工业酚水稀释的RBF神经网络预测控制

针对酚水稀释过程中酚水流量不便测量的工程情况,提出了一种基于RBF（径向基）神经网络的预测控制方法.在酚水罐每个液位变化周期内使用计算机定时测量液位高度,并将这些高度值作为目标输出,在每个循环结束时训练RBF网络,利用RBF网络的逼近能力来实时预测酚水流量,从而控制清水的配比,实现酚水质量浓度的稳定.该方法可避免测量误差带来的干扰,提高控制精度.     

石油企业财务风险评价神经网络模型的建立

石油企业财务风险评价是石油行业的重要课题.在确立石油企业财务风险评价指标体系的基础上,建立了基于模糊神经网络的石油企业财务风险评价模型.该评价模型分为模糊量化模块和模糊神经网络(FNN)模块,可根据实际问题进行具体调节,具有学习的功能.经过对200多家石油企业的实证分析,结果表明该模型网络预测误差小,是一种可靠、有效的...     

网络融合边界的电信DoS攻击检测*

为了检测网络融合边界的电信拒绝服务攻击,首先针对攻击的类型分别提出了基于呼叫统计或流量信号分析的检测方法,并采用分步骤的策略设计了检测系统,将两种检测算法分别应用于粗检测步骤,再通过精检测步骤确认攻击并找出攻击源.模拟实验结果表明,该方案能够有效地检测出典型的攻击,并能够实时在线检测,具有良好的实用价值,为应对网络融合所带来的新安全问题提供了一种解决方案.     

基于模糊神经网络的大场景人群密度估计方法 *

提出了一种估计大场景下密集人群密度的方法。该方法根据人类视觉的模糊性原理,认为用模糊集来划分人群密度范围比用确定的方法更符合人眼视知觉的认知方式,利用统计的方法确定灰度共生矩阵各指标对于各个密度类别的隶属函数;设计基于误差反向传播训练算法（BP）的模糊神经网络,计算样本模式对于各个密度类别的隶属度,并根据人群密度变化的时域连续性原理对人群密度范围进行合理估计。实验表明该方法提高了估计精度。     

基于迁移学习的卷积神经网络通道剪枝

卷积神经网络在计算机视觉等多个领域应用广泛,然而其模型参数量众多、计算开销庞大,导致许多边缘设备无法满足其存储与计算资源要求。针对其边缘部署困难,提出使用迁移学习策略改进基于BN层缩放因子通道剪枝方法的稀疏化过程。本文对比不同层级迁移方案对稀疏化效果与通道剪枝选取容限的影响;并基于网络结构搜索观点设计实验,探究其精度保持极限与迭代结构的收敛性。实验结果表明,对比原模型,采用迁移学习的通道剪枝算法,在精度损失不超过0.10的前提下,参数量减少89.1%,模型存储大小压缩89.3%;对比原剪枝方法,将剪枝阈值从0.85提升到0.97,进一步减少参数42.6%。实验证明,引入迁移策略更易实现充分的稀疏化,提高通道剪枝阈值选取容限,实现更高压缩率;并在迭代剪枝的网络结构搜索过程中,提供更高效的搜索起点,利于快速迭代趋近至搜索空间的一个网络结构局部最优解。     

Protein interaction networks: centrality,modularity, dynamics,and applications

In the post-genomic era, proteomics has achieved significant theoretical and practical advances with the development of high-throughput technologies. Especially the rapid accumulation of protein-protein interactions (PPIs) provides a foundation for constructing protein interaction networks (PINs), which can furnish a new perspective for understanding cellular organizations, processes, and functions at network level. In this paper, we present a comprehensive survey on three main characteristics of PINs: centrality, modularity, and dynamics. 1) Different centrality measures, which are used to calculate the importance of proteins, are summarized based on the structural characteristics of PINs or on the basis of its integrated biological information; 2) Different modularity definitions and various clustering algorithms for predicting protein complexes or identifying functional modules are introduced; 3) The dynamics of proteins, PPIs and sub-networks are discussed, respectively. Finally, the main applications of PINs in the complex diseases are reviewed, and the challenges and future research directions are also discussed.     

基于MRIO与SNA的中国水资源空间转移网络分析

基于2002年、2007年和2012年的多区域投入产出表的相关数据,利用多区域投入产出(MRIO)模型和社会网络分析法(SNA)分析了中国水资源流动网络的空间关联性和结构特征。结果表明:网络中的链接数量没有随水足迹贸易值的增加而增加,链接路径上的流量不断增加,网络的韧性不够,空间关联渠道有待拓展,存在一定的等级差异,稳定性需要加强;网络中一些省份链接的增加,会削弱其他省份的链接数目,这种可塑性特征有利于在全国范围内合理配置水资源;将网络划分为4个板块,板块间的溢出关系主要是以板块内部为主,且少数板块之间没有任何的溢出关系。     

Fuzzy adaptive networks in machining process modeling: surface roughness prediction for turning operations

Due to the complexity of the machine tool structure and the cutting process, the dynamics of machining processes are still not completely understood. This is especially true due to the demand of high-speed machining to increase productivity. In order to model and control these complex processes, new approaches, which can represent complex phenomenon combined with learning ability, are needed. The combined neural–fuzzy approach appears to be ideally suited for this purpose. In this paper, the recently developed fuzzy adaptive network (FAN) is used to model surface roughness in turning operations. The FAN network has both the learning ability of neural network and linguistic representation of complex, not well-understood, vague phenomenon. Furthermore, it can continuously improve the initially obtained rough model based on the daily operating data. To illustrate this approach, a model representing the influences of machining parameters on surface roughness is established and then the model is verified by the use of the results of pilot experiments. Finally, a comparison with the results based on statistical regression is provided.     

Modeling of tool wear in drilling by statistical analysis and artificial neural network

The useful life of a cutting tool and its operating conditions largely control the economics of the machining operations. Hence, it is imperative that the condition of the cutting tool, particularly some indication as to when it requires changing, to be monitored. The drilling operation is frequently used as a preliminary step for many operations like boring, reaming and tapping, however, the operation itself is complex and demanding.

Back propagation neural networks were used for detection of drill wear. The neural network consisted of three layers input, hidden and output. Drill size, feed, spindle speed, torque, machining time and thrust force are given as inputs to the ANN and the flank wear was estimated. Drilling experiments with 8 mm drill size were performed by changing the cutting speed and feed at two different levels. The number of neurons in the hidden layer were selected from 1, 2, 3, …, 20. The learning rate was selected as 0.01 and no smoothing factor was used. The estimated values of tool wear were obtained by statistical analysis and by various neural network structures. Comparative analysis has been done between statistical analysis, neural network structures and the actual values of tool wear obtained by experimentation.     

移动定位技术的现状与发展趋势

基于位置服务为人们的日常生活带来了极大的方便,同时也推动了移动定位技术行业的快速发展。针对移动定位技术发展状况,分析目前主流定位技术的优劣,并对取得的突破作简单的总结归纳。