• 论文 •

### 四层参数自调整BP神经网络模型及其在人口死亡率预测中的应用

1. 1. 中国科学院数学与系统科学研究院,北京 100190;2. 中国科学院预测科学研究中心, 北京 100190;3. 中国科学院大学,北京 100049
• 出版日期:2018-06-25 发布日期:2018-08-21

XIANG Xin, LIU Xiuli. Four-Layer Parameter Self-Adjusting BP Neural Network Model and Its Application in Population Mortality Prediction[J]. Journal of Systems Science and Mathematical Sciences, 2018, 38(6): 702-710.

### Four-Layer Parameter Self-Adjusting BP Neural Network Model and Its Application in Population Mortality Prediction

XIANG Xin 1,3 ,LIU Xiuli 1,2,3

1. 1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190; 2. Chinese Academy of Sciences Prediction Science Research Center, Beijing 100190; 3. Chinese Academy of Sciences, Beijing 100049
• Online:2018-06-25 Published:2018-08-21

In order to effectively improve the learning efficiency of the neural network and reduce its probability of being trapped in the local minimum, a four-layer parameter self-adjusting BP neural network model was constructed in this paper. The model had four special network structures, used additional momentum method and adaptive method to adjust parameters. Numerical experiments showed that compared with the conventional BP neural network, the learning convergence speed and prediction accuracy of this method were greatly improved. Due to the complex changes in the mortality rate of the population, using a single model can not be accurately predicted. This paper also established the GM$(1,1)$ and the ARMA$(2,2)$ model, combined the advantages of these models, used the model average method to predict the mortality rate of our population. The results showed that the mortality rate of the population in China during 2018--2020 would be 7.1042\textperthousand, 7.1040\textperthousand ~and 7.1045\textperthousand, respectively.

()
 [1] 乔鸽, 周建红, 李新民. 广义线性模型下模型平均的比较研究[J]. 系统科学与数学, 2021, 41(4): 1164-1180. [2] 叶菲菲, 杨隆浩, 王应明. 基于不同联合学习方法的扩展置信规则库环境治理成本预测[J]. 系统科学与数学, 2021, 41(3): 705-729. [3] 孙会霞，倪宣明，钱龙，赵慧敏. 基于长期CVaR约束的高频投资组合优化[J]. 系统科学与数学, 2021, 41(2): 344-360. [4] 宋娟，倪志伟，李萍，伍章俊，彭鹏. 基于参数优化深度置信网络的雾霾预测模型[J]. 系统科学与数学, 2020, 40(9): 1644-1661. [5] 陆文星，戴一茹，李楚，李克卿. 基于改进PSO-BP神经网络的旅游客流量预测方法[J]. 系统科学与数学, 2020, 40(8): 1407-1419. [6] 夏平凡，倪志伟，朱旭辉. 基于烟花进化人工鱼群算法和多重分形的属性选择 方法的应用[J]. 系统科学与数学, 2020, 40(7): 1157-1177. [7] 陈心杰，赵志豪.  高维纵向数据的模型平均估计[J]. 系统科学与数学, 2020, 40(7): 1297-1324. [8] 张大斌，蔡超敏，凌立文，陈善盈. 基于CEEMD与GA-SVR的猪肉价格集成预测模型[J]. 系统科学与数学, 2020, 40(6): 1061-1073. [9] 高研，周建红，王海涛，张焕焕. 基于Jackknife模型平均方法的中国港口集装箱吞吐量预测[J]. 系统科学与数学, 2020, 40(4): 729-737. [10] 何琳洁，伍以加，戴娟. 低价揽客、分析师盈余预测与审计质量-----基于中国资本市场的经验证据[J]. 系统科学与数学, 2020, 40(3): 469-484. [11] 王苗苗. 基于线性模型平均估计的置信区间[J]. 系统科学与数学, 2020, 40(10): 1866-1881. [12] 崔金鑫，邹辉文. 基于EWT-PSO-SVM误差校正组合模型的中国股市预测研究[J]. 系统科学与数学, 2019, 39(8): 1212-1235. [13] 崔春生，王辉，李群. 基于用户标签和信任关系的协同过滤推荐算法研究[J]. 系统科学与数学, 2019, 39(3): 437-448. [14] 贾凯，倪志伟，李敬明，陆玉佳，朱旭辉. 基于改进二进制人工蜂群的BP神经网络并行集成学习算法及其应用研究[J]. 系统科学与数学, 2019, 39(3): 477-494. [15] 张文杰，袁红平.  基于灰色马尔可夫模型的节能设备故障预测研究[J]. 系统科学与数学, 2019, 39(1): 65-75.