基于数据挖掘的水文时间序列预测

基于灰色理论和灰色神经网络组合预测模型,对水文时间序列进行数据挖掘。对原始序列首先进行了对数-方根变换,使得数据序列满足灰色理论的覆盖条件,采用灰色预测模型GM（1,1）,对数据序列进行预测,由于灰色预测属于线性预测,因此将灰色预测模型与神经网络模型相结合,提高了预测精度。以都江堰岷江来水数据为原始数据进行实际预测,实验证明,这种组合模型的预测效果优于传统预测模型。     

灰色Verhulst-BP网络组合模型在预测中的应用研究

在灰色Verhulst模型和BP神经网络理论的基础上,对两者的结合方式进行了研究,提出了部分数据Verhulst模型组的概念,得到了一种结合灰色Verhulst与BP神经网络的组合预测模型。利用BP神经网络建立部分数据Verhulst模型组与原始数据之间的非线性映射关系,克服了小样本时间序列数据在神经网络训练时的缺陷。实验结果和仿真验证表明,该组合预测模型具有较高的预测精度和良好的稳定性。     

基于灰色神经网络的烧结碱度预测与仿真

建立了应用灰色神经网络对烧机矿化学成分进行预测的有关理论，并在此基础上构造了灰色神经网络模型。该模型中。灰色理论弱化数据序列波动性和神经网络特有的非线性适应性信息处理能力相融合，本模型能在小样本贫信息的条件下对烧结矿碱度做出比较准确的预测。该模型具有预测精度高、所需样本少、计算简便等优点，取得了比较满意的结果。和BP神经网络算法相比，灰色神经网络算法有很大的应用前景和推广价值。     

具有FIR突触的积单元神经网络预测时间序列

提出一种具有有限脉冲响应(FIR)突触的积单元神经网络(PUNN)结构，并用于预测混沌时间序列。这种神经网络结构既继承了标准PUNN的结构简单、信息存储能力强的优点，又更适合预测混沌时间序列，特别是在小的学习样本情况。分别用具有FIR突触的PUNN、标准PUNN以及模糊神经网络(FNN)等3种神经网络对小的样本混沌时间序列做了1步多步预测对比实验。结果显示具有FIR突触的PUNN比其他2种神经网络预测精度都高。这说明具有FIR突触的PUNN是预测小学习样本时间序列的一种有效方法。     

基于灰色GM(1,1)模型的时间序列预测研究

基于灰色理论GM(1,1)模型,结合Elman神经网络组成灰色神经网络模型。模型的输出误差作为一个新的时间序列,通过Elman神经网络对误差序列进行拟合和预测,更大限度地减小预测误差。GM(1,1)模型所需要的数据少,方法简单;Elman神经网络是动态的神经网络对历史数据具有高度的敏感性。这种灰色理论与动态神经网络的组合模型,比起单个的预测模型提高了预测精度,通过分析和验证表明,该方法实用有效。     

基于傅立叶级数的小样本振荡序列灰色预测方法

针对现有灰色模型不能适用于小样本振荡序列预测的问题, 提出了基于傅立叶级数的小样本振荡序列灰色预测方法. 首先对原始序列建立GM(1,1) 幂模型以描述系统行为的总体趋势; 然后利用傅立叶级数提取模型的残差序列所包含的周期性振荡规律, 并以二者之和构成新的时间响应函数; 最后以平均误差最小化为目标, 建立非线性优化模型求解最优参数. 应用实例表明, 该方法能够有效地提高灰色模型对小样本振荡序列的预测精度.     

多尺度方法结合卷积神经网络的行为识别

为了同时计算行为序列样本在时间和空间的特征,提出了一种基于包含多尺度卷积算子的卷积神经网络识别模型。首先通过叠加的方式将序列样本中的骨骼向量信息整合为一个行为矩阵,然后将矩阵输入识别模型。为了挖掘具有不同邻接关系的骨骼点在描述人体行为时的作用,将卷积神经网络各层中的卷积算子拓展为多尺度卷积算子,并使用该网络得到的特征进行分类。实验在MSR-Action3D数据集和HDM05数据集获得较好的识别率。     

基于灰色径向基神经网络模型的流量预测与分析

根据神经网络能有效修正灰色预测模型的思路,本文提出了基于灰色系统及径向基神经网络的组合预测模型。通过采集园区节点交换机的流量数据,在分析网络流量时间序列特性的基础上建立灰色GM（1,1）模型,并采用径向基神经网络对预测模型残差进行修正。实验结果和仿真实验表明,组合模型效果及预测精度远优于单一灰色预测模型。     

基于灰色Verhulst-小波神经网络的装备故障预测研究

针对现代武器装备故障预测样本少、故障预测精度低、维修保障困难等问题,提出一种基于灰色Verhulst-小波神经网络组合模型的装备故障预测方法。该方法综合了灰色Verhulst模型所需样本少的优点和小波神经网络良好的时频局域化性质和学习能力,克服了小样本故障数据在BP神经网络训练中的缺陷。实验结果表明,与相关研究方法比较,所提出方法具有较高的预测精度,对于武器装备故障预测与维修保障具有一定的理论价值和现实意义。     

基于灰色神经网络建模的水质参数预测

针对水质参数预测过程中样本数据少的特点,结合灰色新陈代谢GM(1,1)模型和BP神经网络模型,提出灰色新陈代谢BP神经网络组合模型。用灰色新陈代谢模型群的数据集作为BP神经网络的学习测试样本,解决了BP网络需要大量样本才能较好地逼近非线性函数的问题。实验表明,与普通BP网络、灰色新陈代谢模型比较,灰色新陈代谢BP神经网络组合模型的预测精度更高,能够应用于水质参数的预测。     

基于数据并行的神经网络预测模型

分析了数据挖掘领域面临的性能问题(主要包括算法的有效性、可伸缩性和并行性);根据数据并行的思想,提出了在时序预测中并行训练神经网络的模型,以提高训练速度。这一模型具有良好的可扩展性,能适应大训练集的情况,是一种粗粒度的并行,且易于在集群系统这样的并行环境下进行数据挖掘。同时,描述了相关算法,并对训练速度进行了测试。     

An investigation of neural networks for linear time-series forecasting

This study examines the capability of neural networks for linear time-series forecasting. Using both simulated and real data, the effects of neural network factors such as the number of input nodes and the number of hidden nodes as well as the training sample size are investigated. Results show that neural networks are quite competent in modeling and forecasting linear time series in a variety of situations and simple neural network structures are often effective in modeling and forecasting linear time series.Scope and purposeNeural network capability for nonlinear modeling and forecasting has been established in the literature both theoretically and empirically. The purpose of this paper is to investigate the effectiveness of neural networks for linear time-series analysis and forecasting. Several research studies on neural network capability for linear problems in regression and classification have yielded mixed findings. This study aims to provide further evidence on the effectiveness of neural network with regard to linear time-series forecasting. The significance of the study is that it is often difficult in reality to determine whether the underlying data generating process is linear or nonlinear. If neural networks can compete with traditional forecasting models for linear data with noise, they can be used in even broader situations for forecasting researchers and practitioners.     

遗传优化的GNNM在瓦斯涌出量预测中的应用

研究矿井瓦斯涌出量准确预测一直是煤矿安全生产中重点关注的问题。煤层瓦斯爆炸因受开发环境、矿层深度、天气等因素的影响,造成与瓦斯涌出量增大而引起的。针对传统预测模型在矿井瓦斯涌出量预测中存在建模困难、收敛速度慢、要求历史数据量大的问题,提出了一种遗传优化的灰色神经网络预测模型。模型利用灰色系统对数据量要求低的特点,将灰色系统理论与神经网络有机结合起来,建立灰色神经网络模型。并采用遗传算法对所建立模型的权值和阈值进行优化。采用模型对矿井瓦斯涌出量进行预测,实验表明,遗传优化的灰色神经网络模型,可以简化系统建模,并能提高瓦斯涌出量预测精度,有一定的实用价值。     

Qualitative-probabilistic-network-based modeling of temporal causalities and its application to feedback loop identification

Modeling and analysis of time-series data attract much attention in data mining and knowledge discovery community due to their many applications in financial analysis, automation control, etc. In such applications, time-series data usually contain several attributes that may be causally dependent in historical time slices. Dangerous feedback loops of attributes’ dependent relationships can make the system collapse due to amplification or oscillation of attribute values. Motivated by efficient analysis of causalities in time-series data, we propose a temporal qualitative probabilistic graphical model in this paper. From given time-series sample data, we construct the structure of the temporal qualitative probabilistic network (TQPN) and derive the corresponding qualitative influences on directed edges. We then present the approach for TQPN reasoning with time-series features. Consequently, positive time-series feedback loops are defined, and the approach to identify them is proposed. Preliminary experiments show that our proposed method is not only feasible but also efficient.     

A simulation study of artificial neural networks for nonlinear time-series forecasting

This study presents an experimental evaluation of neural networks for nonlinear time-series forecasting. The effects of three main factors — input nodes, hidden nodes and sample size, are examined through a simulated computer experiment. Results show that neural networks are valuable tools for modeling and forecasting nonlinear time series while traditional linear methods are not as competent for this task. The number of input nodes is much more important than the number of hidden nodes in neural network model building for forecasting. Moreover, large sample is helpful to ease the overfitting problem.Scope and purposeInterest in using artificial neural networks for forecasting has led to a tremendous surge in research activities in the past decade. Yet, mixed results are often reported in the literature and the effect of key modeling factors on performance has not been thoroughly examined. The lack of systematic approaches to neural network model building is probably the primary cause of inconsistencies in reported findings. In this paper, we present a systematic investigation of the application of neural networks for nonlinear time-series analysis and forecasting. The purpose is to have a detailed examination of the effects of certain important neural network modeling factors on nonlinear time-series modeling and forecasting.     

HYBRID GREY RELATIONAL ARTIFICIAL NEURAL NETWORK AND AUTO REGRESSIVE INTEGRATED MOVING AVERAGE MODEL FOR FORECASTING TIME-SERIES DATA

The aim of this study is to develop a new hybrid model by combining a linear and nonlinear model for forecasting time-series data. The proposed model (GRANN_ARIMA) integrates nonlinear grey relational artificial neural network (GRANN) and a linear autoregressive integrated moving average (ARIMA) model by combining new features and grey relational analysis to select the appropriate inputs and hybridization succession. To validate the performance of the proposed model, small and large scale data sets are used. The forecasting performance is compared with several models, and these include: individual models (ARIMA, multiple regression, GRANN), several hybrid models (MARMA, MR_ANN, ARIMA_ANN), and an artificial neural network (ANN) trained using a Levenberg Marquardt algorithm. The experiments have shown that the proposed model has outperformed other models with 99.5% forecasting accuracy for small-scale data and 99.84% for large-scale data. The obtained empirical results have proven that the GRANN_ARIMA model can provide a better alternative for time-series forecasting due to its promising performance and capability in handling time-series data for both small- and large-scale data.     

粒子群算法优化BP神经网络的粉尘浓度预测

对综采工作面粉尘浓度预测的方法是建立BP神经网络预测模型.为了提高算法的拟合能力及预测的准确度,使用粒子群算法对目标函数进行改进,即将粒子群算法寻到的最优权值和阈值应用于神经网络预测模型求综采工作面粉尘浓度.比较分析新的预测模型与常用的灰色模型以及标准的BP神经网络算法,结果表明粒子群优化的神经网络算法的拟合能力和预测的准确率显著提高.     

基于先验知识的小样本刑期预测算法研究

在传统司法领域,刑期判决不可避免地会受到法官主观判断的影响,从而使得在相似案情的情况下判决结果有所不同,甚至极端情况会出现矛盾,即量刑偏差问题.通过大量样本应用神经网络进行刑期预测在一定程度上可以改善量刑偏差的问题,但是由于量刑偏差对数据集质量的影响,从而使得直接使用神经网络进行刑期预测的效果不佳.为减少训练神经网络所...     

时序神经网络算法的短期风速预测研究

采用神经网络对风速进行短期预测,研究BP型短期风速预测网络中BP算法、BP网络构建以及网络训练方法.结合时间序列法和神经网络法提出了时序神经网络预测方法,对短期风速预测网络中输入变量数量和隐舍层节点数量的选择方法进行了探讨.仿真实验结果表明,时序神经网络法建立的网络,训练时间明显缩短,网络输出的预测值与真实的观察值之间...