.png){kind=icon}
返回
Residual networks using multi-task learning algorithm for near-infrared spectroscopy: A case study
.png){kind=icon}
PRE
AI
DOI：10.1016/j.saa.2025.125866.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Near-infrared spectroscopy (NIRS) is a widely used non-destructive detection method known for its efficiency and environmental friendliness. However, the complex and high-dimensional nature of NIRS data presents challenges in accurately correlating spectral information with specific chemical compositions. In this study, an improved ResNet-18 model integrated with multi-task learning to estimate multiple chemical contents from fulldimensional NIRS data is proposed. The present model has been optimized by reducing the number of channels while maintaining the network's depth to prevent overfitting. The designed model was used to predict four chemical compositions in tobacco, demonstrating superior performance compared with traditional machine learning algorithms. The experimental results indicate that the modified ResNet-18 model offers excellent generalization and predictive accuracy.
Keyword:
Residual networks
Multi-task learning
Near-infrared spectroscopy
Chemical composition
Regression prediction
期刊
IF:
4.6
论文数:
2.4W
被引数:
5.5W
机构
引用论文
Multi -task contrastive learning for automatic CT and X-ray diagnosis of COVID-19.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Predicting oil content in ripe Macaw fruits (Acrocomia aculeata) from unripe ones by near infrared spectroscopy and PLS regressionFOOD CHEMISTRYOAAI
FOOD CHEMISTRYIF9.8
OAAI分享收藏NIR associated to PLS and SVM for fast and non-destructive determination of C, N, P, and K contents in poultry litter与PLS和SVM相关的NIR可快速，无损地测定家禽垫料中的C，N，P和K含量
PREAI
分享收藏Braverman and the Contribution of Labour Process Analysis to the Critique of Capitalist Production – Twenty-Five Years On布拉厄曼与劳动过程分析对资本主义生产批判的贡献——二十五年之后
PREAI
分享收藏Modelling of bioprocess non-linear fluorescence data for at-line prediction of etanercept based on artificial neural networks optimized by response surface methodologyTALANTA
TALANTAIF6.1
PREAI
分享收藏
查看更多内容