Search

The identification of seed quality is very important for which the quality of seed is crucial to the yield and quality of crops. There are two main problems with the acquisition and identification of cracks inside corn seed. One is that most of the methods of near-infrared spectroscopy or X-ray are used to obtain images of cracks inside the seed, the acquisition equipment is expensive and the operation is complicated. The other is the identification of crack images, and the traditional image processing method is usually used which requires professionals to design different model parameters each time, resulting in poor model robustness and low model accuracy. In this study, we originally proposed a simple but effective method to obtain the picture of corn seed internal cracks, which is combined with visible light transmission and ordinary camera acquisition method. We also proposed using the transfer learning methods not only solving the problem of the small scale of our corn seed internal cracks dataset but also avoiding extracting features manually. Our proposed method achieved a promising result, which is able to correctly identify the cracked and intact corn seed 100% in our training stage and testing stage.

Objective. PET (Positron Emission Tomography) inherently involves radiotracer injections and long scanning time, which raises concerns about the risk of radiation exposure and patient comfort. Reductions in radiotracer dosage and acquisition time can lower the potential risk and improve patient comfort, respectively, but both will also reduce photon counts and hence degrade the image quality. Therefore, it is of interest to improve the quality of low-dose PET images. Approach. A supervised multi-modality deep learning model, named M3S-Net, was proposed to generate standard-dose PET images (60 s per bed position) from low-dose ones (10 s per bed position) and the corresponding CT images. Specifically, we designed a multi-branch convolutional neural network with multi-self-attention mechanisms, which first extracted features from PET and CT images in two separate branches and then fused the features to generate the final generated PET images. Moreover, a novel multi-modality structure-promoting term was proposed in the loss function to learn the anatomical information contained in CT images. Main results. We conducted extensive numerical experiments on real clinical data collected from local hospitals. Compared with state-of-the-art methods, the proposed M3S-Net not only achieved higher objective metrics and better generated tumors, but also performed better in preserving edges and suppressing noise and artifacts. Significance. The experimental results of quantitative metrics and qualitative displays demonstrate that the proposed M3S-Net can generate high-quality PET images from low-dose ones, which are competable to standard-dose PET images. This is valuable in reducing PET acquisition time and has potential applications in dynamic PET imaging. [ABSTRACT FROM AUTHOR]

To alleviate soil deterioration caused by tobacco continuous cropping obstacles, the effect of reductive soil disinfestation (RSD) on soil physicochemical and biological characteristics as well as tobacco growth was investigated through a pot experiment, with four treatments including control (CK), moderate nitrogen fertilizer application (NF), RSD, and RSD coupled with NF (RF). Results showed that soil pH, the content of organic matter, available P and available Fe were significantly increased after using RSD technology. Moreover, RSD technology boosted the relative abundance of Gemmatimonadota (9.0–12.0%), Chloroflexi (4.0–11.0%), and Ascomycota (10.0–12.0%) while decreasing the relative abundance of Mucoromycota (2–4%). Therefore, the biomass and quality of tobacco were also improved after the RSD application. Compared with CK, the biomass of tobacco at the mature stage was increased by 233.7–262.8% by RSD technology, and the chemical coordination (sugar difference, sugar alkali ratio and alkali nitrogen ratio) of the plant was also significantly improved. This study verified the feasibility of RSD technology in repairing soil deterioration caused by tobacco continuous cropping obstacles and provided theoretical and technical support for long-term tobacco production. [ABSTRACT FROM AUTHOR]

The advanced language models have enabled us to recognize protein–protein interactions (PPIs) and interaction sites using protein sequences or structures. Here, we trained the MindSpore ProteinBERT (MP-BERT) model, a Bidirectional Encoder Representation from Transformers, using protein pairs as inputs, making it suitable for identifying PPIs and their respective interaction sites. The pretrained model (MP-BERT) was fine-tuned as MPB-PPI (MP-BERT on PPI) and demonstrated its superiority over the state-of-the-art models on diverse benchmark datasets for predicting PPIs. Moreover, the model's capability to recognize PPIs among various organisms was evaluated on multiple organisms. An amalgamated organism model was designed, exhibiting a high level of generalization across the majority of organisms and attaining an accuracy of 92.65%. The model was also customized to predict interaction site propensity by fine-tuning it with PPI site data as MPB-PPISP. Our method facilitates the prediction of both PPIs and their interaction sites, thereby illustrating the potency of transfer learning in dealing with the protein pair task. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to examine the relationship between staff size and perceived organizational support (POS) in early childhood education (ECE) organizations. Design/methodology/approach: A territory-wide questionnaire survey was designed to investigate the perceptions of preschool teachers in Hong Kong on four dimensions of organizational support, namely, teacher participation in decision making, school management support, school performance in organizational support, and organizational negativity in organizational support. In total, 2,066 teachers from 189 schools were sampled with stratified random sampling. Confirmatory factor analysis and latent mean analysis were employed. Findings: There was a significant relationship between staff size and POS. Specifically, teachers working at small schools in terms of staff size reported significantly higher POS than their counterparts in medium and large schools in aspects including teacher participation in decision making, school management support, and school performance in POS. Conversely, both medium and large schools had higher scores on organizational negativity. Research limitations/implications: There may exist other factors (e.g. principal leadership), which are not investigated in this study, that influence POS. Future studies are needed to capture a fuller structural relationship among an array of factors that influence POS. Originality/value: Research on staff size and POS has been conducted separately, without one element informing the other. The findings of the present study will stimulate more research on POS and staff size. The study will stimulate thinking about whether larger preschools are more efficient than smaller preschools in terms of scale of economies in a marker driven, ECE context. Building upon the foundation laid by the study, future studies may explore the interaction between staff size and POS on intended student outcomes in ECE.

Behind a veneer of cosmopolitanism in Hong Kong, racial-ethnic discrimination is pervasively experienced by ethnic minorities such as South and South East Asians (hereafter referred to as South/South East Asians). It is the aim of this study to examine why Hong Kong Chinese and South/South East Asians express what seem to be divergent perceptions of racial-ethnic discrimination in Hong Kong society. Our findings reveal discrepancies in the level of understanding of racial-ethnic discrimination between the two ethnic groups, which likely explains divergent perceptions of racial-ethnic discrimination in Hong Kong society. At the same time, however, the findings revealed no significant group difference in their awareness of social inclusion and the Race Discrimination Ordinance (RDO). Implications of the findings are discussed by focusing on how the specificities of the Hong Kong context encourage different forms of racial-ethnic discrimination that are more insidious than is stipulated in the RDO.

Using direct electrolysis method, the recovery of copper and cyanide from high concentration copper cyanide solution was researched. The distribution of copper cyanide species was calculated by stability constants and balance equation. The results showed that the cupric ion was confirmed to generate at low potential (