Search

To have simple and efficient confidence machine learning is an important focus in confidence machine researches. Using one class classifier as a tool, the paper applies it twice for two-class classification problems. Setting reject options and a multi-layer ensemble learning method are used in this study. In this method there is no necessity to set up a specific threshold and the confidence computation is omitted. Realizing five experiments, the study proves it as efficient.

Thunderstorm is one of the worst natural disasters around the world. Currently, it still lacks of the model that can forecast the high-resolution and short-term approaching thunderstorms. Rough set method can analyze different incomplete information effectively, and then do the effective reasoning. Rough set based two techniques of attribute reduction and rule extraction were used to choose reasonable combination of forecasting factors and extract the effective decision rules, and a forecast solution model was established for the high-resolution(forecast range: 5km×5km) and the short-term (next 3 hours) thunderstorm forecast. Finally, the proposed model was tested on the given real dataset, and compared with the traditional numerical forecast solution model. The results show that it is a better in the accuracy of thunderstorm forecasting.

A system to classify rock mass is described. The knowledge of experts is divided into two parts: the knowledge about the classification according to main parameters, and the knowledge about the evaluation of those parameters. The principle of classification is based on the fuzzy set theory. A scheme that calculates two agendas, or structure sets, plays an important role in the control strategy. This scheme provides a way to parallel a problem-solving method of human experts and raises efficiency. >