[1]袁红春,王敏,刘慧,等.基于特征交互与卷积网络的渔场预测模型[J].江苏农业学报,2021,(06):1501-1509.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
 YUAN Hong-chun,WANG Min,LIU Hui,et al.Fishing ground prediction model based on feature interaction and convolutional network[J].,2021,(06):1501-1509.[doi:doi:10.3969/j.issn.1000-4440.2021.05.019]
点击复制

基于特征交互与卷积网络的渔场预测模型()
分享到:

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2021年06期
页码:
1501-1509
栏目:
畜牧兽医·水产养殖
出版日期:
2021-12-30

文章信息/Info

Title:
Fishing ground prediction model based on feature interaction and convolutional network
作者:
袁红春12王敏1刘慧1陈冠奇1
(1.上海海洋大学信息学院,上海201306;2.农业农村部渔业信息重点实验室,上海201306)
Author(s):
YUAN Hong-chun12WANG Min1LIU Hui1CHEN Guan-qi1
(1.College of Information Technology, Shanghai Ocean University, Shanghai 201306,China;2.Key Laboratory of Fisheries Information,Ministry of Agriculture and Rural Affairs,Shanghai 201306,China)
关键词:
长鳍金枪鱼Cross网络卷积神经网络特征交互
Keywords:
Thunnus alalungaCross network convolutional neural networkfeature interaction
分类号:
S931.41
DOI:
doi:10.3969/j.issn.1000-4440.2021.05.019
文献标志码:
A
摘要:
长鳍金枪鱼是南太平洋渔业生产中主要的捕捞对象,准确预测其渔场分布对提高渔业捕捞效率具有重要意义。针对传统渔场预测方法预测精度低的问题,本研究提出一种基于特征交互与卷积网络的渔场预测模型——CNN-Cross。该模型引入Embedding层对数据进行处理,解决了One-Hot Encoding(独热编码)带来的特征稀疏性问题以及手动特征工程对结果的影响。同时,引入Cross网络提取特征之间的交互信息,消除了单特征对目标拟合不足的问题,并且结合CNN网络对Embedding层生成的二维特征图进行高阶隐藏信息提取,最后将两部分网络提取到的特征融合,输出分类结果。使用渔业数据对模型预测效果进行验证,结果表明,模型预测南太平洋渔场总召回率达到87.4%,中心渔场召回率达到89.4%。表明,将特征交互网络与卷积神经网络相结合可以明显提高渔场预报精度,且精度能够较好地满足现实渔业作业需求。
Abstract:
Thunnus alalunga is the main fishing target of fishery production in the South Pacific Ocean. It is of great significance to accurately predict the fishery distribution of T. alalunga for improving fishery efficiency. In view of lack of accuracy of traditional fishery prediction methods, this paper proposed a fishery prediction model based on feature interaction and convolutional network—CNN-Cross. In this model, the Embedding layer was introduced to process the data, which solved the problem of feature sparsity caused by One-Hot Encoding and the influence of manual feature engineering on the result. At the same time, the Cross network was introduced to extract interactive information between different features to eliminate the problem of insufficient target fitting by single feature, and the two-dimensional feature map generated by the Embedding layer was extracted with the CNN network for high-order hidden information extraction. Finally, the features extracted by two networks were fused and the classification results were output. The effect of the model was verified by fishery data. The results showed that the predicted total recall rate of the South Pacific fishery reached 87.4%, and that of the central fishing ground reached 89.4%. The research results show that the combination of feature interaction network and convolutional neural network can obviously improve the accuracy of fishery forecast, and the accuracy can better meet the needs of practical fishery operations.

参考文献/References:

[1]范永超,陈新军,汪金涛. 基于多因子栖息地指数模型的南太平洋长鳍金枪鱼渔场预报[J].海洋湖沼通报,2015(2):36-44.
[2]郭刚刚,张胜茂,樊伟,等. 基于表层及温跃层环境变量的南太平洋长鳍金枪鱼栖息地适应性指数模型比较[J].海洋学报,2016,38(10):44-51.
[3]王德芬,王玉堂,杨子江,等. 我国渔业多功能性的研究与思考[J].中国水产, 2012(1):15-17.
[4]苗振清,黄锡昌. 远洋金枪鱼渔业[M].上海:上海科学技术文献出版社,2003.
[5]BRIAND K, MOLONY B, LEHODEY P. A study on the variability of albacore (Thunnus alalunga) longline catch rates in the southwest Pacific Ocean[J]. Fisheries Oceanography, 2011, 20(6): 517-529.
[6]ZAINUDDIN M, SAITOH K, SAITOH S E I I. Albacore (Thunnus alalunga) fishing ground in relation to oceanographic conditions in the western North Pacific Ocean using remotely sensed satellite data[J]. Fisheries Oceanography, 2008, 17(2): 61-73.
[7]崔雪森,唐峰华,张衡,等. 基于朴素贝叶斯的西北太平洋柔鱼渔场预报模型的建立[J].中国海洋大学学报(自然科学版),2015,45(2):37-43.
[8]张孝民,石永闯,李凡,等. 基于MAXENT模型预测西北太平洋秋刀鱼潜在渔场[J].上海海洋大学学报,2020,29(2):280-286.
[9]宋利明,周建坤,沈智宾,等. 基于支持向量机的库克群岛海域长鳍金枪鱼栖息环境综合指数[J].海洋通报,2017,36(2):195-208.
[10]ZHOU P, LI P, ZHAO S, et al. Feature interaction for streaming feature selection[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020,10:1-12.
[11]GUO H F, TANG R M, YE Y M, et al. DeepFM: a factorization-machine based neural network for CTR prediction[C]//SIERRA C. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence. Melbourne: International Joint Conferences on Artificial Intelligence, 2017: 1725-1731.
[12]CHENG H T, KOC L, HARMSEN J, et al. Wide & deep learning for recommender systems[C]//KARATZOGLOU A, HIDASI B, TIKK D, et al. Proceedings of the 1st workshop on deep learning for recommender systems. New York: Association for Computing Machinery, 2016: 7-10.
[13]周为峰,黎安舟,纪世建, 等. 基于贝叶斯分类器的南海黄鳍金枪鱼渔场预报模型[J]. 海洋湖沼通报,2018(1):116-122.
[14]陈雪忠,樊伟,崔雪森,等. 基于随机森林的印度洋长鳍金枪鱼渔场预报[J].海洋学报(中文版),2013,35(1):158-164.
[15]RENDLE S. Factorization machines[C]//HINCHEY M, BERGMAN L A, WANG W P, et al. 2010 IEEE International Conference on Data Mining. Los Alamitos: IEEE Computer Society, 2010: 995-1000.
[16]WANG R, FU B, FU G, et al. Deep & cross network for ad click predictions[C]//ACM Special Interest Group on Knowledge Discovery in Data. Proceedings of the ADKDD′17. New York: Association for Computing Machinery, 2017: 1-7.
[17]LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[18]周飞燕,金林鹏,董军. 卷积神经网络研究综述[J].计算机学报,2017,40(6):1229-1251.
[19]邱锡鹏. 神经网络与深度学习[M]. 北京:机械工业出版社,2019:110-115.
[20]AYZEL G, HEISTERMANN M, SOROKIN A, et al. All convolutional neural networks for radar-based precipitation nowcasting[J]. Procedia Computer Science, 2019, 150: 186-192.
[21]崔雪森,唐峰华,周为峰,等. 基于支持向量机的西北太平洋柔鱼渔场预报模型构建[J].南方水产科学,2016,12(5):1-7.
[22]袁红春,陈冠奇,张天蛟,等. 基于全卷积网络的南太平洋长鳍金枪鱼渔场预报模型[J].江苏农业学报,2020,36(2):423-429.

相似文献/References:

[1]袁红春,陈冠奇,张天蛟,等.基于全卷积网络的南太平洋长鳍金枪鱼渔场预报模型[J].江苏农业学报,2020,(02):423.[doi:doi:10.3969/j.issn.1000-4440.2020.02.024]
 YUAN Hong-chun,CHEN Guan-qi,ZHANG Tian-jiao,et al.Fishing ground forecast model of albacore tuna based on fully convolutional networks in the South Pacific[J].,2020,(06):423.[doi:doi:10.3969/j.issn.1000-4440.2020.02.024]
[2]袁红春,张硕,陈冠奇.基于双模态深度学习模型的渔场渔情预报[J].江苏农业学报,2021,(02):435.[doi:doi:10.3969/j.issn.1000-4440.2021.02.021]
 YUAN Hong-chun,ZHANG Shuo,CHEN Guan-qi.Fishery forecasting in the fishing ground based on dual-modal deep learning model[J].,2021,(06):435.[doi:doi:10.3969/j.issn.1000-4440.2021.02.021]

备注/Memo

备注/Memo:
收稿日期:2021-04-08基金项目:国家自然科学基金项目(41776142);国家重点研发计划项目(2018YFD0701003)作者简介:袁红春(1971-),男,江苏海门人,博士,教授,主要从事专家系统、智能计算、智能信息处理等研究。(E-mail)hcyuan@shou.edu.cn
更新日期/Last Update: 2022-01-07