Fire prediction based on online sequence extreme learning machine

In order to avoid the serious loss caused by the fire, to achieve the initial fire alarm, multi-sensor system is widely used in fire prediction. In the processing method, it is essentially different from the traditional classical signal. The multi-sensor information fusion system can be merged at different levels. It can be abstracted distributed into three levels: information fusion layer, feature fusion layer, decision fusion layer. Aiming at the problem of feature fusion layer, a method based on OS-ELM is proposed. Studies have shown that, compared with BP Neural Network and ELM, OS-ELM have a better overall performance on time and accuracy, which more suitable for use in fire prediction system.