sandbox – Creating and Analysing Synthetic Sediment Sections with R

The majority of palaeoenvironmental information is inferred from proxy data contained in accretionary sediments, called geo-archives. The validity of proxy data and analysis workflows are usually assumed implicitly, with systematic tests and uncertainty estimates restricted to modern analogue studies or reduced-complexity case studies. However, a more generic and consistent approach to exploring the validity and variability of proxy functions would be to translate a given geo-archive into a model scenario: a "virtual twin". Here, we introduce a conceptual framework and numerical toolset that allows the definition and analysis of synthetic sediment sections. The R package sandbox describes arbitrary stratigraphically consistent deposits by depth-dependent rules and grain-specific parameters, allowing full scalability and flexibility. Virtual samples can be taken, resulting in discrete grain-mixtures with well-defined parameters. These samples can then be virtually prepared and analysed, for example to test hypotheses. We illustrate the concept of sandbox, explain how a sediment section can be mapped into the model and, by focusing on an exemplary field of application, we explore universal geochronological research questions related to the effects of sample geometry and grain-size specific age inheritance. We summarise further application scenarios of the model framework, relevant for but not restricted to the broader geochronological community.

Few-Shot Charge Prediction with Data Augmentation and Feature Augmentation

The task of charge prediction is to predict the charge based on the fact description. Existing methods have a good effect on the prediction of high-frequency charges, but the prediction of low-frequency charges is still a challenge. Moreover, there exist some confusing charges that have relatively similar fact descriptions, which can be easily misjudged. Therefore, we propose a model with data augmentation and feature augmentation for few-shot charge prediction. Specifically, the model takes the text description as the input and uses the Mixup method to generate virtual samples for data augmentation. Then, the charge information heterogeneous graph is introduced, and a novel graph convolutional network is designed to extract distinguishability features for feature augmentation. A feature fusion network is used to effectively integrate the charge graph knowledge into the fact to learn semantic-enhanced fact representation. Finally, the semantic-enhanced fact representation is used to predict the charge. In addition, based on the distribution of each charge, a category prior loss function is designed to increase the contribution of low-frequency charges to the model optimization. The experimental results on real-work datasets prove the effectiveness and robustness of the proposed model.

A Generative Adversarial Network Structure for Learning with Small Numerical Data Sets

In recent years, generative adversarial networks (GANs) have been proposed to generate simulated images, and some works of literature have applied GAN to the analysis of numerical data in many fields, such as the prediction of building energy consumption and the prediction and identification of liver cancer stages. However, these studies are based on sufficient data volume. In the current era of globalization, the demand for rapid decision-making is increasing, but the data available in a short period of time is scarce. As a result, machine learning may not provide precise results. Obtaining more information from a small number of samples has become an important issue. Therefore, this study aimed to modify the generative adversarial network structure for learning with small numerical datasets, starting with the Wasserstein GAN (WGAN) as the GAN architecture, and using mega-trend-diffusion (MTD) to limit the bound of virtual samples that the GAN generates. The model verification of our proposed structure was conducted with two datasets in the UC Irvine Machine Learning Repository, and the performance was evaluated using three criteria: accuracy, standard deviation, and p-value. The experiment result shows that, using this improved GAN architecture (WGAN_MTD), small sample data can also be used to generate virtual samples that are similar to real samples through GAN.

Virtual samples based robust block-diagonal dictionary learning for face recognition

It is an open question to learn an over-complete dictionary from a limited number of face samples, and the inherent attributes of the samples are underutilized. Besides, the recognition performance may be adversely affected by the noise (and outliers), and the strict binary label based linear classifier is not appropriate for face recognition. To solve above problems, we propose a virtual samples based robust block-diagonal dictionary learning for face recognition. In the proposed model, the original samples and virtual samples are combined to solve the small sample size problem, and both the structure constraint and the low rank constraint are exploited to preserve the intrinsic attributes of the samples. In addition, the fidelity term can effectively reduce negative effects of noise (and outliers), and the ε-dragging is utilized to promote the performance of the linear classifier. Finally, extensive experiments are conducted in comparison with many state-of-the-art methods on benchmark face datasets, and experimental results demonstrate the efficacy of the proposed method.

Self-Attention-Based Conditional Variational Auto-Encoder Generative Adversarial Networks for Hyperspectral Classification

Hyperspectral classification is an important technique for remote sensing image analysis. For the current classification methods, limited training data affect the classification results. Recently, Conditional Variational Autoencoder Generative Adversarial Network (CVAEGAN) has been used to generate virtual samples to augment the training data, which could improve the classification performance. To further improve the classification performance, based on the CVAEGAN, we propose a Self-Attention-Based Conditional Variational Autoencoder Generative Adversarial Network (SACVAEGAN). Compared with CVAEGAN, we first use random latent vectors to obtain more enhanced virtual samples, which can improve the generalization performance. Then, we introduce the self-attention mechanism into our model to force the training process to pay more attention to global information, which can achieve better classification accuracy. Moreover, we explore model stability by incorporating the WGAN-GP loss function into our model to reduce the mode collapse probability. Experiments on three data sets and a comparison of the state-of-art methods show that SACVAEGAN has great advantages in accuracy compared with state-of-the-art HSI classification methods.

Variational Generative Adversarial Network with Crossed Spatial and Spectral Interactions for Hyperspectral Image Classification

Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have been widely used in hyperspectral image classification (HSIC) tasks. However, the generated HSI virtual samples by VAEs are often ambiguous, and GANs are prone to the mode collapse, which lead the poor generalization abilities ultimately. Moreover, most of these models only consider the extraction of spectral or spatial features. They fail to combine the two branches interactively and ignore the correlation between them. Consequently, the variational generative adversarial network with crossed spatial and spectral interactions (CSSVGAN) was proposed in this paper, which includes a dual-branch variational Encoder to map spectral and spatial information to different latent spaces, a crossed interactive Generator to improve the quality of generated virtual samples, and a Discriminator stuck with a classifier to enhance the classification performance. Combining these three subnetworks, the proposed CSSVGAN achieves excellent classification by ensuring the diversity and interacting spectral and spatial features in a crossed manner. The superior experimental results on three datasets verify the effectiveness of this method.

An improved bootstrap method introducing error ellipse for numerical analysis of fatigue life parameters

Purpose The purpose of this paper is to introduce error ellipse into the bootstrap method to improve the reliability of small samples and the credibility of the S-N curve. Design/methodology/approach Based on the bootstrap method and the reliability of the original samples, two error ellipse models are proposed. The error ellipse model reasonably predicts that the discrete law of expanded virtual samples obeys two-dimensional normal distribution. Findings By comparing parameters obtained by the bootstrap method, improved bootstrap method (normal distribution) and error ellipse methods, it is found that the error ellipse method achieves the expansion of sampling range and shortens the confidence interval, which improves the accuracy of the estimation of parameters with small samples. Through case analysis, it is proved that the tangent error ellipse method is feasible, and the series of S-N curves is reasonable by the tangent error ellipse method. Originality/value The error ellipse methods can lay a technical foundation for life prediction of products and have a progressive significance for the quality evaluation of products.

AMOSTRAS VIRTUAIS DE ATRIBUTOS DO SOLO COMO SUBSÍDIO AO PLANEJAMENTO PARA ANÁLISE GEOESTATÍSTICA

AMOSTRAS VIRTUAIS DE ATRIBUTOS DO SOLO COMO SUBSÍDIO AO PLANEJAMENTO PARA ANÁLISE GEOESTATÍSTICA DIEGO AUGUSTO DE CAMPOS MORAES1, ANDERSON ANTÔNIO DA CONCEIÇÃO SARTORI2 1 Professor Doutor, Departamento de Análise e Desenvolvimento de Sistemas, Faculdade Eduvale de Avaré, Av. Prefeito Misael Eufrásio Leal, 347 - Centro, Avaré - SP, 18705-050, [email protected]. 2 Professor Doutor, Grupo de Estudos e Pesquisas Agrárias Georreferenciadas, Faculdade de Ciências Agronômicas de Botucatu – FCA/UNESP, Avenida Universitária, 3780, Altos do Paraíso, Botucatu – SP, 18610-034, [email protected]. RESUMO: O objetivo deste artigo foi propor uma metodologia de amostragem virtual para atributos do solo em área agrícola, a qual pode subsidiar o planejamento para análise geoestatística. Foram selecionadas, aleatoriamente, 23 amostras de solo (profundidades de 0-20 cm e 20-40 cm) do conjunto de dados original, com o objetivo de realizar a validação externa. Foi aplicado o procedimento de polígonos de Thiessen com base nas demais amostras originais do solo (47 amostras) e, em seguida, foram inseridas, aleatoriamente, amostras virtuais (53 amostras). A análise do variograma, validação cruzada, krigagem ordinária e validação externa foram executadas com a finalidade de verificar a robustez da metodologia. A inserção de amostras virtuais mostrou-se promissora, uma vez que o GDE (Grau de Dependência Espacial) e a validação cruzada dos atributos do solo foram aprimorados, situação que não foi observada nos dados originalmente amostrados. A validação externa obteve bons resultados, indicando que a amostragem virtual pode ser utilizada unicamente no planejamento para análise geoestatística. Palavras-chaves: variograma, validação cruzada, solos. VIRTUAL SAMPLES OF SOIL ATTRIBUTES AS A SUBSIDY FOR GEOSTATISTICAL ANALYSIS PLANNING ABSTRACT: The aim of this article was to propose a virtual sampling methodology for soil attributes in an agricultural area, which can support planning for geostatistical analysis. Twenty-three soil samples (depths of 0-20 cm and 20-40 cm) from the original data set were selected randomly, for an external validation process. The Thiessen polygons procedure was applied based on the remaining original soil samples (47 samples), and then, virtual samples (53 samples) were randomly inserted. The analysis of the variogram, cross-validation, ordinary kriging and external validation were performed in order to verify the robustness of the methodology. The insertion of virtual samples was promising, since the GDE (Degree of Spatial Dependence) and the cross-validation of soil attributes were improved, which was not observed in the data originally sampled. The external validation obtained good results, indicating that the virtual sampling can be used only in the planning for geostatistical analysis. Keywords: variogram, cross-validation, soil.