基于SVM-DS融合算法的消防员效能评估方法
An evaluation method of firefighter's working efficiency based on SVM-DS fusion algorithm
关爱科 1杨杰1
作者信息
- 1. 西安科技大学 安全科学与工程学院,陕西 西安 710054
- 折叠
摘要
为了准确量化消防救援环境下消防员效能、保障消防员生命安全,本文通过支持向量机(SVM)后验概率转化对算法进行改进,提出一种基于SVM与Dempster-Shafer(DS)融合的效能评估方法.首先提取消防员的生理、心理特征参数;其次对特征参数进行SVM分类与回归预测;然后将预测结果通过后验概率转化为DS证据的基本概率分配;最后根据DS证据理论对消防员效能进行实时评估.结果表明,SVM回归预测效能参数心率的均方误差为0.002,决定系数为0.95,预测效果优于BP神经网络.SVM-DS融合算法评估效能的平均绝对误差为10.65%,可较好地实现消防员效能实时评估.本文所提出的算法能够有效地量化效能并实时进行评估,为开发预警系统、确定最大安全工作时间,以及实现科学救援和提升灾害应对能力提供理论基础数据.
Abstract
To quantify the firefighter's working efficiency accu-rately and protect the firefighter's life safety in the fire rescue envi-ronment,the study improves the algorithm through a posterior probabilistic transformation of the Support Vector Machine(SVM),and proposes a working efficiency evaluation method based on the fusion of the SVM and the Dempster-Shafer(DS).First,the physiological and psychological parameters of firefight-ers'characteristics are extracted;Second,feature parameters are classified and predicted by SVM regression;Then,the predicted results are transformed into the basic probability assignments of DS evidence by a posteriori probability transformation;Finally,firefighter's working efficiency is evaluated in real time according to the DS evidence theory.The results show that the mean square error of SVM regression for predicting the heart rate of working efficiency parameter is 0.002,and the coefficient of determination is 0.95,which is better than that of BP neural network.The aver-age absolute error of SVM-DS fusion algorithm for evaluation of working efficiency is 10.65%,and it can be better realized to evaluate firefighters'working efficiency in real time.The algo-rithm presented in this study can provide theoretical data for devel-oping early warning system,determining the maximum safe work-ing time,and realizing scientific rescue and enhancement of disas-ter response capability by effectively quantifying the working effi-ciency and evaluating it in real-time.
关键词
效能评估/消防员/多特征融合/支持向量机/DS证据理论Key words
working efficiency evaluation/firefighters/multi-feature fusion/support vector machines/DS evidence theory引用本文复制引用
出版年
2024
NETL
NSTL
万方数据