Ji Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ji Liu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Biao He
School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
1 shared publication - Cuimin Sun
School of Computer and Electronic Information Engineering, Guangxi University, Nanning 530004, China
1 shared publication - Liuxue Huang
School of Computer, Electronics and Information, Guangxi University, Nanning 530004, China
1 shared publication - Qiulian Chen
College of Computer and Electronic Information, Guangxi University, Nanning 530004, China
1 shared publication - Xi Qin
School of Computer and Electronic Information, Guangxi University, Nanning, China
1 shared publication
Latest Publications
- Open Access
SCBI-EfficientNetV2: A Lightweight Attention-Based Network for Regression Prediction of Nitrogen Content in Maize Leaves
Accurate assessment of nitrogen content in maize leaves is crucial for scientific fertilization and environmental protection in agricultural production. Traditional nutrient diagnosis methods are inefficient, costly, and destructive, while machine learning approaches based on handcrafted features rely heavily on manual design, leading to limited generalization ability and suboptimal prediction accuracy. To address these issues, this paper proposes a convolutional neural network model named SCBI-EfficientNetV2, which adopts EfficientNetV2-S as the backbone to overcome the limitations of manual feature engineering through automatic feature extraction. Furthermore, a Spatial and Channel Synergistic Attention (SCSA) module is introduced to enhance the modeling of critical regions and informative channels, and a Bidirectional Feature Pyramid Network (BiFPN) is incorporated to achieve effective multi-scale feature fusion, thereby improving the representation of hierarchical structural features in maize leaves. Experimental results show that SCBI-EfficientNetV2 achieves a coefficient of determination (R2) of 0.9417 on the test set, representing a 5.25% improvement over the baseline model and outperforming five classical deep learning approaches. In addition, the proposed model maintains high prediction accuracy with relatively low computational cost, demonstrating good adaptability for edge deployment. This study provides a feasible solution for non-destructive intelligent diagnosis of maize nutrition and offers technical support for precision fertilization and sustainable agricultural development.
Open AccessSCBI-EfficientNetV2: A Lightweight Attention-Based Network for Regression Prediction of Nitrogen Content in Maize Leaves
Accurate assessment of nitrogen content in maize leaves is crucial for scientific fertilization and environmental protection in agricultural production. Traditional nutrient diagnosis methods are inefficient, costly, and destructive, while machine learning approaches based on handcrafted features rely heavily on manual design, leading to limited generalization ability and suboptimal prediction accuracy. To address these issues, this paper proposes a convolutional neural network model named SCBI-EfficientNetV2, which adopts EfficientNetV2-S as the backbone to overcome the limitations of manual feature engineering through automatic feature extraction. Furthermore, a Spatial and Channel Synergistic Attention (SCSA) module is introduced to enhance the modeling of critical regions and informative channels, and a Bidirectional Feature Pyramid Network (BiFPN) is incorporated to achieve effective multi-scale feature fusion, thereby improving the representation of hierarchical structural features in maize leaves. Experimental results show that SCBI-EfficientNetV2 achieves a coefficient of determination (R2) of 0.9417 on the test set, representing a 5.25% improvement over the baseline model and outperforming five classical deep learning approaches. In addition, the proposed model maintains high prediction accuracy with relatively low computational cost, demonstrating good adaptability for edge deployment. This study provides a feasible solution for non-destructive intelligent diagnosis of maize nutrition and offers technical support for precision fertilization and sustainable agricultural development.