Design on Contingency Classifier of Functioned Link Neural Network

Contingency analysis is thekey computational issue in power system steady state security analysis and reliability calculations. This task requires a large amount of CPU time. In order to reduce effectively requirements of computationin outagesimulation ofbulk power system,a functioned link neural network (FLNN) classified model and algorithm employed to identify contingencies is presented. For the sake of gaining post-accident information of system states, a group of performance index (PI) is designed according to the performance characters relative to the changes of base case.Moreover, a neural network classifieris constructed. A varietyof the effects of PI and combinations of PI on the proposed classifieris discussed. That branch flow performance indices are better than the others is explanted. The resultsof classification by applied the FLNNclassifierto the IEEE-RTS24 show that it not only make network and algorithmsimpler, but also improvethe speed and accurate of contingency analysis.     

Application of modified Deep Belief Network in Forecasting Cotton Diseases and Insect Pests

[Objective] The occurrence and development of cotton diseases and insect pests are mainly related to environmental information. Because this environmental information is various, complex and unstable, the study on the prediction methods of cotton diseases and insect pests is a certain challenge. This study aims to establish a forecasting model for the timely and accurate prediction of cotton diseases and insect pests. [Method] A forecasting model of cotton diseases and insect pests is proposed based on environmental information and a modified Deep Belief Network (DBN) that is constructed by a three-layer restricted Boltzmann machine (RBM) and a supervised back-propagation (BP) network. In the method, the RBM is used to transform the original environmental information vectors into a new feature space related to the diseases and pests; the BP network is trained to classify and forecast the features generated by the last RBM layer and two rules of dynamic learning and comparison and dispersion are adopted to accelerate the training process of RBM. The proposed model was validated on a dataset of cotton bollworm, aphids, spider, cotton Verticillium wilt, and Fusarium wilt in a recent six-year period. [Result] Compared with the traditional prediction models of cotton diseases and insect pests, the proposed model can deeply explore the extensive correlation between the occurrence of cotton diseases and pests and environmental information. The results show that the proposed model has a higher accuracy compared with the classical predictive models, and the average forecasting accuracy is above 83%. [Conclusion] The proposed method is an effective crop disease and pest forecasting method that can provide a technical support for preventing cotton disease and insect pests.     

Algorithm to Transform Dynamic Causality Diagram Into Belief Network

The Dynamic Causality Diagram methodology is a new probabilistic reasoning model based on Belief Network. To some extent, it is similar to the Belief Network in structure. So that knowledge from one can be transformed into the other on some conditions. To begin with, this paper discusses the similarities and differences between them, and finally presents a transformation algorithm from Dynamic Causality Diagram into Belief Network. The algorithm is composed of two parts: a mapping algorithm of structure and a generating algorithm of conditional probability tables.     

Intrusion Detection Based on Adaptive Immune Classifier

The distribution properties of the normally data and anomaly data in the network connectivity features have huge differences ; therefore, there exist the low rate of detection and false positive rate problem for the traditional classifier which is applied to the network intrusion detection. An adaptive classifier based on the artificial immune cluster is presented. The new classifier adopts multi -granularities idea and it effectively eliminates the inconsistency between the classification algorithm and the clustering algorithm. Through the classification of the data sets in real variety of network intrusion data sets, experimental results show that the classifier has high detection rate and low false positive rate; it has better classification performance and generalization ability than RBF and BP classifiers.     

基于支持向量机的蘑菇毒性判别研究

毒蘑菇和可食用蘑菇在外表上非常相似,依靠传统方法难以判别。为了实现判别上的自动化和增强可靠性,提出了一种基于支持向量机的蘑菇毒性判别方法。首先给出了数据样本和数据预处理的方法,其次建立C-SVM模型并进行训练,同时依照一对一方法实现了支持向量机的多分类,最后使用定步长探索法获得了模型的最优参数。仿真实验对比分析了不同样本量,不同参数下所提方法的准确度,验证了该方法在蘑菇毒性判别上的可行性。同时,使用神经网络、决策树方法进行分类器间的性能对比,发现与神经网络、决策树的判别结果相比,所提方法具有准确率高、操作方便、实用性强等优点。     

Markov Logic Networks with its application in De duplication

In order to solve the limitation that the traditional De duplications are mostly used for a specific field and only address one aspect of a problem,a scheme based on Markov Logic Networks (MLNs)is proposed, which is a new Statistical Relational Learning (SRL) model. With its advantage of computing the probability distribution of worlds to serve for the inference, the De duplication is formalized. Discriminative learning algorithm is adopted for Markov Logic Networks weights, MC SAT algorithm is adopted for inference. It shows how to capture the essential features of different aspects in De duplication with a small number of predicate rules and also combines these rules together to compose all kinds of model. The experiment results prove that the method based on Markov Logic Networks not only covers the original Fellegi Sunter model, but also achieves a better result than the traditional methods based on Clustering Algorithms and Similarity Measures in De duplication. It reveals that the Markov Logic Networks can play an important part in practical application.     

Learning the BN Structure Based on the Sum of Mutual Information

The Crossing Entropy is defined to scale the similar level of two probability distribution. In many papers on learning BN structure,the Crossing Entropy was used as an indicator of measuring the learning accuracy of an algorithm.The known scoring metrics for learning BN structure is analyzed in this paper,then a new scoring metrics Sum of Mutual Information is proposed based on the information theory.At last,two algorithm for learning BN structure by SIM is represented.     

农村基督教信仰热现象探析与社会工作干预

为使社会公众对于农村基督教信仰热现象有一种理性的认识,引导基督教与社会主义社会协调发展,利用文献分析的方法,就农村基督教信仰热的现象从社会、个人、基督教的吸引力等3方面探讨了其产生的原因和对农村社会发展带来的复杂影响,针对其负面影响从社会工作干预的视角提出了若干相应对策,如提高农民综合素质,促进社会保障制度的有效实施,端正信徒对于基督教的认识等。最后介绍了世界其他国家的基督教信仰情况对中国的借鉴与指导意义。     

Multi stage Classifier for Unconstrained Handwritten Numerals Recognition

A multi stage character classifier model is presented. By combining four independent algorithms, we integrate on line recognition method, off line recognition method, neural network method, tradition method into an unique pattern recognition system. The results and experiments show that our system has the merit of high recognition rate.     

基于深度卷积神经网络的储粮害虫图像识别

[目的]为了防治储粮害虫带来的危害,借助计算机对储粮害虫进行有效的图像识别是具有重要意义的。[方法]针对基于图像的储粮害虫多分类识别问题,引入了基于深度卷积神经网络的储粮害虫图像识别方法。该方法与传统的储粮害虫识别方法相比,大幅度简化了数据预处理过程,[结果]同时该方法在识别精确度方面达到了97.61%,也明显优于传统方法。[结论]因此基于深度卷积神经网络的储粮害虫识别方法具有较高的实用性,且具有进一步研究和推广的意义。     

Techniques Involved in Network Management and Their Progression

Network management has become a key technique in the network area. This paper presents a comprehensive introduction about the basic ideas of network management,main techniques it involves , and developmental trend.     

Method to Predict the Coke Rate Based on BP Neural Network

Coke rate is a very important technique index in the processing of metallurgical, and it is also an important goal that should be reached and controlled in practice.The blast furnace is a countercurrent heat and mass exchange reactor involving the solid, liquid and gaseous phases. Using computer encoded mathematical and statistical methods can not get the precise result. An improved 9-9-1 BP(Back propagation) neural network was trained and used in the prediction of the coke rate. The result indicates that the BP nets can predict coke rate accurately and the error between prediction and real coke rate less than 2%. And the use of a hybrid model in actual on-line intelligence control was also discussed.     

The Neural Network Method for Searching Graph Minimal Cut Set

The new neural network algorithm for searching graph minimal cut set,called NNMC algorithm, is established on the basis of construction of Hopfield Network energy function according to the concrete problem.In NNMC algorithm, which suffciently uses the fast convergence of Hopfield Network, a way to avoid the local minimum is carried out.     

Cost Estimation of Transmission Line Based on Artificial Neural Network

Based on the structure of cost factor in transmission lines project and the characteristic of neural networks, the paper shows up using artificial neural networks to estimate the cost of project and provide a method to investigate them. By analyzing the structure of project cost and influence factor, the paper builds both input and output neural cell for cost of transmission line project. The paper builds the model of artificial neural networks and exports the steps of the algorithmic. The project sample is used in history to train and test the model. At last, the model gets satisfactory result and meets the investigation requirement of engineering budgetary estimation. Therefore, the paper provides an impersonality and quick investigation method for budgetary estimation of power projects.     

基于高光谱的水稻叶片氮含量估计的深度森林模型研究

高光谱遥感已经成为快速诊断作物水氮状态的一种有效手段。然而,传统的回归方法和机器学习往往难以挖掘高光谱的全部信息,深度神经网络又通常需要大量的训练数据,因此本研究试图探索在少量数据条件下构建深度学习模型并实现叶片氮含量的精准估计。通过在湖北省监利县开展了连续2年不同氮素胁迫水平的水稻试验,测量了作物全生育期内的216组冠层光谱和叶片氮含量。基于一阶导数光谱,本文构建了一种新的深度学习模型(深度森林DF)来进行叶片氮含量的反演,并与2种经典机器学习模型(随机森林RF和支持向量机SVM)和一种深度神经网络模型(多层感知器MLP)进行比较。结果表明,在基于少量高光谱数据的情况下,DF对水稻叶片氮含量的估算精度要高于MLP,其中预测精度最高的模型为全波段光谱反演的DF模型(R²=0.919, RMSE=0.327)。在2种经典机器学习模型中,RF的估计效果优于SVM,但2种模型结果都不够稳定。研究表明,深度森林可以提升高光谱反演叶片氮含量的精度和稳定性,并且可以通过多粒度扫描相对减轻过拟合程度。该研究结果可为少量数据条件下快速监测作物叶片氮含量提供参考。     

Discussion on Some Problems of ExpertSystem for Rock Mass Classification

On the basis of discussing present situation for classification of rock masses and necessity of building expert system of rock masses.The intelligent design software for classification of rock masses CRES has been completed. In this paper the CRES is expounded systematically in the following,such as knowledge_base,data_base,reasoning machine,learning machine,and so on.Finally,the CRES is used for verifying 30 engineering examples and is used to classify rock masses of two roadways successfully .The CRES has been connected to SBSDES.     

基于故障树和贝叶斯网络的冷链配送系统的可靠性分析

生鲜农产品在流通中存在冷链“断链”现象严重、腐损率高的问题。本文以生鲜农产品冷链物流配送系统为研究对象,通过分析冷链配送过程各环节中影响配送效率的不确定性因素,构建冷链配送系统的故障树模型,然后将其转化为贝叶斯网络,评估冷链配送系统的可靠性。本研究将概率重要度引入到冷链配送系统的可靠性分析中,揭示了影响冷链配送系统可靠性的薄弱因素,并通过算例分析,验证模型的有效性,为优化配送流程提供依据。     

Multiple Layer BP Neural Network for Fuzzy Calculating

The FCBP(Fuzzy calculating BP) algorithm which is proposed by this paper hasovercome the sensitivity for samples,reduced the number of input layer's samples,lightened the burden of input layer.it is suitable to fuzzy inference and pattern recognition.     

Incremental Learning Algorithm of Induction

The algorithm about incremental generating decision function is built by modifying the definition of discernibility matrixes. So it is programmed effectively in the computer. The discernibility matrixes is not generated because the great quantity of data is fetched one after another. The lack of memory is solved by handing data in large database. The algorithm is adapted to the dynamic data and is able to deal with dynamic learning. The time of Data Ming decreases because of information reuse. At the same time, the question of learning about multi-classes is solved in essence by using the incremental generating decision function.