Dynamic weighted residual ensemble learning for hyperspectral image classification driven by features and samples.

Dynamic ensemble selection has emerged as a promising approach for hyperspectral image classification. However, selecting relevant features and informative samples remains a pressing challenge. To address this issue, we introduce two novel dynamic residual ensemble learning methods.

Formation mechanism of disc-shaped calcite-a case study on sp. MF-2.

Research on the biogenic-specific morphology of carbonate minerals has made progress in the fields of biomineralization and industrial engineering. In this study, mineralization experiments were performed using sp. MF-2, including its biofilms.

The effect of LV-1 on the crystallization and polymorphs of calcium carbonate.

The study of CaCO polymorphism is of great significance for understanding the mechanism of carbonate mineralization induced by bacteria and the genesis of carbonate rock throughout geological history. To investigate the effect of bacteria and shear force on CaCO precipitation and polymorphs, biomineralization experiments with strain LV-1 were conducted under the standing and shaking conditions. The results show that LV-1 induced the formation of calcite and vaterite under the standing and shaking conditions, respectively.

Mechanism of carbonate mineralization induced by microbes: Taking Curvibacter lanceolatus strain HJ-1 as an example.

Microbial-induced carbonate precipitation is important in the global carbon cycle, especially in fixing atmospheric CO. Many simulation experiments have shown that microbes can induce carbonate precipitation, although there is no established understanding of the mechanism. In this study, several mineralization experiments were performed using Curvibacter lanceolatus strain HJ-1, including its secreted extracellular polymeric substances (EPS) and carbonic anhydrase (CA).

Localization and Classification of Paddy Field Pests using a Saliency Map and Deep Convolutional Neural Network.

We present a pipeline for the visual localization and classification of agricultural pest insects by computing a saliency map and applying deep convolutional neural network (DCNN) learning. First, we used a global contrast region-based approach to compute a saliency map for localizing pest insect objects. Bounding squares containing targets were then extracted, resized to a fixed size, and used to construct a large standard database called Pest ID.