油气藏，其中综合考虑了所有不确定因素，包括油层物理特性、岩石物理特性、流体特性、离散裂缝参数以及压力和渗透率的动态变化。我们成功地找出了证伪的几个原因。结果表明，我们提出的方法可以有效地量化裂缝性储层建模和流动模拟的不确定性。此外，关键参数的不确定性，如裂缝开度和断层传导率，得到了降低。

关键词： 贝叶斯证据学习     证伪     裂隙性储层     随机森林     近似贝叶斯计算    

HTML PDF 收藏

IN2CLOUD: A novel concept for collaborative management of big railway data

Jing LIN, Uday KUMAR

《工程管理前沿（英文）》 2017年 第4卷 第4期   页码 428-436 doi: 10.15302/J-FEM-2017048

摘要： In the EU Horizon 2020 Shift2Rail Multi-Annual Action Plan, the challenge of railway maintenance is generating knowledge from data and/or information. Therefore, we promote a novel concept called “IN2CLOUD,” which comprises three sub-concepts, to address this challenge: 1) A hybrid cloud, 2) an intelligent cloud with hybrid cloud learning, and 3) collaborative management using asset-related data acquired from the intelligent hybrid cloud. The concept is developed under the assumption that organizations want/need to learn from each other (including domain knowledge and experience) but do not want to share their raw data or information. IN2CLOUD will help the movement of railway industry systems from “local” to “global” optimization in a collaborative way. The development of cutting-edge intelligent hybrid cloud-based solutions, including information technology (IT) solutions and related methodologies, will enhance business security, economic sustainability, and decision support in the field of intelligent asset management of railway assets.

关键词： railway     intelligent asset management     collaborative learning     big data     hybrid cloud     Bayesian    

HTML PDF 收藏

Evaluation of liquefaction-induced lateral displacement using Bayesian belief networks

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD

《结构与土木工程前沿（英文）》 2021年 第15卷 第1期   页码 80-98 doi: 10.1007/s11709-021-0682-3

摘要： Liquefaction-induced lateral displacement is responsible for considerable damage to engineered structures during major earthquakes. Therefore, an accurate estimation of lateral displacement in liquefaction-prone regions is an essential task for geotechnical experts for sustainable development. This paper presents a novel probabilistic framework for evaluating liquefaction-induced lateral displacement using the Bayesian belief network (BBN) approach based on an interpretive structural modeling technique. The BBN models are trained and tested using a wide-range case-history records database. The two BBN models are proposed to predict lateral displacements for free-face and sloping ground conditions. The predictive performance results of the proposed BBN models are compared with those of frequently used multiple linear regression and genetic programming models. The results reveal that the BBN models are able to learn complex relationships between lateral displacement and its influencing factors as cause–effect relationships, with reasonable precision. This study also presents a sensitivity analysis to evaluate the impacts of input factors on the lateral displacement.

关键词： Bayesian belief network     seismically induced soil liquefaction     interpretive structural modeling     lateral displacement    

HTML PDF 收藏

Fast implementation of kernel simplex volume analysis based on modified Cholesky factorization for endmember

Jing LI,Xiao-run LI,Li-jiao WANG,Liao-ying ZHAO

《信息与电子工程前沿（英文）》 2016年 第17卷 第3期   页码 250-257 doi: 10.1631/FITEE.1500244

摘要： Endmember extraction is a key step in the hyperspectral image analysis process. The kernel new simplex growing algorithm (KNSGA), recently developed as a nonlinear alternative to the simplex growing algorithm (SGA), has proven a promising endmember extraction technique. However, KNSGA still suffers from two issues limiting its application. First, its random initialization leads to inconsistency in final results; second, excessive computation is caused by the iterations of a simplex volume calculation. To solve the first issue, the spatial pixel purity index (SPPI) method is used in this study to extract the first endmember, eliminating the initialization dependence. A novel approach tackles the second issue by initially using a modified Cholesky factorization to decompose the volume matrix into triangular matrices, in order to avoid directly computing the determinant tautologically in the simplex volume formula. Theoretical analysis and experiments on both simulated and real spectral data demonstrate that the proposed algorithm significantly reduces computational complexity, and runs faster than the original algorithm.

关键词： Endmember extraction     Modified Cholesky factorization     Spatial pixel purity index (SPPI)     New simplex growing algorithm (NSGA)     Kernel new simplex growing algorithm (KNSGA)    

HTML PDF 收藏

A Bayesian modeling approach to bi-directional pedestrian flows in carnival events

S. Q. XIE, S. C. WONG, William H. K. LAM

《工程管理前沿（英文）》 2017年 第4卷 第4期   页码 483-489 doi: 10.15302/J-FEM-2017023

摘要： Bi-directional pedestrian flows are common at crosswalks, footpaths, and shopping areas. However, the properties of pedestrian movement may vary in urban areas according to the type of walking facility. In recent years, crowd movements at carnival events have attracted the attention of researchers. In contrast to pedestrian behavior in other walking facilities, pedestrians whose attention is attracted by carnival displays or activities may slow down and even stop walking. The Lunar New Year Market is a traditional carnival event in Hong Kong held annually one week before the Lunar New Year. During the said event, crowd movements can be easily identified, particularly in Victoria Park, where the largest Lunar New Year Market in Hong Kong is hosted. In this study, we conducted a video-based observational survey to collect pedestrian flow and speed data at the Victoria Park Lunar New Year Market on the eve of the Lunar New Year. Using the collected data, an extant mathematical model was calibrated to capture the relationships between the relevant macroscopic quantities, thereby providing insight into pedestrian behavior at the carnival event. Bayesian inference was employed to calibrate the model by using prior data obtained from a previous controlled experiment. Results obtained enhance our understanding of crowd behavior under different conditions at carnival events, thus facilitating the improvement of the safety and efficiency of similar events in the future.

关键词： pedestrian flow model     bi-directional interactions     empirical studies     Bayesian inference    

HTML PDF 收藏

Development of soft kernel durum wheat

Craig F. MORRIS

《农业科学与工程前沿（英文）》 2019年 第6卷 第3期   页码 273-278 doi: 10.15302/J-FASE-2019259

摘要：

Kernel texture (grain hardness) is a fundamental and determining factor related to wheat ( spp.) milling, baking and flour utilization. There are three kernel texture classes in wheat: soft and hard hexaploid ( ), and very hard durum ( subsp. ). The genetic basis for these three classes lies with the Puroindoline genes. Phenotypically, the easiest means of quantifying kernel texture is with the Single Kernel Characterization System (SKCS), although other means are valid and can provide fundamental material properties. Typical SKCS values for soft wheat would be around 25 and for durum wheat≥80. Soft kernel durum wheat was created via homeologous recombination using the mutation, which facilitated the transfer of ca. 28 Mbp of 5DS that replaced ca. 21 Mbp of 5BS. The 5DS translocation contained a complete and intact locus and both puroindoline genes. Expression of the puroindoline genes in durum grain resulted in kernel texture and flour milling characteristics nearly identical to that of soft wheat, with high yields of break and straight-grade flours, which had small particle size and low starch damage. Dough water absorption was markedly reduced compared to durum flour and semolina. Dough was essentially unchanged and reflected the inherent gluten properties of the durum background. Pasta quality was essentially equal-to-or-better than pasta made from semolina. Agronomically, soft durum germplasm showed good potential with moderate grain yield and resistance to a number of fungal pathogens and insects. Future breeding efforts will no doubt further improve the quality and competitiveness of soft durum cultivars.

关键词： soft durum wheat     grain hardness     puroindolines     milling     baking     pasta     noodles    

HTML PDF 收藏

化学工程师的主动机器学习 Perspective

Yannick Ureel, Maarten R. Dobbelaere, Yi Ouyang, Kevin De Ras, Maarten K. Sabbe, Guy B. Marin, Kevin M. Van Geem

《工程（英文）》 2023年 第27卷 第8期   页码 23-30 doi: 10.1016/j.eng.2023.02.019

摘要：

By combining machine learning with the design of experiments, thereby achieving so-called active machine learning, more efficient and cheaper research can be conducted. Machine learning algorithms are more flexible and are better than traditional design of experiment algorithms at investigating processes spanning all length scales of chemical engineering. While active machine learning algorithms are maturing, their applications are falling behind. In this article, three types of challenges presented by active machine learning—namely, convincing the experimental researcher, the flexibility of data creation, and the robustness of active machine learning algorithms—are identified, and ways to overcome them are discussed. A bright future lies ahead for active machine learning in chemical engineering, thanks to increasing automation and more efficient algorithms that can drive novel discoveries. 

关键词： Active machine learning     Active learning     Bayesian optimization     Chemical engineering     Design of experiments    

HTML PDF 收藏

Identification of pollution sources in rivers using a hydrodynamic diffusion wave model and improved Bayesian-Markov

《环境科学与工程前沿（英文）》 2023年 第17卷 第7期 doi: 10.1007/s11783-023-1685-1

摘要：

● A hydrodynamic-Bayesian inference model was developed for water pollution tracking.

关键词： Identification of pollution sources     Water quality restoration     Bayesian inference     Hydrodynamic model     Inverse problem    

HTML PDF 收藏

基于样地调查的地质碳储量的贝叶斯优化

Xueying Lu, Kirk E. Jordan, Mary F. Wheeler, Edward O. Pyzer-Knapp, Matthew Benatan

《工程（英文）》 2022年 第18卷 第11期   页码 96-104 doi: 10.1016/j.eng.2022.06.011

摘要：

We present a framework that couples a high-fidelity compositional reservoir simulator with Bayesian optimization (BO) for injection well scheduling optimization in geological carbon sequestration. This work represents one of the first at tempts to apply BO and high-fidelity physics models to geological carbon storage. The implicit parallel accurate reservoir simulator (IPARS) is utilized to accurately capture the underlying physical processes during CO2 sequestration. IPARS provides a framework for several flow and mechanics models and thus supports both stand-alone and coupled simulations. In this work, we use the compositional flow module to simulate the geological carbon storage process. The compositional flow model, which includes a hysteretic three-phase relative permeability model, accounts for three major CO2 trapping mechanisms: structural trapping, residual gas trapping, and solubility trapping. Furthermore, IPARS is coupled to the International Business Machines (IBM) Corporation Bayesian Optimization Accelerator (BOA) for parallel optimizations of CO2 injection  strategies during field-scale CO2 sequestration. BO builds a probabilistic surrogate for the objective function using a Bayesian machine learning algorithm—the Gaussian process regression, and then uses an acquisition function that leverages the uncertainty in the surrogate to decide where to sample. The IBM BOA addresses the three weaknesses of standard BO that limits its scalability in that IBM BOA supports parallel (batch) executions, scales better for high-dimensional problems, and is more robust to initializations. We demonstrate these merits by applying the algorithm in the optimization of the CO2 injection schedule in the Cranfield site in Mississippi, USA, using field data. The optimized injection schedule achieves 16% more gas storage volume and 56% less water/surfactant usage compared with the baseline. The performance of BO is compared with that of a genetic algorithm (GA) and a covariance matrix adaptation (CMA)-evolution strategy (ES). The results demonstrate the superior performance of BO, in that it achieves a competitive objective function value with over 60% fewer forward model evaluations. 

关键词： 组分流     贝叶斯优化     地质碳储量     CCUS     机器学习     人工智能科学    

HTML PDF 收藏

标题 作者 时间 类型 操作

An assessment of surrogate fuel using Bayesian multiple kernel learning model in sight of sooting tendency

期刊论文

A novel multimode process monitoring method integrating LDRSKM with Bayesian inference

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

期刊论文

Multiple fault separation and detection by joint subspace learning for the health assessment of wind

Zhaohui DU, Xuefeng CHEN, Han ZHANG, Yanyang ZI, Ruqiang YAN

期刊论文

Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD, Wen-Jing GU

期刊论文

基于带约束最大间隔的贝叶斯分类器判别学习方法

Ke GUO, Xia-bi LIU, Lun-hao GUO, Zong-jie LI, Zeng-min GENG

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

裂缝性储层数据驱动模型证伪与不确定性量化

方军龄, 龚斌, Jef Caers

期刊论文

IN2CLOUD: A novel concept for collaborative management of big railway data

Jing LIN, Uday KUMAR

期刊论文

Evaluation of liquefaction-induced lateral displacement using Bayesian belief networks

Mahmood AHMAD, Xiao-Wei TANG, Jiang-Nan QIU, Feezan AHMAD

期刊论文

Fast implementation of kernel simplex volume analysis based on modified Cholesky factorization for endmember

Jing LI,Xiao-run LI,Li-jiao WANG,Liao-ying ZHAO

期刊论文

A Bayesian modeling approach to bi-directional pedestrian flows in carnival events

S. Q. XIE, S. C. WONG, William H. K. LAM

期刊论文

Development of soft kernel durum wheat

Craig F. MORRIS

期刊论文

化学工程师的主动机器学习

Yannick Ureel, Maarten R. Dobbelaere, Yi Ouyang, Kevin De Ras, Maarten K. Sabbe, Guy B. Marin, Kevin M. Van Geem

期刊论文

Identification of pollution sources in rivers using a hydrodynamic diffusion wave model and improved Bayesian-Markov

期刊论文

基于样地调查的地质碳储量的贝叶斯优化

Xueying Lu, Kirk E. Jordan, Mary F. Wheeler, Edward O. Pyzer-Knapp, Matthew Benatan

期刊论文