论文部分内容阅读
目的建立具有很强预测能力的数学模型来准确评估人机系统操作员功能状态(Operator Function-al States,OFS)。方法基于采集到的一系列操作员电生理信号及性能数据,采用最小二乘支持向量机(Least Squares Support Vector Machine,LSSVM)方法对OFS建模。通过网格搜索和10-折交叉验证方法对模型参数进行优化,并将LSSVM与基于遗传算法的模糊建模方法进行比较。结果模型基本能反映OFS的实际变化趋势,输出误差在可接受的范围之内且与基于遗传算法的模糊建模方法得到的模型输出误差相比较小。结论 LSSVM方法具有更好的泛化性能,将其用于OFS评估是有效的。
Objective To establish a mathematical model with strong predictive power for accurate evaluation of Operator Function-al States (OFS). Methods A series of operator electrophysiological signals and performance data were collected and the OFS was modeled by Least Squares Support Vector Machine (LSSVM). The parameters of the model were optimized by grid search and 10-fold cross validation, and the LSSVM was compared with the fuzzy modeling method based on genetic algorithm. The results show that the model can basically reflect the actual trend of OFS, the output error is within the acceptable range and less than the model output error obtained by the fuzzy modeling method based on genetic algorithm. Conclusion The LSSVM method has better generalization performance, and it is effective to use it for OFS evaluation.