Co-Training for Visual Object Recognition Based on Self-Supervised Models Using a Cross-Entropy Regularization

Automatic recognition of visual objects using a deep learning approach has been successfully applied to multiple areas. However, deep learning techniques require a large amount of labeled data, which is usually expensive to obtain. An alternative is to use semi-supervised models, such as co-training, where multiple complementary views are combined using a small amount of labeled data. A simple way to associate views to visual objects is through the application of a degree of rotation or a type of filter. In this work, we propose a co-training model for visual object recognition using deep neural networks by adding layers of self-supervised neural networks as intermediate inputs to the views, where the views are diversified through the cross-entropy regularization of their outputs. Since the model merges the concepts of co-training and self-supervised learning by considering the differentiation of outputs, we called it Differential Self-Supervised Co-Training (DSSCo-Training). This paper presents some experiments using the DSSCo-Training model to well-known image datasets such as MNIST, CIFAR-100, and SVHN. The results indicate that the proposed model is competitive with the state-of-art models and shows an average relative improvement of 5% in accuracy for several datasets, despite its greater simplicity with respect to more recent approaches.     

Enhanced headspace single drop microextraction method using deep eutectic solvent based magnetic bucky gels: Application to the determination of volatile aromatic hydrocarbons in water and urine samples

A facile headspace single drop microextraction method was developed using deep eutectic solvent‐based magnetic bucky gel as the extraction solvent for the first time. The hydrophobic magnetic bucky gel was formed by combining choline chloride/chlorophenol deep eutectic solvent and magnetic multiwalled carbon nanotube nanocomposite. Magnetic susceptibility, high viscosity, high sorbing ability, and tunable extractability of organic analytes are the desirable advantages of the prepared gel. Using a rod magnet as a suspensor in combination with the magnetic susceptibility of the prepared gel resulted in a highly stable droplet. This stable droplet eliminated the possibility of drop dislodgement. The prepared droplet made it possible to complete the extraction process in high temperatures and elevated agitation rates. Furthermore, using larger micro‐droplet volumes without any operational problems became possible. These facts resulted in shorter sample preparation time, higher sensitivity of the method, and lower detection limits. Under the optimized conditions, an enrichment factor of 520–587, limit of detection of 0.05–0.90 ng/mL, and linearity range of 0.2–2000 ng/mL (coefficient of determination = 0.9982–0.9995) were obtained. Relative standard deviations were < 10%. This method was successfully coupled with gas chromatography and used for the determination of benzene, toluene, ethylbenzene, and xylene isomers as harmful volatile organic compounds in water and urine samples.     

RNAGCN: RNA tertiary structure assessment with a graph convolutional network

RNAs play crucial and versatile roles in cellular biochemical reactions. Since experimental approaches of determining their three-dimensional (3D) structures are costly and less efficient, it is greatly advantageous to develop computational methods to predict RNA 3D structures. For these methods, designing a model or scoring function for structure quality assessment is an essential step but this step poses challenges. In this study, we designed and trained a deep learning model to tackle this problem. The model was based on a graph convolutional network (GCN) and named RNAGCN. The model provided a natural way of representing RNA structures, avoided complex algorithms to preserve atomic rotational equivalence, and was capable of extracting features automatically out of structural patterns. Testing results on two datasets convincingly demonstrated that RNAGCN performs similarly to or better than four leading scoring functions. Our approach provides an alternative way of RNA tertiary structure assessment and may facilitate RNA structure predictions. RNAGCN can be downloaded from https://gitee.com/dcw-RNAGCN/rnagcn.     

Loading rate and confining pressure effect on dilatancy,acoustic emission,and failure characteristics of fissured rock with two pre-existing flaws

Investigating the dilatancy, acoustic emission and failure characteristics of fissured rock are significant to ensure their geotechnical stability. In this paper, the uniaxial and triaxial compression experiments with AE monitoring under different loading rates were carried out on fissured rock specimens with the same geometrical distribution of two pre-existing flaws. The dilatancy and AE activity of these specimens were discussed, and the effects of the confining pressure and loading rate on the mechanical parameters and failure characteristics were analyzed. The results show that the exponential strength criterion is more suitable than the Mohr–Coulomb strength criterion to characterize the strength characteristics of fissured rock. The crack evolution and failure characteristics of fissured rock specimens are more complicated than those of intact rock specimens. The failure characteristics of the fissured rock follow the tensile shear coalescence model, crack branching occurs with increasing the loading rate, and the multi-section coalescence model is verified with increasing the confining pressure. The phenomena of stress drop and yield platform usually occur after the dilatancy onset, the specimen does not fail instantaneously, and the propagation and coalescence of cracks cause a sharp increase in the AE signals, circumferential strain, and volumetric strain.     

Identifying the viscoelastic properties of soft matter from the indentation response of a hard film-soft substrate system

The indentation technique is widely used in measuring the mechanical properties of soft matter at the microscale or nanoscale,but still faces challenges by these unique properties as well as the consequent strong surface adhesion, including the strong nonlinear effect, unclear judgment of the contact point, difficulties in estimating the contact area, and the risk of the indenter piercing the sample. Here we propose a two-step method to solve these problems: lay a hard film on a soft matter, and obtain the viscoelastic properties of this soft matter through the indentation response of this composite structure. We first establish a theoretical indentation model of the hard film-soft substrate system based on the theory of plates, elastic-viscoelastic correspondence principle and Boltzmann superposition principle. To verify the correctness of this method, we measure the mechanical properties of the methyl vinyl silicone rubber(MVSR) covered by a Cu nanofilm. Finally, we test the effectiveness and error sensitivity of this method with the finite element method(FEM). The results show that our method can accurately measure the mechanical properties of soft matter, while effectively circumventing the problems of the traditional indentation technique.     

Green solvent approach for printable large deformation thermoplastic elastomer based piezoresistive sensors and their suitability for biomedical applications

Composites based on biocompatible thermoplastic elastomer styrene‐ethylene/butylene‐styrene (SEBS) as matrix and multi‐walled carbon nanotubes (MWCNT) as nanofillers show excellent mechanical and piezoresistive properties from low to large deformations. The MWCNT/SEBS composites have been prepared following a green solvent approach, to extend their range of applicability to biomedical applications. The obtained composites with 2, 4, and 5 wt % MWCNT content provide suitable piezoresistive response up to 80% deformation with a piezoresistive sensibility near 2.7, depending on the applied strain and MWCNT content. Composite sensors were also developed by spray and screen printing and integrated with an electronic data acquisition system with RF communication. The possibility to accurately control the composites properties and performance by varying MWCNT content, viscosity, and mechanical properties of the polymer matrix, shows the large potential of the system for the development of large deformation printable piezoresistive sensors. © 2016 Wiley Periodicals, Inc. J. Polym. Sci., Part B: Polym. Phys. 2016 , 54, 2092–2103     

A review of computational modeling and deep brain stimulation: applications to Parkinson's disease

Biophysical computational models are complementary to experiments and theories, providing powerful tools for the study of neurological diseases. The focus of this review is the dynamic modeling and control strategies of Parkinson's disease (PD). In previous studies, the development of parkinsonian network dynamics modeling has made great progress. Modeling mainly focuses on the cortex-thalamus-basal ganglia (CTBG) circuit and its sub-circuits, which helps to explore the dynamic behavior of the parkinsonian network, such as synchronization. Deep brain stimulation (DBS) is an effective strategy for the treatment of PD. At present, many studies are based on the side effects of the DBS. However, the translation from modeling results to clinical disease mitigation therapy still faces huge challenges. Here, we introduce the progress of DBS improvement. Its specific purpose is to develop novel DBS treatment methods, optimize the treatment effect of DBS for each patient, and focus on the study in closed-loop DBS. Our goal is to review the inspiration and insights gained by combining the system theory with these computational models to analyze neurodynamics and optimize DBS treatment.     

基于分子工程的方法设计首例具有Sr2Be2B2O7 (SBBO)结构的深紫外氟碳酸盐双折射晶体AMgLi2(CO3)2F (A=K,Rb)※

分子结构设计是开发新化合物和通过原子尺度操纵优化晶体结构的一种引人注目的策略. 在这个工作中, 利用分子工程的思想, 基于SBBO结构, 成功设计并合成两个新型氟碳酸盐KMgLi₂(CO₃)₂F和RbMgLi₂(CO₃)₂F. 在两个结构中, a-b平面是由CO₃和LiO₃F阴离子基团组成的无限[Li₃C₃O₆F₃]_∞层, 进一步相邻的层通过F原子连接形成一个独特的[Li₆C₆O₁₂F₃]_∞双层. 这种结构特征对改善晶体的层状生长习性和消除晶体的多晶性有很大的帮助. 光学测试表明, 该系列晶体具有大的双折射和短的紫外截止边, 是深紫外双折射晶体良好的候选材料.     

基于八面体理论的岩石循环加-卸载本构模型及修正

探究岩石的受力特点及破坏特性是研究岩石地下工程安全性的关键,诸多学者都期望能在岩石本构模型的研究上取得突破性进展。在此背景下,提出了一种能够描述循环加-卸载条件下岩石的本构模型。首先,假设岩石的微元强度服从八面体剪应力理论并且微元破坏服从Weibull概率公式,将岩石本构中的损伤变量以及岩石微元强度表达式里包含的损伤因子进行本构变换,得到关于应力、应变等其他表现加-卸载下岩石损伤本构模型的参数,表示出岩石微元强度和损伤变量,再将得到的岩石微元强度和损伤变量代入所提出的岩石本构模型中,并进行等式变换得到一个函数表达式。通过将其与实验数据进行拟合对比分析,得出修正后的拟合参数,将其代入函数式中,得到损伤本构模型的修正式。最后将拟合参数进行必要的敏感性分析,得出各拟合参数的实际物理意义。     

软体操作器结构设计及植入式光纤传感方法

为解决微创手术软体机器人的形状实时监测问题,将刻有三个光纤布拉格光栅的单根光纤植入软体操作器中,利用其研究柔性硅胶软体操作器光纤传感和三维形状重构方法。进行了软体操作器的结构设计及模型建立,并对光纤光栅波长漂移量和软体操作器弯曲曲率之间的关系进行了理论分析;通过实验验证了软体操作器结构设计及其模型建立的有效性,测试了软体操作器不同弯曲状态下三个FBG传感器的反射谱特征及其变化规律;通过分析三个FBG传感器的中心波长漂移量,利用线性插值算法计算出软体操作器在不同弯曲状态下的曲率等参数,并结合曲线拟合方法实现软体操作器的三维形状重构。实验结果表明:植入式光纤光栅传感方法可以实现硅胶软体手术操作器的三维形状传感,在微创外科手术领域具有广阔的应用前景。