Machine learning powered ellipsometry

Ellipsometry is a powerful method for determining both the optical constants and thickness of thin films. For decades, solutions to ill-posed inverse ellipsomet...     

关于异黄酮类化合物精制方法的探讨

简单介绍了异黄酮类化合物的结构、性质,着重对吸附法、超滤膜法、溶剂提取（萃取）法、色谱法、重结晶法等异黄酮精制方法的特点和应用情况进行了综述。     

深度双重注意力的生成与判别联合学习的行人重识别

在行人重识别任务中存在数据集标注难度大,样本量少,特征提取后细节特征缺失等问题。针对以上问题提出深度双重注意力的生成与判别联合学习的行人重识别。首先,构建联合学习框架,将判别模块嵌入生成模块,实现图像生成和判别端到端的训练,及时将生成图像反馈给判别模块,同时优化生成模块与判别模块。其次,通过相邻的通道注意力模块间连接和相邻空间注意力模块间连接,融合所有通道特征和空间特征,构建深度双重注意力模块,将其嵌入教师模型,使模型能更好地提取行人细节身份特征,提高模型识别能力。实验结果表明,该算法在Market-1501和DukeMTMC-ReID数据集上具有较好的鲁棒性、判别性。     

混合梯度稀疏先验约束下的图像盲复原

图像盲复原旨在无参考的情况下准确估计模糊核并恢复潜在的清晰图像。现有研究成果表明,利用全变分模型对高阶图像梯度先验约束进行描述可以有效抑制复原图像中产生的阶梯效应。本文在实验观察和研究的基础上,提出了采用稀疏先验约束模型对盲复原过程进行正则化的方法,以获得更佳的图像复原效果。该方法利用图像高阶梯度的稀疏性,通过与低阶梯度相结合来构造混合梯度正则项。同时,在正则项中引入基于图像熵的自适应因子,来调节迭代优化过程中两类梯度先验的比例,以此获得更好的收敛性。仿真与实验证明,与现有图像盲复原先进方法相比,本文方法具有更优越的图像复原性能。     

Advances and Challenges in Two?Dimensional Organic–Inorganic Hybrid Perovskites Toward High?Performance Light?Emitting Diodes

Two-dimensional (2D) perovskites are known as one of the most promising luminescent materials due to their structural diversity and outstanding optoelectronic p...     

A viral system algorithm to optimize the car dispatching in elevator group control systems of tall buildings

Nowadays is very common the presence of tall buildings in the business centres of the main cities of the world. Such buildings require the installation of numerous lifts that are coordinated and managed under a unique control system. Population working in the buildings follows a similar traffic pattern generating situations of traffic congestion. The problem arises when a passenger makes a hall call wishing to travel to another floor of the building. The dispatching of the most suitable car is the optimization problem we are tackling in this paper. We develop a viral system algorithm which is based on a bio-inspired virus infection analogy to deal with it. The viral system algorithm is compared to genetic algorithms, and tabu search approaches that have proven efficiency in the vertical transportation literature. The experiments undertaken in tall buildings from 10 to 24 floors, and several car configurations from 2 to 6 cars, provide valuable results and show how viral system outperforms such soft computing algorithms.     

‘Long autonomy or long delay?’ The importance of domain in opinion mining

Nowadays, people do not only navigate the web, but they also contribute contents to the Internet. Among other things, they write their thoughts and opinions in review sites, forums, social networks, blogs and other websites. These opinions constitute a valuable resource for businesses, governments and consumers. In the last years, some researchers have proposed opinion extraction systems, mostly domain-independent ones, to automatically extract structured representations of opinions contained in those texts. In this work, we tackle this task in a domain-oriented approach, defining a set of domain-specific resources which capture valuable knowledge about how people express opinions on a given domain. These resources are automatically induced from a set of annotated documents. Some experiments were carried out on three different domains (user-generated reviews of headphones, hotels and cars), comparing our approach to other state-of-the-art, domain-independent techniques. The results confirm the importance of the domain in order to build accurate opinion extraction systems. Some experiments on the influence of the dataset size and an example of aggregation and visualization of the extracted opinions are also shown.     

A semantic role labelling-based framework for learning ontologies from Spanish documents

Currently, most of the information available in the Web is adapted primarily for human consumption, but there is so much information that can no longer be processed by a person in a reasonable time, either in digital or physical formats. To solve this problem, the idea of the Semantic Web arose. The Semantic Web deals with adding machine-readable information to Web pages. Ontologies represent a very important element of this web, as they provide a valid and robust structure to represent knowledge based on concepts, relations, axioms, etc. The need for overcoming the bottleneck provoked by the manual construction of ontologies has generated several studies and research on obtaining semiautomatic methods to learn ontologies. In this sense, this paper proposes a new ontology learning methodology based on semantic role labeling from digital Spanish documents. The method makes it possible to represent multiple semantic relations specially taxonomic and partonomic ones in the standardized OWL 2.0. A set of experiments has been performed with the approach implemented in educational domain that show promising results.     

Study on Thermal Deformation Behavior and Properties of Vacuum Hot-press Sintered W(50)/Cu-Al_2O_3 Composite

In this work, the tungsten particulate reinforced Al2O3 dispersion strengthened copper base composites were successfully fabricated by using a vacuum hot-press sintering method. With the test temperature varying from 650 to 950 ℃ and the strain rate varying from 0.01 to 5 s-1, the W(50)/Cu-Al2O3 composites were isothermally compressed on a Gleeble-1500D thermal simulator. The true stress-strain curves of the W(50)/Cu-Al2O3 under different test conditions were obtained. The dynamic recrystallization of the W...