Searching for optimal setting conditions in technological processes using parametric estimation models and neural network mapping approach: A tutorial

Engineering optimization is an actual goal in manufacturing and service industries. In the tutorial we represented the concept of traditional parametric estimation models (Factorial Design (FD) and Central Composite Design (CCD)) for searching optimal setting parameters of technological processes. Then the 2D mapping method based on Auto Associative Neural Networks (ANN) (particularly, the Feed Forward Bottle Neck Neural Network (FFBN NN)) was described in comparison with traditional methods.     

具有比例时滞的细胞神经网络的全局稳定性分析

研究了具有比例时滞的细胞神经网络的平衡点的全局稳定性。通过建立李亚普诺夫函数，得到全局渐进稳定的充分条件。     

On the combination of kernel principal component analysis and neural networks for process indirect control

ABSTRACT

A new adaptive kernel principal component analysis (KPCA) for non-linear discrete system control is proposed. The proposed approach can be treated as a new proposition for data pre-processing techniques. Indeed, the input vector of neural network controller is pre-processed by the KPCA method. Then, the obtained reduced neural network controller is applied in the indirect adaptive control. The influence of the input data pre-processing on the accuracy of neural network controller results is discussed by using numerical examples of the cases of time-varying parameters of single-input single-output non-linear discrete system and multi-input multi-output system. It is concluded that, using the KPCA method, a significant reduction in the control error and the identification error is obtained. The lowest mean squared error and mean absolute error are shown that the KPCA neural network with the sigmoid kernel function is the best.     

Improved neural networks based on genetic algorithm for pulse recognition

Pulse diagnosis is an important part of Chinese medicine and has played an important role in the development of Chinese medical science. However, the pulse is traditionally determined by cutting it off, which leads to a lack of objective standard pulse identification methods and affects their accuracy and feasibility. This research has studied and discussed the processing and identification of four kinds of pulse: normal pulse, wiry pulse, smooth pulse, and thready pulse. Four frequency-domain characteristics of the pulse wave and six kinds of wavelet scale energy characteristic information were extracted, and a three-layer BP (backprocessing) neural network was established. The LM (Levenberg–Marquard) algorithm and a genetic algorithm were used to improve the BP neural network, to train on and predict experimental samples, and to obtain classification accuracies of 90% and 95% respectively. Moreover, improved BP neural network based on a genetic algorithm has shown highly superior performance in terms of convergence speed and low error rate.     

Autonomous conveyer gel driven by frontal polymerization

Autonomous mechanical mass transportation for cargos on the microscale with no need of continuous external powering is of great scientific and technological interest due to their extensive applications. However, it is still challenging to create a self‐driven system applicable to diverse micromaterial transportation demands. In this work, we developed a novel autonomous conveyer gel driven by frontal polymerization (FP). The chemical wave produced in FP was stable, and self‐propagating with a constant velocity, which can be easily monitored by thermal imaging or fluorescence labeling. We investigated the influence of the initiation temperature, swelling ratio of the gel substrate, and the size of the cargos on the motion of driven behavior. Results showed that the driving velocity can be well controlled by altering the initiation temperatures of FP. The swelling ratio and the size of the cargos had a key impact on the feasibility of self‐driven behavior. In addition, powerful driven capability by FP was demonstrated by successfully transporting cargos in series, and further applied for targeted synthesis of CdS nanocrystals. The methodology developed here provides an effective way to convert chemical energy to mechanical work, and may be useful in energy conversion and utilization, mass transportation and other applications. © 2015 Wiley Periodicals, Inc. J. Polym. Sci., Part A: Polym. Chem. 2016 , 54, 1323‐1331     

基于U-Net的盐体识别方法

卷积神经网络在计算机视觉领域取得重大突破，利用其强大的图像处理能力，将地下沉积盐体的识别问题转化为图像语义分割问题，应用深度卷积神经网络实现盐体地震图像的像素级语义分割.本文在U-Net基础上，增加网络深度并同时引入批归一化和Dropout处理，使得神经网络模型具有更高的可信度和更强的泛化能力.通过实验发现，在卷积层之后引入批归一化处理，并在池化层和叠加层之后引入Dropout可以稳定提升模型对盐体图像的分割性能.     

Semiotic Aggregation in Deep Learning

Convolutional neural networks utilize a hierarchy of neural network layers. The statistical aspects of information concentration in successive layers can bring an insight into the feature abstraction process. We analyze the saliency maps of these layers from the perspective of semiotics, also known as the study of signs and sign-using behavior. In computational semiotics, this aggregation operation (known as superization) is accompanied by a decrease of spatial entropy: signs are aggregated into supersign. Using spatial entropy, we compute the information content of the saliency maps and study the superization processes which take place between successive layers of the network. In our experiments, we visualize the superization process and show how the obtained knowledge can be used to explain the neural decision model. In addition, we attempt to optimize the architecture of the neural model employing a semiotic greedy technique. To the extent of our knowledge, this is the first application of computational semiotics in the analysis and interpretation of deep neural networks.     

基于多尺度学习与深度卷积神经网络的遥感图像土地利用分类

土地利用信息是国土资源管理的基础和重要依据，随着高分辨率遥感图像数据的日益增多，迫切需要快速准确的土地利用分类方法。目前应用较广的面向对象的分类方法对空间特征的利用尚不够充分，在特征选择上存在一定的局限性。为此，提出一种基于多尺度学习与深度卷积神经网络（deep convolutional neural network，DCNN）的多尺度神经网络（multi-scale neural network，MSNet）模型，基于残差网络构建了100层编码网络，通过并行输入实现输入图像的多尺度学习，利用膨胀卷积实现特征图像的多尺度学习，设计了一种端到端的分类网络。以浙江省0.5 m分辨率的光学航空遥感图像为数据源进行了实验，总体分类精度达91.97%，并将其与传统全卷积网络（fully convolutional networks，FCN）方法和基于支持向量机（support vector machine，SVM）的面向对象方法进行了对比，结果表明，本文所提方法分类精度更高，分类结果整体性更强。     

大脑血液动力学现象中的能量编码

神经信息的编码与解码是神经科学中的核心研究内容,同时又极具挑战性.传统的编码理论都具有各自的局限性,很难从脑的全局运行方式上给出有效的理论.而由于能量是一个标量具有可叠加性,因此能量编码理论可以从神经元活动的能量特征出发来研究脑功能的全局神经编码问题,取得了一系列的研究成果.本研究以王-张神经元能量计算模型为基础,构建了一个多层次结构的神经网络,通过计算机数值模拟得到了神经网络的能量消耗和血液中葡萄糖供能的变化情况.计算结果显示,和网络的神经活动达到峰值的时间相比,血液中葡萄糖的供能达到峰值的时间延迟了约5.6s.从定量的角度再现了功能性核磁共振(fMRI)中的血液动力学现象:大脑某个脑区的神经元集群被激活以后经过5~7 s的延迟,脑血流的变化才会大幅增加.模拟结果表明先前发表的由王-张神经元模型所揭示的负能量机制在控制大脑的血液动力学现象中起着核心的作用,预测了刺激条件下大脑的能量代谢与血流之间变化的本质是由神经元在发放动作电位过程中正、负能量之间的非平衡、不匹配性质所决定的.本文的研究结果为今后进一步探究血液动力学现象的生理学机制提供了新的研究方向,在神经网络的建模与计算方面给出了一个新的视角和研究方法.