Generic Data Model Research Articles

ENSO predictive analytics based on layered rendering

AbstractEl Niño-Southern Oscillation (ENSO) is a periodic climate phenomenon in the equatorial Pacific that significantly influences global climate patterns. Accurate prediction and monitoring of ENSO events are essential for meteorological agencies and governmental institutions. This study introduces a content-guided attention module within a convolutional neural network to improve prediction accuracy. This module models inter-channel relationships and enhances information interaction by integrating channel and spatial attention weights. These advancements substantially improve prediction accuracy and help overcome the spring prediction barrier in ENSO forecasting. The research emphasizes global feature modeling and proposes a novel content-guided ENSO prediction model. It also includes an ocean data generation model utilizing global attention. Furthermore, a layered rendering technique is employed to invert ocean data, facilitating detailed analysis and contributing to the development of an ocean synthetic dataset.

Development of a cerebellar ataxia diagnosis model using conditional GAN-based synthetic data generation for visuomotor adaptation task.

This study proposes a synthetic data generation model to create a classification framework for cerebellar ataxia patients using trajectory data from the visuomotor adaptation task. The classification objectives include patients with cerebellar ataxia, age-matched normal individuals, and young healthy subjects. Synthetic data for the three classes is generated based on class conditions and random noise by leveraging a combination of conditional adversarial generative neural networks and reconstruction networks. This synthetic data, alongside real data, is utilized as training data for the patient classification model to enhance classification accuracy. The fidelity of the synthetic data is assessed visually to measure the validity and diversity of the generated data qualitatively while quantitatively evaluating distribution similarity to real data. Furthermore, the clinical efficacy of the patient classification model employing synthetic data is demonstrated by showcasing improved classification accuracy through a comparative analysis between results obtained using solely real data and those obtained when both real and synthetic data are utilized. This methodological approach holds promise in addressing data insufficiency in the digital healthcare domain, employing deep learning methodologies, and developing early disease diagnosis tools.

Research on Jiangxi Cultural Wisdom Tourism Industry Strategy Based on OHDSI General Data Model and Digital Art Empowerment

With the rapid development and wide application of a new round of information technologies, such as the global Internet of Things, the new generation of mobile Internet, cloud computing, etc., informatization has opened a new stage of smart tourism (ST), and ST has become the main trend of tourism development in China at present and for a long time to come. Tourism industry has become one of the important pillar industries in Jiangxi, and it plays an increasingly prominent role in stimulating and supporting economic and social development. Wisdom tourism is an important means to improve tourism service, tourism management and tourism marketing, and an important starting point to promote the upgrading of tourism industry in Jiangxi Province, and to achieve carry-over and leapfrog development and overtaking at corners. This paper is constantly improving and updating on the basis of data warehouse integration mechanism. Under the data warehouse mechanism, through the effective integration of spatial data, virtual reality data and dynamic data, a comprehensive data warehouse oriented to tourism promotion, scenic spot management and department management is formed. It aims to promote the rapid implementation of ST, bring tourists a comfortable tourism experience, save costs and improve efficiency for tourism service providers.

Modelling ℤ-valued time series with Skellam thinning-based INAR(1) process

ABSTRACT Non-stationary count time series, which are small in value and show a trend having relatively large fluctuation, are commonly encountered in real-world applications. Differencing is a commonly employed method to transform a non-stationary time series into a stationary one. However, the differenced count time series is defined on Z and cannot be fitted by the mainstream count time series models, which are defined on N 0 . Although some integer-valued autoregressive (INAR) models based on the signed thinning operator have been proposed for fitting Z -valued time series, these models still encounter difficulties in terms of data generation mechanism, model selection, and parameter estimation. These difficulties may pose challenges for practitioners in practical applications. Therefore, this article utilizes the reparameterized version of the Skellam (Poisson difference) distribution to construct a new thinning operator, thereby introducing a class of Z -valued time series models. Strict stationarity, ergodicity, statistical properties, and parameter estimation methods of the processes are detailedly discussed. An application to the monthly counts of newly listed companies illustrates that the new model is superior in data analysis of finance and economics.

Design-Based Theory for Lasso Adjustment in Randomized Block Experiments and Rerandomized Experiments

Blocking, a special case of rerandomization, is routinely implemented in the design stage of randomized experiments to balance the baseline covariates. This study proposes a regression adjustment method based on the least absolute shrinkage and selection operator (Lasso) to efficiently estimate the average treatment effect in randomized block experiments with high-dimensional covariates. We derive the asymptotic properties of the proposed estimator and outline the conditions under which this estimator is more efficient than the unadjusted one. We provide a conservative variance estimator to facilitate valid inferences. Our framework allows one treated or control unit in some blocks and heterogeneous propensity scores across blocks, thus including paired experiments and finely stratified experiments as special cases. We further accommodate rerandomized experiments and a combination of blocking and rerandomization. Moreover, our analysis allows both the number of blocks and block sizes to tend to infinity, as well as heterogeneous treatment effects across blocks without assuming a true outcome data-generating model. Simulation studies and two real-data analyses demonstrate the advantages of the proposed method.

Rotor fault diagnosis of centrifugal pumps in nuclear power plants based on CWGAN-GP-CNN for imbalanced dataset

As a crucial device in nuclear power plants, centrifugal pumps undertake the critical role of cooling water circulation. Centrifugal pump rotor misalignment and unbalanced faults cause pump performance degradation, vibration increase, and equipment damage, thus seriously affecting the safety and reliability of nuclear power plants. In the process of centrifugal pump rotor fault, the difficulty in obtaining data samples and the limited amount of data can lead to an imbalance problem between the quantity of normal state and fault state samples in the dataset. In order to solve the problem, this paper proposed a CWGAN-GP model for generating rotor fault data based on CGAN and WGAN-GP models, and combined it with a two-stream CNN model to realize the rotor fault diagnosis with an imbalanced dataset. The quality and performance of the data generated by the proposed method were evaluated and validated in terms of visualization analysis, statistical indicators, and comparison with different data generation models. The results show that the CWGAN-GP model can generate high-quality data. Meanwhile, compared with other models on datasets with different degrees of imbalance, the two-stream CNN model is more effective in fault diagnosis on the expanded dataset by the CWGAN-GP model, and the improvement of fault diagnosis accuracy ranges from 1.40% to 13.33%.

Model of oil pipeline tiny defects detection based on DDPM gated parallel convolutional swin transformer

Abstract To address the challenges of difficult detection of minute magnetic flux leakage (MFL) defects, insufficient inspection data, and low detection accuracy, the denoising diffusion probabilistic model (DDPM) gate dilated parallel convolution swin transformer (DGPST) is proposed. First, we introduce a DDPM-based data generation model, successfully generating a large quantity of diverse and rich MFL defect samples. Second, a gated parallel convolution layer is introduced into the backbone network. This strategy uses the characteristics of dilated convolution to broaden the receptive field of the model, thus enhancing the integration ability of global information. The addition of gating mechanism enables the model to adjust the calculation of attention weight based on broader context information in advance, which not only complicates the shortcomings of window self-attention in global dependence understanding, but also effectively suppress irrelevant calculation. Finally, the loss function of H Intersection over Union is introduced to improve the mean average precision. Following these enhancements, DGPST attains a satisfactory outcome in detecting tiny defects within the MFL problem. Experimental data indicates the accuracy of the algorithm reaches 95.6% and the delay is reduced to 7.6 ms.

Possible Data-Generating Models of Longitudinal Continuous Outcomes and Intercurrent Events to Investigate Estimands

We aim to explore data-generating models to jointly simulate outcomes and intercurrent events for randomized clinical trials to enable the investigation of estimands. We develop four possible data-generating models for the joint distribution of longitudinal continuous clinical outcomes and intercurrent events under the scenario where they are observable: a selection model, a pattern-mixture mixed model, a shared-parameter model, and a joint model of longitudinally observed outcomes and a survival model for intercurrent events. We present a case study in a short-term depression trial with repeated measurements of continuous outcomes and two types of intercurrent events, and evaluate the potential and challenges of such data-generating models. Simulating randomized trials with outcomes and intercurrent events is a complex undertaking. We found that the four possible data-generating models can simulate different types of intercurrent events and associated longitudinal outcomes. They can be used to emulate envisaged patterns of intercurrent events and outcomes informed by prior available trial data or expectations. Model and parameter choice for a given application require further development. The four possible data-generating models could be used to investigate different estimands and their properties in-depth in the design stage. Thereby they are useful tools for the selection of estimands a priori.

A conceptual data modeling framework with four levels of abstraction for environmental information

Environmental data generated by observation infrastructures and models is widely heterogeneous in both structure and semantics. The design and implementation of an ad hoc data model for each new dataset is costly and creates barriers for data integration. On the other hand, designing a single data model that supports any kind of environmental data has shown to be a complex task, and the resulting tools do not provide the required efficiency. In this paper, a new data modeling framework is proposed that enables the reuse of generic structures among different application domains and specific applications. The framework considers four levels of abstraction for the data models. Levels 1 and 2 provide general data model structures for environmental data, based on those defined by the Observations and Measurements (O&M) standard of the Open Geospatial Consortium (OGC). Level 3 incorporates generic data models for different application areas, whereas specific application models are designed at Level 4, reusing structures of the previous levels. Various use cases were implemented to illustrate the capabilities of the framework. A performance evaluation using six datasets of three different use cases has shown that the query response times achieved over the structures of Level 4 are very good compared to both ad hoc models and to a direct implementation of O&M in a Sensor Observation Service (SOS) tool. A qualitative evaluation shows that the framework fulfills a collection of general requirements not supported by any other existing solution.

Relational Persistent Homology for Multispecies Data with Application to the Tumor Microenvironment

Topological data analysis (TDA) is an active field of mathematics for quantifying shape in complex data. Standard methods in TDA such as persistent homology (PH) are typically focused on the analysis of data consisting of a single entity (e.g., cells or molecular species). However, state-of-the-art data collection techniques now generate exquisitely detailed multispecies data, prompting a need for methods that can examine and quantify the relations among them. Such heterogeneous data types arise in many contexts, ranging from biomedical imaging, geospatial analysis, to species ecology. Here, we propose two methods for encoding spatial relations among different data types that are based on Dowker complexes and Witness complexes. We apply the methods to synthetic multispecies data of a tumor microenvironment and analyze topological features that capture relations between different cell types, e.g., blood vessels, macrophages, tumor cells, and necrotic cells. We demonstrate that relational topological features can extract biological insight, including the dominant immune cell phenotype (an important predictor of patient prognosis) and the parameter regimes of a data-generating model. The methods provide a quantitative perspective on the relational analysis of multispecies spatial data, overcome the limits of traditional PH, and are readily computable.

Trust Your Gut: Comparing Human and Machine Inference from Noisy Visualizations.

People commonly utilize visualizations not only to examine a given dataset, but also to draw generalizable conclusions about the underlying models or phenomena. Prior research has compared human visual inference to that of an optimal Bayesian agent, with deviations from rational analysis viewed as problematic. However, human reliance on non-normative heuristics may prove advantageous in certain circumstances. We investigate scenarios where human intuition might surpass idealized statistical rationality. In two experiments, we examine individuals' accuracy in characterizing the parameters of known data-generating models from bivariate visualizations. Our findings indicate that, although participants generally exhibited lower accuracy compared to statistical models, they frequently outperformed Bayesian agents, particularly when faced with extreme samples. Participants appeared to rely on their internal models to filter out noisy visualizations, thus improving their resilience against spurious data. However, participants displayed overconfidence and struggled with uncertainty estimation. They also exhibited higher variance than statistical machines. Our findings suggest that analyst gut reactions to visualizations may provide an advantage, even when departing from rationality. These results carry implications for designing visual analytics tools, offering new perspectives on how to integrate statistical models and analyst intuition for improved inference and decision-making. The data and materials for this paper are available at https://osf.io/qmfv6.

Generative models for synthetic data generation: application to pharmacokinetic/pharmacodynamic data.

The generation of synthetic patient data that reflect the statistical properties of real data plays a fundamental role in today's world because of its potential to (i) be enable proprietary data access for statistical and research purposes and (ii) increase available data (e.g., in low-density regions-i.e., for patients with under-represented characteristics). Generative methods employ a family of solutions for generating synthetic data. The objective of this research is to benchmark numerous state-of-the-art deep-learning generative methods across different scenarios and clinical datasets comprising patient covariates and several pharmacokinetic/pharmacodynamic endpoints. We did this by implementing various probabilistic models aimed at generating synthetic data, such as the Multi-layer Perceptron Conditioning Generative Adversarial Neural Network (MLP cGAN), Time-series Generative Adversarial Networks (TimeGAN), and a more traditional approach like Probabilistic Autoregressive (PAR). We evaluated their performance by calculating discriminative and predictive scores. Furthermore, we conducted comparisons between the distributions of real and synthetic data using Kolmogorov-Smirnov and Chi-square statistical tests, focusing respectively on covariate and output variables of the models. Lastly, we employed pharmacometrics-related metric to enhance interpretation of our results specific to our investigated scenarios. Results indicate that multi-layer perceptron-based conditional generative adversarial networks (MLP cGAN) exhibit the best overall performance for most of the considered metrics. This work highlights the opportunities to employ synthetic data generation in the field of clinical pharmacology for augmentation and sharing of proprietary data across institutions.

Large Language Models for Synthetic Tabular Health Data: A Benchmark Study.

Synthetic tabular health data plays a crucial role in healthcare research, addressing privacy regulations and the scarcity of publicly available datasets. This is essential for diagnostic and treatment advancements. Among the most promising models are transformer-based Large Language Models (LLMs) and Generative Adversarial Networks (GANs). In this paper, we compare LLM models of the Pythia LLM Scaling Suite with varying model sizes ranging from 14M to 1B, against a reference GAN model (CTGAN). The generated synthetic data are used to train random forest estimators for classification tasks to make predictions on the real-world data. Our findings indicate that as the number of parameters increases, LLM models outperform the reference GAN model. Even the smallest 14M parameter models perform comparably to GANs. Moreover, we observe a positive correlation between the size of the training dataset and model performance. We discuss implications, challenges, and considerations for the real-world usage of LLM models for synthetic tabular data generation.

A model is worth tens of thousands of examples for estimation and thousands for classification

Traditional signal processing methods relying on mathematical data generation models have been cast aside in favour of deep neural networks, which require vast amounts of data. Since the theoretical sample complexity is nearly impossible to evaluate, these amounts of examples are usually estimated with crude rules of thumb. However, these rules only suggest when the networks should work, but do not relate to the traditional methods. In particular, an interesting question is: how much data is required for neural networks to be on par or outperform, if possible, the traditional model-based methods? In this work, we empirically investigate this question in three simple examples covering estimation and classification, where the data is generated according to precisely defined mathematical models, and where well-understood optimal or state-of-the-art mathematical data-agnostic solutions are known. A first problem is deconvolving one-dimensional Gaussian signals, a second one is estimating a circle’s radius and location in random grayscale images of disks, and a third one both classifies the presence of a line and locates it when present in a binary random dot image. By training various networks, either naive custom designed or well-established ones, with various amounts of training data, we find that networks require tens of thousands of examples for estimation in comparison to the traditional methods and thousands for classification, whether the networks are trained from scratch or even with transfer-learning or finetuning.

SAR vehicle image generation with integrated deep imaging geometric information

Deep learning is widely applied in synthetic aperture radar (SAR) target recognition. However, the high cost of collecting real SAR target data leads to insufficient data volume and diversity of SAR target datasets, making it challenging to support deep learning models. Therefore, it is necessary to expand SAR target datasets through data generation. However, existing SAR target data generation methods do not fully utilize the SAR imaging geometric information of targets. This results in generating image data that does not conform to SAR physical imaging laws. To address this problem, this paper proposes a SAR vehicle data generation method that integrates deep imaging geometric information. Compared to SAR, optical data, which contains rich geometric structural information of targets, is relatively easy to collect. Therefore, the proposed method computes the dominant scattering edge (DSE) of targets under different radar incident angles with optical data. Then, based on generative adversarial networks (GAN), a SAR vehicle target data generation model is constructed. To guide the model in learning SAR imaging geometric laws of targets, the computed DSE is integrated into the generation network with multi-scale attention mechanism modules. Compared to existing SAR target data generation methods, our proposed method can generate SAR vehicle target data with distinct dominant scattering edges, and effectively addresses the issue of generated target data not conforming to SAR imaging physical laws. Metrics such as Fréchet Inception Distance (FID), scattering intensity difference, and Structural Similarity Index (SSIM) are adopted for evaluation. The SSIM between the generated and the real SAR target data reaches 0.834, the FID minimum of 96.98, and the scattering intensity difference minimum of 0.37 dB, all indicating that the SAR target data generated by the proposed method is similar to real ones in terms of deep feature, scattering intensity, and image structure. Finally, the SAR target data generated by the proposed method is verified through target recognition experiments with VGG16 and ResNet50 as backbone network. The average recognition accuracy increases by 2.80% and 2.14%, respectively. The target recognition results demonstrate that the generated SAR data can help improve target recognition accuracy, thereby validating the effectiveness of data generated by the proposed method.

Model selection for network data based on spectral information

In this work, we explore the extent to which the spectrum of the graph Laplacian can characterize the probability distribution of random graphs for the purpose of model evaluation and model selection for network data applications. Network data, often represented as a graph, consist of a set of pairwise observations between elements of a population of interests. The statistical network analysis literature has developed many different classes of network data models, with notable model classes including stochastic block models, latent node position models, and exponential families of random graph models. We develop a novel methodology which exploits the information contained in the spectrum of the graph Laplacian to predict the data-generating model from a set of candidate models. Through simulation studies, we explore the extent to which network data models can be differentiated by the spectrum of the graph Laplacian. We demonstrate the potential of our method through two applications to well-studied network data sets and validate our findings against existing analyses in the statistical network analysis literature.

Model for generating data from navigation sensors for assessing the spatial position of objects

When selecting or developing new algorithms for assessing the spatial position of objects based on data from consumer navigation equipment (CNA) of global navigation satellite systems (GNSS) and data from inertial MEMS modules, the task of generating test model input data that meets certain conditions arises. Such conditions include, for example, the requirements for limited time increments of elements of spatio-temporal trajectories and ease of formation of their characteristic sections. The characteristic sections of spatio-temporal trajectories can be sections of a stationary position – sections of “Rest” or sections of rectilinear movement. The importance of forming these areas is due to the need to test the potential capabilities of compared or developed algorithms for assessing the spatial position of objects to ensure an improvement in their accuracy characteristics in the presence of such areas in various conditions. A data generation model is proposed for comparing algorithms for estimating the spatial position of objects, which ensures that the time increments of elements of spatio-temporal trajectories are limited in time and the simple formation of their characteristic sections is met. The model is based on the selection of a set of specified parameters that would allow, on the one hand, to form characteristic sections of spatio-temporal trajectories, and, on the other hand, to obtain model output data of NAP GNSS and inertial MEMS modules. The selected set of specified model parameters is determined through a set of analytically specified functions with sequential calculation of their parameters, which is much simpler compared to traditional approaches that involve solving boundary value problems of optimal control with restrictions on the type of control functions or the construction and application of genetic models and algorithms. The use of the developed model makes it possible to generate test model input data for the selection or development of new algorithms for assessing the spatial position of objects, implemented in devices that include CNA of GNSS and inertial MEMS modules and produce results both in real time and in delayed time. The effectiveness of the proposed solution is confirmed by the criterion of suitability under the considered conditions.

High-dimensional multivariate analysis of variance via geometric median and bootstrapping.

The geometric median, which is applicable to high-dimensional data, can be viewed as a generalization of the univariate median used in 1-dimensional data. It can be used as a robust estimator for identifying the location of multi-dimensional data and has a wide range of applications in real-world scenarios. This paper explores the problem of high-dimensional multivariate analysis of variance (MANOVA) using the geometric median. A maximum-type statistic that relies on the differences between the geometric medians among various groups is introduced. The distribution of the new test statistic is derived under the null hypothesis using Gaussian approximations, and its consistency under the alternative hypothesis is established. To approximate the distribution of the new statistic in high dimensions, a wild bootstrap algorithm is proposed and theoretically justified. Through simulation studies conducted across a variety of dimensions, sample sizes, and data-generating models, we demonstrate the finite-sample performance of our geometric median-based MANOVA method. Additionally, we implement the proposed approach to analyze a breast cancer gene expression dataset.

Data-driven Parameterizable Generative Adversarial Networks for Synthetic Data Augmentation of Guided Ultrasonic Wave Sensor Signals

Detecting and characterizing hidden damages in composite materials like Fibre-Metal Laminates (FML) remains a challenge. Guided Ultrasonic Waves (GUW) or X-ray imaging are commonly used to detect these damages, but their interpretation remains limited. Data-driven predictor models can detect damages in structures using GUW time-dependent signals, but the training data lacks variance, quality, and sufficient coverage of the hyper-parameter space. Synthetic data augmentation is often the only solution to create robust and generalized damage predictor models. Synthetic sensor data can be generated using model-based, model-assisted, or model-free methods. However, computed GUW signals show poor reality conformance due to too much constraints and simplifications. Recent developments in Generative Adversarial (Neural) Networks (GAN), commonly driven by a random generation process [1], include deterministic style vectors to generate specific signal data, determining constraints such as damage size, position, transducer positions, material and environmental properties. These new architectures aim to reduce the impact of environmental changes on data-driven damage predictor models by using parameterizable synthetic data generation. We will elaborate these new architectures and discuss the possibilities and challenges of using such GAN models for data generation of US signals in GUW-based SHM applications, as originally proposed in [2]. We will have a focus on low-quality real measuring data used for training and composite materials (e.g., FML) with hidden damages, and show some preliminary results. [1] Karras et al. "A style-based generator architecture for generative adversarial networks." Proceedings of the IEEE/CVF 2019 [2] Virupakshappa et al. "Using Generative Adversarial Networks to Generate Ultrasonic Signals." 2020 IEEE International Ultrasonics Symposium (IUS). IEEE, 2020

AraSpot: Arabic Spoken Command Spotting

Spoken keyword spotting (KWS) is the task of identifying a keyword in an audio stream and is widely used in smart devices at the edge in order to activate voice assistants and perform hands-free tasks. The task is daunting as there is a need, on the one hand, to achieve high accuracy while at the same time ensuring that such systems continue to run efficiently on low power and possibly limited computational capabilities devices. This work presents AraSpot for Arabic keyword spotting trained on 40 Arabic keywords, using different online data augmentation, and introducing ConformerGRU model architecture. Finally, we further improve the performance of the model by training a text-to-speech model for synthetic data generation. AraSpot achieved a State-of-the-Art SOTA 99.59% result outperforming previous approaches.