煤矿安全隐患信息自动分类方法
|
摘要
人工分类方式难以满足海量煤矿安全隐患信息的分类要求,而基于概率统计的文本自动分类方法分类准确率较低。针对上述问题,提出了一种基于Word2vec和卷积神经网络的煤矿安全隐患信息自动分类方法。首先对隐患信息进行分词、去停用词等预处理,然后应用Word2vec来表征词之间的语义相似性关系,最后利用卷积神经网络提取隐患信息的局部上下文高层特征,并使用Softmax分类器实现隐患信息的自动分类。实验结果表明,该方法实现了端到端的自动分类,可有效提升分类的准确性和全面性。
Manual classification method is difficult to meet classification requirements of massive coal mine safety hidden danger information,and automatic text classification method based on probability statistics has low classification accuracy rate.In view of the above problems,an automatic classification method of coal mine safety hidden danger information was proposed which was based on Word2 vec and convolutional neural network. Firstly,hidden danger information is pre-processed through word segmentation and stop word deletion.Then semantic similarity between words is represented by employing Word2 vec.Finally,local context high-level features of hidden danger information are extracted by use of convolutional neural network,and Softmax classifier is used to realize automatic classification of hidden danger information.The experimental results show that the method realizes end-to-end automatic classification and can effectively improve accuracy and comprehensiveness of classification.
Manual classification method is difficult to meet classification requirements of massive coal mine safety hidden danger information,and automatic text classification method based on probability statistics has low classification accuracy rate.In view of the above problems,an automatic classification method of coal mine safety hidden danger information was proposed which was based on Word2 vec and convolutional neural network. Firstly,hidden danger information is pre-processed through word segmentation and stop word deletion.Then semantic similarity between words is represented by employing Word2 vec.Finally,local context high-level features of hidden danger information are extracted by use of convolutional neural network,and Softmax classifier is used to realize automatic classification of hidden danger information.The experimental results show that the method realizes end-to-end automatic classification and can effectively improve accuracy and comprehensiveness of classification.
引文
[1]孟现飞,李克业,刘飞.基于3级嵌套安全管理模式的煤矿安全风险预控研究[J].中国安全科学学报,2013,23(4):102-107.MENG Xianfei,LI Keye,LIU Fei.Study on coal mine safety risk pre-control based on three-levels nested management mode[J].China Safety Science Journal,2013,23(4):102-107.
[2]贾立猛,丁淑艳,陈全.煤矿隐患排查治理信息系统的研究和应用[J].煤矿安全,2014,45(12):239-241.JIA Limeng,DING Shuyan,CHEN Quan.Research and application of coal mine hidden dangers investigation and management information system[J].Safety in Coal Mines,2014,45(12):239-241.
[3]张长鲁.煤矿事故隐患大数据处理与知识发现分析方法研究[J].中国安全生产科学技术,2016,12(9):176-181.ZHANG Changlu.Study on big data processing and knowledge discovery analysis method for safety hazard in coal mine[J].Journal of Safety Science and Technology,2016,12(9):176-181.
[4]陈运启.数据挖掘技术在煤矿隐患管理中的应用[J].工矿自动化,2016,42(2):27-30.CHEN Yunqi.Application of data mining technology in coal mine hidden hazard management[J].Industry and Mine Automation,2016,42(2):27-30.
[5]张大伟.基于OLAM的煤矿企业安全隐患趋势分析[J].煤炭工程,2015,47(5):139-142.ZHANG Dawei.Analysis of coal mine safety hidden danger trends based on OLAM[J].Coal Engineering,2015,47(5):139-142.
[6]周浩,宋保华.大数据在安全生产中的作用[J].安全,2015,36(10):8-11.
[7]谭章禄,陈晓,宋庆正,等.基于文本挖掘的煤矿安全隐患分析[J].安全与环境学报,2017,17(4):1262-1266.TAN Zhanglu,CHEN Xiao,SONG Qingzheng,et al.Analysis for the potential hazardous risks of the coal mines based on the so-called text mining[J].Journal of Safety and Environment,2017,17(4):1262-1266.
[8]KIM S B,HAN K S,RIM H C,et al.Some effective techniques for naive Bayes text classification[J].IEEE Transactions on Knowledge&Data Engineering,2006,18(11):1457-1466.
[9]黄章树,叶志龙.基于改进的CHI统计方法在文本分类中的应用[J].计算机系统应用,2016,25(11):136-140.HUANG Zhangshu,YE Zhilong.Application of text categorization based on improved CHI-square statistic method[J].Computer Systems&Applications,2016,25(11):136-140.
[10]MIKOLOV T,YIH W T,ZWEIG G.Linguistic regularities in continuous space word representations[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Atlanta,2013:746-751.
[11]KIM Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,Doha,2014:1746-1751.
[12]XING Chao,WANG Dong,LIU Chao,et al.Normalized word embedding and orthogonal transform for bilingual word translation[C]//Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Denver,2015:1006-1011.
[13]LI Shuguo.The application of information technology in coal mine management[J].Mechanical Management&Development,2014,340(3):38-45.
[14]LE Q,MIKOLOV T.Distributed representations of sentences and documents[C]//Proceedings of the31st International Conference on Machine Learning,Beijing,2014:1188-1196.
[15]YAROTSKY D.Error bounds for approximations with deep ReLU networks[J].Neural Networks:the Official Journal of the International Neural Network Society,2017,94:103-114.
[2]贾立猛,丁淑艳,陈全.煤矿隐患排查治理信息系统的研究和应用[J].煤矿安全,2014,45(12):239-241.JIA Limeng,DING Shuyan,CHEN Quan.Research and application of coal mine hidden dangers investigation and management information system[J].Safety in Coal Mines,2014,45(12):239-241.
[3]张长鲁.煤矿事故隐患大数据处理与知识发现分析方法研究[J].中国安全生产科学技术,2016,12(9):176-181.ZHANG Changlu.Study on big data processing and knowledge discovery analysis method for safety hazard in coal mine[J].Journal of Safety Science and Technology,2016,12(9):176-181.
[4]陈运启.数据挖掘技术在煤矿隐患管理中的应用[J].工矿自动化,2016,42(2):27-30.CHEN Yunqi.Application of data mining technology in coal mine hidden hazard management[J].Industry and Mine Automation,2016,42(2):27-30.
[5]张大伟.基于OLAM的煤矿企业安全隐患趋势分析[J].煤炭工程,2015,47(5):139-142.ZHANG Dawei.Analysis of coal mine safety hidden danger trends based on OLAM[J].Coal Engineering,2015,47(5):139-142.
[6]周浩,宋保华.大数据在安全生产中的作用[J].安全,2015,36(10):8-11.
[7]谭章禄,陈晓,宋庆正,等.基于文本挖掘的煤矿安全隐患分析[J].安全与环境学报,2017,17(4):1262-1266.TAN Zhanglu,CHEN Xiao,SONG Qingzheng,et al.Analysis for the potential hazardous risks of the coal mines based on the so-called text mining[J].Journal of Safety and Environment,2017,17(4):1262-1266.
[8]KIM S B,HAN K S,RIM H C,et al.Some effective techniques for naive Bayes text classification[J].IEEE Transactions on Knowledge&Data Engineering,2006,18(11):1457-1466.
[9]黄章树,叶志龙.基于改进的CHI统计方法在文本分类中的应用[J].计算机系统应用,2016,25(11):136-140.HUANG Zhangshu,YE Zhilong.Application of text categorization based on improved CHI-square statistic method[J].Computer Systems&Applications,2016,25(11):136-140.
[10]MIKOLOV T,YIH W T,ZWEIG G.Linguistic regularities in continuous space word representations[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Atlanta,2013:746-751.
[11]KIM Y.Convolutional neural networks for sentence classification[C]//Proceedings of the 2014Conference on Empirical Methods in Natural Language Processing,Doha,2014:1746-1751.
[12]XING Chao,WANG Dong,LIU Chao,et al.Normalized word embedding and orthogonal transform for bilingual word translation[C]//Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Denver,2015:1006-1011.
[13]LI Shuguo.The application of information technology in coal mine management[J].Mechanical Management&Development,2014,340(3):38-45.
[14]LE Q,MIKOLOV T.Distributed representations of sentences and documents[C]//Proceedings of the31st International Conference on Machine Learning,Beijing,2014:1188-1196.
[15]YAROTSKY D.Error bounds for approximations with deep ReLU networks[J].Neural Networks:the Official Journal of the International Neural Network Society,2017,94:103-114.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |