论文部分内容阅读
河流水质实时评价技术对当前河流水资源管理和保护具有重要意义。该文以淮河水质为例,利用粒子群优化的极限学习机(Particle Swarm Optimization-Extreme Learning Machine,PSO-ELM)分类算法对淮河水质进行类别判定。在极限学习机(ELM)分类算法中随机给定输入权值矩阵和隐含层偏置,需要较多的隐含层节点才能达到所需的精度要求,隐含层节点过多易于出现过拟合现象并增加算法的计算量。该文利用粒子群算法(PSO)优化极限学习机的输入权值矩阵和隐含层偏置,计算输出权值矩阵,以减少隐含层节点。通过对比PSO-ELM、ELM这2种算法发现,PSO-ELM算法以较少的隐含层节点可获得更高的精度,降低了对实验样本的需求量,提高了模型的拟合能力。实验结果表明,PSO-ELM对于水质类别判定具有一定的可行性和有效性。
Real-time evaluation of river water quality is of great significance to the current water resources management and protection. Taking Huaihe River water quality as an example, this paper uses the Particle Swarm Optimization-Extreme Learning Machine (PSO-ELM) classification algorithm to determine the water quality of Huaihe River. In the ELM classification algorithm, given the input weight matrix and hidden layer bias randomly, more hidden layer nodes are needed to achieve the required accuracy. If too many hidden layer nodes are prone to over-simulation Combine phenomena and increase the computational complexity of the algorithm. In this paper, particle swarm optimization (PSO) is used to optimize the input weight matrix and hidden layer bias of extreme learning machine, and the output weight matrix is calculated to reduce the hidden layer nodes. By comparing PSO-ELM and ELM algorithms, it is found that the PSO-ELM algorithm can obtain higher precision with fewer hidden layer nodes, reduce the demand for experimental samples and improve the fitting ability of the model. The experimental results show that PSO-ELM is feasible and effective for water quality classification.