Page 38 - 《水产学报》2025年第7期

张东，等 水产学报, 2025, 49(7): 079103

[13] Rathi D, Jain S, Indu S. Underwater fish species classification [25] Rastegari H, Nadi F, Lam S S, et al. Internet of Things in
using convolutional neural network and deep aquaculture: a review of the challenges and potential solutions
learning[C]//IEEE. 2017 Ninth International Conference on based on current and future trends[J]. Smart Agricultural Tech-
Advances in Pattern Recognition (ICAPR). Bangalore, India: nology, 2023, 4: 100187.
IEEE, 2017: 1-6. [26] Huang Y P, Khabusi S P. Artificial intelligence of things
[14] Han F F, Zhu J C, Liu B, et al. Fish shoals behavior detection (AIoT) advances in aquaculture: a review[J]. Processes, 2025,
based on convolutional neural network and spatiotemporal 13(1): 73.
information[J]. IEEE Access, 2020, 8: 126907-126926. [27] O’Donncha F, Stockwell C L, Planellas S R, et al. Data driven
[15] Iqbal M A, Wang Z J, Ali Z A, et al. Automatic fish species insight into fish behaviour and their use for precision aquacul-
classification using deep convolutional neural networks[J]. ture[J]. Frontiers in Animal Science, 2021, 2: 695054.
Wireless Personal Communications, 2021, 116(2): 1043-1053. [28] Hu J, Zhao D D, Zhang Y F, et al. Real-time nondestructive fish
[16] Ubina N, Cheng S C, Chang C C, et al. Evaluating fish feeding behavior detecting in mixed polyculture system using deep-
intensity in aquaculture with convolutional neural networks[J]. learning and low-cost devices[J]. Expert Systems with Applica-
Aquacultural Engineering, 2021, 94: 102178. tions, 2021, 178: 115051.
[17] Huang J Z, Yu X N, Chen X W J, et al. Recognizing fish beha- [29] Kadota M, Torisawa S, Takagi T. Quantitative assessment and
vior in aquaculture with graph convolutional network[J]. analysis of fish behavior in closed systems using information
Aquacultural Engineering, 2022, 98: 102246. entropy[J]. Fishes, 2024, 9(6): 224.
[18] Iqbal U, Li D L, Akhter M. Intelligent diagnosis of fish beha- [30] Aung T, Abdul Razak R, Rahiman Bin Md Nor A. Artificial
vior using deep learning method[J]. Fishes, 2022, 7(4): 201. intelligence methods used in various aquaculture applications: a
[19] Zhao J, Bao W J, Zhang F D, et al. Modified motion influence systematic literature review[J]. Journal of the World Aquacul-
map and recurrent neural network-based monitoring of the local ture Society, 2025, 56(1): e13107.
unusual behaviors for fish school in intensive aquaculture[J]. [31] Martinez-Alpiste I, De Tailly J B, Alcaraz-Calero J M, et al.
Aquaculture, 2018, 493: 165-175. Machine learning-based understanding of aquatic animal beha-
[20] 彭秋珺, 李蔚然, 李振波. 基于人工智能的鱼类行为识别研究 viour in high-turbidity waters[J]. Expert Systems With Applica-
综述 [J]. 农业机械学报, 2023, 54(S1): 283-295. tions, 2024, 255: 124804.
Peng Q J, Li W R, Li Z B. Review of fish behavior recognition [32] Wang H, Zhang S, Zhao S L, et al. Real-time detection and
methods based on artificial intelligence[J]. Transactions of the tracking of fish abnormal behavior based on improved
Chinese Society for Agricultural Machinery, 2023, 54(S1): 283- YOLOV5 and SiamRPN++[J]. Computers and Electronics in
295 (in Chinese). Agriculture, 2022, 192: 106512.
[21] Wang G X, Muhammad A, Liu C, et al. Automatic recognition [33] Li X, Hao Y F, Zhang P, et al. A novel automatic detection
of fish behavior with a fusion of RGB and optical flow data method for abnormal behavior of single fish using image
based on deep learning[J]. Animals, 2021, 11(10): 2774. fusion[J]. Computers and Electronics in Agriculture, 2022, 203:
[22] Yang Y X, Yu H, Zhang X, et al. Fish behavior recognition 107435.
based on an audio-visual multimodal interactive fusion net- [34] Li D L, Wang G X, Du L, et al. Recent advances in intelligent
work[J]. Aquacultural Engineering, 2024, 107: 102471. recognition methods for fish stress behavior[J]. Aquacultural
[23] Huang W T, Wang Y P, He W H, et al. RTI-net: a decision sup- Engineering, 2022, 96: 102222.
port system for fish stress classification using multimodal learn- [35] Li Y J, Hu Z Y, Zhang Y X, et al. DDEYOLOv9: network for
ing network[J]. Expert Systems with Applications, 2025, 276: detecting and counting abnormal fish behaviors in complex
127174. water environments[J]. Fishes, 2024, 9(6): 242.
[24] Gu X Y, Zhao S L, Duan Y Q, et al. MMFINet: a multimodal [36] Atoum Y, Srivastava S, Liu X M. Automatic feeding control for
fusion network for accurate fish feeding intensity assessment in dense aquaculture fish tanks[J]. IEEE Signal Processing Letters,
recirculating aquaculture systems[J]. Computers and Electron- 2015, 22(8): 1089-1093.
ics in Agriculture, 2025, 232: 110138. [37] Adegboye M A, Aibinu A M, Kolo J G, et al. Incorporating

https://www.china-fishery.cn 中国水产学会主办 sponsored by China Society of Fisheries
6