课程文献中心 更多>>

关键词： GENOME-WIDE ASSOCIATION   STRESSFUL LIFE EVENTS   ENVIRONMENT INTERACTION RESEARCH   HUMAN DEMOGRAPHIC HISTORY   SUBSTANCE USE   POLYGENIC RISK   5-HTTLPR POLYMORPHISM   PARENTAL ALCOHOLISM   PREDICT ALCOHOL   DRUG PROBLEMS  

摘要： Numerous studies have demonstrated that genetic and environmental factors interact to influence alcohol problems. Yet prior research has primarily focused on samples of European descent and little is known about gene-environment interactions in relation to alcohol problems in non-European populations. In this study, we examined whether and how genetic risk for alcohol problems and peer deviance and interpersonal traumatic events independently and interactively influence trajectories of alcohol use disorder symptoms in a sample of African American students across the college years (N = 1,119; M-age = 18.44 years). Data were drawn from the Spit for Science study where participants completed multiple online surveys throughout college and provided a saliva sample for genotyping. Multilevel growth curve analyses indicated that alcohol dependence genome-wide polygenic risk scores did not predict trajectory of alcohol use disorder symptoms, while family history of alcohol problems was associated with alcohol use disorder symptoms at the start of college but not with the rate of change in symptoms over time. Peer deviance and interpersonal traumatic events were associated with more alcohol use disorder symptoms across college years. Neither alcohol dependence genome-wide polygenic risk scores nor family history of alcohol problems moderated the effects of these environmental risk factors on alcohol use disorder symptoms. Our findings indicated that peer deviance and experience of interpersonal traumatic events are salient risk factors that elevate risk for alcohol problems among African American college students. Family history of alcohol problems could be a useful indicator of genetic risk for alcohol problems. Gene identification efforts with much larger samples of African descent are needed to better characterize genetic risk for alcohol use disorders, in order to better understand gene-environment interaction processes in this understudied population.

关键词： FLUORESCEIN   DRY eye syndromes   PATHOLOGICAL physiology  

关键词： Cambodian floodplain   Flood   PLS-SEM   Vietnam Mekong River Delta   Vulnerability   MEKONG RIVER-DELTA   SEA-LEVEL RISE   SOCIAL VULNERABILITY   NEW-ORLEANS   CLIMATE-CHANGE   HOUSEHOLD VULNERABILITY   HURRICANE KATRINA   NATURAL DISASTERS   PLS   INDICATORS  

摘要： The formation of vulnerability to natural hazards consists of many driving factors that represent multi-facets of the subjected system. However, the interactions among these components remain unclear and have not been clarified. Examining these internal relationships helps to improve the accuracy of vulnerability assessments and provides needed focus in flood management. This study employed partial least squares structural equation modeling (PLS-SEM) to discover the interrelationship of household flood vulnerability determinants in Cambodia's floodplain and Vietnam's Mekong River Delta. The results show that demographics and social capital have direct influences on flood exposure. In this paper, socioeconomic status can reduce flood effect levels through the mediation of coping capacity. In addition, heterogeneity was also observed between Vietnamese and Cambodian families, highlighting the influence of context on understanding social vulnerability. As the two countries are under threat from hydropower and climate change that profoundly affect flooding, flood management strategies should be improved. The study suggests that the focus should be placed with socioeconomic and coping capacity to sustainably strengthen resilience against flooding.

关键词： Semi-supervised learning   Active learning   Sparse coding   Two phase test sample representation classifiers   Pattern classification   ROBUST FACE RECOGNITION   STATISTICAL COMPARISONS   FRAMEWORK  

摘要： Two Phase Test Sample Sparse Representation (TPTSSR) classifier was recently proposed as an efficient alternative to the Sparse Representation Classifier (SRC). It aims at classifying data using sparse coding in two phases with h regularization. Although high performances can be obtained by the TPTSSR classifier, since it is a supervised classifier, it is not able to benefit from unlabeled samples which are very often available. In this paper, we introduce a semi-supervised version of the TPTSSR classifier called Semi-supervised Two Phase Test Sample Sparse Representation (STPTSSR). STPTSSR combines the merits of sparse coding, active learning and the two phase collaborative representation classifiers. The proposed framework is able to make any sparse representation based classifier semi-supervised. Extensive experiments carried out on six benchmark image datasets show that the proposed STPTSSR can outperform the classical TPTSSR as well as many state-of-the-art semi-supervised methods.

关键词： Imbalanced classification   Image classification   Generative adversarial nets   Ensemble learning   NEURAL-NETWORKS   IMBALANCED DATA   SMOTE  

摘要： Most image classification algorithms aim to maximize the percentage of class labels that are predicted correctly. These algorithms often missclassify images from minority categories as into the dominant categories. To overcome the issue of unbalanced data for classifying vehicles from traffic surveillance images, we propose a semi supervised pipeline focused on integrating deep neural networks with data augmentation based on generative adversarial nets (GANs). The proposed approach consists of three main stages. In the first stage, we trained several GANs on the original dataset to generate adversarial samples for the rare classes. In the second stage, an ensemble of CNN models with different architectures are trained on the original imbalanced data set, and then a sample selection step is performed to filter out the low-quality adversarial samples. In the final stage, the aforementioned ensemble model is refined on the augmented dataset by adding the selected adversarial samples. Experiments on the highly imbalanced large benchmark "MIOvision Traffic Camera Dataset (MIO-TCD)" classification challenge dataset demonstrate that the proposed framework is able to increase the mean performance of some categories to some extent, while maintaining a high overall accuracy, compared with the baseline.

关键词： WEIGHTED FEATURE-EXTRACTION  

摘要： Hyperspectral classification with limited training samples is challenging. The current work lies in two aspects: first, we change the statistical distribution of samples by iterative filtering based on the guide images. The filter is called a Simplified Bilateral Filter (SBF), which is a modified bilateral filter for clustering samples. Secondly, new structural convolution kernels are used to generate new hyperspectral data. Finally, the class label of the test sample after dimension reduction is determined by OMP classification or SVM classification. Experimental results on two hyperspectral datasets demonstrate the effectiveness of the proposed feature extraction method in improving classification accuracy with limited training samples.

关键词： 材料智能   智能包装   活性包装   包装设计  

摘要： 目的探索材料智能型包装的分类体系、应用领域与设计实现。方法以现行材料智能型包装案例及文献为基础,对国内外相关的设计实践、专利及相关理论进行系统分析,并根据材料功能特性对其进行分类研究。结果提出了更完善的材料智能型包装的概念、分类、应用领域与设计关键。根据材料本身及其应用在材料智能型包装上表现出来的功能特征,在包装的展示销售、保鲜提醒、商品防伪以及安全防护等方面具有良好的应用前景,重点阐述了功能特征表现较为明显的变色材料包装、发光材料包装、智能水凝胶材料包装、活性包装等,并提出材料在智能型包装设计过程中应着重把握材料选择的恰当性、信息传达的准确性以及图形表现的巧妙性3个方面。结论对材料智能型包装的分类及设计应用进行了细化研究,为智能化包装的拓展研究提供了更多的方向,有利于推动包装产业的转型升级。

关键词： 动物检验检疫   食品安全   作用   措施  

摘要： 随着我国社会经济的不断发展，人民生活水平的不断提高，食品安全问题对人类生活的影响越来越显著，它不仅关系到人民群众的生命安全与健康，还会直接影响国家的稳定与发展。因此，动物检验检疫对食品安全至关重要，是保障食品安全的前提，可有效保证动物性食品安全。为将动物检验检疫的作用发挥到极致，本文通过对动物检验检疫于食品安全的作用进行剖析，进而提出相关改进措施，旨在为加强宣传食品安全的重要性，健全动物检验检疫的监管力度提供有效参考。