长短时记忆神经网络模型在空气污染预测中的研究

基于K均值(K-Means)聚类算法进行聚类分析,将气象条件分为三类,并且分析和阐述各类气象条件的特征.针对气象监测数据和空气污染物的时间序列特点,设计基于长短时记忆(LSTM)神经网络的空气污染预测模型.将时空相关性与长短时记忆神经网络算法进行有效的融合,提出基于时空相关性的长短时记忆(SK-LSTM)神经网络的空气污染预测模型.通过空间划分,空间聚集以及空间插值,获得目标区域和周围区域的历史空气质量检测数据和历史气象监测数据,然后通过等权融合方法将时间数据和空间数据进行融合,并将其作为SK-LSTM神经网络算法的输入,最终输出的结果为带有区域协调的污染物浓度预测值.该算法能有效对空气中污染物的浓度进行更准确、高效的预测.最后通过数值仿真验证所提算法的有效性.     

模糊神经网络在多源数据融合中的应用研究

在T-S模糊神经网络数据融合的基础上,改进了标准T-S模糊融合算法中的模糊算子,并利用聚类算法对网络结构中模糊隶属度个数进行选取.通过仿真实验,验证了改进的算法在融合过程中的合理性、稳定性和准确性.以及聚类算法在T-S模糊神经网络数据融合算法中运用的合理性和有效性.     

基于EMD-GRU的高速公路行程时间组合预测模型

考虑到高速公路行程时间影响因素繁多且行程时间序列非线性、非平稳特征显著,设计了基于经验模态分解和GRU神经网络的高速公路行程时间组合预测模型.首先,利用高速公路收费数据中车辆进出高速公路的时间信息获取路段行程时间序列;然后,利用经验模态分解算法,将复杂的行程时间序列分解为若干时间尺度不同、相对平稳的本征模态函数分量和残...     

多模型加权融合机制的石墨纯度识别

针对人工识别的效率低及单一卷积神经网络提取特征的遗漏问题,提出了多模型加权融合机制的石墨纯度识别算法.在自建小样本数据集上,进行离线扩充和在线增强,提高模型的泛化能力,减少深层CNN的过拟合问题;结合迁移学习,利用优化的AlexNet和ResNet50构建双通道卷积神经网络,提取石墨图像的深层次特征,并将两者的特征进行...     

BP-GA混合优化策略在人力资源战略规划中的应用

采用混合优化策略训练神经网络,进而实现地区人力资源数据的时间序列预测.神经网络,尤其是应用反向传播(back propagation,简称BP)算法训练的神经网络,被广泛应用于预测中.但是BP神经网络训练速度慢、容易陷入局部极值.遗传算法(genetic algorithm,简称GA)具有很好的全局寻优性.因而提出将BP和GA结合起来的混合优化策略训练神经网络,来实现人力资源数据预测.与BP算法相比,数值计算结果表明预测精度高、速度快,为地区人力资源数据的时间序列预测研究提供了一条新的途径.     

基于多特征与卷积神经网络的SAR图像分类方法

针对合成孔径雷达图像的分类优化方法,提出一种基于多特征与卷积神经网络的SAR图像分类方法Canny-WTD-CNN.将Canny算子提取的边缘特征,与小波阈值去噪法提取的小波特征进行自适应融合,作为卷积神经网络的输入;以softmax为分类器,对SAR图像进行分类识别检测.最后利用MSTAR公开数据集的三类目标数据进行试验,并给出该方法与其他方法结果的对比,表明该方法的有效性,识别率达到99.14%.     

基于EEMD-Elman-Adaboost的中美股票价格预测研究

针对股票价格序列高度非正态、非线性、非平稳等复杂特征,文章以Elman神经网络为基础,引入集合经验模态分解(EEMD)与Adaboost算法,对中美股票的日收盘价进行预测。首先,利用EEMD算法将样本分解为多个本征模函数分量和1个残差分量。其次,用Adaboost算法优化Elman神经网络,对各个分量进行预测。最后,将各分量预测结果进行求和,作为最终预测结果。研究结果表明：EEMD-Elman-Adaboost模型对中美股票价格预测的均方根误差、平均相对误差、平均绝对误差均比现有的BP、Elman、EMD-Elman、EEMD-Elman模型小,新组合模型融合了EEMD、Elman神经网络、Adaboost算法的优点,具有更强的泛化能力和跟随能力。     

基于视网膜大细胞通路计算模型和深度学习的无人机目标检测

在复杂背景下的小型无人机红外目标检测是计算机视觉领域的挑战性课题.传统目标检测算法利用深度卷积神经网络提取无人机的静态外观特征并进行模式判别,但在复杂背景下且目标外观不清晰时的性能会显著下降.本文借鉴生物视网膜机制,通过视网膜大细胞通路模型提取无人机目标的时空运动信息,同时借助深度卷积神经网络获得基于静态表观特征的目标置信度图,进而将视网膜时空运动信息与深度卷积网络的目标置信度图进行融合获得目标检测结果.在Anti-UAV2020公开数据集上的评估结果表明,所提出算法的检测精确率达到86.90%,超过了业内主流的YOLO-v3算法.     

基于ICA的时间序列聚类方法及其股票数据分析中的应用

时间序列聚类分析是时间序列数据挖掘中的重要任务之一,通常由于时间序列数据的特殊结构,导致一般的聚类算法不能直接应用于时间序列数据.本文提出了一种基于独立成分分析与改进K-均值算法相结合的时间序列聚类算法,该算法首先利用独立成分分析对时间序列数据进行特征提取,然后利用改进K-均值聚类算法完成对时间序列特征数据的聚类分析,从而得到了一种新的基于特征的时间序列聚类方法.为了验证该方法的有效性和可行性,将其应用于实际的股票时间序列数据聚类分析中,取得了较好的数值结果.     

基于ICA的时间序列聚类方法及其在股票数据分析中的应用

时间序列聚类分析是时间序列数据挖掘中的重要任务之一，通常由于时间序列数据的特殊结构，导致一般的聚类算法不能直接应用于时间序列数据。本文提出了一种基于独立成分分析与改进^一均值算法相结合的时间序列聚类算法，该算法首先利用独立成分分析对时间序列数据进行特征提取，然后利用改进￡．均值聚类算法完成对时间序列特征数据的聚类分析，从而得到了一种新的基于特征的时间序列聚类方法。为了验证该方法的有效性和可行性，将其应用于实际的股票时间序列数据聚类分析中，取得了较好的数值结果。     

A self-organising model for the travelling salesman problem

This work describes a new algorithm, based on a self-organising neural network approach, to solve the Travelling Salesman Problem (TSP). Firstly, various features of the available adaptive neural network algorithms for TSP are reviewed and a new algorithm is proposed. In order to investigate the performance of the algorithms, a comprehensive empirical study has been provided. The simulations, which are conducted on a series of standard data, evaluate the overall performance of this approach by comparing the results with the best known or the optimal solutions of the problems. The proposed algorithm shows significant advances in both the quality of the solution and computational effort for most of the experimental data. The deviation from the optimal solution of this algorithm was, in the worst case, around 2%. This fact indicates that the self-organising neural network may be regarded as a promising heuristic approach for optimisation problems.     

基于组合神经网络的时间分数阶扩散方程计算方法

该文首次采用一种组合神经网络的方法，求解了一维时间分数阶扩散方程.组合神经网络是由径向基函数（RBF）神经网络与幂激励前向神经网络相结合所构造出的一种新型网络结构.首先，利用该网络结构构造出符合时间分数阶扩散方程条件的数值求解格式，同时设置误差函数，使原问题转化为求解误差函数极小值问题；然后，结合神经网络模型中的梯度下降学习算法进行循环迭代，从而获得神经网络的最优权值以及各项最优参数，最终得到问题的数值解.数值算例验证了该方法的可行性、有效性和数值精度.该文工作为时间分数阶扩散方程的求解开辟了一条新的途径.     

Forecasting and recombining time-series components by using neural networks

Operations and other business decisions often depend on accurate time-series forecasts. These time series usually consist of trend-cycle, seasonal, and irregular components. Existing methodologies attempt to first identify and then extrapolate these components to produce forecasts. The proposed process partners this decomposition procedure with neural network methodologies to combine the strengths of economics, statistics, and machine learning research. Stacked generalization first uses transformations and decomposition to pre-process a time series. Then a time-delay neural network receives the resulting components as inputs. The outputs of this neural network are then input to a backpropagation algorithm that synthesizes the processed components into a single forecast. Genetic algorithms guide the architecture selection for both the time-delay and backpropagation neural networks. The empirical examples used in this study reveal that the combination of transformation, feature extraction, and neural networks through stacked generalization gives more accurate forecasts than classical decomposition or ARIMA models.?Scope and Purpose.?The research reported in this paper examines two concurrent issues. The first evaluates the performance of neural networks in forecasting time series. The second assesses the use of stacked generalization as a way of refining this process. The methodology is applied to four economic and business time series. Those studying time series and neural networks, particularly in terms of combining tools from the statistical community with neural network technology, will find this paper relevant.     

On the construction of a nonlinear recursive predictor

In this paper, we present a novel approach for constructing a nonlinear recursive predictor. Given a limited time series data set, our goal is to develop a predictor that is capable of providing reliable long-term forecasting. The approach is based on the use of an artificial neural network and we propose a combination of network architecture, training algorithm, and special procedures for scaling and initializing the weight coefficients. For time series arising from nonlinear dynamical systems, the power of the proposed predictor has been successfully demonstrated by testing on data sets obtained from numerical simulations and actual experiments.     

基于遗传算法和半参数回归的神经网络集成股市预测研究

股票时间序列预测在经济和管理领域具有重要的应用前景,也是很多商业和金融机构成功的基础.首先利用奇异谱分析对股市时间序列重构,降低噪声并提取趋势序列.再利用C-C算法确定股市时间序列的嵌入维数和延迟阶数,对股市时间序列进行相空间重构,生成神经网络的学习矩阵.进一步利用Boosting技术和不同的神经网络模型,生成神经网络集成个体.最后采用带有惩罚项的半参数回归模型进行集成,并利用遗传算法选择最优的光滑参数,以此建立遗传算法和半参数回归的神经网络集成股市预测模型.通过上证指数开盘价进行实例分析,与传统的时间序列分析和其他集成方法对比,发现该方法能获得更准确的预测结果.计算结果表明该方法能充分反映股票价格时间序列趋势,为金融时间序列预测提供一个有效方法.     

Time series forecasting with neural network ensembles: an application for exchange rate prediction

This paper investigates the use of neural network combining methods to improve time series forecasting performance of the traditional single keep-the-best (KTB) model. The ensemble methods are applied to the difficult problem of exchange rate forecasting. Two general approaches to combining neural networks are proposed and examined in predicting the exchange rate between the British pound and US dollar. Specifically, we propose to use systematic and serial partitioning methods to build neural network ensembles for time series forecasting. It is found that the basic ensemble approach created with non-varying network architectures trained using different initial random weights is not effective in improving the accuracy of prediction while ensemble models consisting of different neural network structures can consistently outperform predictions of the single ‘best’ network. Results also show that neural ensembles based on different partitions of the data are more effective than those developed with the full training data in out-of-sample forecasting. Moreover, reducing correlation among forecasts made by the ensemble members by utilizing data partitioning techniques is the key to success for the neural ensemble models. Although our ensemble methods show considerable advantages over the traditional KTB approach, they do not have significant improvement compared to the widely used random walk model in exchange rate forecasting.     

Neural network for the exact RLS adaptive algorithm

This paper proposes a neural network approach to the implementation of the exact recursive least-squares (RLS) algorithm. We show that the proposed neural network is guaranteed to be stable and to provide the results arbitrarily close to the accurate optimal solution of the RLS algorithm within an elapsed time of only a few characteristic time constants of the network. The parameters of the network (such as interconnections strengths and bias currents) can be obtained from the available data with a few computations, which are much fewer than the computations required in the exact RLS algorithm; as a result, this proposed scheme is very suitable for real time applications of the exact RLS algorithm.     

Neural network method for determining embedding dimension of a time series

A method is described for determining the optimal short-term prediction time-delay embedding dimension for a scalar time series by training an artificial neural network on the data and then determining the sensitivity of the output of the network to each time lag averaged over the data set. As a byproduct, the method identifies any intermediate time lags that do not influence the dynamics, thus permitting a possible further reduction in the required embedding dimension. The method is tested on four sample data sets and compares favorably with more conventional methods including false nearest neighbors and the ‘plateau dimension’ determined by saturation of the estimated correlation dimension. The proposed method is especially advantageous when the data set is small or contaminated by noise. The trained network could be used for noise reduction, forecasting, and estimating the dynamical and geometrical properties of the system that produced the data, such as the Lyapunov exponent, entropy, and attractor dimension.     

A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm

Sales forecasting is highly complex due to the influence of internal and external environments. However, reliable prediction of sales can improve the quality of business strategy. Recently, artificial neural networks (ANNs) have been applied for sales forecasting due to their promising performance in the areas of control and pattern recognition. However, further improvement is still necessary since unique circumstances such as promotion can cause sudden changes in sales patterns. Thus, the present study utilizes the proposed fuzzy neural network with initial weights generated by genetic algorithm (GFNN) for the sake of learning fuzzy IF–THEN rules for promotion obtained from marketing experts. The result from GFNN is further integrated with an ANN forecast using the time series data and the promotion length from another ANN. Model evaluation results for a convenience store (CVS) company indicate that the proposed system can perform more accurately than the conventional statistical method and a single ANN.