ShanghaiTech University Knowledge Management System
Nondestructive in-ovo sexing of Hy-Line Sonia eggs by EggFormer using hyperspectral imaging | |
2024-10 | |
发表期刊 | COMPUTERS AND ELECTRONICS IN AGRICULTURE (IF:7.7[JCR-2023],8.4[5-Year]) |
ISSN | 0168-1699 |
EISSN | 1872-7107 |
卷号 | 225 |
发表状态 | 已发表 |
DOI | 10.1016/j.compag.2024.109298 |
摘要 | Early identification of egg gender during incubation is crucial for animal welfare and commercial poultry production, as nowadays day-old male chicks are often culled due to low economic value. Hyperspectral imaging (HSI) recognition presents a swift, non-destructive, and cost-effective solution for in-ovo sexing compared to traditional methods such as Polymerase Chain Reaction (PCR), Volatile Organic Compounds (VOC), and Raman spectroscopy. In this study, we collected spectral images of Hy-Line Sonia chicken eggs even-numbered day from day 0 to 14, with a focus on day 10 for detailed analysis. We introduced the EggFormer model, incorporating channel attention and transformer self-attention mechanisms. To assess model performance, significant wavelengths were extracted by machine learning algorithms, including Random Forest(RF), Principal Component Analysis(PCA), Successive Projections Algorithm (SPA), and Competitive Adaptive Reweighted Sampling Algorithm (CARS). The channel images of these significant wavelengths were then employed with ViT-Base(Vision Transformer) for prediction and comparison. The EggFormer model demonstrated superior results, with accuracy of 95.4%, recall of 98.6%, F1 score of 0.958 and Kappa of 0.908. Furthermore, by interpreting the channel attention block, 22 wavelengths were selected, maintaining optimal results, with 4 bands achieving an accuracy of 94.6%. This outperformance positions it as a promisingly efficient and economical solution for industrial applications. The code of this work is available at https://github.com/quietbamboo/EggFormer for reproducibility. © 2024 Elsevier B.V. |
关键词 | Animals Cost effectiveness Deep learning Forestry Learning algorithms Learning systems Polymerase chain reaction Principal component analysis Volatile organic compounds Animal welfare Chicken eggs Cost-effective solutions Deep learning Economic values In-ovo sexing Interpretable Non destructive Poultry production Spectral images |
URL | 查看原文 |
收录类别 | SCI ; EI |
语种 | 英语 |
WOS研究方向 | Agriculture ; Computer Science |
WOS类目 | Agriculture, Multidisciplinary ; Computer Science, Interdisciplinary Applications |
WOS记录号 | WOS:001292197300001 |
出版者 | Elsevier B.V. |
EI入藏号 | 20243216844893 |
EI主题词 | Hyperspectral imaging |
EI分类号 | 461.4 Ergonomics and Human Factors Engineering ; 723.4.2 Machine Learning ; 746 Imaging Techniques ; 801.2 Biochemistry ; 804.1 Organic Compounds ; 821 Agricultural Equipment and Methods ; Vegetation and Pest Control ; 911.2 Industrial Economics ; 922.2 Mathematical Statistics |
原始文献类型 | Journal article (JA) |
引用统计 | 正在获取...
|
文献类型 | 期刊论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/411223 |
专题 | 信息科学与技术学院 信息科学与技术学院_本科生 |
通讯作者 | Pan, Leiqing |
作者单位 | 1.College of Artificial Intelligence, Nanjing Agricultural University, Jiangsu, Nanjing; 210095, China 2.College of Food Science and Technology, Nanjing Agricultural University, Jiangsu, Nanjing; 210095, China 3.School of Information Science and Technology, ShanghaiTech University, Shanghai, 201210, China |
推荐引用方式 GB/T 7714 | Ji, Chengming,Song, Ke,Chen, Zixin,et al. Nondestructive in-ovo sexing of Hy-Line Sonia eggs by EggFormer using hyperspectral imaging[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2024,225. |
APA | Ji, Chengming.,Song, Ke.,Chen, Zixin.,Wang, Shanyong.,Xu, Huanliang.,...&Huang, Junxian.(2024).Nondestructive in-ovo sexing of Hy-Line Sonia eggs by EggFormer using hyperspectral imaging.COMPUTERS AND ELECTRONICS IN AGRICULTURE,225. |
MLA | Ji, Chengming,et al."Nondestructive in-ovo sexing of Hy-Line Sonia eggs by EggFormer using hyperspectral imaging".COMPUTERS AND ELECTRONICS IN AGRICULTURE 225(2024). |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。