冯继伟,孙开畅

• 1:三峡大学水利与环境学院

摘要(Abstract)：

为了研究水利工程事件的风险状态,引入了机器学习中的因子分解机模型对水利工程事件的风险因素及风险状态进行分析。以修订的人为因素分析与分类系统(HFACS)中的风险因素作为事件数据分析指标,采用因子分解机(FM)理论,并利用数据库对因子分解机模型进行训练和测试,建立了风险因素交叉情况下的风险状态分析模型,根据该模型可以确定风险因素之间交叉项因素的关系并能够表达事件整体的风险状态。结果表明:利用数据库对因子分解机模型进行训练,能够较好地解决风险因素交叉项计算问题,计算出事件交叉项之间的关系,得出与水利工程相匹配的因子分解机风险因素状态模型,有助于后续的应急决策及应急救援工作。

关键词(KeyWords)： 因子分解机;机器学习;风险分析;特征交叉;应急能力

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划资助项目(2017YFC0805100)

作者(Author): 冯继伟,孙开畅

DOI: 10.13928/j.cnki.wrahe.2021.12.017

参考文献(References)：

• [1] 孙开畅，周剑岚.水利水电工程施工安全风险管理[M].北京：中国水利水电出版社，2013.SUN Kaichang,ZHOU Jianlan.Construction safety risk management of water conservancy and hydropower projects [M].Beijing:China Water Power Press,2013.
• [2] RENDLE S.Factorization Machines[C]// WEI Fan.ICDMW:The 10th IEEE International Conference on Data Mining Workshops.Sydney,NSW,Australia:IEEE Computer Society Conference Publishing,2010:995-1000.
• [3] RENDLE S,GANTNER Z,FREUDENTHALER C,et al.Fast context-aware recommendations with factorization machines[C]// MA Weiying.ACM SIGIR:Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval.Beijing:Association for Computing Machinery Publishing,2011:656-644.
• [4] JAMALI M,ESTER M.transitivity aware matrix factorization model for recommendation in social networks [C]// LI Jin.Proceedings of the 6th International Joint Conference on Artificial Intelligence:Chongqing:Association for Computing Machinery Publishing,2011:2644-2649.
• [5] JAHRER M,TOSHER A,LEE J Y,et al.Ensemble of collaborative filtering and feature engineered models for click through rate prediction[C]//CAO Longbing.ACM SIGKDD:Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Sydney,NSW,Australia:IEEE Computer Society Conference Publishing,2012:1-23.
• [6] JUAN Y,ZHUANG Y,CHIN W S,et al.Field-aware factorization machines for CTR prediction[C]// Josef Jannach.ACM:Proceedings of the 10th ACM Conference on Recommender Systems.Boston,Massachusetts:Association for Computing Machinery Publishing,2016:43-50.
• [7] 孙开畅，李昆，徐小峰，等.水电工程施工安全生产与应急决策信息系统研究与应用[J].水力发电学报，2013,32(5):317-320.SUN Kaichang,LI Kun,XU Xiaofeng,et al.Study and application of safety management and emergency decision system for hydropower project[J].Journal of Hydroelectric Engineering,2013,32(5):306-310.
• [8] 哈林顿·皮特.机器学习实战：1版[M].李锐，李鹏，曲亚东，王斌，译.北京：人民邮电出版社，2013.HARRINGTON Pete.Machine learning in practice:1 edition [M].Translated by LI Rui,LI Peng,QU Yadong,WANG Bin.Beijing:People′s Posts and Telecommunications Press.2013.
• [9] 赵卫东，董亮.机器学习[M].北京：人民邮电出版社，2018.ZHAO Weidong,DONG Liang.Machine Learning [M].Beijing:People′s Posts and Telecommunications Press,2018.
• [10] 燕彩蓉，潘乔.机器学习：因子分解机模型与推荐系统[M].北京：科学出版社，2018.YAN Cairong,PAN Qiao.Machine Learning:Factor Decomposition Machine Model and Recommendation System [M].Beijing:Science Press,2018.
• [11] 陈静.基于因子分解机及深度学习的个性化推荐算法研究[D].成都：电子科技大学，2020.CHEN jing.Research on Personalized Recommendation Algorithm Based on Factor Decomposition Machine and Deep Learning [D].Chengdu:University of Electronic Science and Technology of China,2020.
• [12] 陈腾.因子分解机模型在推荐领域的应用研究[D].哈尔滨：哈尔滨理工大学，2019.CHEN Teng.Research on the Application of Factor Decomposition Machine Model in Recommendation Domain [D].Harbin:Harbin University of Science and Technology,2019.
• [13] 陈一文.一种改进的基于DeepFM算法的高效CTR预估方法[D].长春：吉林大学，2020.CHEN Yiwen.An Improved CTR Estimation Method Based on DEEPFM Algorithm [D].Changchun:Jilin University,2020.
• [14] 孙开畅，李权，尹志伟.水利工程高危作业人因评价体系中的认知图理论研究[J].中国安全生产科学技术，2016,12(12):128-132.SUN Kaichang,LI Quan,YIN Zhiwei.Research on Cognitive Map Theory in the Human Factor Evaluation System for High-risk Operations in Water Conservancy Projects[J].China Work Safety Science and Technology,2016,12(12):128-132.
• [15] 中华人民共和国水利部.汉语拼音正词法基本规则：GB/SL 721—2015 [S].北京：水利水电出版社，2015.Ministry of Water Resources of the People′s Republic of China.Basic rules of Chinese pinyin orthography:GB/SL 721—2015 [S].Beijing:Water Conservancy and Hydropower Press,2015.
• [16] IAN G,YOSHUA B,AARON C.Deep Learning[M].Cambridge,Massachusetts:MIT Press,2017.