Simulated Datasets Research Articles

II-LA-KM: Improved Initialization of a Learning-Augmented Clustering Algorithm for Effective Rock Discontinuity Grouping

Rock mass discontinuities are an excellent information set for reflecting the geometric, spatial, and physical properties of the rock mass. Using clustering algorithms to analyze them is a significant way to select advantageous orientations of structural surfaces and provide a scientific theoretical basis for other rock mass engineering research. Traditional clustering algorithms often suffer from sensitivity to initialization and lack practical applicability, as discontinuity data are typically rough, low-precision, and unlabeled. Confronting these challenges, II-LA-KM, a learning-augmented clustering algorithm with improved initialization for rock discontinuity grouping, is proposed. Our method begins with heuristically selecting initial centers to ensure they are well-separated. Then, optimal transport is used to adjust these centers, minimizing the transport cost between them and other points. To enhance fault tolerance, a learning-augmented algorithm is integrated that iteratively reduces clustering costs, refining the initial results toward optimal clustering. Extensive experiments on a simulated artificial dataset and a real dataset from Woxi, Hunan, China, featuring both orientational and non-orientational attributes, demonstrate the effectiveness of II-LA-KM. The algorithm achieves a 97.5% accuracy on the artificial dataset and successfully differentiates between overlapping groups. Its performance is even more pronounced on the real dataset, underscoring its robustness for handling complex and noisy data. These strengths make our approach highly beneficial for practical rock discontinuity grouping applications.

Graph-based self-supervised learning for repeat detection in metagenomic assembly.

Repetitive DNA (repeats) poses significant challenges for accurate and efficient genome assembly and sequence alignment. This is particularly true for metagenomic data, in which genome dynamics such as horizontal gene transfer, gene duplication, and gene loss/gain complicate accurate genome assembly from metagenomic communities. Detecting repeats is a crucial first step in overcoming these challenges. To address this issue, we propose GraSSRep, a novel approach that leverages the assembly graph's structure through graph neural networks (GNNs) within a self-supervised learning framework to classify DNA sequences into repetitive and nonrepetitive categories. Specifically, we frame this problem as a node classification task within a metagenomic assembly graph. In a self-supervised fashion, we rely on a high-precision (but low-recall) heuristic to generate pseudolabels for a small proportion of the nodes. We then use those pseudolabels to train a GNN embedding and a random forest classifier to propagate the labels to the remaining nodes. In this way, GraSSRep combines sequencing features with predefined and learned graph features to achieve state-of-the-art performance in repeat detection. We evaluate our method using simulated and synthetic metagenomic data sets. The results on the simulated data highlight GraSSRep's robustness to repeat attributes, demonstrating its effectiveness in handling the complexity of repeated sequences. Additionally, experiments with synthetic metagenomic data sets reveal that incorporating the graph structure and the GNN enhances the detection performance. Finally, in comparative analyses, GraSSRep outperforms existing repeat detection tools with respect to precision and recall.

Systematic benchmark of single-cell hashtag demultiplexing approaches reveals robust performance of a clustering-based method.

Single-cell technology opened up a new avenue to delineate cellular status at a single-cell resolution and has become an essential tool for studying human diseases. Multiplexing allows cost-effective experiments by combining multiple samples and effectively mitigates batch effects. It starts by giving each sample a unique tag and then pooling them together for library preparation and sequencing. After sequencing, sample demultiplexing is performed based on tag detection, where cells belonging to one sample are expected to have a higher amount of the corresponding tag than cells from other samples. However, in reality, demultiplexing is not straightforward due to the noise and contamination from various sources. Successful demultiplexing depends on the efficient removal of such contamination. Here, we perform a systematic benchmark combining different normalization methods and demultiplexing approaches using real-world data and simulated datasets. We show that accounting for sequencing depth variability increases the separability between tagged and untagged cells, and the clustering-based approach outperforms existing tools. The clustering-based workflow is available as an R package from https://github.com/hwlim/hashDemux.

SIMVI reveals intrinsic and spatial-induced states in spatial omics data.

Spatial omics technologies enable the analysis of gene expression and interaction dynamics in relation to tissue structure and function. However, existing computational methods may not properly distinguish cellular intrinsic variability and intercellular interactions, and may thus fail to capture spatial regulations for further biological discoveries. Here, we present Spatial Interaction Modeling using Variational Inference (SIMVI), an annotation-free framework that disentangles cell intrinsic and spatial-induced latent variables for modeling gene expression in spatial omics data. We derive theoretical support for SIMVI in disentangling intrinsic and spatial-induced variations. By this disentanglement, SIMVI enables estimation of spatial effects (SE) at a single-cell resolution, and opens up various opportunities for novel downstream analyses. To demonstrate the potential of SIMVI, we applied SIMVI to spatial omics data from diverse platforms and tissues (MERFISH human cortex, Slide-seqv2 mouse hippocampus, Slide-tags human tonsil, spatial multiome human melanoma, cohort-level CosMx melanoma). In all tested datasets, SIMVI effectively disentangles variations and infers accurate spatial effects compared with alternative methods. Moreover, on these datasets, SIMVI uniquely uncovers complex spatial regulations and dynamics of biological significance. In the human tonsil data, SIMVI illuminates the cyclical spatial dynamics of germinal center B cells during maturation. Applying SIMVI to both RNA and ATAC modalities of the multiome melanoma data reveals potential tumor epigenetic reprogramming states. Application of SIMVI on our newly-collected cohort-level CosMx melanoma dataset uncovers space-and-outcome-dependent macrophage states and the underlying cellular communication machinery in the tumor microenvironments.

Fault Impulse Inference and Cyclostationary Approximation: A feature-interpretable intelligent fault detection method for few-shot unsupervised domain adaptation

With the advancement of intelligent detection for rotating machinery, numerous domain adaptation methods have been devised to transfer detection knowledge from one source domain working condition to another target domain working condition, involving extensive transfer scenarios including labeled, few-shot labeled, and unlabeled target conditions. Yet, learning from sparsely labeled signals in the source domain working condition and transferring to unlabeled target conditions, termed few-shot unsupervised domain adaptation (FUDA), is closer to reality but almost unexplored. Diverging from the intuition of combining existing transfer and few-shot learning technologies, this paper pioneers a novel single learning principle focusing on the cyclostationary mechanism (CT) of fault signals. In its implementation, named cyclically enhanced cyclostationary variational autoencoder (CCTVAE), the CT principle motivates the encoder to infer domain-shared representations with fault impulses, and the decoder approximates the cyclostationary structure containing the clear fault and working condition information. Then, auxiliary samples for few-shot expansion are generated by adjusting cyclic parameters of the posterior distribution of representations. Experimentally, CCTVAE achieves commendable results on simulated and real fault datasets. Even for compound faults, domain-shared representations and generated auxiliary signals manifest interpretable fault-indicating spectral lines in the frequency domain, underscoring method reliability.

Some density-based silhouette diagnostics for soft clustering algorithms

One of the main objectives of cluster analysis is to determine the most effective clustering algorithm. With the wide variety of algorithms available, assessing which one performs better is important. The performance of different clustering methods is typically measured using the Adjusted Rand Index (ARI), which relies on knowledge of the original class labels. However, this study introduces flexible modified alternatives of density-based silhouette methods for evaluating cluster performance. These proposed Density-based silhouettes can be applied to any soft clustering algorithms and do not require the original class labels. Instead, they rely on posterior probabilities. In this study, eight different soft clustering algorithms were evaluated using real and simulated data sets. The goal is to compare their effectiveness and performance using existing and proposed measures based on silhouette and the ARI.

CLPr_in_ML: Cleft Lip and Palate Reconstructed Features with Machine Learning

Background: Cleft lip and palate are two of the most common craniofacial congenital malformations in humans. It influences tens of millions of patients worldwide. The hazards of this disease are multifaceted, extending beyond the obvious facial malformation to encompass physiological functions, oral health, psychological well-being, and social aspects. Objective: The primary objective of our study is to demonstrate the importance of imaging in detecting cleft lip and palate. By observing the morphological and structural abnormalities involving the lip and palate through imaging methods, this study aims to establish imaging as the primary diagnostic approach for this disease. Methods: In this work, we proposed a novel model to analyze unilateral complete cleft lip and palate after velopharyngeal closure and non-left lip and palate patients from the Department of Stomatology of Xuzhou First People's Hospital, Conical Beam CT (CBCT) images in silicon. In order to demonstrate the generalization, the simulated dataset was constructed using the random disturbance factor, which is from the actual dataset. We extracted several raw features from CBCT images in detail. Then, we proposed a novel feature reconstruction method, including six types of reconstructed factors, to reconstruct the existing features. Then, the reconstructed features weretrained with machine learning algorithms. Finally, the testing and independent data model was utilized to analyze the performance of this work. Results: By comparing different operator features, the min operator, max operator, average operator, and all operators can achieve good performances in both the testing set and the independent set. result: none Conclusion: With the different operator features, the majority of classification models, including Gradient Boosting, Hist Gradient Boosting, Multilayer Perceptron, lightGBM, and broadened learning, classification algorithms can get the well-performances in the selected reconstructed feature operators.

Importance estimate of features via analysis of their weight and gradient profile

Understanding what is important and redundant within data can improve the modelling process of neural networks by reducing unnecessary model complexity, training time and memory storage. This information is however not always priorly available nor trivial to obtain from neural networks. There are existing feature selection methods which utilise the internal working of a neural network for selection, however further analysis and interpretation of the input features’ significance is often limiting. We propose an approach that offers an extension that estimates the significance of features by analysing the gradient descent of a pairwise layer within a model. The changes that occur with the weights and gradients throughout training provide a profile that can be used to better understand the importance hierarchy between the features for ranking and feature selection. Additionally, this method is transferable to existing fully or partially trained models, which is beneficial for understanding existing or active models. The proposed approach is demonstrated empirically with a study which uses benchmark datasets from libraries such as MNIST and scikit-feat, as well as a simulated dataset and an applied real world dataset. This is verified with the ground truth where available, and if not, via a comparison of fundamental feature selection methods, which includes existing statistical based and embedded neural network based feature selection methods through the methodology of Reduce and Retrain.

Spatially Informed Graph Structure Learning Extracts Insights from Spatial Transcriptomics.

Embeddings derived from cell graphs hold significant potential for exploring spatial transcriptomics (ST) datasets. Nevertheless, existing methodologies rely on a graph structure defined by spatial proximity, which inadequately represents the diversity inherent in cell-cell interactions (CCIs). This study introduces STAGUE, an innovative framework that concurrently learns a cell graph structure and a low-dimensional embedding from ST data. STAGUE employs graph structure learning to parameterize and refine a cell graph adjacency matrix, enabling the generation of learnable graph views for effective contrastive learning. The derived embeddings and cell graph improve spatial clustering accuracy and facilitate the discovery of novel CCIs. Experimental benchmarks across 86 real and simulated ST datasets show that STAGUE outperforms 15 comparison methods in clustering performance. Additionally, STAGUE delineates the heterogeneity in human breast cancer tissues, revealing the activation of epithelial-to-mesenchymal transition and PI3K/AKT signaling in specific sub-regions. Furthermore, STAGUE identifies CCIs with greater alignment to established biological knowledge than those ascertained by existing graph autoencoder-based methods. STAGUE also reveals the regulatory genes that participate in these CCIs, including those enriched in neuropeptide signaling and receptor tyrosine kinase signaling pathways, thereby providing insights into the underlying biologicalprocesses.

Automated model-free analysis of cryo-EM volume ensembles with SIREn.

Cryogenic electron microscopy (cryo-EM) has the potential to capture snapshots of proteins in motion and generate hypotheses linking conformational states to biological function. This potential has been increasingly realized by the advent of machine learning models that allow 100s-1,000s of 3D density maps to be generated from a single dataset. How to identify distinct structural states within these volume ensembles and quantify their relative occupancies remain open questions. Here, we present an approach to inferring variable regions directly from a volume ensemble based on the statistical co-occupancy of voxels, as well as a 3D-convolutional neural network that predicts binarization thresholds for volumes in an unbiased and automated manner. We show that these tools recapitulate known heterogeneity in a variety of simulated and real cryo-EM datasets, and highlight how integrating these tools with existing data processing pipelines enables improved particle curation and the construction of quantitative conformational landscapes.

Transfer Learning Enabled Modeling Paradigm for PVT-aware Circuit Performance Estimation

Designing robust performance models for modern complex digital circuits in the face of rapidly accelerating process variations is a critical yet demanding task. This paper introduces an efficient statistical performance modeling approach for VLSI digital circuits that incurs minimal computational expense. The fundamental concept involves capitalizing on knowledge gained from circuit modeling in one technology node to streamline the modeling process in another. This is achieved by merging previously established statistical models of process technology with a limited set of simulation data from a subsequent process technology through transfer learning. Comprehensive experiments conducted across diverse technology nodes demonstrate that the proposed framework is robust, precise, efficient in data usage, and computationally superior to other cutting-edge performance modeling techniques.

Unpaired Image Translation to Mitigate Domain Shift in Liquid Argon Time Projection Chamber Detector Responses

Abstract Deep learning algorithms often are developed and trained on a training dataset and deployed on test datasets. Any systematic difference between the training and a test dataset may severely degrade the final algorithm performance on the test dataset -- what is known as the domain shift problem. This issue is prevalent in many scientific domains where algorithms are trained on simulated data but applied to real-world datasets. Typically, the domain shift problem is solved through various domain adaptation methods. However, these methods are often tailored to a specific downstream task and may not easily generalize to different tasks. This work explores the feasibility of using an alternative way to solve the domain shift problem that is not specific to any downstream algorithm. The proposed approach relies on modern Unpaired Image-to-Image translation techniques, designed to find translations between different image domains in a fully unsupervised fashion. In this study, the approach is applied to a domain shift problem commonly encountered in Liquid Argon Time Projection Chamber detector research when seeking a way to translate samples between two differently distributed LArTPC detector datasets deterministically. This translation allows for mapping real-world data into the simulated data domain where the downstream algorithms can be run with much less domain-shift-related performance degradation. Conversely, using the translation from the simulated data in a real-world domain can increase the realism of the simulated dataset and reduce the magnitude of any systematic uncertainties. We adapted several popular UI2I translation algorithms to work on scientific data and demonstrated the viability of these techniques for solving the domain shift problem with LArTPC detector data. To facilitate further development of domain adaptation techniques for scientific datasets, the "Simple Liquid-Argon Track Samples" (SLATS) dataset used in this study also is published.

Orbital angular momentum superimposed mode recognition based on multi-label image classification

Orbital angular momentum (OAM) multiplexing technology has great potential in high capacity optical communication. OAM superimposed mode can extend communication channels and thus enhance the capacity, and accurate recognition of multi-OAM superimposed mode at the receiver is very crucial. However, traditional methods are inefficient and complex for the recognition task. Machine learning and deep learning can offer fast, accurate and adaptable recognition, but they also face challenges. At present, the OAM mode recognition mainly focus on single OAM mode and ±l superimposed dual-OAM mode, while few researches on multi-OAM superimposed mode, due to the limitations of single-object image classification techniques and the diversity of features to recognize. To this end, we develop a recognition method combined with multi-label image classification to accurately recognize multi-OAM superimposed mode vortex beams. Firstly, we create datasets of intensity distribution map of three-OAM and four-OAM superimposed mode vortex beams based on numerical simulations and experimental acqusitions. Then we design a progressive channel-spatial attention (PCSA) model, which incorporates a progressive training strategy and two weighted attention modules. For the numerical simulation datasets, our model achieves the highest average recognition accuracy of 94.9% and 91.2% for three-OAM and four-OAM superimposed mode vortex beams with different transmission distances and noise strengths respectively. The highest experimental average recognition accuracy for three-OAM superimposed mode achieves 92.7%, which agrees with the numerical result very well. Furthermore, our model significantly outperforms in most metrics compared with ConvNeXt, and all experiments are within the affordable range of computational cost.

Electoral rules and the two-party system: A methodological inquiry with reference to Duverger’s law

The law of Duverger posits that the single-member plurality electoral system favours the two-party system. The empirical tests of Duvergerian effects often rely on the effective number of parties as the most common measure of party system fragmentation. This study, proceeding from the notion that more focused measures of two-partyness could be of greater utility for this purpose, examines the build-up of two already existing, albeit underused, indices that are intended to operationalize the concept of the two-party system and introduces a new family of party-system indices for the purpose of cross-validation. The quantitative analysis performed on simulated and real-life datasets shows that the measures of two-partyness can improve the methods of inquiry in research on Duvergerian effects, and that some of the indices introduced in this study can serve as useful supplements to the toolkit of political science.

The Estimating Parameter and Number of Knots for Nonparametric Regression Methods in Modelling Time Series Data

This research aims to explore and compare several nonparametric regression techniques, including smoothing splines, natural cubic splines, B-splines, and penalized spline methods. The focus is on estimating parameters and determining the optimal number of knots to forecast cyclic and nonlinear patterns, applying these methods to simulated and real-world datasets, such as Thailand’s coal import data. Cross-validation techniques are used to control and specify the number of knots, ensuring the curve fits the data points accurately. The study applies nonparametric regression to forecast time series data with cyclic patterns and nonlinear forms in the dependent variable, treating the independent variable as sequential data. Simulated data featuring cyclical patterns resembling economic cycles and nonlinear data with complex equations to capture variable interactions are used for experimentation. These simulations include variations in standard deviations and sample sizes. The evaluation criterion for the simulated data is the minimum average mean square error (MSE), which indicates the most efficient parameter estimation. For the real data, monthly coal import data from Thailand is used to estimate the parameters of the nonparametric regression model, with the MSE as the evaluation metric. The performance of these techniques is also assessed in forecasting future values, where the mean absolute percentage error (MAPE) is calculated. Among the methods, the natural cubic spline consistently yields the lowest average mean square error across all standard deviations and sample sizes in the simulated data. While the natural cubic spline excels in parameter estimation, B-splines show strong performance in forecasting future values.

A Bayesian hybrid method for the analysis of generalized linear models with missing-not-at-random covariates

Missing data handling is one of the main problems in modelling, particularly if the missingness is of type missing-not-at-random (MNAR) where missingness occurs due to the actual value of the observation. The focus of the current article is generalized linear modelling of fully observed binary response variables depending on at least one MNAR covariate. For the traditional analysis of such models, an individual model for the probability of missingness is assumed and incorporated in the model framework. However, this probability model is untestable, as the missingness of MNAR data depend on their actual values that would have been observed otherwise. In this article, we consider creating a model space that consist of all possible and plausible models for probability of missingness and develop a hybrid method in which a reversible jump Markov chain Monte Carlo (RJMCMC) algorithm is combined with Bayesian Model Averaging (BMA). RJMCMC is adopted to obtain posterior estimates of model parameters as well as probability of each model in the model space. BMA is used to synthesize coefficient estimates from all models in the model space while accounting for model uncertainties. Through a validation study with a simulated data set and a real data application, the performance of the proposed methodology is found to be satisfactory in accuracy and efficiency of estimates.

Using serosurveys to optimize surveillance for zoonotic pathogens.

Zoonotic pathogens pose a significant risk to human health, with spillover into human populations contributing to chronic disease, sporadic epidemics, and occasional pandemics. Despite the widely recognized burden of zoonotic spillover, our ability to identify which animal populations serve as primary reservoirs for these pathogens remains incomplete. This challenge is compounded when prevalence reaches detectable levels only at specific times of year. In these cases, statistical models designed to predict the timing of peak prevalence could guide field sampling for active infections. Thus, we develop a general model that leverages routinely collected serosurveillance data to optimize sampling for elusive pathogens by predicting time windows of peak prevalence. Using simulated data sets, we show that our methodology reliably identifies times when pathogen prevalence is expected to peak. Then, we demonstrate an implementation of our method using publicly available data from two putative Ebolavirus reservoirs, straw-colored fruit bats (Eidolon helvum) and hammer-headed bats (Hypsignathus monstrosus). We envision our method being used to guide the planning of field sampling to maximize the probability of detecting active infections, and in cases when longitudinal data is available, our method can also yield predictions for the times of year that are most likely to produce future spillover events. The generality and simplicity of our methodology make it broadly applicable to a wide range of putative reservoir species where seasonal patterns of birth lead to predictable, but potentially short-lived, pulses of pathogen prevalence.

Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction.

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremely sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

Enhancing EEG data quality and precision for cloud-based clinical applications: an evaluation of the SLOG framework

Automation is revamping our preprocessing pipelines, and accelerating the delivery of personalized digital medicine. It improves efficiency, reduces costs, and allows clinicians to treat patients without significant delays. However, the influx of multimodal data highlights the need to protect sensitive information, such as clinical data, and safeguard data fidelity. One of the neuroimaging modalities that produces large amounts of time-series data is Electroencephalography (EEG). It captures the neural dynamics in a task or resting brain state with high temporal resolution. EEG electrodes placed on the scalp acquire electrical activity from the brain. These electrical potentials attenuate as they cross multiple layers of brain tissue and fluid yielding relatively weaker signals than noise-low signal-to-noise ratio. EEG signals are further distorted by internal physiological artifacts, such as eye movements (EOG) or heartbeat (ECG), and external noise, such as line noise (50 Hz). EOG artifacts, due to their proximity to the frontal brain regions, are particularly challenging to eliminate. Therefore, a widely used EOG rejection method, independent component analysis (ICA), demands manual inspection of the marked EOG components before they are rejected from the EEG data. We underscore the inaccuracy of automatized ICA rejection and provide an auxiliary algorithm-Second Layer Inspection for EOG (SLOG) in the clinical environment. SLOG based on spatial and temporal patterns of eye movements, re-examines the already marked EOG artifacts and confirms no EEG-related activity is mistakenly eliminated in this artifact rejection step. SLOG achieved a 99% precision rate on the simulated dataset while 85% precision on the real EEG dataset. One of the primary considerations for cloud-based applications is operational costs, including computing power. Algorithms like SLOG allow us to maintain data fidelity and precision without overloading the cloud platforms and maxing out our budgets.

Adjustable robust optimization approach for SVM under uncertainty

The support vector machine (SVM) is one of the successful approaches to the classification problem. Since the values of features are typically affected by uncertainty, it is important to incorporate uncertainty into the SVM formulation. This paper focuses on developing a robust optimization (RO) model for SVM. A key distinction from existing literature lies in the timing of optimizing decision variables. To the best of our knowledge, in all existing RO models developed for SVM, a common assumption is that all decision variables are decided before the uncertainty realization, which leads to an overly conservative decision boundary. However, this paper adopts a different strategy by determining the variables that assess the misclassification error of data points or their fall within the margin post-realization, resulting in a less conservative model. The RO models where decisions are made in two stages (some before and the rest after the uncertainty resolution), are called adjustable RO models. This adjustment results in a three-level optimization model for which two decomposition-based algorithms are proposed. In these algorithms, after providing a bi-level reformulation, the model is divided into a master-problem (MP) and a sub-problem the interaction of which yields the optimal solution. Acceleration of algorithms via incorporating valid inequalities into MP is another novelty of this paper. Computational results over simulated and real-world datasets confirm the efficiency of the proposed model and algorithms.