中文摘要：

为提高最小二乘支持向量机的预测精度,拓展其应用范围,采用改进后的粒子群优化算法对最小二乘支持向量机进行参数寻优,并应用于芦岭煤矿煤与瓦斯突出危险性类型预测。结果表明优化后的模型比神经网络预测的结果精度高,总体效果良好。

英文摘要：

To improve the precision of prediction of least squares support vector machine （LS-SVM）, experiment predicts classes of coal and gas outburst in Luling coal mine applying improved PSO to optimize parameters in LS-SVM. Experimental result manifest that prediction accuracy of this model is better than BP neural network and has a great overall effect.