基于IAO优化HKELM的空气质量指数预测

Air quality index prediction based on IAO optimized HKELM

为了精准预测空气质量指数(AQI),本文提出一种基于改进天鹰优化器(IAO)混合核极限学习机(HKELM)的空气质量指数预测模型(IAO-HKELM)。首先,利用径向基核函数和多项式核函数构造混合核极限学习机模型;其次,针对天鹰优化器(AO)算法易陷入局部极值的问题,引入改进的Tent混沌初始化策略和自适应t分布策略;采用改进后的AO算法对HKELM模型的参数进行优化,并建立IAO-HKELM空气质量指数预测模型;最后,将预测模型应用于实际案例中,并与其他模型的预测结果及误差进行对比。结果表明,本文提出的预测模型精度更高、稳定性更强。

In order to accurately predict the air quality index(AQI),this paper proposes an air quality index prediction model(IAO-HKELM)based on the Improved Aquila Optimizer(IAO)Hybrid Kernel Extreme Learning Machine(HKELM).Firstly,a hybrid kernel extreme learning machine model is constructed using radial basis kernel function and polynomial kernel function.Secondly,in view of the problem that the Aquila Optimizer(AO)algorithm is easy to fall into the local extreme value,an improved Tent chaotic initialization strategy and an adaptive t distribution strategy are introduced.Then the improved AO algorithm is used to optimize the parameters of the HKELM model and establish the IAO-HKELM air quality index prediction model.The prediction model is applied to a practical case,and the prediction results and errors of other models are compared.The results show that the prediction model proposed in this paper has higher accuracy and stronger stability.