Publications by authors named "Hang Ran"

Few-shot class-incremental learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. Foundation models combined with prompt tuning showcase robust generalization and zero-shot learning (ZSL) capabilities, endowing them with potential advantages in transfer capabilities for FSCIL. However, existing prompt tuning methods excel in optimizing for stationary datasets, diverging from the inherent sequential nature in the FSCIL paradigm.

View Article and Find Full Text PDF

Large deep learning models are impressive, but they struggle when real-time data is not available. Few-shot class-incremental learning (FSCIL) poses a significant challenge for deep neural networks to learn new tasks from just a few labeled samples without forgetting the previously learned ones. This setup can easily leads to catastrophic forgetting and overfitting problems, severely affecting model performance.

View Article and Find Full Text PDF

AgPO nanoparticles (NPs) was prepared through a facile coprecipitation method, and was first found to have excellent laccase-mimicking catalytic activity. The study confirms that Fumonisin B1 (FB1) can effectively hinder the production of superoxide anion (O) between AgPO NPs and dissolved oxygen, and further inhibit laccase-mimicking activity of AgPO NPs. Thus, a novel rapid colorimetric sensor for FB1 analysis in cereal was first established using laccase-mimicking activity as sensing signal.

View Article and Find Full Text PDF

The aim of this experiment was to study the sustained effects of early supplementation with a starter on the performance of lambs during the pre-weaning, post-weaning, and fattening periods. Sixty male lambs (3.59 ± 0.

View Article and Find Full Text PDF

is an important ornamental plant in China. Due to the lack of efficient molecular markers, although recent studies supported that was phylogenetically closely related to , , , and , relationships among these taxa remained uncertain. To examine the phylogenetic position of within Caprifoliaceae, we characterized the complete chloroplast (cp) genome of .

View Article and Find Full Text PDF

Phylogenetic analyses of complete chloroplast genome sequences have yielded significant improvements in our understanding of relationships in the woody flowering genus (Adoxaceae, Dipsacales); however, these relationships were evaluated focusing only on species within Central and South America and Southeast Asia. By contrast, despite being a hotspot of diversity, phylogenetic relationships of species in China are less well known. Here, we characterized the complete chloroplast (cp) genomes of 21 species endemic to China, as well as three species.

View Article and Find Full Text PDF
Article Synopsis
  • The study focuses on classifying wheat varieties using near infrared (NIR) spectroscopy and emphasizes the challenge of balancing the modeling sample size with information redundancy.
  • It introduces a new sample selection method called k nearest neighbor-density, which is an improvement over traditional random sampling and k nearest neighbor methods.
  • Experimental results show that using k nearest neighbor-density not only reduces the sample size significantly but also enhances the overall accuracy of the classification models for wheat varieties.
View Article and Find Full Text PDF
Article Synopsis
  • The article investigates the use of Near Infrared Reflectance (NIR) and Transmittance (NIT) Spectroscopy for identifying the purity of maize hybrids.
  • Both techniques were compared, showing that NIR achieved a 100% accuracy for one hybrid and 90% for another, but its results were sensitive to seed placement.
  • In contrast, NIT showed a consistent 98% accuracy for both hybrids and demonstrated more reliability for analyzing individual seed kernels.
View Article and Find Full Text PDF