Page 216 - 《水产学报》2025年第7期

曹正良，等 水产学报, 2025, 49(7): 079616

342-349. [19] 徐立鸿, 黄薪, 刘世晶. 基于改进 LRCN 的鱼群摄食强度分类
[13] 袁红春, 高子玥, 张天蛟. 基于改进的 XGBoost 模型预测南 模型 [J]. 农业机械学报, 2022, 53(10): 236-241.
太平洋长鳍金枪鱼资源丰度 [J]. 海洋湖沼通报, 2022, 44(2): Xu L H, Huang X, Liu S J. Recognition of fish feeding intens-
112-120. ity based on improved LRCN[J]. Transactions of the Chinese
Yuan H C, Gao Z Y, Zhang T J. Prediction of albacore tuna Society for Agricultural Machinery, 2022, 53(10): 236-241 (in
abundance in south Pacific based on improved XGBoost Chinese).
model[J]. Transactions of Oceanology and Limnology, 2022,
[20] Althubiti S A, Alenezi F, Shitharth S, et al. Circuit manufactur-
44(2): 112-120 (in Chinese).
ing defect detection using VGG16 convolutional neural net-
[14] 袁红春, 陈骢昊. 基于融合深度学习模型的长鳍金枪鱼渔情
works[J]. Wireless Communications and Mobile Computing,
预测研究 [J]. 渔业现代化, 2019, 46(5): 74-81.
2022, 2022(1): 1070405.
Yuan H C, Chen C H. Prediction of Thunnus alalunga fishery
[21] Aravind K R, Raja P. Disease classification in eggplant using
based on fusion deep learning model[J]. Fishery Modernization,
pre-trained VGG16 and MSVM[J]. Scientific Reports, 2020,
2019, 46(5): 74-81 (in Chinese).
10(1): 2322.
[15] 王印庚, 于永翔, 蔡欣欣, 等. 基于 Deep Forest 算法的对虾急
[22] Theckedath D, Sedamkar R R. Detecting affect states using
性肝胰腺坏死病 (AHPND) 预警数学模型构建 [J]. 渔业科学
VGG16, ResNet50 and SE-ResNet50 networks[J]. SN Com-
进展, 2024, 45(3): 171-181.
puter Science, 2020, 1(2): 79.
Wang Y G, Yu Y X, Cai X X, et al. Construction of an early
[23] 林朗, 王让定, 严迪群, 等. 基于逆梅尔对数频谱系数的回放
warning mathematical model for Litopenaeus vannamei
语音检测算法 [J]. 电信科学, 2018, 34(5): 90-98.
AHPND based on the deep forest algorithm[J]. Progress in
Lin L, Wang R D, Yan D Q, et al. A playback speech detection
Fishery Sciences, 2024, 45(3): 171-181 (in Chinese).
algorithm based on log inverse Mel-frequency spectral coeffi-
[16] 杨雨欣, 于红, 杨宗轶, 等. 基于 Mel 声谱图与改进 SERes-
cient[J]. Telecommunications Science, 2018, 34(5): 90-98 (in
Net 的鱼类行为识别 [J]. 渔业现代化, 2024, 51(1): 56-63.
Chinese).
Yang Y X, Yu H, Yang Z Y, et al. Fish behavior recognition
[24] 杨真真, 匡楠, 范露, 等. 基于卷积神经网络的图像分类算法
based on Mel spectrogram and improved SEResNet[J]. Fishery
综述 [J]. 信号处理, 2018, 34(12): 1474-1489.
Modernization, 2024, 51(1): 56-63 (in Chinese).
Yang Z Z, Kuang N, Fan L, et al. Review of image classifica-
[17] 袁培森, 宋进, 徐焕良. 基于残差网络和小样本学习的鱼图像
tion algorithms based on convolutional neural networks[J]. Jour-
识别 [J]. 农业机械学报, 2022, 53(2): 282-290.
nal of Signal Processing, 2018, 34(12): 1474-1489 (in Chinese).
Yuan P S, Song J, Xu H L. Fish image recognition based on
[25] Thakkar V, Tewary S, Chakraborty C. Batch Normalization in
residual network and few-shot learning[J]. Transactions of the
convolutional neural networks — a comparative study with
Chinese Society for Agricultural Machinery, 2022, 53(2): 282-
290 (in Chinese). CIFAR-10 data[C]// IEEE. 2018 Fifth International Conference
[18] 蔡卫明, 庞海通, 张一涛, 等. 基于卷积神经网络的养殖鱼类 on Emerging Applications of Information Technology (EAIT).
品种识别模型 [J]. 水产学报, 2022, 46(8): 1369-1376. Kolkata, India: IEEE, 2018: 1-5.
Cai W M, Pang H T, Zhang Y T, et al. Recognition model of [26] Bronskill J, Gordon J, Requeima J, et al. Tasknorm: Rethink-
farmed fish species based on convolutional neural network[J]. ing batch normalization for meta-learning[C]// GRLB Work-
Journal of Fisheries of China, 2022, 46(8): 1369-1376 (in shop. Proceedings of the 37th International Conference on
Chinese). Machine Learning, Vienna: PMLR, 2020: 1153-1164.

https://www.china-fishery.cn 中国水产学会主办 sponsored by China Society of Fisheries
10