基于GGInformer模型的多维时间序列特征提取与预测研究

随着大数据与物联网技术的迅猛发展,多维时间序列数据的应用范围变得更加广泛。面对大量的非线性、高维冗余特征的复杂时间序列,传统的时间序列分析方法已经不能很好地解决多维时间序列的复杂高维特征问题,从而导致预测效果欠佳。针对以上问题,通过对遗传算法和Informer模型进行改进,并融合GRU网络,提出了GGInformer模型。该模型不仅可以有效提取多维时间序列的关键特征,而且较好地解决了长程依赖问题。为了验证模型的预测能力,选取了2种实际数据集与3种公共基准数据集进行实验,相比较Informer基准模型,GGInformer模型在5种数据集上的MSE分别降低了22%,13%,20%,23%和38%。实验结果表明,GGInformer模型可以有效解决多维时间序列数据的复杂特征提取问题,并可以进一步提高时序预测能力。     

一种基于深度学习的时间序列预测方法

时间序列是一种广泛存在于现实各领域之中的海量高维数据,时间序列预测是该领域的一个研究重点.传统的时间序列预测方法仅仅从时间的维度对时间序列进行分析,忽略了外界影响因素对时间序列可能产生的影响.针对传统时间序列预测方法存在的问题,提出一种基于深度学习的时间序列预测模型DAFDCRNN (dual-stage attention and full dimension convolution based recurrent neural network).该模型引入目标注意力机制来学习输入特征与被预测特征之间的相关性,引入全维度卷积机制来学习输入特征之间的相关性,并引入时间注意力(temporal attention)机制来学习时间序列的长期时间依赖性.在实验部分首先确定模型的超参数,然后对模型部件的有效性进行验证,最后通过对比实验验证了所提出的DAFDC-RNN模型在大特征量数据集上具有最佳的预测效果.     

事件预测的时间序列数据挖掘方法

研究了应用数据挖掘技术预测时间序列数据中事件的方法。针对时间序列数据提出了显著特征提取算法，给出了特征间的相似度量标准，并应用特征聚类算法，将时间序列数据转换成相应的特征序列表示。应用频繁模式发现算法和预测模式生成算法在预测时段内发现与目标事件相关的时序特征模式，预测事件的发生。实验结果表明，该文所提出的方法能够有效地预测时间序列数据中的事件。     

利用小波分解的时间序列云量预测方法

针对传统模型对高分辨率云量时间序列数据适用性差、拟合效果较差以及预测结果准确度低的问题,提出了一种基于小波分解的云量时间序列组合模型预测方法。该方法可以有效提取高分辨率云量时间序列数据的低频趋势序列信息和高频随机序列信息,利用波动特征与随机项扰动纠正,对未来一段时期的云量分布进行预测。试验结果表明,该预测方法改进了传统方法对高分辨率数据适用性较差的问题,能够较为准确地拟合时间序列数据的变化规律,提高了预测准确度,为较长周期的卫星成像数据的选取提供重要的参考依据。     

基于自适应增量集成学习的非平稳金融时间序列预测

金融市场对于社会经济的发展非常重要,因此金融时间序列预测（Financial time series prediction, FTSP）一直是人们研究的焦点。至今,许多基于统计分析和软计算的方法被提出以解决FTSP问题,其中大多数方法将金融时间序列（Financial time series, FTS）视为或转化为平稳序列进行处理。但是,由于绝大部分FTS是非平稳的,因此这些方法通常存在伪回归或预测性能不佳等问题。本文提出了一种自适应增量集成学习（Self-adaptive incremental ensemble learning, SIEL）算法,用于解决非平稳金融时间序列预测（Non-stationary FTSP, NS-FTSP）问题。SIEL算法的主要思想是为每个非平稳金融时间序列（Non-stationary FTS, NS-FTS）子集增量地训练一个基模型,然后使用自适应加权规则将各基模型组合起来。SIEL算法的重点在于数据权重和基模型权重的更新：数据权重基于当前集成模型在最新数据集上的性能进行更新,其目的不是为了数据采样,而是为了权衡误差;基模型权重基于其所处环境进行自适应更新,且基模型在越新环境下的性能应具有越高的权重。此外,针对NS-FTS的特征,SIEL算法提出了一种能协调新旧知识以及应对环境重演的策略。最后,给出了SIEL算法在3个NS-FTS数据集上的实验结果,并将其与已有算法进行了对比。实验结果表明,SIEL算法能很好地解决NS-FTSP问题。     

融合全局和序列特征的多变量时间序列预测方法

时间序列在现实生活中具有广泛的用途,使用时间序列预测模型能够预估序列的未来变化趋势,为决策提供支撑.对于多变量时间序列的预测研究,已经提出了很多模型,但已有方法存在如下问题：不能同时考虑时间序列本身和协变量的信息;忽略了多变量时间序列中的全局信息;不能对预测结果进行解释.针对这些问题,本文提出了一个基于深度学习的多变量时间序列预测模型TEDGER,可以提取隐藏在单个时间序列中的序列模式和隐藏在多变量时间序列中的全局特征,并将序列模式和全局特征进行融合,通过残差预测的方式实现时间序列的预测.本文所提模型在真实的时间序列数据集上进行了实验评估.结果表明,本文提出的模型在预测准确度上超越了其他基准模型,同时模型拥有一定的可解释性.     

改进KNN的时间序列分析方法

近年来,随着数据挖掘和机器学习的兴起,基于时间序列分析方法的研究愈加丰富.作为机器学习的经典方法,KNN(K-Nearest Neighbor)因其简单、准确度高等特性被广泛应用于时间序列分析的各个领域.然而,使用原始的KNN回归方法预测时间序列具有一定的局限性,直接使用欧氏距离作为相似度度量方法的预测效果并不理想,无法适应具有整体趋势变化的时间序列的预测场景.文中提出一种拟合时间序列趋势的KNN算法TSTF-KNN(Time Series Trend Fitting KNN)算法,该方法通过对每个时刻的特征序列进行归一化处理,改进了KNN相似度度量的效果,使之可以更有效地搜索相似的特征序列.由于序列预测前进行了归一化,文中通过为预测结果添加误差项来还原序列特征,使之可以有效地预测结果.为了验证方法的有效性,从kaggle公开数据集中选取了4个数据集,并通过对这4个数据集分别进行预处理获得5个时间序列以供实验.通过使用TSTF-KNN、KNN、单层LSTM(Long Short-Term Memory)神经网络和ANN(Artificial Neural Network)在处理后的5个时间序列上进行预测实验,分析预测结果,并对比均方误差(Mean Square Error,MSE),验证了该方法的有效性.实验结果表明,该方法能有效提高KNN回归方法对时间序列预测的准确度和稳定性,使之可以更好地适应具有整体趋势变化的时间序列的预测场景.     

运载火箭类周期测试数据特征预测方法研究

鉴于我国运载火箭测试数据判读工作现状,研究测试数据的预测算法,有助于预判故障趋势,提前采取措施;分析了运载火箭测试数据,提出测试数据依时间序列的分类方法;针对类周期型数据,设计了相应的特征提取算法,得出数据特征时间序列;应用滚动自回归预测算法,并将历史实际值与预测值的加权值作为当前时刻的建模数据,实现了类周期数据特征的趋势预测;该方法有助于改进运载火箭类周期型数据判读方法.     

基于支持向量机的股票价格预测研究

在股市投资测试问题的研究中,股价是一种高度不稳定、复杂且难以预测的时间序列数据,传统预测方法都是基于线性模型,忽略了股价的非线性特征,导致预测精度不高.为解决股价预测过程中的精度不高的难题,提出支持向量机引入到股价预测的建模中.首先采用支持向量机非线性扩展样本对时间序列模型定阶,并利用前向浮动特征筛选法选择特征,建立基于支持向量机的股市预测系统模型,对股价进行仿真实验.仿真结果表明,支持向量机模型比神经网络和CAR模型有较高的预测精度,证明适用于股市预测等非线性问题的预测,且有较高的精确度和应用价值.     

基于小波变换的网络流量预测模型应用研究

研究优化网络性能问题,因网络流量数据具有很强的突发性和自相似性等分形特征,引起系统流量不稳定和不精确,用传统网络流量预测模型预测准确低.为解决上述问题,提出一种基于小波变换(WT)的自回归(AR)预测模型,首先对原始流量数据进行小波分解,并将分解得到的近似部分和各细节部分分别单支重构到原级别上,对各个重构后的序列分别建立自回归模型,由所拟合的模型分别进行预测,最后结合各个重构后序列的预测结果,得到对原始序列的预测结果.运用WT_AR进行仿真实验,实验结果表明模型比传统的网络流量预测模型具有更高的准确度.证明WT_AR是一种高效的网络流量检测模型,网络流量预测方法提供参考依据.     

Decision trees and genetic algorithms for condition monitoring forecasting of aircraft air conditioning

Unscheduled maintenance of aircraft can cause significant costs. The machine needs to be repaired before it can operate again. Thus it is desirable to have concepts and methods to prevent unscheduled maintenance. This paper proposes a method for forecasting the condition of aircraft air conditioning system based on observed past data. Forecasting is done in a point by point way, by iterating the algorithm. The proposed method uses decision trees to find and learn patterns in past data and use these patterns to select the best forecasting method to forecast future data points. Forecasting a data point is based on selecting the best applicable approximation method. The selection is done by calculating different features/attributes of the time series and then evaluating the decision tree. A genetic algorithm is used to find the best feature set for the given problem to increase the forecasting performance. The experiments show a good forecasting ability even when the function is disturbed by noise.     

基于周期性截断灰色系统的电力负荷预测

电力负荷预测是电力系统调度和电力生产计划制定的重要依据;电力负荷时间序列有着明显的周期性特征;传统的电力负荷预测主要侧重于预测方法的研究,而忽略了电力负荷数据周期性特性的分析,影响了预测的准确性;针对电力负荷时间序列的周期性特征,提出了一种基于周期性截断的灰色系统模型来进行电力负荷预测;该模型利用周期性截断来反映负荷数据的周期性特征,提高了预测的精度;仿真采用EUNITE Network的公开负荷数据进行算法性能的测试,并与一些主流的电力负荷预测算法:BP神经网络、极限学习机、自回归模型以及传统的灰色系统模型做比较;仿真结果表明,周期性截断的灰色系统负荷预测的归一化均方误差和绝对平均误差是最小的;周期性截断的灰色系统为电力系统负荷预测提供了一种新的有效方法。     

A SIMPLE TIME VARIANT METHOD FOR FUZZY TIME SERIES FORECASTING

Forecasting using fuzzy time series models needs computations of fuzzy relations in adjacent observations of time series data. In view of getting better forecasted values, these fuzzy relations have been considered as time invariant and time variant, and have been computed in several ways. However, the complication lies with the various rules developed for obtaining these fuzzy relations and then the defuzzification process. In this article, we propose a simple time variant method for time series forecasting. It uses the difference operator and the values obtained have been used for developing fuzzy rules for forecast. We develop algorithms to forecast enrollments of the University of Alabama and compared them with existing methods. The method has been also implemented to forecast rice production of Pantnagar (farm), India. The computational algorithms of the proposed method are simple and provide higher accuracy in forecasting.     

Forecasting financial time series using a methodology based on autoregressive integrated moving average and Taylor expansion

Financial time series prediction is regarded as one of the most challenging job because of its inherent complexity, and the hybrid forecasting model incorporating autoregressive integrated moving average and support vector machine (SVM) has been implemented widely to deal with the both linear and nonlinear patterns in time series data. However, the SVM model does not take into consideration the time correlation knowledge between different data points in time series, which impacts the learning efficiency of the SVM in real application. To overcome this restriction, this paper proposes the Taylor Expansion Forecasting model as an alternative to the SVM and develops a novel hybrid methodology via combining autoregressive integrated moving average and Taylor Expansion Forecasting to exploit the comprehensive forecasting capacity to the financial time series data with noise. Both theoretical proof and empirical results obtained on several commodity future prices demonstrate that the proposed hybrid model improves greatly the forecasting accuracy.     

基于SVM的混沌时间序列分析

支持向量机是一种基于统计学习理论的新的机器学习方法,该方法已用于解决模式分类问题．本文将支持向量机（SVM）用于混沌时间序列分析,实验数据采用典型地Mackey-Glass混沌时间序列,先对混沌时间序列进行支持向量回归实验;然后采用局域法多步预报模型,利用支持向量机对混沌时间序列进行预测．仿真实验表明,利用支持向量机可以较准确地预测混沌时间序列的变化趋势．     

INTUITIONISTIC FUZZY SETS BASED METHOD FOR FUZZY TIME SERIES FORECASTING

Fuzzy time series models are of great interest in forecasting when the information is imprecise and vague. However, the major problem in fuzzy time series forecasting is the accuracy of the forecasted values. In the present study we propose a hybrid method of forecasting based on fuzzy time series and intuitionistic fuzzy sets. The proposed model is a simplified computational approach that uses the degree of nondeterminacy to establish fuzzy logical relations on time series data. The developed model was implemented on the historical enrollment data for the University of Alabama and the forecasted values were compared with the results of existing methods to show its superiority. The suitability of the proposed method was also examined in forecasting market share prices of the State Bank of India on the Bombay Stock Exchange, India.     

Quarterly Time-Series Forecasting With Neural Networks

Forecasting of time series that have seasonal and other variations remains an important problem for forecasters. This paper presents a neural network (NN) approach to forecasting quarterly time series. With a large data set of 756 quarterly time series from the M3 forecasting competition, we conduct a comprehensive investigation of the effectiveness of several data preprocessing and modeling approaches. We consider two data preprocessing methods and 48 NN models with different possible combinations of lagged observations, seasonal dummy variables, trigonometric variables, and time index as inputs to the NN. Both parametric and nonparametric statistical analyses are performed to identify the best models under different circumstances and categorize similar models. Results indicate that simpler models, in general, outperform more complex models. In addition, data preprocessing especially with deseasonalization and detrending is very helpful in improving NN performance. Practical guidelines are also provided.     

基于马尔科夫链理论的改进的最大Lyapunov指数混沌预测法

针对很多文献都一直规避的基于最大Lyapunov指数的混沌预测会出现两个预测值的问题,引入马尔科夫链改进最大Lyapunov指数的混沌预测方法。改进的方法将时间序列的斜率作为状态变量,并根据马尔科夫链建立状态转移矩阵,判定预测值演化方向,进而根据混沌动力学系统的演化规律选择最优的预测值。最后利用渝武高速公路的交通流数据进行验证,结果表明了改进算法的可行性和有效性。     

Fuzzy forecasting based on fuzzy time series

This article presents an improved method of fuzzy time series to forecast university enrollments. The historical enrollment data of the University of Alabama were first adopted by Song and Chissom (Song, Q. and Chissom, B. S. (1993). Forecasting enrollment with fuzzy time series-part I, Fuzzy Sets and Systems, 54, 1–9; Song, Q. and Chissom, B. S. (1994). Forecasting enrollment with fuzzy time series-part II, Fuzzy Sets and Systems, 54, 267–277) to illustrate the forecasting process of the fuzzy time series. Later, Chen proposed a simpler method. In this article, we show that our method is as simple as Chen's method but more accurate. In forecasting the enrollment of the University of Alabama, the root mean square percentage error (RMSPE) of our method is 3.1113% while the RMSPE of Chen's method is 4.0516%, which shows that our method is doing much better.