地震 ›› 2020, Vol. 40 ›› Issue (3): 142-152.doi: 10.12196/j.issn.1000-3274.2020.03.011
王晨晖1, 刘立申1, 任佳1, 袁颖2, 王利兵1, 陈凯男1
收稿日期:
2019-07-16
出版日期:
2020-07-31
发布日期:
2020-07-28
通讯作者:
刘立申,高级工程师。E-mail:270882786@qq.com
作者简介:
王晨晖(1992-),男,河北邢台人,硕士研究生,主要从事地震观测研究工作。
基金资助:
WANG Chen-hui1, LIU Li-shen1, REN Jia1, YUAN Ying2, WANG Li-bing1, CHEN Kai-nan1
Received:
2019-07-16
Online:
2020-07-31
Published:
2020-07-28
摘要: 为有效解决地震伤亡人数预测所需影响因子多、 运算量大、 模型训练烦琐等问题, 构建了主成分分析法(PCA)和遗传算法(GA)优化的支持向量机(SVM)模型, 采用PCA对地震伤亡人数影响因子进行降维以去除贡献率较低的主成分, 将贡献率较大的主成分作为支持向量机的输入变量, 以地震伤亡人数作为输出变量, 利用GA对SVM模型性能参数进行优化, 建立基于PCA-GA-SVM的地震伤亡人数预测模型, 并对测试样本进行预测, 结果表明: 与SVM模型、 GA-SVM模型和PCA-GA-BP模型相比, PCA-GA-SVM模型的预测准确率和运行效率分别提高 4.73%、 1.14%、 9.99% 和47.05%、 36.76%、 44.55%。结果显示, PCA-GA-SVM模型预测精度高, 泛化能力强, 能够科学合理地对地震伤亡人数作出预测。
中图分类号:
王晨晖, 刘立申, 任佳, 袁颖, 王利兵, 陈凯男. 主成分分析法和遗传算法优化的支持向量机模型在地震伤亡人数预测中的应用[J]. 地震, 2020, 40(3): 142-152.
WANG Chen-hui, LIU Li-shen, REN Jia, YUAN Ying, WANG Li-bing, CHEN Kai-nan. Application of Support Vector Machine Model Optimized by Principal Component Analysis and Genetic Algorithm in the Prediction of Earthquake Casualties[J]. EARTHQUAKE, 2020, 40(3): 142-152.
[1] 周德红, 冯豪, 程乐棋, 等. 遗传算法优化的BP神经网络在地震死亡人数评估中的应用[J]. 安全与环境学报, 2017, 17(6): 2267-2272. ZHOU De-hong, FENG Hao, CHENG Le-qi, et al. Earthquake casualty assessment based on the BP neural network of the optimized genetic algorithm[J]. Journal of Safety and Environment, 2017, 17(6): 2267-2272 (in Chinese). [2] 袁小祥, 王晓青, 窦爱霞, 等. 面向地震风险评估的人口空间格网化技术研究[J]. 地震, 2018, 38(4): 151-158. YUAN Xiao-xiang, WANG Xiao-qing, DOU Ai-xia, et al. Spatial grid transformation technology of population data for seismic risk assessment[J]. Earthquake, 2018, 38(4): 151-158 (in Chinese). [3] 邵志刚, 王芃. 2008年汶川8.0级地震对地震预测研究的启示思考[J]. 地震, 2018, 38(2): 1-10. SHAO Zhi-gang, WANG Peng. Reflections on earthquake prediction research ten years after the 2008 Wenchuan MS8.0 earthquake[J]. Earthquake, 2018, 38(2): 1-10 (in Chinese). [4] Yu H, Qiang M, Liu S-Q. Territorial suitability assessment and function zoning in the Jiuzhaigou earthquake-stricken area[J]. Journal of Mountain Science, 2019, 16(1): 195-206. [5] Li J C, Qu Z, Wang T. Lessons from the seismic behavior of a steel grid roof structure heavily damaged in Lushan earthquake[J]. Earthquake Engineering and Engineering Vibration, 2019, 18(1): 95-111. [6] 施伟华, 陈坤华, 谢英情, 等. 云南地震灾害人员伤亡预测方法研究[J]. 地震研究, 2012, 35(3): 387-392. SHI Wei-hua, CHEN Kun-hua, XIE Ying-qing, et al. Prediction method research on casualties due to earthquake disaster in Yunnan[J]. Journal of Seismological Research, 2012, 35(3): 387-392 (in Chinese). [7] 吴将丰, 王海霞. 基于AMOS的地震人员伤亡影响因素分析[J]. 地震工程与工程振动, 2013, 33(2): 221-228. WU Jiang-feng, WANG Hai-xia. The factor analysis of earthquake casualties based on AMOS[J]. Earthquake Engineering and Engineering Dynamics, 2013, 33(2): 221-228 (in Chinese). [8] 陈黛, 白鹏飞, 蔡冬雪. 地震灾害人员伤亡预测模型研究[J]. 数学的实践与认识, 2017, 47(13): 208-215. CHEN Dai, BAI Peng-fei, CAI Dong-xue. Study on the prediction model of human casualties in earthquake disasters[J]. Journal of Mathematics in Practice and Theory, 2017, 47(13): 208-215 (in Chinese). [9] Tang P, Zhang H D, Ye T H, et al. A novel method for chemistry tabulation of strained premixed/stratified flames based on principal component analysis[J]. Applied Mathematics and Mechanics (English Edition), 2018, 39(6): 855-866. [10] Yousefi F, Amoozandeh Z. A new model to predict the densities of nanofluids using statistical mechanics and artificial intelligent plus principal component analysis[J]. Chinese Journal of Chemical Engineering, 2017, 25(9): 1273-1281. [11] 袁红春, 赵彦涛, 刘金生. 基于PCA-NARX神经网络的氨氮预测[J]. 大连海洋大学学报, 2018, 33(6): 808-813. YUAN Hong-chun, ZHAO Yan-tao, LIU Jin-sheng. Ammonia nitrogen level forecasting based on PCA-NARX neural network[J]. Journal of Dalian Ocean University, 2018, 33(6): 808-813 (in Chinese). [12] 刘鸿斌, 李祥宇, 杨冲. 基于PCA降维模型的造纸废水处理过程软测量建模[J]. 中国造纸学报, 2018, 33(4): 50-57. LIU Hong-bin, LI Xiang-yu, YANG Chong. Soft sensor modeling of papermaking waste water treatment process using PCA dimensional reduction models[J]. Transactions of China Pulpand Paper, 2018, 33(4): 50-57 (in Chinese). [13] 陈伟根, 滕黎, 刘军, 彭尚怡, 孙才新. 基于遗传优化支持向量机的变压器绕组热点温度预测模型[J]. 电工技术学报, 2014, 29(1): 44-51. CHEN Wei-gen, TENG Li, LIU Jun, et al. Transformer winding hot-spot temperature prediction model of support vector machine optimized by genetic algorithm[J]. Transactions of China Electrotechnical Society, 2014, 29(1): 44-51 (in Chinese). [14] 吴景龙, 杨淑霞, 刘承水. 基于遗传算法优化参数的支持向量机短期负荷预测方法[J]. 中南大学学报(自然科学版), 2009, 40(1): 180-184. WU Jing-long, YANG Shu-xia, LIU Cheng-shui. Parameter selection for support vectormachines based on genetic algorithms to short-term power load forecasting[J]. Journal of Central South University (Science and Technology), 2009, 40(1): 180-184 (in Chinese). [15] Mohammad M, Ebrahim S, Mashallah R. Development of a least squares support vector machine model for prediction of natural gas hydrate formation temperature[J]. Chinese Journal of Chemical Engineering, 2017, 25(9): 1238-1248. [16] Sananda K, Deepak K, Arun M. Future changes in rainfall temperature and reference evapotranspiration in the central India by least square support vector machine[J]. Geoscience Frontiers, 2017, 8(3): 583-596. [17] 苏亮, 何海健. 基于SVM的RC框架结构地震易损性分析[J]. 华中科技大学学报(自然科学版), 2018, 46(5): 115-120. SU Liang, HE Hai-jian. Seismic vulnerability assessment for RC frame structure based on SVM[J]. J.Huazhong Univ.of Sci.& Tech.(Natural Science Edition), 2018, 46(5): 115-120 (in Chinese). [18] 毛志勇, 黄春娟, 路世昌. 基于PSO-SVM的砂土地震液化预测模型[J]. 中国安全科学学报, 2018, 28(3): 25-30. MAO Zhi-yong, HUANG Chun-juan, LU Shi-chang. PSO-SVM based model for prediction of sandy soil liquefaction[J]. China Safety Science Journal, 2018, 28(3): 25-30 (in Chinese). [19] 孙振宇, 彭苏萍, 邹冠贵. 基于SVM算法的地震小断层自动识别[J]. 煤炭学报, 2017, 42(11): 2945-2952. SUN Zhen-yu, PENG Su-ping, ZOU Guan-gui. Automatic identification of small faults based on SVM and seismic data[J]. Journal of China Coal Society, 2017, 42(11): 2945-2952 (in Chinese). [20] Fatemeh A, Baharak M, Hasan A, et al. Landslide susceptibility mapping using Genetic Algorithm for the Rule Set Production (GARP) model[J]. Journal of Mountain Science, 2018, 15(9): 2013-2026. [21] 王世辉, 王仪明, 武淑琴, 等. 基于GA-SVM模型的印刷套准识别[J]. 传感器与微系统, 2018, 37(11): 142-144. WANG Shi-hui, WANG Yi-ming, WU Shu-qin, et al. Printing registration recognition based on GA-SVM model[J]. Transducer and Microsystem Technologies, 2018, 37(11): 142-144 (in Chinese). [22] 温廷新, 于凤娥, 邵良杉, 等. 基于GA-SVM的隧道围岩分类研究[J]. 公路交通科技, 2018, 35(9): 63-70. WEN Ting-xin, YU Feng-e, SHAO Liang-shan, et al. Study on classification of tunnel surrounding rock based on GA-SVM[J]. Journal of Highway and Transportation Research and Development, 2018, 35(9): 63-70 (in Chinese). |
[1] | 曾宪伟, 龙锋, 任家琪, 蔡新华, 李文君. 2019年6月17日长宁MS6.0地震前后b值时空变化分析[J]. 地震, 2020, 40(3): 1-14. |
[2] | 孙凯, 孟国杰, 洪顺英, 黄星, 董彦芳. 基于Sentinel-1A数据的四川长宁MS6.0地震同震形变场分析及断层滑动分布反演[J]. 地震, 2020, 40(3): 15-27. |
[3] | 赵策, 左可桢, 赵翠萍. 2019年6月17日四川长宁6.0级地震序列活动特征[J]. 地震, 2020, 40(3): 28-40. |
[4] | 王玮铭, 谭大诚. 2019年长宁MS6.0地震邻区分钟采样地电场分析[J]. 地震, 2020, 40(3): 41-51. |
[5] | 肖卓, 高原. 伴随成像及其在地球深部结构研究中的应用[J]. 地震, 2020, 40(3): 52-64. |
[6] | 蒋雨函, 高小其, 王阳洋, 张磊. 中国新疆北天山和台湾南部陆地泥火山研究进展[J]. 地震, 2020, 40(3): 65-82. |
[7] | 马禾青, 杨明芝, 罗国富. 地震活动频次场研究[J]. 地震, 2020, 40(3): 99-111. |
[8] | 戴盈磊, 万永革, 梁永朵, 张文静, 惠杨. 基于震源机制解资料的辽宁地区现今构造应力场[J]. 地震, 2020, 40(3): 112-130. |
[9] | 黄颂, 姚丽, 姜楚峰. 基于幅相法的地磁低点位移异常可靠性分析方法[J]. 地震, 2020, 40(3): 131-141. |
[10] | 王洪体, 崔仁胜, 王宏远, 叶鹏, 李丽娟. 对齐误差对测试地震计自噪声的影响[J]. 地震, 2020, 40(3): 153-166. |
[11] | 罗毅, 田云锋, 张苏, 张景发. 利用InSAR技术研究青藏高原冻土形变特征[J]. 地震, 2020, 40(3): 179-188. |
[12] | 薛艳, 姜祥华, 刘桂萍. 华北地区强震活动状态研究[J]. 地震, 2020, 40(2): 1-17. |
[13] | 贾漯昭, 宋美琴, 谢健健, 邢康, 高家乙. 华北块体地震活动显著增强预测效能评估[J]. 地震, 2020, 40(2): 38-48. |
[14] | 万森林, 张军龙, 刘明军, 贺为民, 李海龙, 郭长宝, 李智敏. 岷山断块的发震构造与地震活动性分析[J]. 地震, 2020, 40(2): 49-70. |
[15] | 李瑞莎, 张希, 贾鹏, 白卓立. 青藏块体东北缘跨断层异常场地比指标及其在地震预测中的应用[J]. 地震, 2020, 40(2): 71-81. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||