基于机器学习的半滑舌鳎投饵量预测模型研究

doi:10.19640/j.cnki.jtau.2025.01.013

天津农学院学报 ›› 2025, Vol. 32 ›› Issue (1): 69-76.doi: 10.19640/j.cnki.jtau.2025.01.013

基于机器学习的半滑舌鳎投饵量预测模型研究

佘诗怡¹, 田云臣^{1,2,3,通信作者}, 郑杰¹

1.天津农学院计算机与信息工程学院,天津 300392;
2.天津市水产生态及养殖重点实验室,天津 300392;
3.农业农村部智慧养殖重点实验室（部省共建）,天津 300392

收稿日期:2024-02-22 发布日期:2025-03-04
通讯作者: 田云臣（1967—）,男,教授,硕士,主要从事农业物联网、农业大数据、农业信息化、智慧农业方面研究。E-mail：tianyunchen@tjau.edu.cn。
作者简介:佘诗怡（1996—）,女,硕士在读,主要从事机器学习、水产养殖智能化方面研究。E-mail：543345204@qq.com。
基金资助:
国家重点研发计划项目（2020YFD0900600）; 国家现代农业产业技术体系资助项目（CARS-47）; 天津市海水养殖产业技术体系项目（ITTMRS2021000）; 天津农学院研究生科研创新项目（2021XY016）

Study on Cynoglossus semilaevis feeding model based on machine learning

She Shiyi¹, Tian Yunchen^{1,2,3,Corresponding Author}, Zheng Jie¹

1. College of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300392, China;
2. Tianjin Key Laboratory of Aqua-ecology and Aquaculture, Tianjin 300392, China;
3. Key Laboratory of Intelligent Breeding（Co-construction by Ministry and Province）, Ministry of Agriculture and Rural Affairs, Tianjin 300392, China

Received:2024-02-22 Published:2025-03-04

摘要/Abstract

摘要： 为解决半滑舌鳎养殖中适宜投饲量确定的问题,许多研究者通过收集大量实验数据制定投饲率表,然而投饲率表法存在精细程度不足和依赖人工经验等问题,不利于实现养殖投饲过程的标准化和自动化。为克服这一问题,本文通过收集养殖企业实际养殖记录数据,采用机器学习方法构建半滑舌鳎投饵量预测模型。模型以与半滑舌鳎摄食相关的29项信息作为特征,首先采用Pearson相关系数、Spearman相关系数和Kendall相关系数进行相关性分析,其次采用主成分分析法进行数据降维,再次将降维的数据集按7∶2∶1随机划分为训练集、验证集和测试集,分别用于训练模型、调整模型参数和评估模型性能。为探讨基于不同算法构建机器学习模型对投饵量的预测效果,在训练集上分别构建了BP神经网络、支持向量机和随机森林模型,其中BP神经网络模型在测试集上的平均绝对误差（MAE）为0.210,均方根误差（RMSE）为0.301,决定系数（R²）为0.802;支持向量机模型在测试集上的MAE为0.248,RMSE为0.370,R²为0.701;随机森林模型在测试集上的MAE为0.106,RMSE为0.185,R²为0.925。结果表明,在三种模型中,基于随机森林的投饵量预测模型预测结果最优,最适合执行养殖中的投饲量确定工作,有利于实现投饲过程的标准化和自动化。

关键词: 机器学习, 半滑舌鳎, 投饵量

Abstract: In order to solve the problem of determining the appropriate feeding amount in Cynoglossus semilaevis aquaculture, researchers made the feeding rate table by collecting a lot of experimental data. However, the feeding rate table has problems, such as insufficient precision, reliance on manual experience and so on, which is not conducive to the realization of standardization and automation in feeding processes. To overcome this problem, this study collected the actual breeding record data of breeding enterprises and used machine learning methods to build a prediction model for the feeding amount of Cynoglossus semilaevis. The model was characterized by 29 items of information related to the feeding of Semilaevis. Firstly, Pearson correlation coefficient, Spearman correlation coefficient and Kendall correlation coefficient were used for correlation analysis. Secondly, principal component analysis method was used to reduce the data dimension. Then the dimensionally reduced data set was randomly divided into training set, verification set and test set in a ratio of 7∶2∶1, which were used to train the model, adjust model parameters and evaluate model performance respectively. In order to explore the prediction effect of machine learning models based on different algorithms on the amount of bait, BP neural network, support vector machine and random forest models were constructed on the training set. The average absolute error of the BP neural network model on the test set was（MAE）0.210, the root mean square error（RMSE）was 0.301, and the coefficient of determination（R²）was 0.802; The MAE of the support vector machine model on the test set was 0.248, the RMSE was 0.370, and the R² was 0.701; Of the random forest model on the test set the MAE was 0.106, the RMSE was 0.185, and the R² was 0.925. The results demonstrate that among the three models, the random forest model which performs best in feeding amount prediction, is the most suitable one for the feeding deciding task in actual Cynoglossus semilaevis aquaculture, and is conducive to the realization of standardization and automation in feeding processes.

Key words: machine learning, Cynoglossus semilaevis, feeding amount

中图分类号:

S967.9

佘诗怡, 田云臣, 郑杰. 基于机器学习的半滑舌鳎投饵量预测模型研究[J]. 天津农学院学报, 2025, 32(1): 69-76.

She Shiyi, Tian Yunchen, Zheng Jie. Study on Cynoglossus semilaevis feeding model based on machine learning[J]. Journal of Tianjin Agricultural University, 2025, 32(1): 69-76.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xuebao.tjau.edu.cn/CN/10.19640/j.cnki.jtau.2025.01.013

http://xuebao.tjau.edu.cn/CN/Y2025/V32/I1/69

参考文献

[1] HOU J K,TIAN Y C,SUN Z L.Study on growth model of tongue sole based on parallel BP neural network[C]//Association for Computing Machinery. Proceedings of the 2021 7th International Conference on Computing and Artificial Intelligence. New York:Association for Computing Machinery,2021:132-137.
[2] ANSARI F A,GULDHE A,GUPTA S K,et al.Improving the feasibility of aquaculture feed by using microalgae[J]. Environmental Science and Pollution Research,2021,28(32):43234-43257.
[3] 柳阳,李勇,王华,等. 投喂方式对工业化养殖半滑舌鳎生长、摄食、免疫及水质的影响[J]. 水产科学,2015,34(8):469-475.
[4] 周兴,牛化欣. 颗粒饲料和杂鱼对半滑舌鳎生长和饲料利用率的影响[J]. 饲料工业,2020,41(8):48-52.
[5] 黄亚冬,王庆奎,徐大为,等. 日投饲率对半滑舌鳎生长的影响[J]. 河北渔业,2021,332(8):1-5.
[6] CHATVIJITKUL S,BOYD C E,DAVIS D A,et al.Pollution potential indicators for feed-based fish and shrimp culture[J]. Aquaculture,2017,477:43-49.
[7] MEI Y,HOU Z,GAO Q,et al.Effects of different feeding rations on the CO₂ fluxes at water-air interface and energy budget of sea cucumber Apostichopus japonicus (Selenka)[J]. Aquaculture Reports,2023,28:101447.
[8] 于建霖,刘敏,康会会,等. 天津市海水工厂化养殖尾水水质监测与处理情况调查[J]. 天津农学院学报,2023,30(6):51-61.
[9] 褚志鹏,金佳利,陈细华,等. 不同投喂率和投喂频率对大杂交鲟幼鱼生长、体成分和生化指标的影响[J]. 中国水产科学,2020,27(2):177-185.
[10] 吴俊男,鲍婷,王梦杰,等. 投喂率对稻-黄颡鱼共作系统气态氮散失和饲料氮利用率的影响[J]. 农业资源与环境学报,2022,39(4):749-757.
[11] 赵思琪,丁为民,张建凯. 基于模糊逻辑控制的鱼塘养殖精准投饲系统设计与试验[J]. 农业现代化研究,2019,40(3):527-536.
[12] 陈澜,杨信廷,孙传恒,等. 基于自适应模糊神经网络的鱼类投喂预测方法研究[J]. 中国农业科技导报,2020,22(2):91-100.
[13] CHEN L,YANG X,SUN C,et al.Feed intake prediction model for group fish using the MEA-BP neural network in intensive aquaculture[J]. Information Processing in Agriculture,2020,7(2):261-271.
[14] 隋金柱,田云臣,李振忠,等. 基于鱼类摄食行为的智能投饲技术研究进展[J]. 天津农学院学报,2022,29(2):63-68.
[15] 张峻铭,郁二蒙,孙金辉. 水体生态因子对养殖鱼类品质影响研究进展[J]. 天津农学院学报,2022,29(2):69-75.
[16] 谷雪勤,王庆奎,王洋. 海水鱼循环水养殖系统中细菌群落结构研究进展[J]. 天津农学院学报,2022,29(2):76-84.
[17] 聂国梁,王庆奎,赵鸿昊,等. 溶解氧对半滑舌鳎呼吸频率、生理生化指标和组织结构的影响[J]. 天津农学院学报,2024,31(1):54-60.
[18] 典彩华,田云臣. 基于机器学习的梭鲈鱼生长发育模型[J]. 天津农学院学报,2021,28(2):72-78.
[19] 何津民,张丽珍. 基于自注意力机制和CNN-LSTM深度学习的对虾投饵量预测模型[J]. 大连海洋大学学报,2022,37(2):304-311.
[20] 孙雪倩,李丽,董双林,等. 基于不同投喂策略的循环水养殖系统氨氮预测模型[J]. 水产学报,49(1):137-148.

基于机器学习的半滑舌鳎投饵量预测模型研究

Study on Cynoglossus semilaevis feeding model based on machine learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 12

编辑推荐

Metrics

本文评价

[1]	杨艳凤, 王庆奎, 石洪玥, 徐大为, 孙学亮. 养殖与野生半滑舌鳎肌肉营养成分对比分析[J]. 天津农学院学报, 2024, 31(2): 56-62.
[2]	马国宁, 田云臣, 胡金城, 赵晴晴, 隋金柱, 郑杰. 一家典型海水工厂化循环水养殖系统运行效果分析——以半滑舌鳎为例[J]. 天津农学院学报, 2024, 31(2): 71-77.
[3]	聂国梁, 王庆奎, 赵鸿昊, 王祯辉, 付建东, 李强. 溶解氧对半滑舌鳎呼吸频率、生理生化指标和组织结构的影响[J]. 天津农学院学报, 2024, 31(1): 54-60.
[4]	王妍, 王庆奎, 方珍珍, 石洪玥, 吴京霞, 郑海玲. 半滑舌鳎幼鱼不同阶段肠道和肝脏的组织切片观察[J]. 天津农学院学报, 2023, 30(6): 32-40.
[5]	葛仑华, 江博赟, 孙敬锋, 吕爱军, 胡秀彩, 陈丽梅. 三种DNA提取方法对半滑舌鳎肠道菌群高通量测序结果的影响[J]. 天津农学院学报, 2022, 29(3): 29-35.
[6]	刘厚孚, 谭静, 胡秀彩, 管振国, 吕爱军, 孙敬锋. 半滑舌鳎细胞分裂周期蛋白42基因克隆与结构预测[J]. 天津农学院学报, 2022, 29(3): 36-42.
[7]	典彩华, 田云臣. 基于机器学习的梭鲈鱼生长发育模型[J]. 天津农学院学报, 2021, 28(2): 72-78.
[8]	谭静, 胡秀彩, 吕爱军, 孙敬锋, 刘小雪, 廉正义. 半滑舌鳎黏蛋白MUC5AC基因的克隆与结构预测[J]. 天津农学院学报, 2019, 26(2): 51-56.
[9]	葛婧, 郭永军, 王庆奎, 徐大为, 孙学亮, 陈成勋, 邢克智. 连翘、黄连、穿心莲对半滑舌鳎血液抗氧化指标的影响[J]. 天津农学院学报, 2016, 23(4): 21-27.
[10]	方珍珍, 王庆奎, 陈成勋, 郭永军, 邢克智. 复方中草药对半滑舌鳎和盾纤毛虫的急性毒性研究[J]. 天津农学院学报, 2015, 22(4): 6-8.
[11]	胡璇, 孙敬锋, 陈成勋, 邢克智. 养殖半滑舌鳎腹水病的病原分离鉴定及药物敏感性分析[J]. 天津农学院学报, 2014, 21(3): 12-16.
[12]	赵从明, 刘刚. 养殖密度对半滑舌鳎成鱼生长的影响[J]. 天津农学院学报, 2013, 20(3): 34-36.