The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
It is completed the introduction and analysis for modeling method of glutamic acid fermentation process. Then modeling method using support vector machine is adopted, select a grid search-crossover integrated validation method to choose the parameters of the model in modeling, making the prediction model more accurate. Finally the comparison of SVM and BP networks model, simulation results show that...
Research on scalable machine learning algorithms has gained a considerable amount of traction since the exponential growth in data assets during the past decades. Many Big Data applications resort to somewhat "simple" data modelling techniques due to the computational constraints associated with more complex models. Simple models, while being very efficient to estimate, often fail to capture...
Asset quality is the foundation of enterprise survival and development we choose one-class support vector machine (OCSVM) is chosen to deal with asset quality abnormal detection for it pays great roles to acquire the abnormal data. As well as flexible to be constructed, Biorthogonal wavelet consists linear-phase nature and high vanishing moment, therefore, corresponding wavelet kernel functions are...
Hydrology time series prediction is significant. It is not only helpful to set the planning in daily configuration works of water resources, but also provides guidance for leaders to make decision, especially in some special case such as flood and seriously lack water. In order to solve the imbalance complexity of prediction model and complexity of samples and raise forecasting accuracy, combined...
In the evaluation process of Military communication network effectiveness (MCNE), the evaluation data mainly come from expert judgments, simulation results and test bed data, and these data cannot be directly used to evaluate MCNE because these three kinds of data are very different in form and in attribute. This research proposed a novel method which synthesizes expert judgments, simulation results,...
Financial forecasting is the basis for budgeting activities and estimating future financing needs. Applying machine learning and data mining models to financial forecasting is both effective and efficient. Among different kinds of machine learning models, kernel methods are well accepted since they are more robust and accurate than traditional models, such as neural networks. However, learning from...
A Project risk forecast model was investigated using least square support vector machine(LS-SVM) method. Risk estimation data of experts was acted as eigenvector of learning samples to train the constructed LS-SVM regression model for realizing mapping relationship between the risk and the characteristic. The test samples were used to compare between the constructed LS-SVM model and BP neural network...
In this research, optimized SVM models were designed to describe eutrophication processes, based on the field measured data from Bohai Bay. A new data-driven model called Support Vector Machine (SVM) based on structural risk minimization principle was presented, which minimized a bound on a generalized risk. In the eutrophication model, the Principal Component Analysis (PCA) was used to identify the...
This paper brings forward a new model based on fuzzy theory and multi-classes support vector machines to value the effect of promotion. On the one hand, the fuzzy theory is used to reduce the subjective effect of value experts. On the other hand, The multi-classes support vector machines (SVM) was used to classify the value of promotion effect accurately. The new model can not only improve the objectivity...
To establish suitable models to describe the behavior of biochemistry systems, a new modeling method was introduced, combining multiple objective ant colony optimization(MOACO) with the dynamic Epsilon-SVM. The hyper-parameters of Epsilon-SVM were automatically decided by using multiple objective ant colony optimization(MOACO). Each training sample used different error. The model for penicillin production's...
In tradition, grey System treats any random variations as a variation in the grey value within a certain range, and the random process is treated as a time-varying grey process within a certain range. Grey System successfully utilizes accumulated generation data instead of original data to build forecasting model, which makes raw data stochastic weak, or reduces noise influence to a certain extent...
Nowadays, information disclosure is a noticeable topic to both practice and academy since it has significant effect on corporate governance and capital market operation. Open and transparent information disclosure can reduce the information asymmetry between insiders and outsiders. The main purpose of this study is to construct an information transparency evaluation model. In this paper, we used the...
Making precise predictions about the future behavior of a system such as a country's economy, a firm or a lake, or about the population of some species of animal has always been a challenge. While prediction methods and modeling procedures have been developed and used over the past decades, the high degree of uncertainty and complexity that underlie some systems makes it difficult, and in some cases...
This paper presents a soft computing based heterogeneous catalysis modeling and optimization strategy, namely SVR-GA, for the discovery and optimization of dimethyl ether synthesis on new catalytic materials. In the SVR-GA approach, a support vector regression model is constructed for correlating process data comprising values of input variables of catalyst compositional, operating conditions and...
In order to detect the abnormal status of business process and reduce possible loss, it is necessary to build an outlier detect model. Based on the statistic learning and the support vector classifier theory, a new business processes' outlier detection model is proposed based on the support vector data description. Firstly, the paper discussed the concept of the business process and the abnormal running...
Credit Risk Identification in small and medium enterprises(SMEs) is a real problem which is necessary to be solved in financial sector. Focusing on 32 small and medium enterprises which had bank loan, dimension of six indicators used to judge whether enterprises had credit risk was reduced to simplify model by adopting the factor analysis method. Then small sample data was trained and simulated in...
The framework based on multi-agent (MA) is proposed for energy supply/demand prediction, facing to the drawback hard to model energy supply/demand prediction system mathematically and attractions of multi-agent methods used in a complex system. In the proposed framework an intelligent hybrid agent and a MA hierarchical infrastructure of energy supply/ demand prediction are presented. The intelligent...
Support vector machines have been extensively used in machine learning because of its efficiency and its theoretical background. This paper focuses on nu-transductive support vector machines for classification (nu-TSVC) and construct a new algorithm - Unconstrained nu-Transductive Support Vector Machines (Unu-TSVM). After researching on the special construction of primal problem in nu-TSVM, we transform...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.