GAFSA优化SVR的网络流量预测模型研究

现有的诸多网络流量预测模型存在预测稳定性不好、精度较低等问题。针对此类问题, 研究了一种通过GAFSA(全局人工鱼群算法)优化SVR模型的网络流量预测方法。GAFSA是一种群智能优化算法, 寻优效果显著。采用GAFSA对SVR预测模型进行参数寻优, 可以得到使预测效果最佳的训练参数; 使用这组最优参数训练SVR, 建立网络流量预测模型, 可以很好地改善基于其他智能优化算法改进的SVR网络流量预测模型多次预测结果相差较大的问题, 使预测结果趋于稳定, 同时也可以提高预测精准度。仿真结果表明, GAFSA-SVR网络流量预测模型与其他模型相比, 预测结果基本稳定, 精准度提高到89%以上, 对于指导网络控制行为、分析网络安全态势有重要意义。     

网络安全态势感知研究综述

随着科学技术的发展,网络规模在不断的扩大,复杂性也在逐渐的增强,面临的网络安全问题也越来越严峻。传统的网络安全技术已经无法满足网络快速发展的需要,无法全面的防御网络攻击行为,必须对新的网络安全技术进行大力研究和开发。网络安全态势感知能够对影响网络安全的因素进行量化分析,为保障网络安全提供重要的依据,因此,对网络安全态势感知进行研究意义重大。本文将在网络安全态势感知概念模型的基础上,对网络安全态势感知的相关研究进行探讨。     

丙烯腈的国内外生产和市场情况

对丙烯腈的国内外生产情况、市场供需情况作了详细阐述。     

HYDRODYNAMIC STUDIES IN A HALF SLOT-RECTANGULAR SPOUTED BED COLUMN

Experiments were carried out in a half slot-rectangular spouted bed to investigate the effects of slot width and lower section basal angle on column hydrodynamics. Flow regimes, minimum spouting velocity, spouting and maximum pressure drops, and maximum spoutable bed height were determined for 4 mm diameter polyethylene particles. The results are compared with those for conventional cylindrical and rectangular spouted beds. Correlations for each hydrodynamic parameter are developed and compared with equations available in the literature.     

基于改进的BASS模型的服装产品生命周期研究

为提高服装的销售预测准确度,通过产品的生命周期曲线模型,使得服装销售预测的定性分析与定量预测有机地结合在一起。针对目前服装产品生命周期曲线模型的局限性,引入改进的BASS模型,对服装产品生命周期进行研究。通过销售实例探讨改进的BASS模型用于描述服装生命周期的可行性,建立了以改进的BASS模型为基础的服装产品生命周期模型,并利用该模型对服装销售量做预测,取得了比其他模型更高的精度。     

Integrated reliability or travel time and capacity or urban road network under ice and snowfall conditions

In order to evaluate and integrate travel time reliability and capacity reliability of a road network subjected to ice and snowfall conditions, the conceptions of travel time reliability and capacity reliability were defined under special conditions. The link travel time model (ice and snowfall based-bureau public road, ISB-BPR) and the path choice decision model (elastic demand user equilibrium, EDUE) were proposed. The integrated reliability was defined and the model was set up. Monte Carlo simulation was used to calculate the model and a numerical example was provided to demonstrate the application of the model and efficiency of the solution algorithm. The results show that the intensity of ice and snowfall, the traffic demand and supply, and the requirements for level of service (LOS) have great influence on the reliability of a road network. For example, the reliability drops from 65% to 5% when the traffic demand increases by 30%. The comprehensive performance index may be used for network planning, design and maintenance.     

Effect of fretting amplitudes on fretting wear behavior of steel wires in coal mines

Given that fretting wear causes failure in steel wires, we carried out tangential fretting wear tests of steel wires on a self-made fretting wear test rig under contact loads of 9 and 29 N and fretting amplitudes ranging from 5 to 180 μm. We observed morphologies of fretted steel wire surfaces on an S-3000N scanning electron microscope in order to analyze fretting wear mecha-nisms. The results show that the fretting regime of steel wires transforms from partial slip regime into mixed fretting regime and gross slip regime with an increase in fretting amplitudes under a given contact load. In partial slip regime, the friction coefficient has a relatively low value. Four stages can be defined in mixed fretting and gross slip regimes. The fretting wear of steel wires in-creases obviously with increases in fretting amplitudes. Fretting scars present a typical morphology of annularity, showing slight damage in partial slip regime. However, wear clearly increases in mixed fretting regime where wear mechanism is a combination of plastic deformation, abrasive wear and oxidative wear. In gross slip regime, more severe degradation is present than in the other regimes. The main fretting wear mechanisms of steel wires are abrasive wear, surface fatigue and friction oxidation.     

Establishmen and vertification of an improved similitude law for dynamic ice force model test

To study the similitude laws for dynamic ice force model test which is a hot problem in ice mechanics.In this paper,a new modified similitude law for dynamic ice force model test is proposed based on ice-induced virbration theory and two reasonable assumptions.And the new law is vertified with an ice-induced pier virbration example.The numerical calculation results show that,firstly,the error of frequency factor between test value and theory value is small as well as that of displacement and velocity;Secondly,the time scale completely meet the similitude relation,the waveforms anastomotic well,and the phenomenon of offset and omit do not occur;Thirdly,as the damping ratio between prototype and model is nearly equal,the improved similitude law will still be applied.Therefore,the new modified similitude law is feasible to study dynamic ice force model test and can provide reference for the ice mechanics.     

GM(1,1)模型在虚拟仪器测量过程控制中的应用

虚拟仪器的测量过程控制是保证测量数据有效的重要手段,利用灰色系统GM(1,1)模型对虚拟仪器的测量过程进行控制,由少量数据信息得到未来的预期测量结果,通过与核查标准的测量结果相比较来判别测量过程是否受控.论文给出了测量过程控制判别限、适用灰色系统GM(1,1)模型的条件以及模型精度检验判据.     

神经网络在个人信用组合预测中的应用

该文运用组合预测的思想,提出了通过感知器、BP、Elman和LVQ等不同的具有代表性的神经网络模型,将多元线性回归和logistic回归两单一方法进行组合,并分别应用于某商业银行的个人信用评估,其结果表明:感知器、BP、Elman和LVQ神经网络组合预测方法精确度不尽相同,但总体上能够获得比多元线性回归和logistic回归更高的预测精度,尤其在避免纳伪错误方面更具优势。