Fish school feeding behavior quantification using acoustic signal and improved Swin Transformer
文献类型: 外文期刊
作者: Zeng, Yuhao 1 ; Yang, Xinting 1 ; Pan, Liang 2 ; Zhu, Wentao 2 ; Wang, Dinghong 2 ; Zhao, Zhengxi 2 ; Liu, Jintao 2 ; Sun, Chuanheng 2 ; Zhou, Chao 2 ;
作者机构: 1.Jiangsu Univ, Sch Agr Engn, Zhenjiang 212013, Jiangsu, Peoples R China
2.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China
3.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Beijing 100097, Peoples R China
4.Natl Engn Lab Agriprod Qual Traceabil, Beijing 100097, Peoples R China
5.Shuguang Huayuan Middle Rd 9, Beijing, Peoples R China
关键词: Aquaculture; Feeding acoustics recognition; Fish feeding behavior quantification; Improved Swin Transformer network; Deep learning
期刊名称:COMPUTERS AND ELECTRONICS IN AGRICULTURE ( 影响因子:8.3; 五年影响因子:8.3 )
ISSN: 0168-1699
年卷期: 2023 年 204 卷
页码:
收录情况: SCI
摘要: In aquaculture, the real-time quantification of fish feeding behavior is an important basis for feeding decisions. The acoustics produced by fish chewing feed and activities during feeding can be used to quantify feeding behavior. This study proposes an Audio Spectrum Swin Transformer (ASST) model based on an acoustic signal and attention mechanism that can divide the feeding intensity of fish into four grades: strong, medium, weak, and none. The specific implementation methods are: (1) A sliding window was applied to clip the audio and the acoustic. Signals are transformed into spectrograms. (2) The perceptual domain of fish feeding acoustic spectrum recognition task was gradually expanded by adopting the Swin Transformer and utilizing its hierarchical structure. (3) The model's performance for small data sets was further improved by adding SPT, LSA, and enhanced residual connections. (4) A predictive optimization module was designed to correct the feeding strategy according to four feeding levels. The final experimental results demonstrate that the accuracy of the improved ASST network for fish feeding behavior quantification reached 96.16%. It can effectively identify-four fish feeding intensities, allowing on-demand feeding and providing a basis for developing intelligent feeding machines.
- 相关文献
作者其他论文 更多>>
-
Synchronous fluorescence detection of nitrite in meat products based on dual-emitting dye@MOF and its portable hydrogel test kit
作者:Deng, Siyang;Liu, Junmei;Han, Dong;Zhang, Chunhui;Yang, Xinting;Liu, Huan;Yang, Xinting;Liu, Huan;Deng, Siyang;Liu, Junmei;Blecker, Christophe
关键词:Luminescent metal organic framework; Dual-mode detection; On-spot visualization; NO2-; Rh6G@UIO-66-NH2
-
A novel method for real-time prediction of the shelf life of pork at different storage temperatures using front-face fluorescence excitation-emission matrices
作者:Liu, Huan;Zhu, Wenying;Luo, Na;Ji, Zengtao;Yang, Xinting;Liu, Huan;Zhu, Wenying;Luo, Na;Ji, Zengtao;Yang, Xinting;Liu, Huan;Zhu, Wenying;Luo, Na;Ji, Zengtao;Yang, Xinting
关键词:Front-face fluorescence excitation-emission; matrices; Pork; Modified; Gompertz model; Shelf life prediction
-
Artificial neural network-based shelf life prediction approach in the food storage process: A review
作者:Shi, Ce;Jia, Zhixin;Hou, Mengyuan;Yang, Xinting;Ji, Zengtao;Shi, Ce;Jia, Zhixin;Hou, Mengyuan;Yang, Xinting;Ji, Zengtao;Shi, Ce;Jia, Zhixin;Hou, Mengyuan;Yang, Xinting;Ji, Zengtao;Shi, Ce;Jia, Zhixin;Hou, Mengyuan;Yang, Xinting;Ji, Zengtao;Zhao, Zhiyao;Ying, Xiaoguo
关键词:Artificial neural network; modeling; shelf life prediction; food; storage
-
FARNET: FARMING ACTION RECOGNITION FROM VIDEOS BASED ON COORDINATE ATTENTION AND YOLOV7-TINY NETWORK IN AQUACULTURE
作者:Yang, Xinting;Pan, Liang;Wang, Dinghong;Zeng, Yuhao;Zhou, Chao;Jiao, Dongxiang;Sun, Zhenlong;Sun, Chuanheng
关键词:Action detection; Applying pesticides; Coordinate attention; FARnet; Inspection
-
EFFECT OF DIFFERENT SELENIUM FERTILIZER CONCENTRATIONS ON PEAR YIELD AND QUALITY
作者:Wang, Lei;Jin, Liang;Li, Yan;An, Zhizhuang;Suo, Linna;Ding, Jianli;Wei, Dan;Wang, Lei;Wu, Jiajun;Xie, Jianzhi;Han, Yehui;Zhou, Chao
关键词:Huangtukan pear; Selenium; Yield; Quality; Nutrient absorption
-
An efficient mobile model for insect image classification in the field pest management
作者:Zheng, Tengfei;Yang, Xinting;Zheng, Tengfei;Yang, Xinting;Lv, Jiawei;Li, Ming;Li, Wenyong;Zheng, Tengfei;Yang, Xinting;Lv, Jiawei;Li, Ming;Li, Wenyong;Wang, Shanning;Lv, Jiawei
关键词:Insect recognition; Lightweight model; Attention mechanism; Feature fusion; Data augmentation
-
Applications of Gas Sensing in Food Quality Detection: A Review
作者:Ma, Minzhen;Yang, Xinting;Shi, Ce;Jia, Zhixin;Jia, Boce;Ma, Minzhen;Ying, Xiaoguo;Yang, Xinting;Shi, Ce;Jia, Zhixin;Yang, Xinting;Shi, Ce;Jia, Zhixin;Yang, Xinting;Shi, Ce;Jia, Zhixin;Ying, Xiaoguo;Jia, Boce
关键词:gas sensor; gas sensor arrays; VOCs; quality monitoring; freshness prediction