基于XGBoost算法的人—虎共存区域风险等级划分  

Risk Classification Model of Human-Tiger Coexistence Area Based on XGBoost Algorithm

作　　者：曲智林[1] 桂宁晨 QU Zhilin;GUI Ningchen(College of Science,Northeast Forestry University,Harbin 150040,China)

机构地区：[1]东北林业大学理学院,黑龙江哈尔滨150040

出　　处：《沈阳大学学报（自然科学版）》2024年第3期262-266,F0003,共6页Journal of Shenyang University：Natural Science

基　　金：国家自然科学基金资助项目(12001088);黑龙江省自然科学基金项资助目(2572022DS04)。

摘　　要：以2014—2019年珲春地区红外相机拍摄的东北虎数据为基础,基于XGBoost算法构建了虎出没区域风险等级划分模型。由模型检验可知:模型的准确率为93.51%,精确率为93.85%,召回率为93.08%,F1值为93.31%,Cohen s Kappa统计系数为90.2%。研究结果表明:基于XGBoost算法构建的人-虎共存区域风险等级划分模型分类效果好、预测准确度高,运用该模型对人-虎共存区域进行风险等级划分是可行的。Based on the data of Siberian tigers taken by infrared cameras in Hunchun from 2014 to 2019,a risk classification model of tiger infested areas was constructed using XGBoost algorithm.The model test showed that the accuracy rate of the model was 93.51%,the precision was 93.85%,the recall rate was 93.08%,the F1-score value was 93.31%,and the Cohen s Kappa statistical coefficient was 90.2%.The research results showed that the risk classification model of human-tiger coexistence area based on XGBoost algorithm had good classification effect and high prediction accuracy.It was feasible to use this model to classify the risk level of human-tiger coexistence area.

关 键 词：人-虎共存区域 XGBoost算法 风险等级 划分模型 红外相机陷阱 

分 类 号：O242.1[理学—计算数学] S863[理学—数学]