共查询到18条相似文献，搜索用时 468 毫秒
1.
《科研管理》2017,(5)
BDI指数的预测对于航运市场经营管理具有重要的指导作用。本研究构建了基于周期、均值回复和跳跃特性的BDI指数O-U随机预测模型,主要创新点有:一是分析了BDI指数的周期、均值回复以及跳跃特性,将该三大特性纳入BDI指数随机预测模型,有效提升了BDI指数预测理论科学性。二是借助O-U随机过程,建立了基于周期、均值回复以及跳跃特性BDI指数预测模型,同时,利用Fourier级数函数估计周期参数,借助一阶自回归估计均值回复参数,以及Gamma分布和双指数分布来估计跳跃参数,解决了参数较多、估计难度较大的问题。三是采集2013年-2015年BDI指数日数据进行拟合,并借助蒙特卡罗方法对2016年上半年BDI指数开展了预测,结果表明本模型预测精确度较高。 相似文献
2.
本文全面考虑BDI指数不同类型的影响因素,将影响因素划分为供给方面、需求方面以及宏观经济三种类型,采用基于VMD分解、小波分析与随机森林回归算法构建的VMD-WA-RF模型,综合分析各影响因素与BDI指数的关系,增强了BDI指数影响因素分析的数学理论。进一步的研究发现：一是,借助VMD-WA-RF模型能够得出BDI指数影响因素的重要性排名,有助于有针对性的调节航运市场;二是,能够得出最重要的五个影响因素分别对BDI指数的影响程度,科学地找出能够迅速调节当前航运市场最有效的方案;三是,通过随机森林回归模型,对BDI指数进行预测,表明本模型预测的精确度较高。 相似文献
3.
4.
本文主要研究了基于改进指数平滑算法的气温预测问题。首先引入时间序列模型概念,对常用气温预测模型进行简要分析,另外对一阶指数平滑算法进行相关推导,同时提出了自适应指数平滑算法;其次,结合广西容县近30年月均气温实测数据,分别建立BP神经网络预测模型、传统指数平滑算法预测模型以及改进后的基于自适应指数平滑算法的预测模型,对2016年气温数据进行预测并分析模型优势;最后,将改进模型用于预测2017年和2018年中未知月份的月平均气温值,并针对实验结果进行数据分析修正。通过对不同预测模型的比较和仿真实验,结果表明基于自适应指数平滑算法的气温预测模型预测精度较高,实用性强,具有一定的推广性。 相似文献
5.
6.
采用不同的损失函数和罚函数构建了广义指数预报因子模型,用该模型来预测国际黄金价格.构建方法包括:1)岭估计方法;2)基于L1、L2以及二者结合的损失函数LM,利用LASSO和SCAD 2种罚函数选取不同参数EWMA的线性组合作为预报因子.实证检验表明,该方法构建的模型有效改进了单参数EWMA预测模型,其预测精度优于已有方法. 相似文献
7.
连接航运指数船舶融资租赁区间积息互换是航运企业一种财务风险管理创新模式,在当前航运背景下具有潜在的广泛应用价值,因此本文围绕连接航运指数船舶融资租赁区间积息互换展开研究。首先,结合利率互换理论和该模式特征,提出了连接BDI指数的船舶融资租赁区间积息互换框架和无套利中性定价理论;其次,借助随机过程方法,构建了BDI指数和利率走势双随机情景模拟下、连接BDI指数的船舶融资租赁区间积息互换模型,并给出了蒙特卡罗法模拟求解步骤。最后,采用实例进行了模型验证和情景分析,结果表明本文建立的连接BDI指数的船舶融资租赁区间积息互换模型可靠性较好,更贴近实际情况。 相似文献
8.
本文应用FM-OLS来估计阈值协整参数,并利用Monte-Carlo模拟详细研究了其小样本性质,结果表明FM-OLS法能修正OLS估计的小样本偏差,且数据过程的持久性(均值回复速度)、随机干扰项与解释变量的相关程度以及样本容量是影响FM-OLS小样本性质的主要因素.模拟结果还表明不论是阈值协整还是线性协整,FM-OLS都比OLS估计具有明显优势,因此在宏观经济协整分析中,利用FM-OLS法能获得较准确的参数估计,同时还可以利用标准分布对协整参数进行Wald检验. 相似文献
9.
甚低频电波传播特性分析与预测是提高甚低频导航/授时系统精度的关键。本文基于甚低频电磁波在"地-电离层"波导中的传播理论,结合IRI模型和NRLMSISE-00大气模型以及传播矩阵方法,构建了甚低频电波传播场强实时预测模型。对比了不同电离层模型间的差异以及电离层参数的时变特性,仿真预测了接收点场强及其日变化情况,并与文献实测结果进行了比较。计算结果表明:本文预测结果与实测数据吻合较好,较采用电离层指数模型的传统解析方法精度得到明显提升,可更有效地反映接收点场强的时变特性。 相似文献
10.
11.
《Journal of The Franklin Institute》2023,360(12):7770-7807
In this article, combining the transmission features of HPV infection and secondary cervical cancer in Xinjiang, China, a stochastic dynamical model for the HPV infection and secondary cervical cancer with environmental white noise is proposed. Firstly, the stochastic extinction of disease is investigated. A sufficient criterion for the asymptotic behavior of any positive solution of stochastic model revolving around the disease-free equilibrium of corresponding deterministic model is established. Secondly, a threshold criterion for the existence of unique ergodic stationary distribution is obtained by means of the auxiliary function. Furthermore, a new technique of partitioned matrix for the calculation of probability density function is proposed, the expression of a log-normal density function around the quasi-endemic equilibrium of stochastic model is calculated. Lastly, the best-fit parameter values in our model are identified by the MCMC algorithm on the basis of the cervical cancer data in Xinjiang province, China. The basic reproduction number is estimated as 1.3496 (95% CnI: (1.3458, 1.3716)). Then, to determine the key parameters of the model, the sensitivity analysis is explored. Some possible interventions and control measures are provided to reduce the HPV infection spread and cervical cancer in Xinjiang of China. 相似文献
12.
This paper addresses the stabilization of stochastic jump diffusion system in both almost sure and mean square sense by state-feedback control. We find conditions under which the solutions to the class of jump-diffusion process are mean square exponentially stable and almost sure exponentially stable. We investigate the stabilization of the stochastic jump diffusion systems by applying the state-feedback controllers not only in the drift term, but also in jump diffusion terms. Meanwhile our theory is generalized to cope with the uncertainty of system parameters. All the results are expressed in terms of linear matrix inequalities (LMIs), which are easy to be checked in a MATLAB Toolbox. 相似文献
13.
This paper presents three identification methods for dual-rate sampled systems. The first method combines the stochastic gradient algorithm with the polynomial transformation technique, which can estimate the parameters of the identification model. The second method is the finite impulse response model based stochastic gradient algorithm, which can indirectly estimate the parameters of the dual-rate systems by using all the inputs and the available outputs. The third method is the missing output estimation model based stochastic gradient algorithm with a forgetting factor, which can directly estimate the parameters of the dual-rate systems by using all the inputs and all the outputs (include the estimated outputs). An example is provided to verify the effectiveness of the proposed methods. 相似文献
14.
This paper develops the secure control strategy design issue for jump cyber–physical systems (CPSs) with malicious attacks. In the jump CPSs, the jump signals are assumed to obey the semi-Markov distribution with the transition probability depends on the stochastic sojourn-time, the physical plant and actuator simultaneous subject to the adversarial attack. A secure control strategy on robust sliding-mode control (SMC) is designed to deal with the malicious attacks. Firstly, an integral sliding-mode hyperplane is constructed, and the sliding-mode dynamics is discussed. Then, the slide-mode parameters are solved by the linear matrix inequality method with prescribed H∞ damping index. Furthermore, a robust sliding-mode controller is presented, and the reachability of the sliding-mode motion is analyzed. Finally, two examples are implemented to prove the potential of the secure control approach. 相似文献
15.
The robust stochastic convergence in mean square is investigated for a class of uncertain Cohen–Grossberg neural networks with both Markovian jump parameters and mode-dependent time-varying delays. By employing the Lyapunov method and a generalized Halanay-type inequality, a delay-dependent condition is derived to guarantee the state variables of the discussed neural networks to be globally uniformly exponentially stochastic convergent to a ball in the state space with a pre-specified convergence rate. After some parameters being fixed in advance, the proposed conditions are all in terms of linear matrix inequalities, which can be solved numerically by employing the LMI toolbox in Matlab. Finally, an illustrated example is given to show the effectiveness and usefulness of the obtained results. 相似文献
16.
This paper deals with the stochastically asymptotic stability in the mean square for a new class of stochastic neural networks of neutral type with both Markovian jump parameters and mixed time delays. The jumping parameters are modeled as a continuous-time, finite-state Markov chain. Based on the Lyapunov–Krasovskii functional, stochastic analysis theory and the delay-fractioning approach, the stochastically asymptotic stability of the considered neural network has been achieved by solving some linear matrix inequalities, which can be easily facilitated by using the standard numerical software. The obtained results are shown to be much less conservative via constructing a new Lyapunov–Krasovskii functional and the idea of “delay fractioning”. Finally, four numerical examples are provided to show the effectiveness of the proposed method. 相似文献
17.
《Information processing & management》2023,60(4):103399
Developing a tourism forecasting function in decision support systems has become critical for businesses and governments. The existing forecasting models considering spatial relations contain insufficient information, and the spatial aggregation of simple tourist volume series limits the forecasting accuracy. Using human-generated search engines and social media data has the potential to address this issue. In this paper, a spatial aggregation-based multimodal deep learning method for hourly attraction tourist volume forecasting is developed. The model first extracts the daily features of attractions from search engine data; then mines the spatial aggregation relationships in social media data and multi-attraction tourist volume data. Finally, the model fuses hourly features with daily features to make forecasting. The model is tested using a dataset containing several attractions with real-time tourist volume at 15-minute intervals from November 27, 2018, to March 18, 2019, in Beijing. And the empirical and Diebold-Mariano test results demonstrate that the proposed framework can outperform state-of-the-art baseline models with statistically significant improvements at the 1% level. Compared with the best baseline model, the MAPE values are reduced by 50.0% and 27.3% in 4A attractions and 5A attractions, respectively; and the RMSE values are reduced by 48.3% and 26.1%, respectively. The method in this paper can be used as a function embedded in the decision support system to help multi-department collaboration. 相似文献
18.
A problem of stabilization about uncertain networked control systems (NCSs) with random but bounded delays is discussed in this paper. By using augmented state-space method, this class of problems can be modeled as discrete-time jump linear systems governed by finite-state Markov chains. A new switched model based on probability is proposed to research problems of reliable control when actuators become ageing or partially disabled. Using improved V-K iteration algorithm, a class of reliable controllers are designed to make systems asymptotically mean square stable under several stochastic disturbances such as random time-delay and stochastic actuator failure and the maximal redundancy degree is given through this method. 相似文献