The forecast of grain production is not only an important resource for establishing agriculture policy but also is of great significance to ensure our nation's food security based on studying the change rule of our country grain production system. In view of the fact that the complexity and incomplete information of grain production system, the primary factors influencing the grain production is decided on the basis of the grey ralational analysis of the grain producing system, then, the grey ralational analysis and support vector machine model is established by the principle of the Support vection machine regression.The result is given that the forecasting model is effective and offers a newmethod to forecast the grain production.

Application of the Grey Relational Analysis and Support Vector Machine

The forecast of production is an important resource for establishing policy. Aimed at the character of the agriculture system, the least squares support vector machine prediction model is given based on the principle of the statistical learning theory and structural risk minimization from the Service-Oriented Architecture. The result is given that the forecasting model is effective and offers a new method to forecast the grain production.

A Service-Oriented Modeling of Production Forecasting

This paper proposes a new method: GRA-SVM model which is composed of GRA and SVM to predict grain production through annual production data. In view of the fact that the complexity and incomplete information of grain production system, the primary factors influencing the grain production is decided on the basis of the grey ralational analysis of the grain producing system, then, the grey ralational analysis and support vector machine model is established by the principle of the support vection machine regression. The application case proved that the proposed method can improve the feasibility of the program in grain production, and it is suitable for on-line grain production control for food system.

Application of the GRA and SVM for Forecast of China Grain Production

The financial pre-warning is an important resource for establish financial policy. Aimed at the character of the power industry, the least squares support vector machine prediction model is given based on the principle of the statistical learning theory and structural risk minimization. The result is given that the forecasting model is effective and offers a new method to forecast the financial risk.

Early Warning of the Financial Risk on the Power Industry

Security detections for networked manufacturing can improve availability of security configuration and also lower life cycle cost. But the threat level should be classified scientifically before a safety decision could be given. In this paper, a new machine learning method suitable for small-sample pattern recognition, called least squares support vector machine, is studied, and the optimization method for selecting the parameters of least squares support vector machines is presented. Then we built a security detection multi-class classifier for networked manufacturing and tested the model by classifying new security detections. The simulation results show that this method is efficient and feasible.

Jiao Hejun

Papers

Research of Security Detection for Networked Manufacturing Based on Optimized Support Vector Machine