Stability analysis of fractional order fuzzy cellular neural networks with leakage delay and time varying delays

In this paper we investigated the stability of fractional order fuzzy cellular neural networks with leakage delay and time varying delays. Based on Lyapunov theory and applying bounded techniques of fractional calculation, sufficient criterion are established to guarantee the stability. Hybrid feedback control is applied to derive the proposed results. Finally, numerical examples with simulation results are given to illustrate the effectiveness of the proposed method.     

Some methods of training radial basis neural networks in solving the Navier‐Stokes equations

The purpose of this research is to analyze the application of neural networks and specific features of training radial basis functions for solving 2‐dimensional Navier‐Stokes equations. The authors developed an algorithm for solving hydrodynamic equations with representation of their solution by the method of weighted residuals upon the general neural network approximation throughout the entire computational domain. The article deals with testing of the developed algorithm through solving the 2‐dimensional Navier‐Stokes equations. Artificial neural networks are widely used for solving problems of mathematical physics; however, their use for modeling of hydrodynamic problems is very limited. At the same time, the problem of hydrodynamic modeling can be solved through neural network modeling, and our study demonstrates an example of its solution. The choice of neural networks based on radial basis functions is due to the ease of implementation and organization of the training process, the accuracy of the approximations, and smoothness of solutions. Radial basis neural networks in the solution of differential equations in partial derivatives allow obtaining a sufficiently accurate solution with a relatively small size of the neural network model. The authors propose to consider the neural network as an approximation of the unknown solution of the equation. The Gaussian distribution is used as the activation function.     

Polymer chain diffusion in polymer blends: A theoretical interpretation based on a memory function formalism

The diffusion of polymer chains in miscible polymer blends with large dynamic asymmetry—those where the two blend components display very different segmental mobility—is not well understood yet. In the extreme case of the blend system of poly(ethylene oxide) (PEO) and poly(methyl methacrylate)(PMMA), the diffusion coefficient of PEO chains in the blend can change by more than five orders of magnitude while the segmental time scale hardly changes with respect to that of pure PEO. This behavior is not observed in blend systems with small or moderate dynamic asymmetry as, for instance, polyisoprene/poly(vinyl ethylene) blends. These two very different behaviors can be understood and quantitatively explained in a unified way in the framework of a memory function formalism, which takes into account the effect of the collective dynamics on the chain dynamics of a tagged chain. © 2019 Wiley Periodicals, Inc. J. Polym. Sci., Part B: Polym. Phys. 2019 , 57, 1239–1245     

Hyperparameter on-line learning of stochastic resonance based threshold networks

Aiming at training the feed-forward threshold neural network consisting of nondifferentiable activation functions, the approach of noise injection forms a stochastic resonance based threshold network that can be optimized by various gradient-based optimizers. The introduction of injected noise extends the noise level into the parameter space of the designed threshold network, but leads to a highly non-convex optimization landscape of the loss function. Thus, the hyperparameter on-line learning procedure with respective to network weights and noise levels becomes of challenge. It is shown that the Adam optimizer, as an adaptive variant of stochastic gradient descent, manifests its superior learning ability in training the stochastic resonance based threshold network effectively. Experimental results demonstrate the significant improvement of performance of the designed threshold network trained by the Adam optimizer for function approximation and image classification.     

基于毛竹叶片理化参数的刚竹毒蛾危害检测研究

虫害检测算法研究是开展虫害快速、准确监测，制定精准森防检疫措施的重要基础。以毛竹叶片为研究尺度，基于刚竹毒蛾危害下的寄主外部形态与内部生理现象总结，选择并实测叶损量LL、相对叶绿素含量RCC、相对含水量RWC、原始光谱的733.66~898.56 nm值(ρ_{733.66~898.56})、一阶微分光谱的562.95~585.25 nm值(ρ′_{562.95~585.25})与706.18~725.41 nm值(ρ′_{706.18~725.41})等理化参数，随机划分实验组(63组)和验证组(37组)并设计5次重复实验；分别运用Fisher判别分析、BP神经网络、随机森林等三种方法建立刚竹毒蛾危害等级的检测模型，从检测精度、Kappa系数及R2等指标对模型的检测效果予以分析和比较。结果显示，Fisher判别分析、BP神经网络、随机森林的检测精度分别为69.19%，65.41%，83.78%，Kappa系数分别为0.576 9，0.532 4和0.778 8，R2分别为0.722 2，0.582 6和0.870 9，总体而言，三种方法均具备刚竹毒蛾危害的检测能力，随机森林的检测效果最优，Fisher判别分析次之，再次为BP神经网络；从分等级来看，随机森林的检测精度亦优于Fisher判别分析与BP神经网络，但3种方法对中度危害等级的检测精度均有所不足。该成果可为刚竹毒蛾危害及其他病虫害检测算法的选择提供参考，并为进一步建立冠层、遥感影像像元等尺度的虫害检测模型奠定基础。     

贝叶斯优化卷积神经网络公共场所异常声识别*

针对公共场所异常声的感知和识别问题,提出一种基于贝叶斯优化卷积神经网络的识别方法。提取声信号的Gammatone倒谱系数、倍频程功率谱、短时能量和谱质心,组合成声信号的特征图。构建卷积神经网络作为分类器,利用递增的卷积核设置和池化操作处理不同尺度的特征。基于贝叶斯优化算法优化卷积神经网络的模型参数,对包括火苗噼啪声、婴儿啼哭声、烟花燃放声、玻璃破碎声和警报声的5种公共场所异常声进行识别。该方法的识别结果与基于不同的特征提取和分类器方案得到的识别结果进行比较,结果表明该方法的识别效果优于其他特征提取和分类器方案的识别效果。最后分析了该方法在不同信噪比噪声干扰下的识别结果,验证了该方法的有效性。     

Porous shape memory polymers: Design and applications

Porous shape memory polymers (SMPs) exhibit geometric and volumetric shape change when actuated by an external stimulus and can be fabricated as foams, scaffolds, meshes, and other polymeric substrates that possess porous three-dimensional macrostructures. These materials have applications in multiple industries such as textiles, biomedical devices, tissue engineering, and aerospace. This review article examines recent developments in porous SMPs, with a focus on fabrication methods, methods of characterization, modes of actuation, and applications. © 2016 Wiley Periodicals, Inc. J. Polym. Sci., Part B: Polym. Phys. 2016 , 54, 1300–1318     

Cold,warm, and hot programming of shape memory polymers

In this article, programming is classified as hot, warm, and cold, based on the temperature zone within which the programming is conducted. The strain and stress locking and releasing mechanisms are discussed within the thermodynamics framework. A new formula is developed for quantifying the strain recovery ratio of cold-programmed SMPs. Stress fixity ratio and stress recovery ratio are also defined based on the understanding of stress locking and recovery mechanisms. State-of-the-art literature on warm and cold programming is reviewed. Well-controlled programming as well as free strain recovery test and constrained stress recovery test are conducted, in order to validate the memory mechanisms discussed in this study. It is found that, while programming temperature has an insignificant effect on the final free shape recovery, it has a significant effect on the stress recovery. The recovery stress programmed by cold programming may be lower, equal to, or higher than that by hot programming, due to the different stress locking mechanisms and other factors such as damage during the thermomechanical cycle. Cold, Warm, and Hot Programming of Shape Memory Polymers © 2016 Wiley Periodicals, Inc. J. Polym. Sci., Part B: Polym. Phys. 2016 , 54, 1319–1339     

Comparative analysis of shape memory-based self-healing coatings

Self-healing materials exhibit the ability to repair and to recover their functionality upon damage. Here, we report on an investigation into preparation and characterization of shape memory assisted self-healing coatings. We built on past work in which poly(ε-caprolactone) electrospun fibers were infiltrated with a shape memory epoxy matrix and delve into fabricating and characterizing a coating with the same materials, but employing a blending approach, polymerization induced phase separation. After applying controlled damage, the ability of both coatings to self-heal upon heating was investigated. In both methods, coatings showed excellent thermally induced crack closure and protection against corrosion, with the blend approach being more suitable for large-scale applications given its process simplicity. Two different approaches to the preparation of shape memory-based self-healing coatings were compared for their ability to heal structurally and functionally by heating. These two approaches, electrospinning versus polymerization-induced phase separation were found to feature comparable and quite complete healing, with the latter system offering the advantage of facile processing. © 2016 Wiley Periodicals, Inc. J. Polym. Sci., Part B: Polym. Phys. 2016 , 54, 1415–1426