为及时辨识集约化水产养殖水质变化趋势、动态调控水质,确保无应激环境下健康养殖,该文提出了基于时序列相似数据的最小二乘支持向量回归机(least squares support vector regression,LSSVR)水质溶解氧在线预测模型。采用特征点分段时...为及时辨识集约化水产养殖水质变化趋势、动态调控水质,确保无应激环境下健康养殖,该文提出了基于时序列相似数据的最小二乘支持向量回归机(least squares support vector regression,LSSVR)水质溶解氧在线预测模型。采用特征点分段时间弯曲距离(feature points segmented time warping distance,FPSTWD)算法对在线采集的时间序列数据进行分段与相似度计算,以缩减规模的子序列数据集对LSSVR模型进行快速训练优化,实现了多个LSSVR子模型在线建模,将预测数据序列与LSSVR子模型的相似度匹配,自适应地选取最佳的子模型作为在线预测模型。应用该模型对集约化河蟹福利养殖水质参数溶解氧浓度进行在线预测,模型评价指标中最大相对误差、平均绝对百分比误差、相对均方根误差和运行时间分别为4.76%、8.18%、5.23%、8.32 s。研究结果表明,与其他预测方法相比,该模型具有较好的综合预测性能,能够满足河蟹福利养殖水质在线预测的实际需求,并为集约化水产养殖水质精准调控提供研究基础。展开更多
In this paper, we study the thermodynamic geometry for the charged Ad S black hole surrounded by quintessence. Three different kinds of the geometries are constructed, and the corresponding curvatures are obtained. It...In this paper, we study the thermodynamic geometry for the charged Ad S black hole surrounded by quintessence. Three different kinds of the geometries are constructed, and the corresponding curvatures are obtained. It is found that there are different divergence behaviors of these curvatures, which is general thought to closely link to the phase transition of the black hole.展开更多
基金Supported by the National Natural Science Foundation of China under Grant Nos.11675064,11205074the Fundamental Research Funds for the Central Universities under Grant No.lzujbky-2016-121
文摘In this paper, we study the thermodynamic geometry for the charged Ad S black hole surrounded by quintessence. Three different kinds of the geometries are constructed, and the corresponding curvatures are obtained. It is found that there are different divergence behaviors of these curvatures, which is general thought to closely link to the phase transition of the black hole.