arXiv subjects

Xiaoxuan Zhang

Publications and source records attributed to Xiaoxuan Zhang.

17 recordsLinked to original sources

arXiv2025

GFM-Planner: Perception-Aware Trajectory Planning with Geometric Feature Metric

Like humans who rely on landmarks for orientation, autonomous robots depend on feature-rich environments for accurate localization. In this paper, we propose the GFM-Planner, a perception-aware trajectory planning framework based on the geometric feature metric, which enhances LiDAR localization accuracy by guiding the robot to avoid degraded areas. First, we derive the Geometric Feature Metric (GFM) from the fundamental LiDAR localization problem. Next, we design a 2D grid-based Metric Encoding Map (MEM) to efficiently store GFM values across the environment. A constant-time decoding algorithm is further proposed to retrieve GFM values for arbitrary poses from the MEM. Finally, we develop a perception-aware trajectory planning algorithm that improves LiDAR localization capabilities by guiding the robot in selecting trajectories through feature-rich areas. Both simulation and real-world experiments demonstrate that our approach enables the robot to actively select trajectories that significantly enhance LiDAR localization accuracy.

cs.RO↗

arXiv2024

Multisource Semisupervised Adversarial Domain Generalization Network for Cross-Scene Sea-Land Clutter Classification

Deep learning (DL)-based sea\textendash land clutter classification for sky-wave over-the-horizon-radar (OTHR) has become a novel research topic. In engineering applications, real-time predictions of sea\textendash land clutter with existing distribution discrepancies are crucial. To solve this problem, this article proposes a novel Multisource Semisupervised Adversarial Domain Generalization Network (MSADGN) for cross-scene sea\textendash land clutter classification. MSADGN can extract domain-invariant and domain-specific features from one labeled source domain and multiple unlabeled source domains, and then generalize these features to an arbitrary unseen target domain for real-time prediction of sea\textendash land clutter. Specifically, MSADGN consists of three modules: domain-related pseudolabeling module, domain-invariant module, and domain-specific module. The first module introduces an improved pseudolabel method called domain-related pseudolabel, which is designed to generate reliable pseudolabels to fully exploit unlabeled source domains. The second module utilizes a generative adversarial network (GAN) with a multidiscriminator to extract domain-invariant features, to enhance the model's transferability in the target domain. The third module employs a parallel multiclassifier branch to extract domain-specific features, to enhance the model's discriminability in the target domain. The effectiveness of our method is validated in twelve domain generalizations (DG) scenarios. Meanwhile, we selected 10 state-of-the-art DG methods for comparison. The experimental results demonstrate the superiority of our method.

cs.CV↗

arXiv2023

A Joint Processing Strategy for Image Quality Improvement in 3D Digital Subtraction Angiography

Three-dimensional digital subtraction angiography (3D-DSA) is a widely adopted technique for clinical evaluation of contrast-enhanced vasculatures. The distribution of a contrast agent such as iodine is often estimated via temporal subtraction. Advancements in spectral imaging technologies such as photon counting detectors offer new opportunities to improve DSA image quality. In this work, we propose a novel joint processing strategy to achieve an iodine image using two-bin spectral measurements from a photon counting detector acquired both the pre- and post-contrast injection. Simulation studies were performed using a digital phantom with iodine-enhanced vessels. The proposed method was compared with temporal subtraction and conventional spectral imaging using just the post-contrast measurements. Imaging performance was evaluated in terms of noise-resolution tradeoffs. Preliminary findings have shown measurably improved image quality given by joint processing, reducing noise by 40% and 70% compared to temporal subtraction and conventional spectral imaging, respectively.

physics.med-ph↗

arXiv2023

A treatment of particle-electrolyte sharp interface fracture in solid-state batteries with multi-field discontinuities

In this work, we present a computational framework for coupled electro-chemo-(nonlinear) mechanics at the particle scale for solid-state batteries. The framework accounts for interfacial fracture between the active particles and solid electrolyte due to intercalation stresses. We extend discontinuous finite element methods for a sharp interface treatment of discontinuities in concentrations, fluxes, electric fields and in displacements, the latter arising from active particle-solid electrolyte interface fracture. We model the degradation in the charge transfer process that results from the loss of contact due to fracture at the electrolyte-active particle interfaces. Additionally, we account for the stress-dependent kinetics that can influence the charge transfer reactions and solid state diffusion. The discontinuous finite element approach does not require a conformal mesh. This offers the flexibility to construct arbitrary particle shapes and geometries that are based on design, or are obtained from microscopy images. The finite element mesh, however, can remain Cartesian, and independent of the particle geometries. We demonstrate this computational framework on micro-structures that are representative of solid-sate batteries with single and multiple anode and cathode particles.

cond-mat.mtrl-sci↗

arXiv2023

A Sea-Land Clutter Classification Framework for Over-the-Horizon-Radar Based on Weighted Loss Semi-supervised GAN

Deep convolutional neural network has made great achievements in sea-land clutter classification for over-the-horizon-radar (OTHR). The premise is that a large number of labeled training samples must be provided for a sea-land clutter classifier. In practical engineering applications, it is relatively easy to obtain label-free sea-land clutter samples. However, the labeling process is extremely cumbersome and requires expertise in the field of OTHR. To solve this problem, we propose an improved generative adversarial network, namely weighted loss semi-supervised generative adversarial network (WL-SSGAN). Specifically, we propose a joint feature matching loss by weighting the middle layer features of the discriminator of semi-supervised generative adversarial network. Furthermore, we propose the weighted loss of WL-SSGAN by linearly weighting standard adversarial loss and joint feature matching loss. The semi-supervised classification performance of WL-SSGAN is evaluated on a sea-land clutter dataset. The experimental results show that WL-SSGAN can improve the performance of the fully supervised classifier with only a small number of labeled samples by utilizing a large number of unlabeled sea-land clutter samples. Further, the proposed weighted loss is superior to both the adversarial loss and the feature matching loss. Additionally, we compare WL-SSGAN with conventional semi-supervised classification methods and demonstrate that WL-SSGAN achieves the highest classification accuracy.

cs.CV↗

arXiv2023

Label-free learning of elliptic partial differential equation solvers with generalizability across boundary value problems

Traditional, numerical discretization-based solvers of partial differential equations (PDEs) are fundamentally agnostic to domains, boundary conditions and coefficients. In contrast, machine learnt solvers have a limited generalizability across these elements of boundary value problems. This is strongly true in the case of surrogate models that are typically trained on direct numerical simulations of PDEs applied to one specific boundary value problem. In a departure from this direct approach, the label-free machine learning of solvers is centered on a loss function that incorporates the PDE and boundary conditions in residual form. However, their generalization across boundary conditions is limited and they remain strongly domain-dependent. Here, we present a framework that generalizes across domains, boundary conditions and coefficients simultaneously with learning the PDE in weak form. Our work explores the ability of simple, convolutional neural network (CNN)-based encoder-decoder architectures to learn to solve a PDE in greater generality than its restriction to a particular boundary value problem. In this first communication, we consider the elliptic PDEs of Fickean diffusion, linear and nonlinear elasticity. Importantly, the learning happens independently of any labelled field data from either experiments or direct numerical solutions. Extensive results for these problem classes demonstrate the framework's ability to learn PDE solvers that generalize across hundreds of thousands of domains, boundary conditions and coefficients, including extrapolation beyond the learning regime. Once trained, the machine learning solvers are orders of magnitude faster than discretization-based solvers. We place our work in the context of recent continuous operator learning frameworks, and note extensions to transfer learning, active learning and reinforcement learning.

math.NA↗

arXiv2023

Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN

In the sea-land clutter classification of sky-wave over-the-horizon-radar (OTHR), the imbalanced and scarce data leads to a poor performance of the deep learning-based classification model. To solve this problem, this paper proposes an improved auxiliary classifier generative adversarial network~(AC-GAN) architecture, namely auxiliary classifier variational autoencoder generative adversarial network (AC-VAEGAN). AC-VAEGAN can synthesize higher quality sea-land clutter samples than AC-GAN and serve as an effective tool for data augmentation. Specifically, a 1-dimensional convolutional AC-VAEGAN architecture is designed to synthesize sea-land clutter samples. Additionally, an evaluation method combining both traditional evaluation of GAN domain and statistical evaluation of signal domain is proposed to evaluate the quality of synthetic samples. Using a dataset of OTHR sea-land clutter, both the quality of the synthetic samples and the performance of data augmentation of AC-VAEGAN are verified. Further, the effect of AC-VAEGAN as a data augmentation method on the classification performance of imbalanced and scarce sea-land clutter samples is validated. The experiment results show that the quality of samples synthesized by AC-VAEGAN is better than that of AC-GAN, and the data augmentation method with AC-VAEGAN is able to improve the classification performance in the case of imbalanced and scarce sea-land clutter samples.

eess.SY↗

arXiv2022

A heteroencoder architecture for prediction of failure locations in porous metals using variational inference

In this work we employ an encoder-decoder convolutional neural network to predict the failure locations of porous metal tension specimens based only on their initial porosities. The process we model is complex, with a progression from initial void nucleation, to saturation, and ultimately failure. The objective of predicting failure locations presents an extreme case of class imbalance since most of the material in the specimens do not fail. In response to this challenge, we develop and demonstrate the effectiveness of data- and loss-based regularization methods. Since there is considerable sensitivity of the failure location to the particular configuration of voids, we also use variational inference to provide uncertainties for the neural network predictions. We connect the deterministic and Bayesian convolutional neural networks at a theoretical level to explain how variational inference regularizes the training and predictions. We demonstrate that the resulting predicted variances are effective in ranking the locations that are most likely to fail in any given specimen.

physics.app-ph↗

arXiv2021

Using Uncertainty in Deep Learning Reconstruction for Cone-Beam CT of the Brain

Contrast resolution beyond the limits of conventional cone-beam CT (CBCT) systems is essential to high-quality imaging of the brain. We present a deep learning reconstruction method (dubbed DL-Recon) that integrates physically principled reconstruction models with DL-based image synthesis based on the statistical uncertainty in the synthesis image. A synthesis network was developed to generate a synthesized CBCT image (DL-Synthesis) from an uncorrected filtered back-projection (FBP) image. To improve generalizability (including accurate representation of lesions not seen in training), voxel-wise epistemic uncertainty of DL-Synthesis was computed using a Bayesian inference technique (Monte-Carlo dropout). In regions of high uncertainty, the DL-Recon method incorporates information from a physics-based reconstruction model and artifact-corrected projection data. Two forms of the DL-Recon method are proposed: (i) image-domain fusion of DL-Synthesis and FBP (DL-FBP) weighted by DL uncertainty; and (ii) a model-based iterative image reconstruction (MBIR) optimization using DL-Synthesis to compute a spatially varying regularization term based on DL uncertainty (DL-MBIR). The error in DL-Synthesis images was correlated with the uncertainty in the synthesis estimate. Compared to FBP and PWLS, the DL-Recon methods (both DL-FBP and DL-MBIR) showed ~50% reduction in noise (at matched spatial resolution) and ~40-70% improvement in image uniformity. Conventional DL-Synthesis alone exhibited ~10-60% under-estimation of lesion contrast and ~5-40% reduction in lesion segmentation accuracy (Dice coefficient) in simulated and real brain lesions, suggesting a lack of reliability / generalizability for structures unseen in the training data. DL-FBP and DL-MBIR improved the accuracy of reconstruction by directly incorporating information from the measurements in regions of high uncertainty.

physics.med-ph↗

arXiv2021

System inference via field inversion for the spatio-temporal progression of infectious diseases: Studies of COVID-19 in Michigan and Mexico

We present an approach to studying and predicting the spatio-temporal progression of infectious diseases. We treat the problem by adopting a partial differential equation (PDE) version of the Susceptible, Infected, Recovered, Deceased (SIRD) compartmental model of epidemiology, which is achieved by replacing compartmental populations by their densities. Building on our recent work (Computational Mechanics, 66, 1177, 2020), we replace our earlier use of global polynomial basis functions with those having local support, as epitomized in the finite element method, for the spatial representation of the SIRD parameters. The time dependence is treated by inferring constant parameters over time intervals that coincide with the time step in semi-discrete numerical implementations. In combination, this amounts to a scheme of field inversion of the SIRD parameters over each time step. Applied to data over ten months of 2020 for the pandemic in the US state of Michigan and to all of Mexico, our system inference via field inversion infers spatio-temporally varying PDE SIRD parameters that replicate the progression of the pandemic with high accuracy. It also produces accurate predictions, when compared against data, for a three week period into 2021. Of note is the insight that is suggested on the spatio-temporal variation of infection, recovery and death rates, as well as patterns of the population's mobility revealed by diffusivities of the compartments.

physics.bio-ph↗

arXiv2021

There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It

Limerick generation exemplifies some of the most difficult challenges faced in poetry generation, as the poems must tell a story in only five lines, with constraints on rhyme, stress, and meter. To address these challenges, we introduce LimGen, a novel and fully automated system for limerick generation that outperforms state-of-the-art neural network-based poetry models, as well as prior rule-based poetry models. LimGen consists of three important pieces: the Adaptive Multi-Templated Constraint algorithm that constrains our search to the space of realistic poems, the Multi-Templated Beam Search algorithm which searches efficiently through the space, and the probabilistic Storyline algorithm that provides coherent storylines related to a user-provided prompt word. The resulting limericks satisfy poetic constraints and have thematically coherent storylines, which are sometimes even funny (when we are lucky).

cs.CL↗

arXiv2021

Biomembranes undergo complex, non-axisymmetric deformations governed by Kirchhoff-Love kinematics and revealed by a three dimensional computational framework

Biomembranes play a central role in various phenomena like locomotion of cells, cell-cell interactions, packaging of nutrients, and in maintaining organelle morphology and functionality. During these processes, the membranes undergo significant morphological changes through deformation, scission, and fusion. Modeling the underlying mechanics of such morphological changes has traditionally relied on reduced order axisymmetric representations of membrane geometry and deformation. Axisymmetric representations, while robust and extensively deployed, suffer from their inability to model symmetry breaking deformations and structural bifurcations. To address this limitation, a 3D computational mechanics framework for high fidelity modeling of biomembrane deformation is presented. The proposed framework brings together Kirchhoff-Love thin-shell kinematics, Helfrich-energy based mechanics, and state-of-the-art numerical techniques for modeling deformation of surface geometries. Lipid bilayers are represented as spline-based surfaces immersed in a 3D space; this enables modeling of a wide spectrum of membrane geometries, boundary conditions, and deformations that are physically admissible in a 3D space. The mathematical basis of the framework and its numerical machinery are presented, and their utility is demonstrated by modeling 3 classical, yet non-trivial, membrane problems: formation of tubular shapes and their lateral constriction, Piezo1-induced membrane footprint generation and gating response, and the budding of membranes by protein coats during endocytosis. For each problem, the full 3D membrane deformation is captured, potential symmetry-breaking deformation paths identified, and various case studies of boundary and load conditions are presented. Using the endocytic vesicle budding as a case study, we also present a "phase diagram" for its symmetric and broken-symmetry states.

q-bio.QM↗

arXiv2021

Bayesian neural networks for weak solution of PDEs with uncertainty quantification

Solving partial differential equations (PDEs) is the canonical approach for understanding the behavior of physical systems. However, large scale solutions of PDEs using state of the art discretization techniques remains an expensive proposition. In this work, a new physics-constrained neural network (NN) approach is proposed to solve PDEs without labels, with a view to enabling high-throughput solutions in support of design and decision-making. Distinct from existing physics-informed NN approaches, where the strong form or weak form of PDEs are used to construct the loss function, we write the loss function of NNs based on the discretized residual of PDEs through an efficient, convolutional operator-based, and vectorized implementation. We explore an encoder-decoder NN structure for both deterministic and probabilistic models, with Bayesian NNs (BNNs) for the latter, which allow us to quantify both epistemic uncertainty from model parameters and aleatoric uncertainty from noise in the data. For BNNs, the discretized residual is used to construct the likelihood function. In our approach, both deterministic and probabilistic convolutional layers are used to learn the applied boundary conditions (BCs) and to detect the problem domain. As both Dirichlet and Neumann BCs are specified as inputs to NNs, a single NN can solve for similar physics, but with different BCs and on a number of problem domains. The trained surrogate PDE solvers can also make interpolating and extrapolating (to a certain extent) predictions for BCs that they were not exposed to during training. Such surrogate models are of particular importance for problems, where similar types of PDEs need to be repeatedly solved for many times with slight variations. We demonstrate the capability and performance of the proposed framework by applying it to steady-state diffusion, linear elasticity, and nonlinear elasticity.

cs.CE↗

arXiv2020

System inference for the spatio-temporal evolution of infectious diseases: Michigan in the time of COVID-19

We extend the classical SIR model of infectious disease spread to account for time dependence in the parameters, which also include diffusivities. The temporal dependence accounts for the changing characteristics of testing, quarantine and treatment protocols, while diffusivity incorporates a mobile population. This model has been applied to data on the evolution of the COVID-19 pandemic in the US state of Michigan. For system inference, we use recent advances; specifically our framework for Variational System Identification (Wang et al., Comp. Meth. App. Mech. Eng., 356, 44-74, 2019; arXiv:2001.04816 [cs.CE]) as well as Bayesian machine learning methods.

q-bio.PE↗

arXiv2020

Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures

Many important multi-component crystalline solids undergo mechanochemical spinodal decomposition: a phase transformation in which the compositional redistribution is coupled with structural changes of the crystal, resulting in dynamically evolving microstructures. The ability to rapidly compute the macroscopic behavior based on these detailed microstructures is of paramount importance for accelerating material discovery and design. Here, our focus is on the macroscopic, nonlinear elastic response of materials harboring microstructure. Because of the diversity of microstructural patterns that can form, there is interest in taking a purely computational approach to predicting their macroscopic response. However, the evaluation of macroscopic, nonlinear elastic properties purely based on direct numerical simulations (DNS) is computationally very expensive, and hence impractical for material design when a large number of microstructures need to be tested. A further complexity of a hierarchical nature arises if the elastic free energy and its variation with strain is a small-scale fluctuation on the dominant trajectory of the total free energy driven by microstructural dynamics. To address these challenges, we present a data-driven approach, which combines advanced neural network (NN) models with DNS to predict the homogenized, macroscopic, mechanical free energy and stress fields arising in a family of multi-component crystalline solids that develop microstructure. The hierarchical structure of the free energy's evolution induces a multi-resolution character to the machine learning paradigm: We construct knowledge-based neural networks (KBNNs) with either pre-trained fully connected deep neural networks (DNNs), or pre-trained convolutional neural networks (CNNs) that describe the dominant characteristic of the data to fully represent the hierarchically evolving free energy.

cs.CE↗

arXiv2018

Fast Rates of ERM and Stochastic Approximation: Adaptive to Error Bound Conditions

Error bound conditions (EBC) are properties that characterize the growth of an objective function when a point is moved away from the optimal set. They have recently received increasing attention in the field of optimization for developing optimization algorithms with fast convergence. However, the studies of EBC in statistical learning are hitherto still limited. The main contributions of this paper are two-fold. First, we develop fast and intermediate rates of empirical risk minimization (ERM) under EBC for risk minimization with Lipschitz continuous, and smooth convex random functions. Second, we establish fast and intermediate rates of an efficient stochastic approximation (SA) algorithm for risk minimization with Lipschitz continuous random functions, which requires only one pass of $n$ samples and adapts to EBC. For both approaches, the convergence rates span a full spectrum between $\widetilde O(1/\sqrt{n})$ and $\widetilde O(1/n)$ depending on the power constant in EBC, and could be even faster than $O(1/n)$ in special cases for ERM. Moreover, these convergence rates are automatically adaptive without using any knowledge of EBC. Overall, this work not only strengthens the understanding of ERM for statistical learning but also brings new fast stochastic algorithms for solving a broad range of statistical learning problems.

stat.ML↗

arXiv2013

Optimal Switching On and Off the Entire Service Capacity of a Parallel Queue

This paper studies optimal switching on and o? of the entire service capacity of an M/M/Infinity queue with holding, running and switching costs where the running costs depend only on whether the system is running or not. The goal is to minimize average costs per unit time. The main result is that an average-optimal policy either always runs the system or is an (M, N)-policy defined by two thresholds M and N, such that the system is switched on upon an arrival epoch when the system size accumulates to N and is switched off upon a departure epoch when the system size decreases to M. It is shown that this optimization problem can be reduced to a problem with a finite number of states and actions, and an average-optimal policy can be computed via linear programming. An example, in which the optimal (M, N)-policy outperforms the best (0, N)-policy, is provided. Thus, unlike the case of single-server queues studied in the literature, (0, N)-policies may not be average-optimal.

math.OC↗