Access to individual-level health data is essential for gaining new insights and advancing science. In particular, modern methods based on artificial intelligence rely on the availability of and access to large datasets. In the health sector, access to individual-level data is often challenging due to privacy concerns. A promising alternative is the generation of fully synthetic data, i.e. data generated through a randomised process that have similar statistical properties as the original data, but do not have a one-to-one correspondence with the original individual-level records. In this study, we use a state-of-the-art synthetic data generation method and perform in-depth quality analyses of the generated data for a specific use case in the field of nutrition. We demonstrate the need for careful analyses of synthetic data that go beyond descriptive statistics and provide valuable insights into how to realise the full potential of synthetic datasets. By extending the methods, but also by thoroughly analysing the effects of sampling from a trained model, we are able to largely reproduce significant real-world analysis results in the chosen use case.
相關內容
Federal administrative data, such as tax data, are invaluable for research, but because of privacy concerns, access to these data is typically limited to select agencies and a few individuals. An alternative to sharing microlevel data is to allow individuals to query statistics without directly accessing the confidential data. This paper studies the feasibility of using differentially private (DP) methods to make certain queries while preserving privacy. We also include new methodological adaptations to existing DP regression methods for using new data types and returning standard error estimates. We define feasibility as the impact of DP methods on analyses for making public policy decisions and the queries accuracy according to several utility metrics. We evaluate the methods using Internal Revenue Service data and public-use Current Population Survey data and identify how specific data features might challenge some of these methods. Our findings show that DP methods are feasible for simple, univariate statistics but struggle to produce accurate regression estimates and confidence intervals. To the best of our knowledge, this is the first comprehensive statistical study of DP regression methodology on real, complex datasets, and the findings have significant implications for the direction of a growing research field and public policy.
Modeling binary and categorical data is one of the most commonly encountered tasks of applied statisticians and econometricians. While Bayesian methods in this context have been available for decades now, they often require a high level of familiarity with Bayesian statistics or suffer from issues such as low sampling efficiency. To contribute to the accessibility of Bayesian models for binary and categorical data, we introduce novel latent variable representations based on P\'olya-Gamma random variables for a range of commonly encountered logistic regression models. From these latent variable representations, new Gibbs sampling algorithms for binary, binomial, and multinomial logit models are derived. All models allow for a conditionally Gaussian likelihood representation, rendering extensions to more complex modeling frameworks such as state space models straightforward. However, sampling efficiency may still be an issue in these data augmentation based estimation frameworks. To counteract this, novel marginal data augmentation strategies are developed and discussed in detail. The merits of our approach are illustrated through extensive simulations and real data applications.
In observational studies, covariate imbalance generates confounding, resulting in biased comparisons. Although propensity score-based weighting approaches facilitate unconfounded group comparisons for implicit target populations, existing techniques may not directly or efficiently analyze multiple studies with multiple groups and provide results generalizable to larger populations. Moreover, few methods deliver precise inferences for various estimands with censored survival outcomes. We propose a new concordant target population approach, which constructs generalized balancing weights and realistic target populations. Our method can incorporate researcher-specified natural population attributes and synthesize information by appropriately compensating for over- or under-represented groups to achieve covariate balance. The constructed {concordant} weights are agnostic to specific estimators, estimands, and outcomes and maximize the effective sample size (ESS) for more precise inferences. Simulation studies and descriptive comparisons of glioblastoma outcomes of racial groups in multiple TCGA studies demonstrate the strategy's practical advantages. Unlike existing weighting techniques, the proposed concordant target population revealed a drastically different result: Blacks were more vulnerable and endured significantly worse prognoses; Asians had the best outcomes with a median overall survival of 1,024 (SE: 15.2) days, compared to 384 (SE: 1.2) and 329 (SE: 19.7) days for Whites and Blacks, respectively.
While meta-analyzing retrospective cancer patient cohorts, an investigation of differences in the expressions of target oncogenes across cancer subtypes is of substantial interest because the results may uncover novel tumorigenesis mechanisms and improve screening and treatment strategies. Weighting methods facilitate unconfounded comparisons of multigroup potential outcomes in multiple observational studies. For example, Guha et al. (2022) introduced concordant weights, allowing integrative analyses of survival outcomes by maximizing the effective sample size. However, it remains unclear how to use this or other weighting approaches to analyze a variety of continuous, categorical, ordinal, or multivariate outcomes, especially when research interests prioritize uncommon or unplanned estimands suggested by post hoc analyses; examples include percentiles and moments of group potential outcomes and pairwise correlations of multivariate outcomes. This paper proposes a unified meta-analytical approach accommodating various types of endpoints and fosters new estimators compatible with most weighting frameworks. Asymptotic properties of the estimators are investigated under mild assumptions. For undersampled groups, we devise small-sample procedures for quantifying estimation uncertainty. We meta-analyze multi-site TCGA breast cancer data, shedding light on the differential mRNA expression patterns of eight targeted genes for the subtypes infiltrating ductal carcinoma and infiltrating lobular carcinoma.
Using machine learning models to generate synthetic data has become common in many fields. Technology to generate synthetic transactions that can be used to detect fraud is also growing fast. Generally, this synthetic data contains only information about the transaction, such as the time, place, and amount of money. It does not usually contain the individual user's characteristics (age and gender are occasionally included). Using relatively complex synthetic demographic data may improve the complexity of transaction data features, thus improving the fraud detection performance. Benefiting from developments of machine learning, some deep learning models have potential to perform better than other well-established synthetic data generation methods, such as microsimulation. In this study, we built a deep-learning Generative Adversarial Network (GAN), called DGGAN, which will be used for demographic data generation. Our model generates samples during model training, which we found important to overcame class imbalance issues. This study can help improve the cognition of synthetic data and further explore the application of synthetic data generation in card fraud detection.
While open-ended self-explanations have been shown to promote robust learning in multiple studies, they pose significant challenges to automated grading and feedback in technology-enhanced learning, due to the unconstrained nature of the students' input. Our work investigates whether recent advances in Large Language Models, and in particular ChatGPT, can address this issue. Using decimal exercises and student data from a prior study of the learning game Decimal Point, with more than 5,000 open-ended self-explanation responses, we investigate ChatGPT's capability in (1) solving the in-game exercises, (2) determining the correctness of students' answers, and (3) providing meaningful feedback to incorrect answers. Our results showed that ChatGPT can respond well to conceptual questions, but struggled with decimal place values and number line problems. In addition, it was able to accurately assess the correctness of 75% of the students' answers and generated generally high-quality feedback, similar to human instructors. We conclude with a discussion of ChatGPT's strengths and weaknesses and suggest several venues for extending its use cases in digital teaching and learning.
Segmentation is an essential step for remote sensing image processing. This study aims to advance the application of the Segment Anything Model (SAM), an innovative image segmentation model by Meta AI, in the field of remote sensing image analysis. SAM is known for its exceptional generalization capabilities and zero-shot learning, making it a promising approach to processing aerial and orbital images from diverse geographical contexts. Our exploration involved testing SAM across multi-scale datasets using various input prompts, such as bounding boxes, individual points, and text descriptors. To enhance the model's performance, we implemented a novel automated technique that combines a text-prompt-derived general example with one-shot training. This adjustment resulted in an improvement in accuracy, underscoring SAM's potential for deployment in remote sensing imagery and reducing the need for manual annotation. Despite the limitations encountered with lower spatial resolution images, SAM exhibits promising adaptability to remote sensing data analysis. We recommend future research to enhance the model's proficiency through integration with supplementary fine-tuning techniques and other networks. Furthermore, we provide the open-source code of our modifications on online repositories, encouraging further and broader adaptations of SAM to the remote sensing domain.
During the usage phase, a technical product system is in permanent interaction with its environment. This interaction can lead to failures that significantly endanger the safety of the user and negatively affect the quality and reliability of the product. Conventional methods of failure analysis focus on the technical product system. The interaction of the product with its environment in the usage phase is not sufficiently considered, resulting in undetected potential failures of the product that lead to complaints. For this purpose, a methodology for failure identification is developed, which is continuously improved through product usage scenarios. The use cases are modelled according to a systems engineering approach with four views. The linking of the product system, physical effects, events and environmental factors enable the analysis of fault chains. These four parameters are subject to great complexity and must be systematically analysed using databases and expert knowledge. The scenarios are continuously updated by field data and complaints. The new approach can identify potential failures in a more systematic and holistic way. Complaints provide direct input on the scenarios. Unknown, previously unrecognized events can be systematically identified through continuous improvement. The complexity of the relationship between the product system and its environmental factors can thus be adequately taken into account in product development. Keywords: failure analysis, methodology, product development, systems engineering, scenario analysis, scenario improvement, environmental factors, product environment, continuous improvement.
In recent years, Graph Neural Networks have reported outstanding performance in tasks like community detection, molecule classification and link prediction. However, the black-box nature of these models prevents their application in domains like health and finance, where understanding the models' decisions is essential. Counterfactual Explanations (CE) provide these understandings through examples. Moreover, the literature on CE is flourishing with novel explanation methods which are tailored to graph learning. In this survey, we analyse the existing Graph Counterfactual Explanation methods, by providing the reader with an organisation of the literature according to a uniform formal notation for definitions, datasets, and metrics, thus, simplifying potential comparisons w.r.t to the method advantages and disadvantages. We discussed seven methods and sixteen synthetic and real datasets providing details on the possible generation strategies. We highlight the most common evaluation strategies and formalise nine of the metrics used in the literature. We first introduce the evaluation framework GRETEL and how it is possible to extend and use it while providing a further dimension of comparison encompassing reproducibility aspects. Finally, we provide a discussion on how counterfactual explanation interplays with privacy and fairness, before delving into open challenges and future works.
The development of unmanned aerial vehicles (UAVs) has been gaining momentum in recent years owing to technological advances and a significant reduction in their cost. UAV technology can be used in a wide range of domains, including communication, agriculture, security, and transportation. It may be useful to group the UAVs into clusters/flocks in certain domains, and various challenges associated with UAV usage can be alleviated by clustering. Several computational challenges arise in UAV flock management, which can be solved by using machine learning (ML) methods. In this survey, we describe the basic terms relating to UAVS and modern ML methods, and we provide an overview of related tutorials and surveys. We subsequently consider the different challenges that appear in UAV flocks. For each issue, we survey several machine learning-based methods that have been suggested in the literature to handle the associated challenges. Thereafter, we describe various open issues in which ML can be applied to solve the different challenges of flocks, and we suggest means of using ML methods for this purpose. This comprehensive review may be useful for both researchers and developers in providing a wide view of various aspects of state-of-the-art ML technologies that are applicable to flock management.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191