arXiv subjects

Shuoyang Wang

Publications and source records attributed to Shuoyang Wang.

12 recordsLinked to original sources

arXiv2026

Stability of periodic waves in the model with intensity--dependent dispersion

We study standing periodic waves modeled by the nonlinear Schrodinger equation with the intensity-dependent dispersion coefficient. Spatial periodic profiles are smooth if the frequency of the standing waves is below the limiting frequency, for which the profiles become peaked (piecewise continuously differentiable with a finite jump of the first derivative). We prove that there exist two families of the periodic waves with smooth profiles separated by a homoclinic orbit and the period function (the energy-to-period mapping) is monotonically increasing for the family inside the homoclinic orbit and decreasing for the family outside the homoclinic orbit. This property allows us to derive a sharp criterion for the energetic stability of such standing periodic waves under time evolution if the perturbations are periodic with the same period for both families and, additionally, for the family outside the homoclinic orbit, spatially odd with respect to the half-period. By numerically approximating the sharp stability criterion, we show that both families are energetically stable for small frequencies but become unstable when the frequency approaches the limiting frequency of the peaked waves.

math.AP↗

arXiv2025

YOLO-FireAD: Efficient Fire Detection via Attention-Guided Inverted Residual Learning and Dual-Pooling Feature Preservation

Fire detection in dynamic environments faces continuous challenges, including the interference of illumination changes, many false detections or missed detections, and it is difficult to achieve both efficiency and accuracy. To address the problem of feature extraction limitation and information loss in the existing YOLO-based models, this study propose You Only Look Once for Fire Detection with Attention-guided Inverted Residual and Dual-pooling Downscale Fusion (YOLO-FireAD) with two core innovations: (1) Attention-guided Inverted Residual Block (AIR) integrates hybrid channel-spatial attention with inverted residuals to adaptively enhance fire features and suppress environmental noise; (2) Dual Pool Downscale Fusion Block (DPDF) preserves multi-scale fire patterns through learnable fusion of max-average pooling outputs, mitigating small-fire detection failures. Extensive evaluation on two public datasets shows the efficient performance of our model. Our proposed model keeps the sum amount of parameters (1.45M, 51.8% lower than YOLOv8n) (4.6G, 43.2% lower than YOLOv8n), and mAP75 is higher than the mainstream real-time object detection models YOLOv8n, YOL-Ov9t, YOLOv10n, YOLO11n, YOLOv12n and other YOLOv8 variants 1.3-5.5%. For more details, please visit our repository: https://github.com/JEFfersusu/YOLO-FireAD

cs.CV↗

arXiv2025

Empowering Multi-class Classification for Multivariate Functional Data with Simultaneous Feature Selection

The opportunity to utilize complex functional data types for conducting classification tasks is emerging with the growing availability of imaging data. However, the tools capable of effectively managing imaging data are limited, let alone those that can further leverage other one-dimensional functional data. Inspired by the extensive data provided by the Alzheimer's Disease Neuroimaging Initiative (ADNI), we introduce a novel classifier tailored for complex functional data. Each observation in this framework may be associated with numerous functional processes, varying in dimensions, such as curves and images. Each predictor is a random element in an infinite dimensional function space, and the number of functional predictors p can potentially be much greater than the sample size n. In this paper, we introduce a novel and scalable classifier termed functional BIC deep neural network. By adopting a sparse deep Rectified Linear Unit network architecture and incorporating the LassoNet algorithm, the proposed unified model performs feature selection and classification simultaneously, which is contrast to the existing functional data classifiers. The challenge arises from the complex inter-correlation structures among multiple functional processes, and at meanwhile without any assumptions on the distribution of these processes. Simulation study and real data application are carried out to demonstrate its favorable performance.

stat.ME↗

arXiv2025

Instability of the peaked traveling wave in a local model for shallow water waves

The traveling wave with the peaked profile arises in the limit of the family of traveling waves with the smooth profiles. We study the linear and nonlinear stability of the peaked traveling wave by using a local model for shallow water waves, which is related to the Hunter--Saxton equation. The evolution problem is well-defined in the function space $H^1_{\rm per} \cap W^{1,\infty}$, where we derive the linearized equations of motion and study the nonlinear evolution of co-periodic perturbations to the peaked periodic wave by using methods of characteristics. Within the linearized equations, we prove the spectral instability of the peaked traveling wave from the spectrum of the linearized operator in a Hilbert space, which completely covers the closed vertical strip with a specific half-width. Within the nonlinear equations, we prove the nonlinear instability of the peaked traveling wave by showing that the gradient of perturbations grow at the wave peak. By using numerical approximations of the smooth traveling waves and the spectrum of their associated linearized operator, we show that the spectral instability of the peaked traveling wave cannot be obtained in the limit along the family of the spectrally stable smooth traveling waves.

math.AP↗

arXiv2023

Multiclass classification for multidimensional functional data through deep neural networks

The intrinsically infinite-dimensional features of the functional observations over multidimensional domains render the standard classification methods effectively inapplicable. To address this problem, we introduce a novel multiclass functional deep neural network (mfDNN) classifier as an innovative data mining and classification tool. Specifically, we consider sparse deep neural network architecture with rectifier linear unit (ReLU) activation function and minimize the cross-entropy loss in the multiclass classification setup. This neural network architecture allows us to employ modern computational tools in the implementation. The convergence rates of the misclassification risk functions are also derived for both fully observed and discretely observed multidimensional functional data. We demonstrate the performance of mfDNN on simulated data and several benchmark datasets from different application domains.

cs.LG↗

arXiv2023

Minimax optimal high-dimensional classification using deep neural networks

High-dimensional classification is a fundamentally important research problem in high-dimensional data analysis. In this paper, we derive a nonasymptotic rate for the minimax excess misclassification risk when feature dimension exponentially diverges with the sample size and the Bayes classifier possesses a complicated modular structure. We also show that classifiers based on deep neural networks can attain the above rate, hence, are minimax optimal.

math.ST↗

arXiv2022

Robust Deep Neural Network Estimation for Multi-dimensional Functional Data

In this paper, we propose a robust estimator for the location function from multi-dimensional functional data. The proposed estimators are based on the deep neural networks with ReLU activation function. At the meanwhile, the estimators are less susceptible to outlying observations and model-misspecification. For any multi-dimensional functional data, we provide the uniform convergence rates for the proposed robust deep neural networks estimators. Simulation studies illustrate the competitive performance of the robust deep neural network estimators on regular data and their superior performance on data that contain anomalies. The proposed method is also applied to analyze 2D and 3D images of patients with Alzheimer's disease obtained from the Alzheimer Disease Neuroimaging Initiative database.

stat.ME↗

arXiv2022

Deep Neural Network Classifier for Multi-dimensional Functional Data

We propose a new approach, called as functional deep neural network (FDNN), for classifying multi-dimensional functional data. Specifically, a deep neural network is trained based on the principle components of the training data which shall be used to predict the class label of a future data function. Unlike the popular functional discriminant analysis approaches which rely on Gaussian assumption, the proposed FDNN approach applies to general non-Gaussian multi-dimensional functional data. Moreover, when the log density ratio possesses a locally connected functional modular structure, we show that FDNN achieves minimax optimality. The superiority of our approach is demonstrated through both simulated and real-world datasets.

stat.ML↗

arXiv2021

Optimal Classification for Functional Data

A central topic in functional data analysis is how to design an optimaldecision rule, based on training samples, to classify a data function. We exploit the optimal classification problem when data functions are Gaussian processes. Sharp nonasymptotic convergence rates for minimax excess mis-classification risk are derived in both settings that data functions are fully observed and discretely observed. We explore two easily implementable classifiers based on discriminant analysis and deep neural network, respectively, which are both proven to achieve optimality in Gaussian setting. Our deepneural network classifier is new in literature which demonstrates outstanding performance even when data functions are non-Gaussian. In case of discretely observed data, we discover a novel critical sampling frequency thatgoverns the sharp convergence rates. The proposed classifiers perform favorably in finite-sample applications, as we demonstrate through comparisonswith other functional classifiers in simulations and one real data application.

stat.ME↗

arXiv2020

Estimation of the Mean Function of Functional Data via Deep Neural Networks

In this work, we propose a deep neural network method to perform nonparametric regression for functional data. The proposed estimators are based on sparsely connected deep neural networks with ReLU activation function. By properly choosing network architecture, our estimator achieves the optimal nonparametric convergence rate in empirical norm. Under certain circumstances such as trigonometric polynomial kernel and a sufficiently large sampling frequency, the convergence rate is even faster than root-$n$ rate. Through Monte Carlo simulation studies we examine the finite-sample performance of the proposed method. Finally, the proposed method is applied to analyze positron emission tomography images of patients with Alzheimer disease obtained from the Alzheimer Disease Neuroimaging Initiative database.

stat.ML↗

arXiv2019

Diffusion regions and 3D energy mode development in spontaneous reconnection

The understanding of magnetic reconnection in three-dimension (3D) is far shallower than its counterpart in two-dimension (2D) due to its potential complication, not to mention the evolving of the spontaneously growing turbulence. We investigate the reason for reconnection acceleration on the characters and development of diffusion regions and sheared 3D energy modes (energy modes that are not parallel to the anti-parallel magnetic fields) during the turbulence building stage. We found that multiple reconnection layers emerge due to the growth of 3D sheared tearing instability. Diffusion regions on adjacent reconnection layers form an inflow-outflow coupling that enhances the local reconnection. Further coupling of the existing energy modes breeds new energy modes near the current sheet edge. As reconnection layers span and interact with each other across the whole current sheet, global magnetic energy consumption accelerates. The significant contribution of 3D energy modes and their interaction to the reconnection rate enhancement seems to be independent on magnetic diffusivity. On the other hand, the global guide field changes the layout of 3D reconnection layer thus determines whether the system is fast-reconnection-preferable.

astro-ph.SR↗

arXiv2015

Three-Dimensional MHD Magnetic Reconnection Simulations with Finite Guide Field: Proposal of the Shock-Evoking Positive-Feedback Model

Using a three-dimensional magnetohydrodynamic model, we simulate the magnetic reconnection in a single current sheet. We assume a finite guide field, a random perturbation on the velocity field and uniform resistivity. Our model enhances the reconnection rate relative to the classical Sweet-Parker model in the same configuration. The efficiency of magnetic energy conversion is increased by interactions between the multiple tearing layers coexisting in the global current sheet. This interaction, which forms a positive-feedback system, arises from coupling of the inflow and outflow regions in different layers across the current sheet. The coupling accelerates the elementary reconnection events, thereby enhancing the global reconnection rate. The reconnection establishes flux tubes along each tearing layer. Slow-mode shocks gradually form along the outer boundaries of these tubes, further accelerating the magnetic energy conversion.Such positive-feedback system is absent in two-dimensional simulation, three-dimensional reconnection without a guide field and a reconnection under a single perturbation mode. We refer to our model as the "shock-evoking positive-feedback" model.

astro-ph.SR↗