金融风险预警的RST-FNN模型研究

将粗糙集理论（RST）与模糊神经网络（FNN）相结合,提出了一种基于粗糙集理论的模糊神经网络（RST-FNN）模型。新模型利用粗糙集的知识约简对样本数据去噪消冗,提取最优规则,从而克服模糊神经网络的“维数爆炸”灾难。实例仿真的结果表明,该模型的预测准确性较高,且具有结构精简、收敛速度快及泛化能力强等特点。     

基于模块化模糊子系统的分层模糊神经网络

提出一种基于模块化模糊子系统的分层模糊神经网络，该分层模糊神经网络基于高斯隶属函数，且功能上等价于一个TSK模糊系统，这种分层神经网络在保留了传统模糊神经网络很多优点的同时有效地抑制了“维数灾”问题,而且在模糊子系统中模糊规则的激活强度有所提高，仿真试验结果表明。该方法能获得更为简洁有效的模糊规则集。     

基于距离比值尺度的模糊粗糙集属性约简

属性约简能有效地去除不必要属性,提高分类器的性能。模糊粗糙集是处理不确定信息的重要范式,能有效地应用于属性约简。在模糊粗糙集中,样本分布的不确定性会影响对象的近似集,进而影响有效属性约简的获取。为有效地定义近似集,文中提出了基于距离比值尺度的模糊粗糙集,该模型引入了基于距离比值尺度的样本集的定义,通过对距离比值尺度的控制,避免了样本分布不确定性对近似集的影响;给出了该模型的基本性质,定义了新的依赖度函数,进而设计了属性约简算法;以SVM,NaiveBayes和J48作为测试分类器,在UCI数据集上评测所提算法的性能。实验结果表明,所提出的属性约简算法能够有效获取约简并提高分类的精度。     

基于人工智能技术的不完备信息系统智能诊断方法研究

为了提高不完备信息系统故障诊断的正确性与效率,本文提出一种基于粗糙集理论、蚁群优化算法和RBF神经网络相结合的故障智能诊断方法。该方法首先利用“条件组合补齐算法”对不完备的数据进行完备化处理,再利用粗糙集对条件属性进行知识约简,得到具有最大完备度的最小规则集,接着用蚁群算法优化RBF神经网络的权值,并将最小规则集用于训练RBF神经网络模型,获得故障智能诊断模型。通过实际工程数据验证故障智能诊断模型的有效性,结果表明提出的方法能有效实现系统故障的诊断。     

结合粗集和神经网络的图像识别模型

通过对粗集和神经网络在图像识别中的作用分析,以及对两者结合的可能性研究,将粗集和神经网络进行了有机结合,提出了一个基于粗集和神经网络的图像识别模型。该模型先对原始图像数据进行预处理,然后用粗集进行特征选择,减少了神经网络的输入维数,提高神经网络学习和识别速度,也提高了识别正确率。最后将该模型应用于手写体数字图像识别之中,实验结果表明,该模型是有效的、可行的。     

模糊粗糙集在音频检索中的应用

音频具有数据量大、维数高等特点,直接进行音频检索会造成“特征维数灾难”,因此有必要从音频提取最能表现音频特征的音频帧。提出一种基于模糊粗糙集模型（Fuzzy Rough Set Model,FRSM）的音频数据约简算法,根据隶属度对音频数据进行模糊离散,基于知识表达能力约简属性,以等价划分计算具有等同分类能力的知识核。实验结果表明,该算法能够得到最小约简,并且最大程度地保持音频特征,提高检索效率。     

分层模糊神经网络的轧钢产品质量建模

轧钢生产过程是极其复杂的大系统,模糊神经网络进行质量建模将不可避免地陷入维数灾。分层模糊神经网络是解决维数灾的有效手段。文中采用分层模糊神经网络对轧钢产品质量进行建模,并用预处理后的数据进行训练和校验。仿真结果表明所建质量模型能够较好地拟合建模数据,表明了该方法的有效性。     

大规模高维数据集环境下的路面使用性能评价方法研究

传统中由单一的神经网络等算法所构架起的评价模型主要存在着精度低、网络学习速度慢等不合理之处.为此,提出了基于粗糙集和RBF神经网络的大规模数据集环境下的评价方法.首先详解了粗糙集理论对大规模高维数据所确定的宽泛属性集的分类、约简;然后把处理后的数据指标作为RBF神经网络的输入进行训练、仿真.以高速公路路面性能使用评价为...     

基于文本挖掘的上市公司财务风险预警研究

上市公司年报中的描述性文本信息是上市公司信息披露的重要组成部分,通过对上市公司信息披露文本的挖掘与分析可以提高对其财务风险的预测能力。基于BERT（bidirectional encoder representations from transformer）模型与自编码器（autoencoder,AE）,提出了BERT-AE融合文本特征提取模型,提取A股市场531家上市公司年报中“经营情况讨论与分析”和“审计报告”的文本特征,构建能够反映财务困境公司与正常公司的文本特征指标,随后将文本特征指标与财务指标数据结合,分别使用Logistic回归、极端梯度提升（extreme gradient boosting,XGBoost）、人工神经网络（artificial neural networks,ANN）、卷积神经网络（convolutional neural networks,CNN）四种模型,检验加入文本特征指标后财务风险预测的准确性是否得到提高,并使用Word2Vec-CNN-AE、Word2Vec-LSTM-AE模型提取财务文本特征进行对比实验。结果表明,三种模型提取的财务文本特征均能使财务预警模型预测的AUC得到提升,且BERT-AE模型提取的财务文本特征使得四种财务预警模型预测的AUC值提升效果更为显著,表明BERT-AE模型有效地提取了财务文本特征,提高了上市公司财务风险预警模型的预测能力。     

一个新的模糊聚类有效性指标

提出一个新的模糊聚类有效性指标。该指标能确定由模糊C-均值算法(FCM)所得模糊划分的最优划分和最优聚类数,结合了模糊聚类的紧致性和分离性信息,用类内加权平方误差和计算紧致性,用类间相似度计算分离性。在3个人造数据集和3个真实数据集上进行对比实验,结果证明该指标的性能优于其他有效性指标。     

Early warning of enterprise decline in a life cycle using neural networks and rough set theory

Early warning of whether an enterprise will fall into decline stage in a near future is a new problem aroused by the enterprise life cycle theory and financial risk management. This paper presents an approach by use of back propagation neural networks and rough set theory in order to give an early warning whether enterprises will fall into a decline stage. Through attribute reduction by rough set, the influence of noise data and redundant data are eliminated when training the networks. Our models obtained favorable accuracy, especially in predicting whether enterprises will fall into decline or not.     

A nature inspired Ying–Yang approach for intelligent decision support in bank solvency analysis

Since the collapse or failure of a bank could trigger an adverse financial repercussion and generate negative impacts, it is desirable to have an early warning system (EWS) that identifies potential bank failures or high-risk banks through the traits of financial distress. This research is aimed to construct a novel fuzzy neural CMAC as an alternative to analyze bank solvency, in which a nature inspiration motivated from the famous Chinese ancient Ying–Yang philosophy is introduced to find the optimal fuzzy sets, and truth value restriction (TVR) inference scheme is employed to derive the truth-values of the rule weights. The proposed model functions as an early warning system and is able to identify the inherent traits of financial distress based on financial covariates (features) derived from publicly available financial statements. Our experiments are conducted on a benchmark dataset of a population of 3635 US banks observed over a 21 years period. Three sets of experiments are performed – bank failure classification based on the last available financial record and prediction using financial records one and two years prior to the last available financial statements. The performance of the proposed Ying–Yang FCMAC network as a bank failure classification and early warning system is very encouraging.     

Analysis of early warning of corporate financial risk via deep learning artificial neural network

To forecast the financial crisis of manufacturing corporations more accurately, a risk warning model of corporate finance is constructed based on back propagation (BP) neural network to forecast the financial crisis. Firstly, based on the principle of index selection, the forecast indexes are selected and the index system of financial risk early warning is constructed. Then the index system is optimized by factor analysis. Finally, the BP neural network algorithm model is adopted to forecast the financial crisis of 200 manufacturing corporations in 2018 and 2019, and the forecasting results are compared with the traditional method. The results show that the prediction accuracy of the enterprise financial risk early warning model based on the BP neural network for 2018 is above 85%, and the prediction accuracy for 2019 is above 95%, or even 100%. Through comparison with other traditional methods, the prediction accuracy of the BP neural network in 2018 (above 88%) is higher than that of other algorithms (below 87%). In 2019, the prediction accuracy of BP neural network (above 90%) is higher than other algorithms (less than 88%). The accuracy of the proposed financial risk warning model is 95%, and the accuracy is at least 2% higher than traditional method, which prove that the risk early warning model constructed in this study can accurately forecast the financial crisis of the corporation. This study is of important reference value for the establishment of efficient financial crisis forecasting model under deep learning.     

金融风险预警的MPSO-FNN模型构建与应用

提出了一种改进型粒子群算法,并结合神经网络与模糊逻辑系统建立金融风险预警模型。将模型应用于信贷风险预警研究,仿真实例的结果表明,该模型所获得的预测准确性更高,是处理金融风险这类复杂经济系统预警问题的一种有效方法。     

Prediction of service life of large centrifugal compressor remanufactured impeller based on clustering rough set and fuzzy Bandelet neural network

In order to predict the service life of large centrifugal compressor impeller correctly, the rough set and fuzzy Bandelet neural network are combined to construct the novel prediction model which can give full play to theirs advantages. The attribute reduction algorithm based rough set and clustering method is firstly designed to optimize the inputting variables of fuzzy Bandelet neural network. And then the prediction model based on fuzzy Bandelet neural network is proposed, the Bandelet function is used as the excitation function of hidden layer and is combined with fuzzy theory to improve the prediction effectiveness of the prediction model. The training algorithm of fuzzy Bandelet neural network is designed based on improved genetic algorithm, the improved genetic algorithm introduces the adaptive differential evolution method into the traditional genetic algorithm, which can effectively optimize the parameters of fuzzy Bandelet neural network. Finally, the original 30 input variables of fuzzy Bandelet neural network are reduced to 9 input nodes based on rough set using 500 remanufacturing impellers as research objects. The service life of remanufacturing impeller is predicted based on three prediction models, and simulation results show that the fuzzy Bandelet neural network optimized by improved genetic algorithm has highest prediction precision and efficiency, which can correctly predict the service life of remanufacturing impeller.     

基于粗-模糊神经网络的决策控制

通过将模糊集和粗集,神经网络结合,提出了一种基于模糊规则的新的粗模糊神经网络,它通过利用误差反向传播算法实时修正该新型网络中的权值参数,从而能被有效地应用于不确定系统的决策分类与模式识别问题.最后通过对一个不确定决策系统的模式识别的仿真结果表明该粗模糊神经网络能大大提高模式识别决策的准确率.     

Financial time-series analysis with rough sets

We investigate the use of the rough set model for financial time-series data analysis and forecasting. The rough set model is an emerging technique for dealing with vagueness and uncertainty in data. It has many advantages over other techniques, such as fuzzy sets and neural networks, including attribute reduction and variable partitioning of data. These characteristics can be very useful for improving the quality of results from data analysis. We demonstrate a rough set data analysis model for the discovery of decision rules from time series data for example, the New Zealand stock exchanges. Rules are generated through reducts and can be used for future prediction. A unique ranking system for the decision rules based both on strength of the rule and stability of the rule is used in this study. The ranking system gives the user confidence regarding their market decisions. Our experiment results indicate that the forecasting of future stock index values using rough sets obtains decision ruleswith high accuracy and coverage.