Classification Method of Feeding Intensity of Sea Bass Based on Self-Attention-DSC-CNN6 and Multi-modal Fusion
Abstract
Feeding intensity recognition and classification is an important link to realize accurate feeding in aquaculture. Existing feeding methods have problems such as over-reliance on manual experience judgment, imprecise feeding amount, and serious feed waste. Fish feeding degree classification based on multi-modal fusion can synthesize different types of data (e.g., video, sound, and water quality parameters) to provide a more comprehensive and accurate decision basis for fish feeding. Therefore, a multi-modal fusion framework that integrated video and audio data was proposed with the aim of improving the performance of sea bass feeding intensity classification. The preprocessed Mel Spectrogram (Mel) and video frame images were input into the self-attention-depthwise separable convolution-CNN6 (Self-Attention-DSC-CNN6) optimization model for high-level feature extraction, respectively, and the extracted features were further spliced and fused, and finally the spliced features were classified by a classifier. The Self-Attention-DSC-CNN6 optimization model was improved based on the CNN6 algorithm by replacing the traditional convolutional layers with depthwise separable convolution (DSC) to reduce the computational complexity, and the Self-Attention mechanism was introduced to enhance the feature extraction capability. The experimental results showed that the multi-modal fusion framework proposed achieved an accuracy of 90.24% in sea bass feeding intensity classification, and the model can effectively utilize the information from different data sources to improve the understanding of fish behavior in complex environments, enhance the decision-making ability of the model, and ensure the timeliness and accuracy of the feeding strategy, thus effectively reducing the waste of feed. This not only provided strong technical support for the intelligent management of aquaculture, but also laid the foundation for the development of intelligent feeding system.
Keywords: sea bass, classification of feeding intensity, multi-modal fusion, Self-Attention-DSC-CNN6
Download Full Text:
PDFReferences
BONDAD-REANTASO M G, MACKINNON В, KARUNASAGAR I, et al. Review of alternatives to antibiotic use in aquaculture [J] . Reviews in Aquaculture, 2023,15(4) : 1421 - 1451.
GU Lishuai. Research and implementation of fish feeding behavior quantification system based on spatiotemporal feature fusion [D]. Dalian: Dalian Ocean University, 2024.
LI W, DU Z, LI D, et al. A review of aquaculture: from single modality analysis to multimodality fusion[J]. Computers and Electronics in Agriculture, 2024, 226; 109367.
CHEN Hao. Intelligent baiting decision system for captive bass based on multi-source data fusion [D]. Wuhan; Huazhong Agricultural University, 2023.
FENG Shuangxing, WANG Dinghong, FAN Liang, et al. Implementation of fish feeding intensity identification system using light-weight S3D algorithm [J]. Fishery Modernization, 2023, 50(3) ; 79 -86.
WU Y, WANG X, SHI Y, et al. Fish feeding intensity assessment method using deep learning-based analysis of feeding splashes[J]. Computers and Electronics in Agriculture, 2024, 221 ; 108995.
CAI K, YANG Z, GAO T, et al. Efficient recognition of fish feeding behavior; a novel two-stage framework pioneering intelligent aquaculture strategies[ J]. Computers and Electronics in Agriculture, 2024, 224: 109129.
LIU H, MA X, YU Y, et al. Application of deep learning-based object detection techniques in fish aquaculture: a review [J]. Mar. Sci. Eng., 2023, 11 (4): 867 -888.
XU Jingwen, YU Hong, ZHANG Peng, et al. A fish behavior recognition model based on multi-level fusion of sound and vision U - FusionNet ~ ResNet50 +SENet[J]. Journal of Dalian Ocean University, 2023, 38(2) ; 348 -356.
DU Z, GUI M, WANG Q, et al. Feeding intensity assessment of aquaculture fish using Mel spectrogram and deep learning algorithms[ J ]. Aquacultural Engineering, 2023, 102: 102345.
DENG Jincun, YE Zhangying, ZHAO Jian, et al. Sensitive detection of fish feeding intensity by using sound and image features of feeding process [J]. Oceanologia et Linmologia Sinic., 2024, 55(3) : 577 -588.
YANG Yuxin. Fish behavior recognition method based on acoustic and visual features fusion under complex conditions [13]. Dalian; Dalian Ocean University, 2024.
DU Z, XU X, BAI Z, et al. Feature fusion strategy and improved GhostNet for accurate recognition of fish feeding behavior [J]. Computers and Electronics in Agriculture, 2023, 214; 108310.
DU Z, CU1 M, XU X, et al. Harnessing multimodal data fusion to advance accurate identification of fish feeding intensity [J]. Biosystems Engineering, 2024, 246: 135 - 149.
HU Xuelong, ZHU Wentao, YANG Xinting, et al. Identification of feeding intensity in recirculating aquaculture fish using water quality - sound - vision fusion [J] . Transactions of the CSAE, 2023, 39( 10) : 141 - 150. (in Chinese)
XU Lihong, HUANG Zhizun, LONG Wei, et al. Classification model of fish feeding intensity based on MobileViT - CBAM - BiLSTM [J]. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55 (11): 147 -153.
XU Lihong, HUANG Xin, LIU Shijing. Recognition of fish feeding intensity based on improved LKCN [J]. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53(10) : 236 -241.
TANG Chen, XU Lihong, LIU Shijing. Fine-grained classification algorithm of fish feeding state based on opticalflow method [J]. Transactions of the CSAE, 2021, 37(9) : 238 -244.
LIU Shijing, TU Xueying, QIAN Cheng, et al. Feeding state classification of grass carp based on optical flow and improved KNN [J] . Acta Hydrobiologica Sinica, 2022, 46(6) ; 914 -921.
ZHOU C, XU D, CHEN L, et al. Evaluation of fish feeding intensity in aquaculture using a convolutional neural network and machine vision [J]. Aquaculture, 2019, 507: 457 -465.
ZHOU Chao, XU Darning, LIN Kai, et al. Evaluation of fish feeding intensity in aquaculture based on near-infrared machine vision [J]. Smart Agriculture, 2019,1 (1) : 76 -84.
Refbacks
- There are currently no refbacks.
