基于GM(1,N)模型的湖北省物流需求预测分析

文章通过对湖北省物流需求影响因素进行分析,采用湖北省2011—2020年的统计数据构建灰色(1,N)模型,遴选出与系统特征序列相关程度较高的几个影响因素作为预测指标,构建GM(1,6)模型对湖北省物流进行预测研究。模型检验结果表明灰色(1,6)模型具有较高的可信度和准确度,为湖北省有关部门制定物流业发展规划提供一定的参考。

GM(1,N)模型的病态性研究及其在生态创新中的应用

本文以中国工业企业为研究对象,深入探究适用于多因素、少数据的生态创新相关指标特征的灰色模型预测技术。针对传统灰色预测模型在进行参数估计时可能存在的病态性问题展开研究,通过引入L2正则项的最小二乘法,利用粒子群算法求解最优值。将该模型应用于生态创新,与其他模型进行结果对比。结果表明,引入L2正则项的最小二乘法解决了模型的病态性问题,具有良好的预测性能,验证了该模型的有效性。

Predicting GM(1,N) Model for the Coefficient of Variation of Hectometer Yarn's Weight

The Coefficient of Variation(CV)of hectometer yarn's weight is one of the guidelines to evaluate its intrinsic quality.In the spinning manufacturing,the control of cotton yarn's weight unevenness is accomplished mainly in terms of a spot-check on semi-product and a succedent adjust in process parameters during spinning based on technicians' experience.However,it is theoretically believed among manufacturers that with fixed technical levels and parameters in the spinning process,the quality parameters of assorted cotton have a certain influence on the CV.In order to find out a rule of the influence that assorted cotton has on the CV,a GM(1,N)model,correlated raw cotton's quality parameter with the CV,has firstly been developed according to the modeling theory of grey system,and then been applied in the designing step to predict the CV.It has been approved by practical modeling and validation that the model could fit preferably an accrual CV value,and provide a method of quantitative predicting analysis for textile manufacturers to design cotton yarn's quality.

基于改进GM(1,n)的动态网络舆情预警模型

舆情的自由传播会导致网络集群行为的发生,易产生负面社会影响,威胁公共安全,因此建立网络舆情监控及预警机制是防控舆情传播、维护社会稳定的必要措施。首先,通过分析谣言的形成机制,构建了舆情发展预测指标体系;其次,通过建立多因素GM(1,n)模型对舆情发展的走向进行预测;然后,分别结合新陈代谢理论与马尔可夫理论改进上述预测模型;最后,以微博“新疆棉”事件和“成都四十九中”事件为例,对GM(1,n)模型、马尔可夫GM(1,n)模型和新陈代谢马尔可夫GM(1,n)模型预测舆情发展的能力进行对比,并比较了新陈代谢马尔可夫GM(1,n)模型与随机森林模型。实验结果表明,相较于原始模型与随机森林模型,新陈代谢马尔可夫GM(1,n)模型的平均预测精度分别提高了10.6和5.8%。可见,新陈代谢马尔可夫GM(1,n)模型在预测网络舆情发展趋势问题上具有良好的性能。

基于TDOGM(1,N)灰色模型的高校科研能力预测与滞后效应分析

针对高校人才、经费、平台等科研资源投入与科研产出存在的不平衡现象,提出利用带时滞效应的TDOGM(1,N)灰色模型,对在一定的资源投入下,高校科研能力未来发展趋势进行预测,为高校科学配置投入资源、有效评价科研投入效率提供理论基础。通过研究发现,利用带时滞效应的TDOGM(1,N)灰色模型进行投入与产出关系分析、预测,其精度比传统的OGM(1,N)灰色模型高。同时,预测模型还能充分反映其核心要素存在的滞后效应。

Predicting the Number of Beijing Science and Technology Personnel Based on GM(1,N) Model

In this paper, based on the Science and Technology Statistics in Beijing Statistical Yearbook, grey theory is used to study the relationship among S&T (Science and Technology) activities personnel, R&D (research and development) personnel FTE (Full Time Equivalent), intramural expenditure for R&D and Patent Application Amount. According to the grey correlation coefficient, screening of grey GM(1,N) prediction variables, the grey prediction model is established. Meanwhile, time series model and GM(1,1) model are established for patent applications and R&D personnel equivalent FTE. By comparing the simulating results with the real data, the absolute relative error of prediction models is less than 10%. The results of the prediction model are tested. In order to improve the prediction accuracy, the mean values of the predicted values of the two models are brought into the GM(1,N) model to predict the number of scientific and technical personnel in Beijing during 2015-2025. Forecast results show that the number of science and technology personnel in Beijing will grow with exponential growth trend in the next ten years, which has a certain reference value for predicting the science and technology activities and formulating the policy in Beijing.

基于新陈代谢算法优化的GM(1,N)动态网络灰分拟合

煤炭是我国能源资源安全的压舱石,“双碳”背景下实现煤炭清洁加工与高效利用意义重大,而灰分检测对煤炭清洁化和智能化发展尤为重要。针对现有灰分检测存在的检测精度有待提高的突出问题,以两淮矿区典型煤样为研究对象,通过慢灰和X射线荧光(X ray fluorescence,XRF)测试系统地探究了煤样的灰分和元素组成分布规律,并结合机器学习理论构建了灰分-元素特征数据集;结合灰色系统理论和新陈代谢算法,构建了自适应的GM(1,N)动态网络灰分拟合优化模型,并详细设计了动态网络算法流程;提出了GM(1,N)动态模型的关键超参数,并通过与常规拟合方法对比,全面地评价了模型拟合性能。结果表明:两淮矿区煤可视为由可燃元素和成灰元素共同构成,且成灰元素中质量分数占比最高为Si和Al,次之为S、Fe和Ca等,最少为P和Cl等,并且煤中成灰元素总含量与灰分呈正相关,而可燃元素与之相反;以灰分为标签值、以组成元素为特征值,形成了煤的灰分-元素特征数据集;以样本数据划分→动态网络灰分拟合→模型评价机制→动态拟合模型自适应优化→鲁棒性提升→多轮迭代优化为主线设计了GM(1,N)动态网络灰分拟合模型及其算法流程,有效提升了数据集稳定性和新鲜度,并且迭代收敛速度快,灰分误差阈值5%时其准确率达100%;对比经典GM(1,N)模型和常规多元线性回归模型,证明了新模型的灰分拟合性能得到显著提升,其相对误差为0.16%~4.96%、误差均值仅2.29%。

湖北省农产品物流需求预测研究——基于GM(1,N)模型

农产品物流既是保障民生的基础,也关乎现代农业的发展。文中基于湖北省2011-2020年数据,对湖北省农产品物流需求量的相关因子进行分析,采用一阶多变量的GM(1,N)灰色预测模型,构建湖北省农产品物流需求预测指标体系,以灰色关联度计算为依据,选出与湖北省农产品物流需求量相关程度高的相关因子作为预测指标,构建灰色GM(1,6)模型,结果显示预测模型精确度和可信度较高,并根据预测结果提出农产品物流发展相关建议,为湖北省农产品物流业制定规划、提供参考。

优化MGM(1,n)模型在边坡沉降预测中的应用研究

为更好地预测边坡沉降,考虑边坡整体变化趋势,采用多变量的优化MGM(1,n)模型,对边坡相关的各监测点的沉降变形进行了预测。该研究先以平均相对残差为指标筛选初值,引入背景值系数重构背景值计算公式;再据此建立改进的双值MGM(1,n)优化模型;最后,以中山西环高速公路A段的边坡工程为实例,分别建立传统MGM(1,n)模型、GM(1,1)模型和优化MGM(1,n)模型,并对所测数据进行建模预测和比较分析。研究结果表明:在3种优化模型中,优化MGM(1,n)模型的预测精度最高。该模型在边坡沉降预测方面具有一定的应用前景,可为类似工程和研究提供参考。

中国金融压力指数的测度——基于AHM-EWM-GM(1,N)耦合下中国金融压力指数的测度

当前,全球金融市场动荡不安,我国经济的发展进入新的历史阶段,中央在多次会议上提出“靠靠守住不发生系统性金融风险的底线”,因此建立风险测度、预警和防范机制至关重要。本文从银行市场,宏观金融,债券与保险市场,股票市场,外部市场,房地产市场6个金融子市场方面选取指标,基于AHM (Attribute Hierarchy Model)-EWM (Entropy Weight Method)模型,构建中国金融压力指数,并利用GM(1,N)模型进行检验。研究结果表明:AHM (Attribute Hierarchy Model)-EWM (Entropy Weight Method)模型可以较好拟合中国金融市场压力值并能较好地对风险进行拟合;同时表明银行市场和股票市场对我国金融系统的风险贡献最大,监管部门要继续加强对子市场的监管。

基于改进的GM(1,N)模型的我国碳排放预测研究

“双碳”背景下,精准预测碳排放强度,有利于制定科学的减排路径,对于我国发展低碳经济具有重要的参考意义。为了提高预测精度,本文建立了时滞GM(1,N)幂模型,采用蜻蜓算法来为模型选择最佳幂指数,并给出了具体的模型构建方法和严格的数学证明。为了验证模型的适用性和有效性,本文将该模型与传统灰色模型进行了比较,并对我国2014~2021年的碳排放进行了模拟。结果表明,改进的GM(1,N)模型具有更好的模拟效果,因此,本文将其应用于我国碳排放预测,为制定科学的减排路径提供参考意见。

基于优化GM(1,N)模型的油气管道腐蚀速率预测

为了提高油气管道腐蚀速率的预测精度,解决样本缺失情况下管道剩余寿命的预测问题,通过斯皮尔曼相关系数和随机森林算法寻找腐蚀因素中相关性较高的变量,去除相关性较高但重要性较低的变量,采用人工蜂群算法(ABC)对GM(1,N)模型的背景值进行动态优化,形成优化GM(1,N)模型,并对不同模型的预测结果进行了对比。结果表明,腐蚀因素中一些变量存在较强的相关性,筛选出重要性较高且相关性较小的5个变量,分别为土壤电阻率、含盐量、氧化还原电位、含水量和硫化物质量分数;与GM(1,10)和GM(1,6)模型相比,优化的GM(1,6)模型在训练阶段和预测阶段的平均相对误差均大幅降低,分别为1.52%和2.03%,预测结果更接近实际值,说明了降低因素冗余性和对背景值进行优化的必要性。该优化模型可为油气管道腐蚀速率的准确预测提供实际参考和借鉴。

关于农产品冷链物流需求预测的灰色GM(1,N) 模型

经济区域冷链物流的基础设施规划的基础工作在于对冷链物流的需求预测,对农产品冷链物流需求预测建立分析框架、选择适合的预测方法具有非常重要的现实意义。文中通过灰色关联分析,选取能够影响全国冷链物流指标的部分影响因素。利用2013-2020年全国冷链物流需求相关数据,选取全国社会物流总费用、全国冷链物流总需求量来建立GM(1,N)灰色预测模型,对全国农产品冷链物流的需求量进行预测。通过实验,其预测结果精度较好,平均误差为3.63%。通过此模型,提出相关建议来完善全国的农产品冷链物流。

Prediction of efficient outputs based on GM(1,N) model and weak DEA efficiency

This paper expresses the efficient outputs of decisionmaking unit（DMU） as the sum of ＂average outputs＂ forecasted by a GM（1,N） model and ＂increased outputs＂ which reflect the difficulty to realize efficient outputs.The increased outputs are solved by linear programming using data envelopment analysis efficiency theories,wherein a new sample is introduced whose inputs are equal to the budget in the issue No.n ＋ 1 and outputs are forecasted by the GM（1,N） model.The shortcoming in the existing methods that the forecasted efficient outputs may be less than the possible actual outputs according to developing trends of input-output rate in the periods of pre-n is overcome.The new prediction method provides decision-makers with more decisionmaking information,and the initial conditions are easy to be given.

Forecast Grain “Three Quantities” Based on Grey GM (1, 1) and Promote the Structural Reform of Grain Supply Side

As a special product, the cultivation and production of grain directly affect the consumption of people, which has an important influence on the development of social economy and the national economy and people’s livelihood. Firstly, the present situation of grain production is analyzed, and the problems facing the structural reform of grain supply side in China are analyzed from grain output and its import and export volume. Secondly, we use grey GM (1, 1) model to predict grain output and consumption, grain import and export volume and all kinds of grain crops output in China, and then analyze the future trend of grain production in China. Finally, we put forward construction of grain branding, rational allocation of grain planting varieties, construction of traceability system for grain production, further grain processing and development of “Internet agriculture” industrial model to promote structural reform of grain supply side.

Application of Renewal Gray GM (1,1) Model to Prediction of Landslide Deformation

The gray renewal GM (1,1) landslide prediction model was established by improving the gray model. Based on the established model, the author has made prediction of landslide deformation to the Xiangjiapo landslide and the Lianziya dangerous rock body. The results show that the gray renewal GM (1,1) model can supplement the new information in time and remove the old information which reduces the meaning of the information because of time lapse. Therefore, the model is closer to reality.

Application of Gray Metabolic GM (1,1) Model in Prediction of Annual Total Yields of Chinese Aquatic Products

To predict the annual total yields of Chinese aquatic products in future five years ( 2011-2015) ,based on the theory and method of gray system,this paper firstly establishes a conventional GM ( 1,1) model and a gray metabolic GM ( 1,1) model respectively to predict the annual total yields of Chinese aquatic products in 2006-2009 and compare the prediction accuracy between these two models. Then,it selects the model with higher accuracy to predict the annual total yields of Chinese aquatic products in future five years. The comparison indicates that gray metabolic GM ( 1,1) model has higher prediction accuracy and smaller error,thus it is more suitable for prediction of annual total yields of aquatic products. Therefore,it adopts the gray metabolic GM ( 1,1) model to predict annual total yields of Chinese aquatic products in 2011-2015. The prediction results of annual total yields are 55. 32,57. 46,59. 72,62. 02 and 64. 43 million tons respectively in future five years with annual average increase rate of about 3. 7% ,much higher than the objective of 2. 2% specified in the Twelfth Five-Year Plan of the National Fishery Development ( 2011 to 2015) . The results of this research show that the gray metabolic GM ( 1,1) model is suitable for prediction of yields of aquatic products and the total yields of Chinese aquatic products in 2011-2015 will totally be able to realize the objective of the Twelfth Five-Year Plan.

Effect of Aluminum Hydroxide Adjuvant on the Immunogenicity of the 2009 Pandemic Influenza A/H1N1 Vaccine:Multi-level Modeling of Data with Repeated Measures

Objective To evaluate the effect of the aluminum hydroxide （Al-OH） adjuvant on the 2009 pandemic influenza A/H1N1 （pH1N1） vaccine. Methods In a multicenter, double-blind, randomized, placebo-controlled trial, participants received two doses of split-virion formulation containing 15 ug hemagglutinin antigen, with or without aluminum hydroxide （N-OH）. We classified the participants into six age categories （〉61 years, 41-60 years, 19-40 years, 13-18 years, 8-12 years, and 3-7 years） and obtained four blood samples from each participant on days 0, 21, 35, and 42 following the first dose of immunization. We assessed vaccine immunogenicity by measuring the geometric mean titer （GMT） of hemagglutination inhibiting antibody. We used a two-level model to evaluate the fixed effect of aluminum Al-OH and other factors, accounting for repeated measures. Results The predictions of repeated measurement on GMTs of formulations with or without Al-OH, were 80.35 and 112.72, respectively. Al-OH significantly reduced immunogenicity after controlling for time post immunization, age-group and gender. Conclusion The Al-OH adjuvant does not increase but actually reduces the immunogenicity of the split-virion pH1N1 vaccine.

Construction of GM(2,1)Model for Oscillating Pitch Angle Series

GM(1, 1) is generally used in Grey System Theory which constructs an Ordinary Differential Equation for given se-ries. It is effective for monotone series, and its simulating effect is good and error is small. However, If the series dosen’ t havea property of monotone, the simulating effect of GM(1,1) is not fine, and its error gets bigger. In this paper, we use GM(2,1) to handle the oxcillation series, which uses the Method of Minimum Squares in determining the uncertain parameters.

The Modified GM( 1 , 1) Grey Forecast Model

Because the impacts of the factors such as some disturbances are graduallyadded into the system, the grey forecast results will deviate from the systemtrue value. To improve the forecast precision, Pro-Dens Julons provided twomethfor-But they had not consider the impact of artificial disturbance. LiZhihua et al. of Qinghua Univ. presented another method. This paper revisesthe method and make it be a spocial case.