Automated Maize Ear Phenotyping Using 3D Reconstructions
为解决玉米育种中手动测量玉米粒性状效率低的问题，本文开发了一种基于3D点云重建的全自动分析管道，实现了高精度的玉米粒计数与行数估计。
0 citationsRead paper
Selected work
Representative Papers
Learning with Volterra Neural Networks: A System Theoretic Perspective
本文提出kVNN，一种可学习的核化Volterra神经算子，用于高效高阶滤波，通过结合Volterra滤波结构和可学习多项式核原子来解决高阶运算成本问题。
0 citationsRead paper
Machine learning and machine learned prediction in chest X-ray images
This study addresses binary classification of thoracic diseases from chest X-ray images, leveraging a clinical dataset of 5,824 images. Method: We systematically compare a baseline CNN against DenseNet-121, fine-tuning the latter via transfer learning and integrating Grad-CAM for lesion localization and enhanced decision interpretability. Results: DenseNet-121 significantly outperforms the baseline—achieving a 3.2% higher accuracy and a 0.042 improvement in AUC. Its dense connectivity enables more effective capture of localized pathological features, yielding superior localization precision in pulmonary abnormal regions and greater classification robustness. This work validates DenseNet-121’s efficacy in medical imaging tasks with limited training data and, through rigorous interpretability analysis, provides clinically credible, human-interpretable decision support for AI-assisted diagnosis.
0 citationsRead paper
Recent publications
Latest Papers
Automated Maize Ear Phenotyping Using 3D Reconstructions
为解决玉米育种中手动测量玉米粒性状效率低的问题，本文开发了一种基于3D点云重建的全自动分析管道，实现了高精度的玉米粒计数与行数估计。
0 citationsRead paper
Learning with Volterra Neural Networks: A System Theoretic Perspective
本文提出kVNN，一种可学习的核化Volterra神经算子，用于高效高阶滤波，通过结合Volterra滤波结构和可学习多项式核原子来解决高阶运算成本问题。
0 citationsRead paper
Machine learning and machine learned prediction in chest X-ray images
This study addresses binary classification of thoracic diseases from chest X-ray images, leveraging a clinical dataset of 5,824 images. Method: We systematically compare a baseline CNN against DenseNet-121, fine-tuning the latter via transfer learning and integrating Grad-CAM for lesion localization and enhanced decision interpretability. Results: DenseNet-121 significantly outperforms the baseline—achieving a 3.2% higher accuracy and a 0.042 improvement in AUC. Its dense connectivity enables more effective capture of localized pathological features, yielding superior localization precision in pulmonary abnormal regions and greater classification robustness. This work validates DenseNet-121’s efficacy in medical imaging tasks with limited training data and, through rigorous interpretability analysis, provides clinically credible, human-interpretable decision support for AI-assisted diagnosis.
0 citationsRead paper