School of Maritime and Transportation, Ningbo University, Ningbo 315211, China.
Comput Intell Neurosci. 2022 Apr 28;2022:7327072. doi: 10.1155/2022/7327072. eCollection 2022.
Multiparameter water quality trend prediction technique is one of the important tools for water environment management and regulation. This study proposes a new water quality prediction model with better prediction performance, which is combined with improved sparrow search algorithm (ISSA) and support vector regression (SVR) machine. For the problems of low population diversity and easily falling into local optimum of sparrow search algorithm (SSA), ISSA is proposed to increase the initial population diversity by introducing Skew-Tent mapping and to help the algorithm jump out of local optimum by using the adaptive elimination mechanism. The optimal values of the penalty factor C and kernel function parameter of the SVR model are selected using ISSA to make the model have better prediction accuracy and generalization performance. The performance of the ISSA-SVR water quality prediction model is compared with BP neural network, SVR model, and other hybrid models by conducting water quality prediction experiments with actual breeding-water quality data. The experimental results showed that the prediction accuracy of the ISSA-SVR model was significantly higher than that of other models, reaching 99.2%; the mean square deviation (MSE) was 0.013, which was 79.37% lower than that of the SVR model and 75% lower than that of SSA-SVR model, and the coefficient of determination ( ) was 0.98, which was 5.38% higher than that of the SVR model and 7.57% higher than that of the SSA-SVR model, indicating that the ISSA-SVR water quality prediction model has some engineering application value in the field of water body management.
多参数水质趋势预测技术是水环境管理和调控的重要工具之一。本研究提出了一种新的水质预测模型，该模型具有更好的预测性能，结合了改进的麻雀搜索算法（ISSA）和支持向量回归（SVR）机。针对麻雀搜索算法（SSA）种群多样性低和容易陷入局部最优的问题，提出了 ISSA 通过引入斜 Tent映射来增加初始种群多样性，并通过自适应淘汰机制帮助算法跳出局部最优。使用 ISSA 选择 SVR 模型的惩罚因子 C 和核函数参数 的最优值，使模型具有更好的预测精度和泛化性能。通过使用实际养殖水质数据进行水质预测实验，将 ISSA-SVR 水质预测模型的性能与 BP 神经网络、SVR 模型和其他混合模型进行比较。实验结果表明，ISSA-SVR 模型的预测精度明显高于其他模型，达到 99.2%；均方根误差（MSE）为 0.013，比 SVR 模型低 79.37%，比 SSA-SVR 模型低 75%；决定系数（ ）为 0.98，比 SVR 模型高 5.38%，比 SSA-SVR 模型高 7.57%，表明 ISSA-SVR 水质预测模型在水体管理领域具有一定的工程应用价值。
