基于梯度提升迭代决策树模型的渔船转移数据挖掘

doi:10.19788/j.issn.2096-6369.210306

摘要/Abstract

摘要：

渔船转移是海洋渔船日常管理过程中的一项关键业务，也是所有渔船管理业务中涉及流程最多、数据传递量最大的业务，通过对大量渔船历史转移数据进行处理分析，可挖掘出与渔船转移活动相关的潜在决定性因子，对保障渔民经济利益和制定渔船管理政策等活动具有重要意义。本文基于中国渔政管理指挥系统中的渔船基础数据和渔船转移数据，并以浙江省为典型案例，选取2018年1月至2020年7月共计5641条渔船的历史转移业务数据进行数值化处理。采用梯度提升迭代决策树（GBDT）算法进行分类器逐级迭代，给出了特征分类结果与模型训练集，并最终构建了渔船被交易潜在可能性的单决策树和多决策树模型。通过模型中船龄、船长、船体材质、作业类型等渔船基本参数的权重，分析了渔民购置渔船的倾向性。结果表明：不同类型的渔船，被购置的可能性存在较大的差异，大船长、大吨位、高船龄、拖网及张网作业类型是渔船发生转移的重要决定因子。对比各项特征损失函数计算得到的损失值大小，20年船龄、大中型船长等特征的损失值比其他特征损失值小15%以上，意味着使用所选特征进行计算的分类识别率更高。本研究通过定量化分析渔民购置渔船的倾向性，可在渔船转移过程中最大化保障渔民的经济利益，同时可对渔船管理政策的制定起到辅助决策作用。

关键词: 渔船转移, GBDT算法, 决策树, 数据挖掘, 渔业大数据, 迭代决策树, 渔船管理

Abstract:

The purchase of a fishing vessel is a significant and complex process in the daily management of marine fishing fleets, and it yields the largest amount of data in all fishing vessel management operations. Through processing and analysis of the historical purchase data of fishing vessels, the potential decisive factors related to the purchase of fishing vessels can be found. This is significant to the protection of fishermen's economic interests and the development of fishing vessel management policies. We extracted and numerically processed the historical purchase data of fishing vessels from January 2018 to July 2020 using the physical and purchase data of fishing vessels in the Chinese Fishery Law Enforcement Command System (CFLECS) and taking Zhejiang Province as a typical case. The gradient boosting iterative decision tree (GBDT) algorithm was used to iterate the classifier regularly. We produced the results of feature classification and training set, and these were used to generate single decision tree and multiple decision tree models. We calculated the weight of the basic parameters of fishing vessels, such as length, material, and fishing type, to predict the potential possibility of fishing vessel transactions and to analyze the tendencies of fishermen when purchasing fishing vessels. The results indicate that age, length, trawler, and stow net are the principal determinants of fishing vessel transactions. The trawler and stow net vessel can only be obtained through the fishing vessel transaction. Thus, when the fishing vessel types are different, there is a great difference in the possibility of their being purchased. By comparing the loss functions of various features, we can find that the loss values of features with 20 years of age and ship length are more than 15% smaller than the loss values of other features, which means that the classification recognition rate calculated with selected features is higher. Consequently, quantitative analysis for fishermen's propensity to purchase fishing vessels can maximize fishermen's economic interests, and it can also play an auxiliary role in the formulation of fishing vessel management policy.

Key words: fishing vessel transaction, GBDT algorithm, decision tree, data mining, big data in fishery, Gradient Boosting Decision Tree, fishing vessel management

中图分类号:

S972.7

李怡德, 鲁峰, 朱勇, 徐硕, 孙璐. 基于梯度提升迭代决策树模型的渔船转移数据挖掘[J]. 农业大数据学报, 2021, 3(3): 55-61.

Yide Li, Feng Lu, Yong Zhu, Shuo Xu, Lu Sun. Data Mining for Fishing Vessel Purchase Based on Gradient Boosting Decision Tree Algorithm[J]. Journal of Agricultural Big Data, 2021, 3(3): 55-61.

图/表 4

表1

表2

表3

参考文献 31

1	王立华,黄其泉,徐硕,等.中国渔政管理指挥系统总体架构设计[J].中国农学通报,2015,10:261-268.
	Wang L H, Huang Q Q, Xu S, et al. The Overall Design of Chinese Fishery Law Enforcement Command System Architecture[J]. Chinese Agricultural Science Bulletin, 2015,10:261-268.
2	罗福才.船舶资产评估研究[D].大连:大连理工大学,2011.
	Luo F C. Study on Ship Assets Valuation[D]. Dalian: Dalian University of Technology,2011.
3	张添翼,孙胜祥,谢力.基于云隶属度支持向量机的舰船购置费时间序列预测[J].装备学院学报,2012,23(2):54-58.
	Zhang T Y, Sun S X, Xie L. Vessel Purchase Cost Time Series Forecasting Based on C-SVM[J]. Journal of Academy of Equipment, 2012,23(2):54-58.
4	YOON H, KIM S. Naval vessel spare parts demand forecasting using data mining[J]. Journal of Society of Korea Industrial and Systems Engineering, 2017, 40(4):253-259.
5	PUTTEN I E VAN, QUILLEROU E, GUYADER O. How Constrained? Entry into the French Atlantic Fishery through Second-Hand Vessel Purchase[J]. Ocean & Coastal Management, 2012, 69:50-57.
6	肖启俊,张延猛.基于BP神经网络的二手船价格评估研究[J].船舶工程,2013,35(2):100-103.
	Xiao Q J, Zhang Y M. Study on Calculating Second-hand Ship Price Based on BP Neural Network[J]. Ship Engineering, 2013,35(2):100-103.
7	HSIEH A C, CHOU H, LIN K, et al. Trade-Off relationship between the hire rates and exercise prices of purchase options in ship charter contracts:an option pricing application[J]. Journal of Marine Science and Technology, 2013, 21(3):268-277.
8	PARK K S, SEO Y J, KIM A R, et, al. Ship acquisition of shipping companies by sale & purchase activities for sustainable growth:exploratory Fuzzy-AHP application[J]. Sustainability, 2018, 10(6):1763.
9	PENA-TORRES J, DRESDNER J, QUEZADA F, et al. Collective share quotas and the role of fishermen's organizations in Ex-vessel price determination[J]. Marine Resource Economics, 2019, 34(4):361-385.
10	张仁颐.二手船购置价格的确定[J].上海交通大学学报,1996(10):71-74.
	Zhang R Y. Determination of Purchasing Price for Second Hand Ship[J]. Journal of Shanghai Jiaotong University, 1996(10):71-74.
11	魏黎, 林滨.船舶市场研究的方法论探讨[J].船艇,2006,(08):28-33.
	Wei L, Lin B. Study on the Methodology of Ship Marketing Research[J]. Ships & Yachts, 2006,(08):28-33.
12	李珩.船舶市场的规律性分析与发展研究[D].大连:大连海事大学,2007.
	Li H. Research on the Regularity Analysis and Development of the Ship Market[D]. Dalian: Dalian Maritime University,2007.
13	徐一军.大型半潜船工程项目的可行性与市场评估研究[D].上海:上海交通大学,2011.
	Xu Y J. Study on Feasibility and Market Evaluation for Large Semi-submersible Heavy Lift Vessel. Shanghai: Shanghai Jiao Tong University,2011.
14	李巍.浅析船舶价值的评估方法及评估程序[J].价值工程,2020,39(1):282-284.
	Li W. Analysis on the Evaluation Method and Evaluation Procedure of Ship Value[J]. Value Engineering, 39(1):282-284.
15	PENG Y, FLACH P A. Soft discretization to enhance the continuous decision tree induction[J]. Integrating Aspects of Data Mining, Decision Support and Meta-Learning, 2001, 1(34):109-118.
16	梁杰,陈嘉豪,张雪芹,等.基于独热编码和卷积神经网络的异常检测[J].清华大学学报(自然科学版),2019,59(7):523-529.
	Liang J, Chen J H, Zhang X Q, et al. One-hot encoding and convolutional neural network based anomaly detection. Journal of Tsinghua University(Science and Technology),2019,59(7):523-529.
17	李永生,王沉平.国内海洋渔船安全风险评估体系的研究[J].浙江海洋大学学报(自然科学版),2020,39(2):180-186.
	Li Y S, Wang C P. Research on Safety Risk Assessment System of Domestic Marine Fishing Vessels[J]. Journal of Zhejiang Ocean University (Natural Science),2020,39(2):180-186.
18	Myles A J, Feudale R N, Liu Y, et al. An Introduction to Decision Tree Modeling[J]. Journal of Chemometrics,2004,18(6): 275-285.
19	FRIEDMAN J H. Greedy function approximation:a gradient boosting machine[J]. Annals of Statistics, 2001, 29(5):1189-1232.
20	段大高,盖新新,韩忠明,等.基于梯度提升决策树的微博虚假消息检测[J].计算机应用,2018,38(2):410-414, 420.
	Duan D G, Gai X X, Han Z M, et al. Micro-blog Misinformation Detection Based on Gradient Boost Decision Tree[J]. Journal of Computer Applications,2018,38(2):410-414, 420.
21	FRIEDMAN J H, HASTIEV T, TIBSHIRANI R. Additive logistic regression:a statistical view of boosting[J]. The Annals of Statistics, 2000, 28(2):337-407.
22	刘红岩,陈剑,陈国青.数据挖掘中的数据分类算法综述[J].清华大学学报(自然科学版),2002(6):727-730.
	Liu H Y, Chen J, Chen G Q. Review of Classification Algorithms for Data Mining[J]. Tsinghua University(Science and Technology), 2002(6):727-730.
23	Pillay A, Wang J, Wall A, et al. Formal Safety Assessment of Fishing Vessels: Risk and Maintenance Modelling[J]. Journal of Marine Engineering & Technology,2004, 3(1):29-42.
24	Huang H G, Hong F, Liu J, et al. FVID: Fishing Vessel Type Identification Based on VMS Trajectories[J]. Journal of Ocean University of China (Oceanic and Coastal Sea Research),2019,18(2):403-412.
25	林光纪.重构我国渔业捕捞准入制度的理论探讨[J].福建水产,2012,34(2):163-170.
	Lin G J. Theoretical Study on The Reconstruction of China's Fishing Access Institution[J].Journal of Fujian Fisheries,2012,34(2):163-170.
26	王颖,潘亚男.渔船燃油补贴的金融效应—以赣榆县下口村为例[J].中国渔业经济,2016,34(3):18-22.
	Wang Y, Pan Y N. Financial Effect of Fishing bBoats with Fuel Subsidies: Based on Ganyu County Village[J]. Chinese Fisheries Economics,2016,34(3):18-22.
27	钟小金,俞国平,周伟,等.科学实施渔业柴油补贴政策的建议[J].渔业信息与战略,2012,27(04):272-276.
	Zhong X J, Yu G P, Zhou W, et al. Advices on Application of Diesel Subsidies in Fishery[J]. Fishery Information & Strategy, ,2012,27(04):272-276.
28	牛琨,陈俊亮,张舒博.决策树分类准确率极限的研究[J].计算机工程,2007(10):222-224.
	Niu K, Chen J L, Zhang S B. Research on Classification Accuracy Limit of Decision Tree[J]. Computer Engineering, 2007(10):222-224.
29	Hall M A, Holmes G. Benchmarking attribute selection techniques for discrete class data mining[J]. IEEE Transactions on Knowledge & Data Engineering, 2003, 15(6):1437-1447.
30	Svensson P, Rodwell L D, Attrill M J. The Perceptions of Local Fishermen towards a Hotel Managed Marine Reserve in Vietnam[J]. Ocean & Coastal Management, 2010, 53(3):114-122.
31	Mozumder M M H, Shamsuzzaman M, Rashed-Un-Nabi, et al. Socio-Economic Characteristics and Fishing Operation Activities of the Artisanal Fishers in the Sundarbans Mangrove Forest, Bangladesh[J]. Turkish Journal of Fisheries and Aquatic Sciences,2018,18(6):789-799.

特征参数	参数类型	值域
是否老旧	布尔型	0或1
船龄(年)	整数型	1~100
船长(米)	浮点型	0.1~50
船体材质	整数型	1~5
作业类型	整数型	1~9
油价补贴档位	整数型	1~14
吨位与船长比	浮点型	0.1~10.5

特征	分类区间	分类后特征值
船龄	船龄<10	1
	10≤船龄<20	2
	船龄≥20	3
船体材质	船体材质∈[钢制，水泥，玻璃钢]	1
船体材质	船体材质∈[木制，其他]	2
作业类型	船体材质∈[刺网]	1
	船体材质∈[围网]	2
	船体材质∈[拖网]	3
	船体材质∈[张网]	4
	船体材质∈[钓具]	5
	船体材质∈[耙刺，陷阱，笼壶，杂渔具]	6

学习率 r	树的数量 t（个）	最大深度 d	准确率
10%	60	7	61.7%
10%	90	7	62.9%
10%	60	11	64.9%
10%	90	11	65.9%

[1]	薛沐涵, 徐硕, 鲁峰, 朱勇, 吴建光, 王义刚. 渔船渔港综合管理服务平台构建与应用[J]. 农业大数据学报, 2021, 3(3): 45-54.
[2]	陈富桥, 凌晨. 茶叶全产业链大数据中心功能设计与开发进展[J]. 农业大数据学报, 2021, 3(2): 54-66.
[3]	程锦祥, 孙英泽, 胡婧, 闫雪, 欧阳海鹰. 我国渔业大数据应用进展综述[J]. 农业大数据学报, 2020, 2(1): 11-20.
[4]	张萌, 董伟, 钱蓉, 杨前进, 张立平. 安徽省植保大数据平台建设与应用展望[J]. 农业大数据学报, 2020, 2(1): 36-44.
[5]	鲁峰,王立华,徐硕. 渔业科学数据中心建设研究[J]. 农业大数据学报, 2019, 1(3): 57-70.
[6]	赵春江. 植物表型组学大数据及其研究进展[J]. 农业大数据学报, 2019, 1(2): 5-14.
[7]	李晓曼,张扬,徐倩,谢能付. 基于文献计量的植物表型组学研究进展分析[J]. 农业大数据学报, 2019, 1(2): 64-75.
[8]	吴蕾,梁晓贺,乌吉斯古楞,王瑞. 基于词向量的检索扩展方法与农业领域实证[J]. 农业大数据学报, 2019, 1(2): 114-120.
[9]	崔运鹏, 王健, 刘娟. 基于深度学习的自然语言处理技术的发展及其在农业领域的应用[J]. 农业大数据学报, 2019, 1(1): 38-44.
[10]	姜侯, 杨雅萍, 孙九林. 农业大数据研究与应用[J]. 农业大数据学报, 2019, 1(1): 5-10.