arXiv subjects

Yi Wang

Publications and source records attributed to Yi Wang.

At least 487 records · Page 27Linked to original sources

arXiv2024

Implicit neural representation for free-breathing MR fingerprinting (INR-MRF): co-registered 3D whole-liver water T1, water T2, proton density fat fraction, and R2* mapping

Purpose: To develop an MRI technique for free-breathing 3D whole-liver quantification of water T1, water T2, proton density fat fraction (PDFF), R2*. Methods: An Eight-echo spoiled gradient echo pulse sequence with spiral readout was developed by interleaving inversion recovery and T2 magnetization preparation. We propose a neural network based on a 4D and a 3D implicit neural representation (INR) which simultaneously learns the motion deformation fields and the static reference frame MRI subspace images respectively. Water and fat singular images were separated during network training, with no need of performing retrospective water-fat separation. T1, T2, R2* and proton density fat fraction (PDFF) produced by the proposed method were validated in vivo on 10 healthy subjects, using quantitative maps generated from conventional scans as reference. Results: Our results showed minimal bias and narrow 95% limits of agreement on T1, T2, R2* and PDFF values in the liver compared to conventional breath-holding scans. Conclusions: INR-MRF enabled co-registered 3D whole liver T1, T2, R2* and PDFF mapping in a single free-breathing scan.

physics.med-ph↗

arXiv2024

Subdivision method in the Laplacian matching polynomial

As a bridge connecting the matching polynomial and the Laplacian matching polynomial of graphs, the subdivision method is expected to be useful for investigating the Laplacian matching polynomial. In this paper, we study applications of the method from three aspects. We prove that the zero sequence of the Laplacian matching polynomial of a graph majorizes its degree sequence, establishing a dual relation between the Laplacian matching polynomial and the characteristic polynomial of the signless Laplacian matrix of graphs. In addition, from different viewpoints, we give a new combinatorial interpretations for the coefficients of the Laplacian matching polynomial.

math.CO↗

arXiv2024

FiRework: Field Refinement Framework for Efficient Enhancement of Deformable Registration

Deformable image registration remains a fundamental task in clinical practice, yet solving registration problems involving complex deformations remains challenging. Current deep learning-based registration methods employ continuous deformation to model large deformations, which often suffer from accumulated registration errors and interpolation inaccuracies. Moreover, achieving satisfactory results with these frameworks typically requires a large number of cascade stages, demanding substantial computational resources. Therefore, we propose a novel approach, the field refinement framework (FiRework), tailored for unsupervised deformable registration, aiming to address these challenges. In FiRework, we redesign the continuous deformation framework to mitigate the aforementioned errors. Notably, our FiRework requires only one level of recursion during training and supports continuous inference, offering improved efficacy compared to continuous deformation frameworks. We conducted experiments on two brain MRI datasets, enhancing two existing deformable registration networks with FiRework. The experimental results demonstrate the superior performance of our proposed framework in deformable registration. The code is publicly available at https://github.com/ZAX130/FiRework.

cs.CV↗

arXiv2024

Fast Decentralized State Estimation for Legged Robot Locomotion via EKF and MHE

In this paper, we present a fast and decentralized state estimation framework for the control of legged locomotion. The nonlinear estimation of the floating base states is decentralized to an orientation estimation via Extended Kalman Filter (EKF) and a linear velocity estimation via Moving Horizon Estimation (MHE). The EKF fuses the inertia sensor with vision to estimate the floating base orientation. The MHE uses the estimated orientation with all the sensors within a time window in the past to estimate the linear velocities based on a time-varying linear dynamics formulation of the interested states with state constraints. More importantly, a marginalization method based on the optimization structure of the full information filter (FIF) is proposed to convert the equality-constrained FIF to an equivalent MHE. This decoupling of state estimation promotes the desired balance of computation efficiency, accuracy of estimation, and the inclusion of state constraints. The proposed method is shown to be capable of providing accurate state estimation to several legged robots, including the highly dynamic hopping robot PogoX, the bipedal robot Cassie, and the quadrupedal robot Unitree Go1, with a frequency at 200 Hz and a window interval of 0.1s.

cs.RO↗

arXiv2024

Task-oriented Time Series Imputation Evaluation via Generalized Representers

Time series analysis is widely used in many fields such as power energy, economics, and transportation, including different tasks such as forecasting, anomaly detection, classification, etc. Missing values are widely observed in these tasks, and often leading to unpredictable negative effects on existing methods, hindering their further application. In response to this situation, existing time series imputation methods mainly focus on restoring sequences based on their data characteristics, while ignoring the performance of the restored sequences in downstream tasks. Considering different requirements of downstream tasks (e.g., forecasting), this paper proposes an efficient downstream task-oriented time series imputation evaluation approach. By combining time series imputation with neural network models used for downstream tasks, the gain of different imputation strategies on downstream tasks is estimated without retraining, and the most favorable imputation value for downstream tasks is given by combining different imputation strategies according to the estimated gain.

cs.LG↗

arXiv2024

Separable pathway effects of semi-competing risks using multi-state models

Semi-competing risks refer to the phenomenon where a primary event (such as mortality) can ``censor'' an intermediate event (such as relapse of a disease), but not vice versa. Under the multi-state model, the primary event consists of two specific types: the direct outcome event and an indirect outcome event developed from intermediate events. Within this framework, we show that the total treatment effect on the cumulative incidence of the primary event can be decomposed into three separable pathway effects, capturing treatment effects on population-level transition rates between states. We next propose two estimators for the counterfactual cumulative incidences of the primary event under hypothetical treatment components. One estimator is given by the generalized Nelson--Aalen estimator with inverse probability weighting under covariates isolation, and the other is given based on the efficient influence function. The asymptotic normality of these estimators is established. The first estimator only involves a propensity score model and avoid modeling the cause-specific hazards. The second estimator has robustness against the misspecification of submodels. As an illustration of its potential usefulness, the proposed method is applied to compare effects of different allogeneic stem cell transplantation types on overall survival after transplantation.

stat.ME↗

arXiv2024

A Narrative Review of Image Processing Techniques Related to Prostate Ultrasound

Prostate cancer (PCa) poses a significant threat to men's health, with early diagnosis being crucial for improving prognosis and reducing mortality rates. Transrectal ultrasound (TRUS) plays a vital role in the diagnosis and image-guided intervention of PCa.To facilitate physicians with more accurate and efficient computer-assisted diagnosis and interventions, many image processing algorithms in TRUS have been proposed and achieved state-of-the-art performance in several tasks, including prostate gland segmentation, prostate image registration, PCa classification and detection, and interventional needle detection. The rapid development of these algorithms over the past two decades necessitates a comprehensive summary. In consequence, this survey provides a \textcolor{blue}{narrative } analysis of this field, outlining the evolution of image processing methods in the context of TRUS image analysis and meanwhile highlighting their relevant contributions. Furthermore, this survey discusses current challenges and suggests future research directions to possibly advance this field further.

eess.IV↗

arXiv2024

MRI quantification of liver fibrosis using diamagnetic susceptibility: An ex-vivo feasibility study

In chronic liver disease, liver fibrosis develops as excessive deposition of extracellular matrix macromolecules, predominantly collagens, progressively form fibrous scars that disrupt the hepatic architecture, and fibrosis, iron, and fat are interrelated. Fibrosis is the best predictor of morbidity and mortality in chronic liver disease but liver biopsy, the reference method for diagnosis and staging, is invasive and limited by sampling and interobserver variability and risks of complications. The overall objective of this study was to develop a new non-invasive method to quantify fibrosis using diamagnetic susceptibility sources with histology validation in ex vivo liver explants.

physics.med-ph↗

arXiv2024

Optimal $H_{\infty}$ control based on stable manifold of discounted Hamilton-Jacobi-Isaacs equation

The optimal $H_{\infty}$ control problem over an infinite time horizon, which incorporates a performance function with a discount factor $e^{-αt}$ ($α> 0$), is important in various fields. Solving this optimal $H_{\infty}$ control problem is equivalent to addressing a discounted Hamilton-Jacobi-Isaacs (HJI) partial differential equation. In this paper, we first provide a precise estimate for the discount factor $α$ that ensures the existence of a nonnegative stabilizing solution to the HJI equation. This stabilizing solution corresponds to the stable manifold of the characteristic system of the HJI equation, which is a contact Hamiltonian system due to the presence of the discount factor. Secondly, we demonstrate that approximating the optimal controller in a natural manner results in a closed-loop system with a finite $L_2$-gain that is nearly less than the gain of the original system. Thirdly, based on the theoretical results obtained, we propose a deep learning algorithm to approximate the optimal controller using the stable manifold of the contact Hamiltonian system associated with the HJI equation. Finally, we apply our method to the $H_{\infty}$ control of the Allen-Cahn equation to illustrate its effectiveness.

math.OC↗

arXiv2024

Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts

Complex distribution shifts are the main obstacle to achieving accurate long-term time series forecasting. Several efforts have been conducted to capture the distribution characteristics and propose adaptive normalization techniques to alleviate the influence of distribution shifts. However, these methods neglect the intricate distribution dynamics observed from various scales and the evolving functions of distribution dynamics and normalized mapping relationships. To this end, we propose a novel model-agnostic Evolving Multi-Scale Normalization (EvoMSN) framework to tackle the distribution shift problem. Flexible normalization and denormalization are proposed based on the multi-scale statistics prediction module and adaptive ensembling. An evolving optimization strategy is designed to update the forecasting model and statistics prediction module collaboratively to track the shifting distributions. We evaluate the effectiveness of EvoMSN in improving the performance of five mainstream forecasting methods on benchmark datasets and also show its superiority compared to existing advanced normalization and online learning approaches. The code is publicly available at https://github.com/qindalin/EvoMSN.

cs.LG↗

arXiv2024

Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining

Self-supervised pretraining on large-scale satellite data has raised great interest in building Earth observation (EO) foundation models. However, many important resources beyond pure satellite imagery, such as land-cover-land-use products that provide free global semantic information, as well as vision foundation models that hold strong knowledge of the natural world, are not widely studied. In this work, we show these free additional resources not only help resolve common contrastive learning bottlenecks, but also significantly boost the efficiency and effectiveness of EO pretraining. Specifically, we first propose soft contrastive learning that optimizes cross-scene soft similarity based on land-cover-generated multi-label supervision, naturally solving the issue of multiple positive samples and too strict positive matching in complex scenes. Second, we revisit and explore cross-domain continual pretraining for both multispectral and SAR imagery, building efficient EO foundation models from strongest vision models such as DINOv2. Adapting simple weight-initialization and Siamese masking strategies into our soft contrastive learning framework, we demonstrate impressive continual pretraining performance even when the input modalities are not aligned. Without prohibitive training, we produce multispectral and SAR foundation models that achieve significantly better results in 10 out of 11 downstream tasks than most existing SOTA models. For example, our ResNet50/ViT-S achieve 84.8/85.0 linear probing mAP scores on BigEarthNet-10\% which are better than most existing ViT-L models; under the same setting, our ViT-B sets a new record of 86.8 in multispectral, and 82.5 in SAR, the latter even better than many multispectral models. Dataset and models are available at \url{https://github.com/zhu-xlab/softcon}.

cs.CV↗

arXiv2024

Towards Real-world Deployment of NILM Systems: Challenges and Practices

Non-intrusive load monitoring (NILM), as a key load monitoring technology, can much reduce the deployment cost of traditional power sensors. Previous research has largely focused on developing cloud-exclusive NILM algorithms, which often result in high computation costs and significant service delays. To address these issues, we propose a three-tier framework to enhance the real-world applicability of NILM systems through edge-cloud collaboration. Considering the computational resources available at both the edge and cloud, we implement a lightweight NILM model at the edge and a deep learning based model at the cloud, respectively. In addition to the differential model implementations, we also design a NILM-specific deployment scheme that integrates Gunicorn and NGINX to bridge the gap between theoretical algorithms and practical applications. To verify the effectiveness of the proposed framework, we apply real-world NILM scenario settings and implement the entire process of data acquisition, model training, and system deployment. The results demonstrate that our framework can achieve high decomposition accuracy while significantly reducing the cloud workload and communication overhead under practical considerations.

eess.SY↗

arXiv2024

Internal Consistency and Self-Feedback in Large Language Models: A Survey

Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations. To address these, studies prefixed with "Self-" such as Self-Consistency, Self-Improve, and Self-Refine have been initiated. They share a commonality: involving LLMs evaluating and updating themselves. Nonetheless, these efforts lack a unified perspective on summarization, as existing surveys predominantly focus on categorization. In this paper, we use a unified perspective of internal consistency, offering explanations for reasoning deficiencies and hallucinations. Internal consistency refers to the consistency in expressions among LLMs' latent, decoding, or response layers based on sampling methodologies. Then, we introduce an effective theoretical framework capable of mining internal consistency, named Self-Feedback. This framework consists of two modules: Self-Evaluation and Self-Update. The former captures internal consistency signals, while the latter leverages the signals to enhance either the model's response or the model itself. This framework has been employed in numerous studies. We systematically classify these studies by tasks and lines of work; summarize relevant evaluation methods and benchmarks; and delve into the concern, "Does Self-Feedback Really Work?" We also propose several critical viewpoints, including the "Hourglass Evolution of Internal Consistency", "Consistency Is (Almost) Correctness" hypothesis, and "The Paradox of Latent and Explicit Reasoning". The relevant resources are open-sourced at https://github.com/IAAR-Shanghai/ICSFSurvey.

cs.CL↗

arXiv2024

Factorization method for inverse elastic cavity scattering

This paper is concerned with the inverse elastic scattering problem to determine the shape and location of an elastic cavity. By establishing a one-to-one correspondence between the Herglotz wave function and its kernel, we introduce the far-field operator which is crucial in the factorization method. We present a theoretical factorization of the far-field operator and rigorously prove the properties of its associated operators involved in the factorization. Unlike the Dirichlet problem where the boundary integral operator of the single-layer potential involved in the factorization of the far-field operator is weakly singular, the boundary integral operator of the conormal derivative of the double-layer potential involved in the factorization of the far-field operator with Neumann boundary conditions is hypersingular, which forces us to prove that this operator is isomorphic using Fredholm's theorem. Meanwhile, we present theoretical analyses of the factorization method for various illumination and measurement cases, including compression-wave illumination and compression-wave measurement, shear-wave illumination and shear-wave measurement, and full-wave illumination and full-wave measurement. In addition, we also consider the limited aperture problem and provide a rigorous theoretical analysis of the factorization method in this case. Numerous numerical experiments are carried out to demonstrate the effectiveness of the proposed method, and to analyze the influence of various factors, such as polarization direction, frequency, wavenumber, and multi-scale scatterers on the reconstructed results.

math.NA↗

arXiv2024

Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras

Recently, 3D Gaussian Splatting (3DGS) has garnered attention for its high fidelity and real-time rendering. However, adapting 3DGS to different camera models, particularly fisheye lenses, poses challenges due to the unique 3D to 2D projection calculation. Additionally, there are inefficiencies in the tile-based splatting, especially for the extreme curvature and wide field of view of fisheye lenses, which are crucial for its broader real-life applications. To tackle these challenges, we introduce Fisheye-GS.This innovative method recalculates the projection transformation and its gradients for fisheye cameras. Our approach can be seamlessly integrated as a module into other efficient 3D rendering methods, emphasizing its extensibility, lightweight nature, and modular design. Since we only modified the projection component, it can also be easily adapted for use with different camera models. Compared to methods that train after undistortion, our approach demonstrates a clear improvement in visual quality.

cs.CV↗

arXiv2024

Time-asymptotic stability of composite waves of degenerate Oleinik shock and rarefaction for non-convex conservation laws

We are concerned with the large-time behavior of the solution to one-dimensional (1D) cubic non-convex scalar viscous conservation laws. Due to the inflection point of the cubic non-convex flux, the solution to the corresponding inviscid Riemann problem can be the composite wave of a degenerate Oleinik shock and a rarefaction wave and these two nonlinear waves are always attached together. We give a first proof of the time-asymptotic stability of this composite wave, up to a time-dependent shift to the viscous Oleinik shock, for the viscous equation. The Oleinik shock wave strength can be arbitrarily large. The main difficulty is due to the incompatibility of the time-asymptotic stability proof framework of individual viscous shock by the so-called anti-derivative method and the direct $L^2$-energy method to rarefaction wave. Here we develop a new type of $a$-contraction method with suitable weight function and the time-dependent shift to the viscous shock, which is motivated by [9,12]. Another difficulty comes from that the Oleinik shock and rarefaction wave are always attached together and their wave interactions are very subtle. Therefore, the same time-dependent shift needs to be equipped to both Oleinik shock and rarefaction wave such that the wave interactions can be treated in our stability proof. Time-asymptotically, this shift function grows strictly sub-linear with respect to the time and then the shifted rarefaction wave is equivalent to the original self-similar rarefaction wave.

math.AP↗

arXiv2024

DiffLoad: Uncertainty Quantification in Electrical Load Forecasting with the Diffusion Model

Electrical load forecasting plays a crucial role in decision-making for power systems, including unit commitment and economic dispatch. The integration of renewable energy sources and the occurrence of external events, such as the COVID-19 pandemic, have rapidly increased uncertainties in load forecasting. The uncertainties in load forecasting can be divided into two types: epistemic uncertainty and aleatoric uncertainty. Separating these types of uncertainties can help decision-makers better understand where and to what extent the uncertainty is, thereby enhancing their confidence in the following decision-making. This paper proposes a diffusion-based Seq2Seq structure to estimate epistemic uncertainty and employs the robust additive Cauchy distribution to estimate aleatoric uncertainty. Our method not only ensures the accuracy of load forecasting but also demonstrates the ability to separate the two types of uncertainties and be applicable to different levels of loads. The relevant code can be found at \url{https://anonymous.4open.science/r/DiffLoad-4714/}.

cs.LG↗

arXiv2024

Xinyu: An Efficient LLM-based System for Commentary Generation

Commentary provides readers with a deep understanding of events by presenting diverse arguments and evidence. However, creating commentary is a time-consuming task, even for skilled commentators. Large language models (LLMs) have simplified the process of natural language generation, but their direct application in commentary creation still faces challenges due to unique task requirements. These requirements can be categorized into two levels: 1) fundamental requirements, which include creating well-structured and logically consistent narratives, and 2) advanced requirements, which involve generating quality arguments and providing convincing evidence. In this paper, we introduce Xinyu, an efficient LLM-based system designed to assist commentators in generating Chinese commentaries. To meet the fundamental requirements, we deconstruct the generation process into sequential steps, proposing targeted strategies and supervised fine-tuning (SFT) for each step. To address the advanced requirements, we present an argument ranking model for arguments and establish a comprehensive evidence database that includes up-to-date events and classic books, thereby strengthening the substantiation of the evidence with retrieval augmented generation (RAG) technology. To evaluate the generated commentaries more fairly, corresponding to the two-level requirements, we introduce a comprehensive evaluation metric that considers five distinct perspectives in commentary generation. Our experiments confirm the effectiveness of our proposed system. We also observe a significant increase in the efficiency of commentators in real-world scenarios, with the average time spent on creating a commentary dropping from 4 hours to 20 minutes. Importantly, such an increase in efficiency does not compromise the quality of the commentaries.

cs.CL↗