Sample Problems Research Articles

Causal discovery from nonstationary time series

AbstractThis paper introduces a new causal structure learning method for nonstationary time series data, a common data type found in fields such as finance, economics, healthcare, and environmental science. Our work builds upon the constraint-based causal discovery from nonstationary data algorithm (CD-NOD). We introduce a refined version (CD-NOTS) which is designed specifically to account for lagged dependencies in time series data. We compare the performance of different algorithmic choices, such as the type of conditional independence test and the significance level, to help select the best hyperparameters given various scenarios of sample size, problem dimensionality, and availability of computational resources. Using the results from the simulated data, we apply CD-NOTS to a broad range of real-world financial applications in order to identify causal connections among nonstationary time series data, thereby illustrating applications in factor-based investing, portfolio diversification, and comprehension of market dynamics.

Host-Guest Binding Free Energies à la Carte: An Automated OneOPES Protocol.

Estimating absolute binding free energies from molecular simulations is a key step in computer-aided drug design pipelines, but the agreement between computational results and experiments is still very inconsistent. Both the accuracy of the computational model and the quality of the statistical sampling contribute to this discrepancy, yet disentangling the two remains a challenge. In this study, we present an automated protocol based on OneOPES, an enhanced sampling method that exploits replica exchange and can accelerate several collective variables to address the sampling problem. We apply this protocol to 37 host-guest systems. The simplicity of setting up the simulations and producing well-converged binding free energy estimates without the need to optimize simulation parameters provides a reliable solution to the sampling problem. This, in turn, allows for a systematic force field comparison and ranking according to the correlation between simulations and experiments, which can inform the selection of an appropriate model. The protocol can be readily adapted to test more force field combinations and study more complex protein-ligand systems, where the choice of an appropriate physical model is often based on heuristic considerations rather than systematic optimization.

Calculating linear and nonlinear multi-ensemble slow collective variables for protein folding.

Traditional molecular dynamics simulation of biomolecules suffers from the conformational sampling problem. It is often difficult to produce enough valid data for post analysis such as free energy calculation and transition path construction. To improve the sampling, one practical solution is putting an adaptive bias potential on some predefined collective variables. The quality of collective variables strongly affects the sampling ability of a molecule in the simulation. In the past, collective variables were built with the sampling data at a constant temperature. This is insufficient because of the same sampling problem. In this work, we apply the standard weighted histogram analysis method to calculate the multi-ensemble averages of pairs of time-lagged features for the construction of both linear and nonlinear slow collective variables. Compared to previous single-ensemble methods, the presented method produces averages with much smaller statistical uncertainties. The generated collective variables help a peptide and a miniprotein fold to their near-native states in a short simulation time period. By using the method, enhanced sampling simulations could be more effective and productive.

Dynamic model-based intelligent fault diagnosis method for fault detection in a rod fastening rotor

A complete fault sample database is of great significance for the intelligent fault diagnosis method of rod fastening rotor. However, the lack of fault samples makes the fault diagnosis results unbelievable. To solve this issue, the dynamic model-based intelligent fault diagnosis method is established for a rod fastening rotor, and the fault sample database is enriched by numerical simulations. First, the lumped parameter model of the rod fastening rotor system is constructed and further updated using Euclidean Distance between measurement and numerical simulation of the intact system. Second, mathematical models of various fault types are incorporate into the updated model to obtain numerical simulation fault samples. Thirdly, the utilization of numerical simulation fault samples is severed as training data to the artificial intelligence (AI) models and the unknown measurement test samples will be finally classified. In this paper, Support Vector Machine, Random Forest, Bayesian Network and Decision Tree are selected as the typical AI models. Subsequently, the feasibility of classification is validated by the test bench of the rod fastening rotor system, and the problem of insufficient fault samples can be solved.

Small-Sample Data Pricing Based on Data Augmentation and Meta-Learning

Data trading platforms play a crucial role in facilitating data circulation and promoting the sustainable allocation of data resources. Establishing a transparent, fair, and efficient pricing mechanism is key to ensuring the long-term stability and development of such platforms. However, these platforms face challenges in pricing due to the small sample problem, as traditional machine learning methods typically rely on large amounts of data. To address this issue, this paper proposes a data resource pricing model that combines WGAN-GP data augmentation and the Reptile algorithm. Data augmentation generates related datasets to increase sample size, enhancing the renewability of data resources, while meta-learning transfers knowledge across tasks, improving the model’s ability to quickly adapt to new tasks and efficiently utilize resources. Validation using actual trading data from the data trading platform shows that the proposed model accurately predicts data resource prices under small-sample conditions, outperforming other models. This study addresses the limitations of existing pricing methods in small-sample scenarios, providing a sustainable pricing solution for small-sample data resources and improving the accuracy and long-term stability of data pricing in the market.

Aero-engine defect detection by integrating attention and multi-scale features

The structural integrity of aircraft engines is related to flight safety. At present, aircraft engine defect detection based on borescope technology is mainly manual operation. In order to improve the detection accuracy and efficiency, an intelligent aircraft engine defect detection algorithm that integrates attention and multi-scale features is proposed to assist borescope work. First, to address the class imbalance problem of defect samples in the original borescope image, a multi- sample fusion data enhancement method based on geometric transformation and Poisson image editing is used to enrich small sample images and construct a defect dataset. Then, the coordinated attention module (CA) is integrated into the baseline network YOLOv5 to emphasize the extraction of defect features and enhance the network's distinction between defect targets and complex backgrounds. A weighted bidirectional feature pyramid structure (BiFPN) is constructed in the neck network to complete higher-level feature fusion and improve the expression ability of multi-scale targets. Finally, the bounding box regression loss function is defined as the EIOU loss to achieve fast and accurate positioning and identification of defect targets. Experimental results show that the average accuracy of defect detection of the proposed algorithm reaches 89.7%, which is improved compared with the baseline network 6.3%, and the size of the trained model is only 14.0 M. Therefore, the proposed method can effectively detect the main defects of aircraft engines.

A fault diagnosis method for bearings and gears in rotating machinery based on data fusion and transfer learning

Abstract Rotating machinery is a crucial component of industrial equipment, and the fault diagnosis of bearings and gears, as vital elements of rotating machinery, is essential since they often fail under harsh working conditions, leading to significant property losses and serious personal safety problems. However, fault data for gears and bearings are often sparse in actual condition, and it is a challenge to ensure the reliability and stability of fault diagnosis results by extracting the features of a single data. To solve the above problems, this paper proposes a fault diagnosis method that combines Transfer Learning and data fusion techniques. Firstly, in this method, two kinds of fault signals are transformed into Gramian Angular Difference Fields and Recurrence Plot. Next, a U-shaped feature fusion dual discriminator generative adversarial network is used to fuse two-dimensional images from multiple sensor data. Its feature fusion module deeply integrates the features of the two images, thereby solving the impact of single data on the reliability and stability of fault diagnosis. Moreover, open-source datasets are used for Transfer Learning training to tackle the small sample problem. Finally, a decision-level information fusion classifier, the Dual-Branch Dempster-Shafer Classifier (DB-DSC), classifies the fused images. This classifier incorporates an improved soft threshold function and D-S evidence theory to achieve adaptive gradient changes and improve the robustness and accuracy of classification results. The experimental results show the effectiveness and stability of the proposed method, and the generated images get high score in several metrics. The average classification accuracy of the classification network reaches 93% and 92.5% on the two datasets, Therefore, the proposed method exhibits strong fault diagnosis capabilities under the small sample conditions of bearings and gears.

Convolutional variational autoencoder and multi-scale attention convolutional neural network based diagnostics on filament current sensors for mass spectrometers

Fault detection of the filament current sensor of the spaceborne mass spectrometer is of great significance to the safe operation of the mass spectrometer. Neglecting sensor failures may affect the normal operation of the mass spectrometer, which in turn affects the health of the astronauts and the space missions. This paper proposes an enhanced intelligent diagnosis method based on filament current sensor for mass spectrometer via improved deep learning network, aiming to improve the accuracy and reliability of the filament current sensor when the fault samples are insufficient. The improved convolutional variational autoencoder (CVAE) model not only enhances the data for four typical sensor fault signals, namely bias, drift, missing and random, but also solves the problem of insufficient samples when spike, Precision degradation and stuck fault occur in sensors. Short-time Fourier transform (STFT) is utilized to transform one-dimensional data into two-dimensional spectrograms, which gives more fault characteristics to the data set. The improved multi-scale attention mechanism convolutional neural network (MSAM-CNN) model is constructed to perform fault diagnosis on the generated spectrogram, which solves the problem of low accuracy of fault identification in traditional convolutional neural network (CNN) models. The results of ablation and comparison experiments show that the samples generated by CVAE have smaller Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Square Error (RMSE), the enhanced samples improve the classification and clustering of MSAM-CNN, and compared to other diagnostic models, MSAM-CNN achieves the highest accuracy, precision, recall, and F1-score of 99.2%, 99.3%, 98.8%, and 0.991.

Effectiveness Evaluation Method Using System of Systems Architecture Description of Aircraft Health Management in Aircraft Maintenance Program

This study proposes a system modeling method for aircraft maintenance program development that adopts condition-based maintenance using aircraft health management (AHM) based on a systems engineering approach, which considers AHM as a system of systems. The metamodel is tailored on the basis of the Unified Architecture Framework (UAF) and the NASA Systems Modeling Handbook for Systems Engineering. It is described using the modeling tool "Balus 2.0" (Levii, Inc). The applicability and effectiveness of a maintenance program adopting AHM is analyzed on the basis of the Maintenance Steering Group-3 (MSG-3), and its effectiveness is evaluated using the proposed system modeling method. The proposed method considers the uncertainty of the aircraft maintenance environment related to airline operations in addition to the uncertainty of the aircraft system. The effectiveness of the proposed system is investigated through a sample problem that considers a tire system using a pressure monitoring system as AHM based on the MSG-3 approach. Finally, the limitations of the proposed method are discussed.

Advantages of general parametric solution Approach in dynamics courses

Problems of dynamics are treated using a general parametric solution approach. The advantages of treating problems in the parametric way is discussed. The approach has many advantages over the numerical calculations starting from the beginning: 1) Solutions are expressed in the general form suitable for algorithmic programming 2) Unit check on the correctness of the results are easier 3) Effect of each input parameter on the desired output parameter can be easily observed 4) Results can be evaluated for the limiting cases to recognize the soundness of the solutions. 5) Mathematical principles can be more exploited on the solutions 6) Solutions give more insight on the design principles. The ideas are outlined using three sample problems. The advantages of the approach have been tested on Mechanical Engineering Sophomore students for over 16 years with success.

Multi-Scale Candidate Fusion and Optimization-Based 3D Object Detection Algorithm

To address the issues of target omission and the inclusion of a large number of background points in keypoint sampling for point cloud-based object detection, an improved algorithm based on the PV-RCNN network is introduced. This approach employs both a regional proposal fusion network and weighted Non-Maximum Suppression (NMS) to merge proposals generated at various scales while eliminating redundancy. A segmentation network is utilized to segment foreground points from the original point cloud, and object center points are identified based on these proposals. Gaussian density functions are employed for regional density estimation, which assigns different sampling weights to solve the problem of difficult sampling in sparse areas. Experimental evaluations on the KITTI dataset indicate that the algorithm enhances the average precision at medium difficulty levels by 0.39%, 1.31%, and 0.63%for cars, pedestrians, and cyclists, respectively. Generalization experiments were also conducted on the Waymo dataset. The results suggest that the introduced algorithm achieves higher accuracy compared to most of the existing 3D object detection networks.

A Deep Learning-Driven Sampling Technique to Explore the Phase Space of an RNA Stem-Loop.

The folding and unfolding of RNA stem-loops are critical biological processes; however, their computational studies are often hampered by the ruggedness of their folding landscape, necessitating long simulation times at the atomistic scale. Here, we adapted DeepDriveMD (DDMD), an advanced deep learning-driven sampling technique originally developed for protein folding, to address the challenges of RNA stem-loop folding. Although tempering- and order parameter-based techniques are commonly used for similar rare-event problems, the computational costs or the need for a priori knowledge about the system often present a challenge in their effective use. DDMD overcomes these challenges by adaptively learning from an ensemble of running MD simulations using generic contact maps as the raw input. DeepDriveMD enables on-the-fly learning of a low-dimensional latent representation and guides the simulation toward the undersampled regions while optimizing the resources to explore the relevant parts of the phase space. We showed that DDMD estimates the free energy landscape of the RNA stem-loop reasonably well at room temperature. Our simulation framework runs at a constant temperature without external biasing potential, hence preserving the information on transition rates, with a computational cost much lower than that of the simulations performed with external biasing potentials. We also introduced a reweighting strategy for obtaining unbiased free energy surfaces and presented a qualitative analysis of the latent space. This analysis showed that the latent space captures the relevant slow degrees of freedom for the RNA folding problem of interest. Finally, throughout the manuscript, we outlined how different parameters are selected and optimized to adapt DDMD for this system. We believe this compendium of decision-making processes will help new users adapt this technique for the rare-event sampling problems of their interest.

Analysis of the Grid Quantization for the Microwave Radar Coincidence Imaging Based on Basic Correlation Algorithm

In Microwave Radar Coincidence Imaging (MRCI), the imaging region is typically discretized into a fine grid. In other words, it assumes that the equivalent scatterers of the target are precisely located at the centers of these pre-discretized grids. However, this approach usually encounters the off-grid problem, which can significantly degrade the imaging performance. In this paper, to establish a criterion for grid quantization, the performance of the MRCI system related to the grid size and the distribution of imaging points is investigated. First, the discretization of the imaging scene is regarded as a random sampling problem, and the off-grid imaging model for MRCI is established. Then, the probability distribution function (PDF) of the imaging amplitude for a single point target is analyzed, and the mean first-order imaging error (MFE) for multiple point targets is derived based on the Basic Correlation Algorithm (BCA). Finally, the relationship between the grid quantization of the imaging area and the performance of the MRCI system is analyzed, providing a theoretical guidance for enhancing the performance of MRCI. The validity of the analyses is verified through simulation experiments.

A novel reinforcement learning agent for rotating machinery fault diagnosis with data augmentation

The problem of data imbalance and limited sample poses a prominent challenge to fault diagnosis in industry, especially in rotating machinery fault diagnosis due to the constraints of sampling and labeling. Reinforcement learning is known for its auto-optimized learning ability but it is severely limited by the quality and quantity of data it is able to collect. This paper applies the Equilibrium Deep Q-Network (Equilibrium-DQN) based agent with the Variational Autoencoder with Wasserstein Generative Adversarial Network and Gradient Penalty (VAE-WGAN-GP) for rotating machinery fault diagnosis. The Equilibrium-DQN possesses the property of leveraging multiple target networks to improve training stability and accuracy. The VAE-WGAN-GP excels in resolving data scarcity problems in fault diagnosis, especially in enriching labeled data with more typical samples while keeping the original data features. Herein, a novel framework is presented that integrates both data augmentation techniques with reinforcement learning agent for fault diagnosis. The proposed framework improves the weakness of insufficient samples in fault diagnosis and reveals its potential in complex industrial applications. The experiments, both on the test bench dataset and on the real locomotive dataset, confirm the advantage of the proposed framework.

Fault diagnosis of planetary gearboxes under small and imbalanced samples based on enhanced Siamese network with improved downsampling module

Due to the limitations of the operating conditions and equipment status, in practice, the normal data for planetary gearboxes are often sufficient, but the fault data are scarce and difficult to obtain, causing the fault diagnosis to face not only an imbalance problem but also a small sample problem. It leads to serious misdiagnosis and poor generalizability. To overcome above challenges, an enhanced Siamese network with improved downsampling module is proposed to reduce the negative impact of small and imbalanced datasets on fault diagnosis. Firstly, the Siamese network is combined with data enhancement to adaptively increase the fault training data with different small sample degrees. It can make the number of training data of each class get rid of small sample, while avoiding the excessive use of scarce fault data causing additional overfitting, so as to improve the generalization of the model. Among them, the data enhancement adopts the extreme noise expansion method proposed in this work, which can quickly generate samples that meet the requirements and help to improve the performance of the model in noisy environments. Secondly, adding the improved downsampling module to the Siamese network. The improved downsampling module introduces density-based spatial clustering of applications with noise (DBSCAN) and distribution ratio calculation, which can consider the distribution range and density of data when selecting. It can not only balance the training data, but also avoid serious information loss, and then reduce the probability of misdiagnosis. Finally, using six imbalanced planetary gearbox datasets with different small sample degrees for verification. The experimental results show that the proposed method can efficiently increase and balance the training data, which greatly improves the accuracy of fault diagnosis under the condition of small and imbalanced samples, especially when the small sample degree is very serious, the accuracy is improved by 57.76% on average.

Opportunities and challenges of diffusion models for generative AI

ABSTRACT Diffusion models, a powerful and universal generative artificial intelligence technology, have achieved tremendous success and opened up new possibilities in diverse applications. In these applications, diffusion models provide flexible high-dimensional data modeling, and act as a sampler for generating new samples under active control towards task-desired properties. Despite the significant empirical success, theoretical underpinnings of diffusion models are very limited, potentially slowing down principled methodological innovations for further harnessing and improving diffusion models. In this paper, we review emerging applications of diffusion models to highlight their sample generation capabilities under various control goals. At the same time, we dive into the unique working flow of diffusion models through the lens of stochastic processes. We identify theoretical challenges in analyzing diffusion models, owing to their complicated training procedure and interaction with the underlying data distribution. To address these challenges, we overview several promising advances, demonstrating diffusion models as an efficient distribution learner and a sampler. Furthermore, we introduce a new avenue in high-dimensional structured optimization through diffusion models, where searching for solutions is reformulated as a conditional sampling problem and solved by diffusion models. Lastly, we discuss future directions about diffusion models. The purpose of this paper is to provide a well-rounded exposure for stimulating forward-looking theories and methods of diffusion models.

Causal Attention Deep-learning Model for Solar Flare Forecasting

Solar flares originate from the sudden release of energy stored in the magnetic field of the active region on the Sun, but the trigger for flares is still uncertain. Currently, deep-learning-based solar flare prediction models have achieved good results and are widely recognized. However, these models focus more on data correlation rather than causality. An ideal flare prediction model should probe into the causes/triggers of solar flares, and diagnose the precursors of flares rather than just correlation analysis. To extract more informative precursors of flares from magnetograms, while suppressing the interference of confounding factors, a causal attention module is introduced to disentangle causal and confounder features from the input features. To address the problem of imbalanced positive and negative samples in the data set, an adaptive data set split mechanism is proposed. It divides the data set into several balanced subsets of positive and negative samples, and dynamically adjusts the subsets according to the model’s prediction results during the training process. The experimental results demonstrate that our proposed model achieves 4.08%, 8.38%, and 2.19% higher accuracy, true skill score, and area under the receiver operating characteristic curve than the baseline model. Additionally, the class-specific heatmaps by using the gradient-weighted class activation mapping method reveal that our proposed model generally focuses on the polarity inverse line of active regions, well in line with theoretical study.

Self-supervised learning-based re-parameterization instance segmentation for hazardous object in terahertz image

Recently, terahertz imaging technology has shown widespread potential applications in the public security screening field. Previous terahertz hazardous object detection techniques primarily relied on manual recognition and image processing methods. Some solutions incorporating deep learning technologies depend on large quantities of high-quality data, making it challenging to achieve low-cost and high-performance detection. To solve the issue of dependency on large amounts of high-quality data, we propose a diversified dynamic structure You Only Look Once (DDS-YOLO) model based on masked image modeling and structural reparameterization for the instance segmentation of hazardous objects in terahertz security inspection images. To address the scarcity and annotating difficulty problems of terahertz security inspection image samples, we combine automatic data strategies with masked image modeling for self-supervised learning. We propose a multilevel feature refinement fusion mechanism to enhance the quality of learned feature representations. The backbone parameter transfer and fine-tuning training strategies are employed to achieve hazardous object instance segmentation on the terahertz dataset. To address the low detection accuracy issue caused by the poor terahertz image quality, we develop a reparameterizable hierarchical structure for the backbone, improve a multi-scale feature-integrating neck, and design a dynamically decoupled head with lower computational requirements to enhance the performance of the instance segmentation model. Experimental results demonstrate that the proposed model accurately outputs detection boxes, categories, and segmentation masks for hazardous objects with minimal training samples. The comparative experimental results indicate that the proposed model outperforms existing state-of-the-art methods in terms of detection performance. The proposed DDS-YOLO model achieves 59.3 % in mask mean Average Precision (mAP) and 61.3 % in box mAP, and the model parameters and computational requirements also meet practical application scenarios.

Contribution of Lobe Power to Experiment Heating in the Advanced Test Reactor

In order to ease the computational burden associated with designing irradiation experiments in the Advanced Test Reactor (ATR), scaling factors are often used to estimate design parameters at different lobe powers. This paper examines the validity of long-standing assumptions about the contribution of lobe power to total experiment heating in the ATR. For each of the ATR’s 77 different experiment positions, the fractional contribution of each of the ATR’s five lobes to the total heating in that position is calculated and compared to traditional assumptions. The updated fractional contributions are then used to scale heating rates in a sample problem, and the results are compared to traditional scaling methods as well as explicit MC21 heating calculations. It is concluded that for experiment locations in close proximity to the ATR driver fuel (i.e. flux traps and the A, H, and B positions), heating rates scaled with the updated fractional contributions generally agree better with explicit MC21 calculations than do heating rates scaled using the traditionally assumed contributions. For the I positions, which are located on the very periphery of the ATR core, both scaling methods led to poor results when compared against explicit calculations due to the effect that movement of the outer shim control cylinders has on the experiment heating in those positions.

Assessing AI-generated (GPT-4) Versus Human Created MCQs In Mathematics Education: A Comparative Inquiry into Vector Topics

Using multiple-choice questions as learning and assessment tools is standard at all levels of education. However, when discussing the positive and negative aspects of their use, the time and complexity involved in producing plausible distractor options emerge as a disadvantage that offsets the time savings in relation to feedback. The article attempts to understand whether, with the AI conquests on the educational landscape, we can now remove this aspect from the list of drawbacks. This paper aims to determine the suitability of GPT-4 for generating questions and answer options for multiple-choice questions using prompts in Estonian on topics related to vectors and their similarities and differences compared to questions and answers created by a human expert. The results show that GPT-4 can generate multiple-choice questions and answer options based on given learning objectives, theory, and sample problems. However, the suggested correct answer option often requires correction and is not yet linguistically at such a level that teachers can use the questions without editing. Verifying the generated tasks still becomes labour-intensive for teachers. Nonetheless, it is more crucial that the AI tool accurately determines the correct answer than that some of the generated distractors are not plausible.