arXiv subjects

Qing Xia

Publications and source records attributed to Qing Xia.

52 records · Page 3Linked to original sources

arXiv2022

Local-basis Difference Potentials Method for elliptic PDEs in complex geometry

We develop efficient and high-order accurate finite difference methods for elliptic partial differential equations in complex geometry in the Difference Potentials framework. The main novelty of the developed schemes is the use of local basis functions defined at near-boundary grid points. The use of local basis functions allow unified numerical treatment of (i) explicitly and implicitly defined geometry; (ii) geometry of more complicated shapes, such as those with corners, multi-connected domain, etc; and (iii) different types of boundary conditions. This geometrically flexible approach is complementary to the classical difference potentials method using global basis functions, especially in the case where a large number of global basis functions are needed to resolve the boundary, or where the optimal global basis functions are difficult to obtain. Fast Poisson solvers based on FFT are employed for standard centered finite difference stencils regardless of the designed order of accuracy. Proofs of convergence of difference potentials in maximum norm are outlined both theoretically and numerically.

math.NA↗

arXiv2022

Electroweak Constraints from the COHERENT Experiment

We compute bounds on coefficients of effective operators in the Standard Model that can be inferred from observations of neutrino scattering by the COHERENT experiment. While many operators are bound extremely well by past experiments the full future data set from COHERENT will provide modest improvements for some operators.

hep-ph↗

arXiv2022

Improving Sample Efficiency of Deep Learning Models in Electricity Market

The superior performance of deep learning relies heavily on a large collection of sample data, but the data insufficiency problem turns out to be relatively common in global electricity markets. How to prevent overfitting in this case becomes a fundamental challenge when training deep learning models in different market applications. With this in mind, we propose a general framework, namely Knowledge-Augmented Training (KAT), to improve the sample efficiency, and the main idea is to incorporate domain knowledge into the training procedures of deep learning models. Specifically, we propose a novel data augmentation technique to generate some synthetic data, which are later processed by an improved training strategy. This KAT methodology follows and realizes the idea of combining analytical and deep learning models together. Modern learning theories demonstrate the effectiveness of our method in terms of effective prediction error feedbacks, a reliable loss function, and rich gradient noises. At last, we study two popular applications in detail: user modeling and probabilistic price forecasting. The proposed method outperforms other competitors in all numerical tests, and the underlying reasons are explained by further statistical and visualization results.

eess.SY↗

arXiv2022

SenseCare: A Research Platform for Medical Image Informatics and Interactive 3D Visualization

Clinical research on smart health has an increasing demand for intelligent and clinic-oriented medical image computing algorithms and platforms that support various applications. To this end, we have developed SenseCare research platform, which is designed to facilitate translational research on intelligent diagnosis and treatment planning in various clinical scenarios. To enable clinical research with Artificial Intelligence (AI), SenseCare provides a range of AI toolkits for different tasks, including image segmentation, registration, lesion and landmark detection from various image modalities ranging from radiology to pathology. In addition, SenseCare is clinic-oriented and supports a wide range of clinical applications such as diagnosis and surgical planning for lung cancer, pelvic tumor, coronary artery disease, etc. SenseCare provides several appealing functions and features such as advanced 3D visualization, concurrent and efficient web-based access, fast data synchronization and high data security, multi-center deployment, support for collaborative research, etc. In this report, we present an overview of SenseCare as an efficient platform providing comprehensive toolkits and high extensibility for intelligent image analysis and clinical research in different application scenarios. We also summarize the research outcome through the collaboration with multiple hospitals.

cs.HC↗

arXiv2022

Towards Self-supervised and Weight-preserving Neural Architecture Search

Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However, it is still cumbersome to deploy the NAS techniques in real-world applications due to the fussy procedures and the supervised learning paradigm. In this work, we propose the self-supervised and weight-preserving neural architecture search (SSWP-NAS) as an extension of the current NAS framework by allowing the self-supervision and retaining the concomitant weights discovered during the search stage. As such, we simplify the workflow of NAS to a one-stage and proxy-free procedure. Experiments show that the architectures searched by the proposed framework achieve state-of-the-art accuracy on CIFAR-10, CIFAR-100, and ImageNet datasets without using manual labels. Moreover, we show that employing the concomitant weights as initialization consistently outperforms the random initialization and the two-stage weight pre-training method by a clear margin under semi-supervised learning scenarios. Codes are publicly available at https://github.com/LzVv123456/SSWP-NAS.

cs.CV↗

arXiv2022

Open-Access Data and Toolbox for Tracking COVID-19 Impact on Power Systems

Intervention policies against COVID-19 have caused large-scale disruptions globally, and led to a series of pattern changes in the power system operation. Analyzing these pandemic-induced patterns is imperative to identify the potential risks and impacts of this extreme event. With this purpose, we developed an open-access data hub (COVID-EMDA+), an open-source toolbox (CoVEMDA), and a few evaluation methods to explore what the U.S. power systems are experiencing during COVID-19. These resources could be broadly used for research, public policy, and educational purposes. Technically, our data hub harmonizes a variety of raw data such as generation mix, demand profiles, electricity price, weather observations, mobility, confirmed cases and deaths. Typical methods are reformulated and standardized in our toolbox, including baseline estimation, regression analysis, and scientific visualization. Here the fluctuation index and probabilistic baseline are proposed for the first time to consider data fluctuation and estimation uncertainty. Based on these, we conduct three empirical studies on the U.S. power systems, and share new solutions and unexpected findings to address the issues of public concerns. This conveys a more complete picture of the pandemic's impacts, and also opens up several attractive topics for future work. Python, Matlab source codes, and user manuals are all publicly shared on a Github repository.

eess.SY↗

arXiv2022

Contrastive and Selective Hidden Embeddings for Medical Image Segmentation

Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation process lags down the speed of further advances. Contrastive learning-based weight pre-training provides an alternative by leveraging unlabeled data to learn a good representation. In this paper, we investigate how contrastive learning benefits the general supervised medical segmentation tasks. To this end, patch-dragsaw contrastive regularization (PDCR) is proposed to perform patch-level tugging and repulsing with the extent controlled by a continuous affinity score. And a new structure dubbed uncertainty-aware feature selection block (UAFS) is designed to perform the feature selection process, which can handle the learning target shift caused by minority features with high uncertainty. By plugging the proposed 2 modules into the existing segmentation architecture, we achieve state-of-the-art results across 8 public datasets from 6 domains. Newly designed modules further decrease the amount of training data to a quarter while achieving comparable, if not better, performances. From this perspective, we take the opposite direction of the original self/un-supervised contrastive learning by further excavating information contained within the label.

cs.CV↗

arXiv2021

Estimating Demand Flexibility Using Siamese LSTM Neural Networks

There is an opportunity in modern power systems to explore the demand flexibility by incentivizing consumers with dynamic prices. In this paper, we quantify demand flexibility using an efficient tool called time-varying elasticity, whose value may change depending on the prices and decision dynamics. This tool is particularly useful for evaluating the demand response potential and system reliability. Recent empirical evidences have highlighted some abnormal features when studying demand flexibility, such as delayed responses and vanishing elasticities after price spikes. Existing methods fail to capture these complicated features because they heavily rely on some predefined (often over-simplified) regression expressions. Instead, this paper proposes a model-free methodology to automatically and accurately derive the optimal estimation pattern. We further develop a two-stage estimation process with Siamese long short-term memory (LSTM) networks. Here, a LSTM network encodes the price response, while the other network estimates the time-varying elasticities. In the case study, the proposed framework and models are validated to achieve higher overall estimation accuracy and better description for various abnormal features when compared with the state-of-the-art methods.

cs.LG↗

arXiv2021

High-order accurate schemes for Maxwell's equations with nonlinear active media and material interfaces

We describe a fourth-order accurate finite-difference time-domain scheme for solving dispersive Maxwell's equations with nonlinear multi-level carrier kinetics models. The scheme is based on an efficient single-step three time-level modified equation approach for Maxwell's equations in second-order form for the electric field coupled to ODEs for the polarization vectors and population densities of the atomic levels. The resulting scheme has a large CFL-one time-step. Curved interfaces between different materials are accurately treated with curvilinear grids and compatibility conditions. A novel hierarchical modified equation approach leads to an explicit scheme that does not require any nonlinear iterations. The hierarchical approach at interfaces leads to local updates at the interface with no coupling in the tangential directions. Complex geometry is treated with overset grids. Numerical stability is maintained using high-order upwind dissipation designed for Maxwell's equations in second-order form. The scheme is carefully verified for a number of two and three-dimensional problems. The resulting numerical model with generalized dispersion and arbitrary nonlinear multi-level system can be used for many plasmonic applications such as for ab initio time domain modeling of nonlinear engineered materials for nanolasing applications, where nano-patterned plasmonic dispersive arrays are used to enhance otherwise weak nonlinearity in the active media.

math.NA↗

arXiv2021

Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation

Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive labors. In this paper, we aim to boost the performance of semi-supervised learning for medical image segmentation with limited labels using a self-ensembling contrastive learning technique. To this end, we propose to train an encoder-decoder network at image-level with small amounts of labeled images, and more importantly, we learn latent representations directly at feature-level by imposing contrastive loss on unlabeled images. This method strengthens intra-class compactness and inter-class separability, so as to get a better pixel classifier. Moreover, we devise a student encoder for online learning and an exponential moving average version of it, called teacher encoder, to improve the performance iteratively in a self-ensembling manner. To construct contrastive samples with unlabeled images, two sampling strategies that exploit structure similarity across medical images and utilize pseudo-labels for construction, termed region-aware and anatomical-aware contrastive sampling, are investigated. We conduct extensive experiments on an MRI and a CT segmentation dataset and demonstrate that in a limited label setting, the proposed method achieves state-of-the-art performance. Moreover, the anatomical-aware strategy that prepares contrastive samples on-the-fly using pseudo-labels realizes better contrastive regularization on feature representations.

cs.CV↗

arXiv2021

CRT-Net: A Generalized and Scalable Framework for the Computer-Aided Diagnosis of Electrocardiogram Signals

Electrocardiogram (ECG) signals play critical roles in the clinical screening and diagnosis of many types of cardiovascular diseases. Despite deep neural networks that have been greatly facilitated computer-aided diagnosis (CAD) in many clinical tasks, the variability and complexity of ECG in the clinic still pose significant challenges in both diagnostic performance and clinical applications. In this paper, we develop a robust and scalable framework for the clinical recognition of ECG. Considering the fact that hospitals generally record ECG signals in the form of graphic waves of 2-D images, we first extract the graphic waves of 12-lead images into numerical 1-D ECG signals by a proposed bi-directional connectivity method. Subsequently, a novel deep neural network, namely CRT-Net, is designed for the fine-grained and comprehensive representation and recognition of 1-D ECG signals. The CRT-Net can well explore waveform features, morphological characteristics and time domain features of ECG by embedding convolution neural network(CNN), recurrent neural network(RNN), and transformer module in a scalable deep model, which is especially suitable in clinical scenarios with different lengths of ECG signals captured from different devices. The proposed framework is first evaluated on two widely investigated public repositories, demonstrating the superior performance of ECG recognition in comparison with state-of-the-art. Moreover, we validate the effectiveness of our proposed bi-directional connectivity and CRT-Net on clinical ECG images collected from the local hospital, including 258 patients with chronic kidney disease (CKD), 351 patients with Type-2 Diabetes (T2DM), and around 300 patients in the control group. In the experiments, our methods can achieve excellent performance in the recognition of these two types of disease.

cs.LG↗

arXiv2020

Quantitative Assessment of U.S. Bulk Power Systems and Market Operations during COVID-19

Starting in early 2020, the novel coronavirus disease (COVID-19) severely affected the U.S., causing substantial changes in the operations of bulk power systems and electricity markets. In this paper, we develop a data-driven analysis to substantiate the pandemic's impacts from the perspectives of power system security, electric power generation, electric power demand and electricity prices. Our results suggest that both electric power demand and electricity prices have discernibly dropped during the COVID-19 pandemic. Geographical variances in the impact are observed and quantified, and the bulk power market and power system operations in the northeast region are most severely affected. All the data sources, assessment criteria, and analysis codes reported in this paper are available on a GitHub repository.

physics.soc-ph↗

arXiv2020

A Global Benchmark of Algorithms for Segmenting Late Gadolinium-Enhanced Cardiac Magnetic Resonance Imaging

Segmentation of cardiac images, particularly late gadolinium-enhanced magnetic resonance imaging (LGE-MRI) widely used for visualizing diseased cardiac structures, is a crucial first step for clinical diagnosis and treatment. However, direct segmentation of LGE-MRIs is challenging due to its attenuated contrast. Since most clinical studies have relied on manual and labor-intensive approaches, automatic methods are of high interest, particularly optimized machine learning approaches. To address this, we organized the "2018 Left Atrium Segmentation Challenge" using 154 3D LGE-MRIs, currently the world's largest cardiac LGE-MRI dataset, and associated labels of the left atrium segmented by three medical experts, ultimately attracting the participation of 27 international teams. In this paper, extensive analysis of the submitted algorithms using technical and biological metrics was performed by undergoing subgroup analysis and conducting hyper-parameter analysis, offering an overall picture of the major design choices of convolutional neural networks (CNNs) and practical considerations for achieving state-of-the-art left atrium segmentation. Results show the top method achieved a dice score of 93.2% and a mean surface to a surface distance of 0.7 mm, significantly outperforming prior state-of-the-art. Particularly, our analysis demonstrated that double, sequentially used CNNs, in which a first CNN is used for automatic region-of-interest localization and a subsequent CNN is used for refined regional segmentation, achieved far superior results than traditional methods and pipelines containing single CNNs. This large-scale benchmarking study makes a significant step towards much-improved segmentation methods for cardiac LGE-MRIs, and will serve as an important benchmark for evaluating and comparing the future works in the field.

cs.CV↗

arXiv2020

Difference Potentials Method for Models with Dynamic Boundary Conditions and Bulk-Surface Problems

In this work, we consider parabolic models with dynamic boundary conditions and parabolic bulk-surface problems in 3D. Such partial differential equations based models describe phenomena that happen both on the surface and in the bulk/domain. These problems may appear in many applications, ranging from cell dynamics in biology, to grain growth models in polycrystalline materials. Using Difference Potentials framework, we develop novel numerical algorithms for the approximation of the problems. The constructed algorithms efficiently and accurately handle the coupling of the models in the bulk and on the surface, approximate 3D irregular geometry in the bulk by the use of only Cartesian meshes, employ Fast Poisson Solvers, and utilize spectral approximation on the surface. Several numerical tests are given to illustrate the robustness of the developed numerical algorithms.

math.NA↗

arXiv2019

Efficient Numerical Algorithms based on Difference Potentials for Chemotaxis Systems in 3D

In this work, we propose efficient and accurate numerical algorithms based on Difference Potentials Method for numerical solution of chemotaxis systems and related models in 3D. The developed algorithms handle 3D irregular geometry with the use of only Cartesian meshes and employ Fast Poisson Solvers. In addition, to further enhance computational efficiency of the methods, we design a Difference-Potentials-based domain decomposition approach which allows mesh adaptivity and easy parallelization of the algorithm in space. Extensive numerical experiments are presented to illustrate the accuracy, efficiency and robustness of the developed numerical algorithms.

math.NA↗

arXiv2017

High-order numerical methods for 2D parabolic problems in single and composite domains

In this work, we discuss and compare three methods for the numerical approximation of constant- and variable-coefficient diffusion equations in both single and composite domains with possible discontinuity in the solution/flux at interfaces, considering (i) the Cut Finite Element Method; (ii) the Difference Potentials Method; and (iii) the summation-by-parts Finite Difference Method. First we give a brief introduction for each of the three methods. Next, we propose benchmark problems, and consider numerical tests-with respect to accuracy and convergence-for linear parabolic problems on a single domain, and continue with similar tests for linear parabolic problems on a composite domain (with the interface defined either explicitly or implicitly). Lastly, a comparative discussion of the methods and numerical results will be given.

math.NA↗