Decentralized adaptive recurrent neural control structure

This paper presents a novel decentralized variable structure neural control approach for large-scale uncertain systems, which is developed using recurrent high-order neural networks (RHONN). It is assumed that each subsystem belongs to a class of block-controllable nonlinear systems whose vector fields includes interconnection terms, which are bounded by nonlinear functions. A decentralized RHONN structure and the respective learning law are proposed in order to approximate online the dynamical behavior of each nonlinear subsystem. The control law, which is able to regulate and to track the desired reference signals, is designed using the well-known variable structure theory. The stability of the whole system is analyzed via the Lyapunov methodology. The applicability of the proposed decentralized identification and control algorithm is illustrated via simulations as applied to an interconnected double inverted pendulum.     

动态核的形态分解联想算法及抗随机噪声研究

在灰度图像分解算法和动态核形态联想记忆网络的基础上,提出了一种新的联想记忆算法--动态核的形态分解联想算法.该方法显著地提高了联想记忆抗随机噪声的能力,较好地解决了灰度图像在含噪时的联想记忆和识别的问题,从而给出了一种恢复含噪灰度图像的途径,并把该方法推广到了彩色图像的处理.通过实验,验证了该方法的良好性能,取得了理想的结果.     

浅议高职高专计算机网络实验室的建设

文章分析了计算机网络实验的建设对于计算机网络及相关课程的必要性,对高职高专计算机网络实验室的建设问题进行了探讨,提出了网络实验室应具备的功能及建设原则,并给出一种较为全面实用的解决方案。     

基于 GAN 网络的电力设施遥感图像去云算法研究

针对电力设施遥感图像云层遮挡问题,提出了基于生成对抗网络(GAN) 的遥感图像去云算法。以条件生成对抗网络 (cGAN) 为主体结构,在编码器自适应填充卷积,设计了基于 Soft Attention的递归神经网络模块,通过对所有特征节点增加 全局依赖关系来解决网络局部最优问题,通过空间信息转换提取关键信息,提高去云与重建效果。实验结果表明,方法对遥 感图像中云层遮挡去除效果较好,重建图像的结构相似性(SSIM) 与峰值信噪比(PSNR) 分别达到0.983与32.899,分别提高 了23.93%与8.86%,均优于其他改进型GAN 网络。研究的方法不仅为基于遥感图像电力设施识别提供了基础,深度学习 遥感图像处理应用提供了参考。     

关于细胞神经网络无性模板的设计

本文以连通片检测器无性模板的设计为例，给出了细胞神经网络中无性模板的设计方法及连通片检测器无性模板中各元素的数值范围。     

Hybrid Petri-nets for modelling and performance evaluation of supply chains

Modelling and analysis of complex and co-ordinated supply chains is a crucial task due to its inherent complexity and uncertainty. Therefore, the current research direction is to devise an efficient modelling technique that maps the dynamics of a real life supply chain and assists industrial practitioners in evaluating and comparing their network with other competing networks. Here an effective modelling technique, the hybrid Petri-net, is proposed to efficiently handle the dynamic behaviour of the supply chain. This modelling methodology embeds two enticing features, i.e. cost and batch sizes, in deterministic and stochastic Petri-net for the modelling and performance evaluation of supply chain networks. The model is subsequently used for risk management to investigate the issues of supply chain vulnerability and risk that has become a major research subject in recent years. In the test bed, a simple productive supply chain and an industrial supply chain are modelled with fundamental inventory replenishment policy. Subsequently, its performance is evaluated along with the identification and assessment of risk factors using analytical and simulation techniques respectively. Thus, this paper presents a complete package for industrial practitioners to model, evaluate performance and manage risky events in a supply chain.     

ENet-6mA: Identification of 6mA Modification Sites in Plant Genomes Using ElasticNet and Neural Networks

N6-methyladenine (6mA) has been recognized as a key epigenetic alteration that affects a variety of biological activities. Precise prediction of 6mA modification sites is essential for understanding the logical consistency of biological activity. There are various experimental methods for identifying 6mA modification sites, but in silico prediction has emerged as a potential option due to the very high cost and labor-intensive nature of experimental procedures. Taking this into consideration, developing an efficient and accurate model for identifying N6-methyladenine is one of the top objectives in the field of bioinformatics. Therefore, we have created an in silico model for the classification of 6mA modifications in plant genomes. ENet-6mA uses three encoding methods, including one-hot, nucleotide chemical properties (NCP), and electron–ion interaction potential (EIIP), which are concatenated and fed as input to ElasticNet for feature reduction, and then the optimized features are given directly to the neural network to get classified. We used a benchmark dataset of rice for five-fold cross-validation testing and three other datasets from plant genomes for cross-species testing purposes. The results show that the model can predict the N6-methyladenine sites very well, even cross-species. Additionally, we separated the datasets into different ratios and calculated the performance using the area under the precision–recall curve (AUPRC), achieving 0.81, 0.79, and 0.50 with 1:10 (positive:negative) samples for F. vesca, R. chinensis, and A. thaliana, respectively.     

基于白鲸优化算法的配电网故障恢复方法

提出了一种基于白鲸优化（BWO）算法的配电网故障恢复方法。首先,建立光储、风储系统模型以及负荷模型,以故障后重要负荷损失量最小为目标函数,进行配电网的初步孤岛划分。其次,以网络损耗和开关操作次数加权求和最小为目标,采用BWO算法求解,获取孤岛划分与开关操作配合的故障恢复结果。然后,通过3种场景对比,验证了所提方法能够在不同故障时段获得配电网故障恢复的最优结果。最后,将BWO算法与二进制粒子群优化算法、灰狼优化算法的运行结果进行对比,验证了BWO算法寻优效果更好。     

Learning Structure from Data and Its Application to Ozone Prediction

In this paper we propose an algorithm for structure learning in predictive expert systems based on a probabilistic network representation. The idea is to have the simplest structure (minimum number of links) with acceptable predictive capability. The algorithm starts by building a tree structure based on measuring mutual information between pairs of variables, and then it adds links as necessary to obtain certain predictive performance. We have applied this method for ozone prediction in México City, where the ozone level is used as a global indicator for the air quality in different parts of the city. It is important to predict the ozone level a day, or at least several hours in advance, to reduce the health hazards and industrial losses that occur when the ozone reaches emergency levels. We obtained as a first approximation a tree-structured dependency model for predicting ozone in one part of the city. We observe that even with only three parameters, its estimations are acceptable.A causal network representation and the structure learning techniques produced some very interesting results for the ozone prediction problem. Firstly, we got some insight into the dependence structure of the phenomena. Secondly, we got an indication of which are the important and not so important variables for ozone forecasting. Taking this into account, the measurement and computational costs for ozone prediction could be reduced. And thirdly, we have obtained satisfactory short term ozone predictions based on a small set of the most important parameters.     

基于极端学习机的MANET移动性预测模型

针对移动自组织网络移动性在管理无线网络带宽资源可用性方面的重要性,为了更好地规划连续服务可用性和有效能源管理以提升网络的整体服务质量,提出了一种基于极端学习机的MANET移动性预测模型。利用ELM对MANET中的任意节点进行建模;假设已知每个移动节点当前的移动性信息（位置、速度和运动方向角度）,以这种方式预测节点未来的位置和相邻节点之间未来的距离;基于几个标准移动性模型,产生更加真实、精确的移动性预测,从而更好地捕捉任意节点直角坐标系之间现有交互/相关性。使用标准移动性模型的仿真结果验证了所提模型的有效性,实验结果表明,提出的预测模型明显改进了传统基于多层感知器的模型,此外,当预测相邻节点之间未来距离时,避免了当前算法对预测精度的限制。