基于随机森林模型的船员选择培训机构影响因素分析
PDF下载 (3085)袁玉峰,郁晓红,郑彭军.基于随机森林模型的船员选择培训机构影响因素分析[J].宁波大学学报(理工版),2021,34(3):79-83.DOI:
YUAN Yufeng,YU Xiaohong,Zheng Pengjun.Analysis of factors influencing ship crew’s choice of training institutions based on random forest model[J].Journal of Ningbo University(Natural Science & Engineering Edition),2021,34(3):79-83.DOI:
| Title: | Analysis of factors influencing ship crew’s choice of training institutions based on random forest model |
| 作者: | 袁玉峰, 郁晓红, 郑彭军 |
| Author(s): | YUAN Yufeng, YU Xiaohong, Zheng Pengjun |
| 关键词: | 船员选择培训机构行为; 影响因素; 区域差异; 随机森林; crew’s selection of training institutions |
| Keywords: | influencing factor; regional differences; random forest |
| 分类号: | U6-9 |
| 文献标识码: | A |
| 摘要: | 选取培训机构地理位置、培训机构许可培训项目数、培训机构服务质量以及船员年龄、籍贯、已参加培训次数作为影响因子, 采用随机森林模型对浙江省船员选择培训机构的影响因素进行了分析. 结果表明 (1)地理位置对船员培训机构选择的影响最大, 可解释58.7%的船员选择培训机构的行为, 年龄对船员培训机构选择的影响最小; (2)影响因素的作用存在区域差异性, 同一影响因素对不同区域的船员选择培训机构的影响程度有所不同, 地理位置对舟山地区船员选择行为的影响最大, 对省内其他地区影响较小. |
| Abstract: | The geological location of the training institution, the number of training projects licensed by the training authorities, the quality of training services, the age of the ship crew, the place of birth of the crew, and the number of trainings having participated by the crew have been selected as the influencing factors in this study. The random forest model is used to analyze the factors influencing the selection of training institutions by crew members in Zhejiang Province. The results show that (1) Geographic location has the most significant impact on selecting the training institutions, which may account for 58.7% of the crew’s choice of training institutions; in comparison, age has the least influence. (2) The role of influencing factors varies according to regions. Also noted is that the same influencing factors have different impacts on crew’s selection of training institutions in different regions. Geographic location has the greatest impact on the crew’s selection preference in Zhoushan area, and less is found in other areas across the province. |
| 参考文献 /References: | [1] 关腾飞. 论述船员培训存在的问题及建议[J]. 珠江水运, 2003(8):25-26. [2] 邓慧云. 高等教育资源共享问题与对策研究[D]. 开封: 河南师范大学, 2016. [3] 刘炳恩, 隽志才, 李艳玲, 等. 居民出行方式选择非集计模型的建立[J]. 公路交通科技, 2008(5):116-120. [4] Meng C, Cheng T H, Gu X F, et al. Contribution of meteorological factors to particulate pollution during winters in Beijing[J]. Science of the Total Environment, 2019, 656:977-985. [5] Quinlan J R. Induction of decision trees[J]. Machine learning, 1986, 1(1):81-106. [6] Quinlan J R. C4.5: programs for machine learning[M]. San Diego: Morgan Kaufmann, 1993. [7] Breiman L. Random forests[J]. Machine learning, 2001, 45(1):5-32. [8] 丁良萍, 张智雄, 刘欢. 影响支持向量机模型语步自动识别效果的因素研究[J]. 数据分析与知识发现, 2019, 3(11):16-23. [9] 尹晓梅, 李梓铭, 熊亚军, 等. 2014-2017北京市气象条件和人为排放变化对空气质量改善的贡献评估[J]. 环境科学, 2019, 40(3):1011-1023. [10] 王文富. 企业人力资源结构的神经网络预测[J]. 天津大学学报(社会科学版), 2005, 7(1):20-22. [11] 王坤, 刘小杰, 刘二浩, 等. 基于AdaBoost算法的炉芯温度预测模型[J]. 钢铁研究学报, 2020, 32(5):363-369. [12] 柳本民, 寒. 基于SVM事故分类的连环追尾事故影响因素分析[J]. 交通信息与安全, 2020(1):43-51. [13] Li J M, Jin M J, Li H L. Exploring spatial influence of remotely sensed PM2.5 concentration using a developed deep convolutional neural network model[J]. International Journal of Environmental Research and Public Health, 2019, 16(3):E454. [14] 王超, 阚瑷珂, 曾业隆, 等. 基于随机森林模型的西藏人口分布格局及影响因素[J]. 地理学报, 2019, 74(4): 664-680. [15] 张荣花, 关宏志, 赵磊, 等. 考虑汽车共享服务的出行方式选择影响因素研究[J]. 交通运输研究, 2020, 6(3): 48-54. [16] 王慧芬, 王立晓, 孙小慧. 基于Logit模型的汽车共享换乘地铁选择行为研究[J]. 交通科技与经济, 2020, 22(4):33-38. [17] 练胜, 李晓达, 黄舒晴, 等. 基于分层Logit模型的自行车选择行为影响因素调研[J]. 科技与创新, 2017(23): 8-10. [18] 中华人民共和国海事局. 中华人民共和国海事局关于公布2019年1-11月海船船员培训机构适任考试及格率的公告[EB/OL]. []. http://www.msa.gov. cn/public/documents/document/mtax/nduy/~edisp/20191231101452703.wps. [19] 方匡南. 随机森林组合预测理论及其在金融中的应用[M]. 厦门: 厦门大学出版社, 2012. |
| 备注/Memo: | 收稿日期:2020-09-15.宁波大学学报（理工版）网址:http://journallg.nbu.edu.cn/ 基金项目:国家重点研发计划政府间国合重点专项（2017YFE9134700）;欧盟地平线2020项目（690713）;浙江海事局科技项目（HS2019000170）. 第一作者:袁玉峰（1993－）,男,安徽合肥人,在读硕士研究生,主要研究方向:港航技术与管理工程.E-mail:1593565982@qq.com *通信作者:郑彭军（1965－）,男,浙江慈溪人,教授,主要研究方向:海事技术.E-mail:zhengpengjun@nbu.edu.cn 宁波大学学报（理工版）网址：http://journallg.nbu.edu.cn/ |
