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

doi:10.12196/j.issn.1000-3274.2020.03.011

Abstract

Abstract: The prediction of earthquake casualties involves many influencing factors, such as heavy computation, complicated model training, etc. In order to solve these problems, support vector machine (SVM) model optimized by genetic algorithm (GA) based on principle component analysis (PCA) was proposed. PCA was used to reduce the number of earthquake casualties influencing factors, and abandon those principal components with low contribution. The principal components with high contribution were used as input variables of SVM, and earthquake casualties were taken as output variable. Then GA was used to optimize the SVM parameters. Finally the prediction model for earthquake casualties based on PCA-GA-SVM was established, and used to predict the test samples. The result shows that the average prediction accuracy and operation efficiency of PCA-GA-SVM model respectively increased by 4.73%, 1.14%, 9.99% and 47.05%, 36.76%, 44.55% compared with prediction results of SVM model, GA-SVM model and PCA-GA-BP model. Therefore, the PCA-GA-SVM model has high prediction accuracy and strong generalization ability, which can predict earthquake casualties scientifically and reasonably.

Key words: Prediction of earthquake casualties, Principal component analysis, Genetic algorithm, Support vector machine

CLC Number:

P315.7

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.

References

[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 M_S8.0 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).

Application of Support Vector Machine Model Optimized by Principal Component Analysis and Genetic Algorithm in the Prediction of Earthquake Casualties

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 10

Recommended Articles

Metrics

Comments

[1]	LI Cheng-long, ZHANG Jing-fa. Method and Application of Earthquake Damage Change Detection from Remote Sensing Images Based on Principal Component Analysis [J]. EARTHQUAKE, 2013, 33(2): 103-108.
[2]	WU An-xu, ZHANG Yong-xian, ZHANG Xiao-dong, LI Ping-an, MU Hui-yong, LU Ya-jun. Study on model of support vector machine for synthetic prediction of seismic precursors [J]. EARTHQUAKE, 2008, 28(3): 55-60.
[3]	LI Zhi-xiong, YUAN Xi-wen, QIU Xue-qiang, WANG Zhi-cheng. Using correlation factors to forecast strong earth- quakes in China′s mainland with Support Vector Machine [J]. EARTHQUAKE, 2007, 27(1): 33-38.
[4]	WANG Wei, ZHAO Li-fei, WU Geng-feng, MA Qin-zhong, LIN Ming-zhou. The support vector machine method for analogizing and forecasting groundwater data [J]. EARTHQUAKE, 2007, 27(1): 9-16.
[5]	WANG Wei, ZHAO Li-fei, LIN Ming-zhou, MA Qin-zhong, WU Geng-feng, WU Shao-chun. A method to optimize earthquake precursor observatories [J]. EARTHQUAKE, 2006, 26(4): 22-28.
[6]	LI Zhi-xiong, WANG Zhi-cheng, YUAN Xi-wen, QIU Xue-qiang, LIN Jun. Forecasting of strong earthquakes in China's mainland based on wavelet transform and support vector machine [J]. EARTHQUAKE, 2006, 26(3): 64-70.
[7]	WANG Hong-ti, CHEN Yang, ZHUANG Can-tao. A local earthquake locating method based on genetic algorithm [J]. EARTHQUAKE, 2006, 26(2): 12-18.
[8]	LIU Li-fang, LIU Jie, SU You-jin. Comparison study on source parameters of Yao'an earth- quake sequence and Dayao earthquake sequence [J]. EARTHQUAKE, 2006, 26(1): 10-18.
[9]	WANG Wei, LIU Yue, LI Guo-zheng, WU Geng-feng, LIN Ming-zhou, MA Qin-zhong, ZHAO Li-fei. The support vector machine method for time sequence forecasting of strong earthquakes in China′s mainland [J]. EARTHQUAKE, 2005, 25(4): 26-32.
[10]	Jiang Haikun, Zhang Liu, Wang qi. 3-D LOCATION OF ACOUSTIC EMISSION AND STUDY ON THE ANISOTROPIC VELOCITY STRUCTURE IN THE SAMPLE [J]. EARTHQUAKE, 1999, 19(3): 245-252.