An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) mod...An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) model and a radial basis function(RBF) model,to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing,P. R. China. Our models used the historical monitoring data of biological oxygen demand,dissolved oxygen,ammonia,oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models,the RBF model calculates with a smaller mean error,but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models.展开更多
【目的】探究ERNIE模型(Enhanced Language Representation with Informative Entities)和双向门限循环单元(Bi GRU)在医疗疾病名称科室分类中的效果及差异。【方法】以医疗疾病名称为训练样本,以BERT(Bidirectional Encoder Representa...【目的】探究ERNIE模型(Enhanced Language Representation with Informative Entities)和双向门限循环单元(Bi GRU)在医疗疾病名称科室分类中的效果及差异。【方法】以医疗疾病名称为训练样本,以BERT(Bidirectional Encoder Representation from Transformers)为对比模型并在模型之后加入不同网络层进行训练探究。【结果】ERNIE模型在分类效果上优于BERT模型,精度约高4%,其中精确度可达79.48%,召回率可达79.73%,F1分数可达79.50%。【局限】仅对其中的八个科室进行分类研究,其他类别由于数据量过少而未纳入分类体系中。【结论】ERNIE-BiGRU分类效果较好,可应用于医疗导诊系统或者卫生统计学中。展开更多
基金Funded by the Natural Science Foundation of China (No. 59778021)
文摘An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network(ANN) models,a feed-forward back-propagation(BP) model and a radial basis function(RBF) model,to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing,P. R. China. Our models used the historical monitoring data of biological oxygen demand,dissolved oxygen,ammonia,oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models,the RBF model calculates with a smaller mean error,but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models.
文摘【目的】探究ERNIE模型(Enhanced Language Representation with Informative Entities)和双向门限循环单元(Bi GRU)在医疗疾病名称科室分类中的效果及差异。【方法】以医疗疾病名称为训练样本,以BERT(Bidirectional Encoder Representation from Transformers)为对比模型并在模型之后加入不同网络层进行训练探究。【结果】ERNIE模型在分类效果上优于BERT模型,精度约高4%,其中精确度可达79.48%,召回率可达79.73%,F1分数可达79.50%。【局限】仅对其中的八个科室进行分类研究,其他类别由于数据量过少而未纳入分类体系中。【结论】ERNIE-BiGRU分类效果较好,可应用于医疗导诊系统或者卫生统计学中。
