Search

Multiple-instance learning (MIL) is a significant weakly supervised learning problem, where the training data consist of bags containing multiple instances and bag-level labels. Most previous MIL research required fully labeled bags. However, collecting such data is challenging due to the labeling costs or privacy concerns. Fortunately, we can easily collect pairwise comparison information, indicating one bag is more likely to be positive than the other. Therefore, we investigate a novel MIL problem about learning a bag-level binary classifier only from pairwise comparison bags. To solve this problem, we display the data generation process and provide a baseline method to train an instance-level classifier based on unlabeled-unlabeled learning. To achieve better performance, we propose a convex formulation to train a bag-level classifier and give a generalization error bound. Comprehensive experiments show that both the baseline method and the convex formulation achieve satisfactory performance, while the convex formulation performs better.1 [ABSTRACT FROM AUTHOR]

Advancements in remote sensing technology have significantly contributed to the improvement of models for estimating terrestrial gross primary productivity (GPP). However, discrepancies in the spatial distribution and interannual variability within GPP datasets pose challenges to a comprehensive understanding of the terrestrial carbon cycle. In contrast to previous models that rely on remote sensing and environmental variables, we developed an ensemble model based on the random forest method (denoted ERF model). This model used GPP outputs from established models: Eddy Covariance Light Use Efficiency (EC-LUE), GPP estimate model based on Kernel Normalized Difference Vegetation Index (GPP-kNDVI), GPP estimate model based on Near-Infrared Reflectance of Vegetation (GPP-NIRv), Revised-EC-LUE, Vegetation Photosynthesis Model (VPM), and GPP estimate model based on the Moderate Resolution Imaging Spectroradiometer (MODIS). These outputs were used as inputs to estimate GPP. The ERF model demonstrated superior performance, explaining 85.1 % of the monthly GPP variations at 170 sites and surpassing the performance of selected GPP estimate models (67.7 %–77.5 %) and an independent random forest model using remote sensing and environmental variables (81.5 %). Additionally, the ERF model improved accuracy across each month and with various subranges, mitigating the issue of "high-value underestimation and low-value overestimation" in GPP estimates. Over the period from 2001 to 2022, the global GPP estimated by the ERF model was 132.7 PgC yr -1 , with an increasing trend of 0.42 PgC yr -2 , which is comparable to or slightly better than the accuracy of other mainstream GPP datasets in terms of validation results of GPP observations independent of FLUXNET (i.e., ChinaFLUX). Importantly, for a growing number of GPP datasets, our study provides a way to integrate these GPP datasets, which may lead to a more reliable estimate of global GPP. [ABSTRACT FROM AUTHOR]

The Asian seabass (Lates calcarifer) has high economic value and is the primary aquaculture species in China. Licorice (Glycyrrhiza uralensis) as a feed additive has demonstrated significant immunological benefits in aquaculture. However, its effects on the growth of aquatic animals are largely unexplored. This study explored the influence of licorice on the level of growth-related genes in Asian seabass by conducting an experiment using artificial feed with 0%, 1%, 3%, and 5% licorice. The impact on growth performance and the expression of several genes, including growth hormone–releasing hormone (GHRH), growth hormone (GH), growth hormone receptor (GHR), insulin-like growth factor 1 (IGF1), IGF2, IGF2 receptor (IGF2R), myostatin 1 (MSTN1), and myostatin 2 (MSTN2), were studied over 56 d. According to the results, the 3% and 5% licorice-supplemented diets significantly improved survival rates and weight gain compared to the control group. Licorice affected the level of growth-associated genes in Asian seabass and significantly increased the levels of GHR and IGF1 in the liver. However, a 5% licorice diet downregulated the expression of IGF2. As the licorice content in the diet increased, the levels of IGF2R and MSTN1 in the muscle tissue first decreased and then increased, and licorice addition inhibited the MSTN2 expression. The inclusion of licorice in the feed led to a significant downregulation of the GH and GHRH expression (p < 0.05). In summary, adding a certain proportion of licorice to the diet can improve the survival rate of the Asian seabass. Moreover, a proper proportion of licorice can increase the expression of related growth genes of fish, effectively increasing their weight gain rate and specific growth rate. [ABSTRACT FROM AUTHOR]

This article discusses the synthesis and spectroscopic properties of 3-/3,5-styryl-substituted BODIPY dyes with N-bridged annulation. The study focuses on modifying the BODIPY structure to enhance its properties for interdisciplinary fields like biomedicine and materials science. The authors report the successful synthesis of the desired compounds and analyze their spectroscopic properties, including absorption and emission spectra, fluorescence quantum yield, and fluorescence lifetime. The compounds exhibited high fluorescence quantum yield and red fluorescence emission, making them potentially useful in organic biological materials. Supporting information, including spectra of the new compounds, is available online. [Extracted from the article]

The continuous advancement of remote sensing technology has been instrumental in improving models for estimating terrestrial gross primary productivity (GPP). However, challenges arise from inconsistent spatial distributions and interannual variations in GPP datasets, impeding our comprehensive understanding of the entire terrestrial carbon cycle. In contrast to previous models relying on remote sensing and environmental variables, we developed a an ensemble model based on random forest named GPPERF. This model utilized the GPP outputs from established remote sensing-based models (EC-LUE, GPP-kNDVI, GPP-NIRv, Revised-EC-LUE) as inputs for GPP estimations. GPPERF demonstrated significant effectiveness by explaining 83.7 % of the monthly variation in GPP across 171 sites. This performance surpassed the selected remote sensing models (72.4 %–77.1 %) and an independent random forest model using remote sensing and environmental variables (77.7 %). Over the period from 2001 to 2022, the global estimated GPP value using the ensemble model based on random forest was 131.2 PgC yr-1, exhibiting a trend of 0.45 PgC yr-2. Furthermore, evaluation results utilizing flux sites from ChinaFlux indicated that the dateset exhibited good generalization. In summary, the machine learning-based ensemble method helps to reduce the uncertainty in the estimation of a single remote sensing model and provides a more reliable estimation of global GPP. [ABSTRACT FROM AUTHOR]