Michael K. Ng
YOU?
Author Swipe
View article: Heatwaves on the Rise: The Role of El Niño‐Southern Oscillation and Local Water‐Energy Exchanges in Shaping Global Patterns
Heatwaves on the Rise: The Role of El Niño‐Southern Oscillation and Local Water‐Energy Exchanges in Shaping Global Patterns Open
Large‐scale and intense heatwaves pose significant risks to ecosystems and human society due to associated heat and water stress. Heatwaves can be classified as daytime, nighttime, and compound, depending on their occurrence time. However,…
View article: A global daily seamless 9 km vegetation optical depth (VOD) product from 2010 to 2021
A global daily seamless 9 km vegetation optical depth (VOD) product from 2010 to 2021 Open
Vegetation optical depth (VOD) products provide information on vegetation water content and correlate with vegetation growth status; these are closely related to the global water and carbon cycles. The L-band signal penetrates deeper into …
View article: Reconstruction-free magnetic control of DIII-D plasma with deep reinforcement learning
Reconstruction-free magnetic control of DIII-D plasma with deep reinforcement learning Open
Precise control of plasma shape and position is essential for stable tokamak operation and achieving commercial fusion energy. Traditional control methods rely on equilibrium reconstruction and linearized models, limiting adaptability and …
View article: ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging
ConnectomeDiffuser: Generative AI Enables Brain Network Construction from Diffusion Tensor Imaging Open
Brain network analysis plays a crucial role in diagnosing and monitoring neurodegenerative disorders such as Alzheimer's disease (AD). Existing approaches for constructing structural brain networks from diffusion tensor imaging (DTI) often…
View article: Deep Learning Optimization Using Self-Adaptive Weighted Auxiliary Variables
Deep Learning Optimization Using Self-Adaptive Weighted Auxiliary Variables Open
In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning be…
View article: Quaternion Nuclear Norms Over Frobenius Norms Minimization for Robust Matrix Completion
Quaternion Nuclear Norms Over Frobenius Norms Minimization for Robust Matrix Completion Open
Recovering hidden structures from incomplete or noisy data remains a pervasive challenge across many fields, particularly where multi-dimensional data representation is essential. Quaternion matrices, with their ability to naturally model …
View article: Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport
Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport Open
Unsupervised graph alignment aims to find corresponding nodes across different graphs without supervision. Existing methods usually leverage the graph structure to aggregate features of nodes to find relations between nodes. However, the g…
View article: Truncated Huber Penalty for Sparse Signal Recovery with Convergence Analysis
Truncated Huber Penalty for Sparse Signal Recovery with Convergence Analysis Open
Sparse signal recovery from under-determined systems presents significant challenges when using conventional L_0 and L_1 penalties, primarily due to computational complexity and estimation bias. This paper introduces a truncated Huber pena…
View article: Tensor recovery from quantized measurements based on modewise operators
Tensor recovery from quantized measurements based on modewise operators Open
The problem of tensor recovery from quantized measurements aims to reconstruct a low-rank tensor based on its quantized linear inner-product measurements, which has diverse applications in achieving compressed representation or efficient t…
View article: A Graph-Partitioning Based Continuous Optimization Approach to Semi-supervised Clustering Problems
A Graph-Partitioning Based Continuous Optimization Approach to Semi-supervised Clustering Problems Open
Semi-supervised clustering is a basic problem in various applications. Most existing methods require knowledge of the ideal cluster number, which is often difficult to obtain in practice. Besides, satisfying the must-link constraints is an…
View article: Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networks
Low Tensor-Rank Adaptation of Kolmogorov--Arnold Networks Open
Kolmogorov--Arnold networks (KANs) have demonstrated their potential as an alternative to multi-layer perceptions (MLPs) in various domains, especially for science-related tasks. However, transfer learning of KANs remains a relatively unex…
View article: EGD-Net: Eigenimage Guided Diffusion Network for Hyperspectral Mixed Noise Removal
EGD-Net: Eigenimage Guided Diffusion Network for Hyperspectral Mixed Noise Removal Open
In this article, we study diffusion-type network methods for denoising remote sensing images with hyperspectral mixed noise (Gaussian noise and stripe noise). Two key issues should be addressed: 1) there are many wavelengths in remote sens…
View article: A global daily seamless 9-km Vegetation Optical Depth (VOD) product from 2010 to 2021
A global daily seamless 9-km Vegetation Optical Depth (VOD) product from 2010 to 2021 Open
Vegetation optical depth (VOD) products provide information on vegetation water content and correlate with vegetation growth status, which are closely related to the global water and carbon cycles. The L-band signal penetrates deeper into …
View article: Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection
Optimal-Transport-Based Positive and Unlabeled Learning Method for Windshear Detection Open
Windshear is a microscale meteorological phenomenon that can be dangerous to aircraft during the take-off and landing phases. Accurate windshear detection plays a significant role in air traffic control. In this paper, we aim to investigat…
View article: GSTRPCA: irregular tensor singular value decomposition for single-cell multi-omics data clustering
GSTRPCA: irregular tensor singular value decomposition for single-cell multi-omics data clustering Open
Single-cell multi-omics refers to the various types of biological data at the single-cell level. These data have enabled insight and resolution to cellular phenotypes, biological processes, and developmental stages. Current advances hold h…
View article: Low-Rank Tensor Learning by Generalized Nonconvex Regularization
Low-Rank Tensor Learning by Generalized Nonconvex Regularization Open
In this paper, we study the problem of low-rank tensor learning, where only a few of training samples are observed and the underlying tensor has a low-rank structure. The existing methods are based on the sum of nuclear norms of unfolding …
View article: Learnable Transform-Assisted Tensor Decomposition for Spatio-Irregular Multidimensional Data Recovery
Learnable Transform-Assisted Tensor Decomposition for Spatio-Irregular Multidimensional Data Recovery Open
Tensor decompositions have been successfully applied to multidimensional data recovery. However, classical tensor decompositions are not suitable for emerging spatio-irregular multidimensional data (i.e., spatio-irregular tensor), whose sp…
View article: DAPE V2: Process Attention Score as Feature Map for Length Extrapolation
DAPE V2: Process Attention Score as Feature Map for Length Extrapolation Open
The attention mechanism is a fundamental component of the Transformer model, contributing to interactions among distinct tokens, in contrast to earlier feed-forward neural networks. In general, the attention scores are determined simply by…
View article: Robust Instance Optimal Phase-Only Compressed Sensing
Robust Instance Optimal Phase-Only Compressed Sensing Open
Phase-only compressed sensing (PO-CS) concerns the recovery of sparse signals from the phases of complex measurements. Recent results show that sparse signals in the standard sphere $\mathbb{S}^{n-1}$ can be exactly recovered from complex …
View article: Non-Negative Reduced Biquaternion Matrix Factorization with Applications in Color Face Recognition
Non-Negative Reduced Biquaternion Matrix Factorization with Applications in Color Face Recognition Open
Reduced biquaternion (RB), as a four-dimensional algebra highly suitable for representing color pixels, has recently garnered significant attention from numerous scholars. In this paper, for color image processing problems, we introduce a …
View article: Multi-modal Mood Reader: Pre-trained Model Empowers Cross-Subject Emotion Recognition
Multi-modal Mood Reader: Pre-trained Model Empowers Cross-Subject Emotion Recognition Open
Emotion recognition based on Electroencephalography (EEG) has gained significant attention and diversified development in fields such as neural signal processing and affective computing. However, the unique brain anatomy of individuals lea…
View article: Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representations
Hyperspectral and multispectral image fusion with arbitrary resolution through self-supervised representations Open
The fusion of a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) has emerged as an effective technique for achieving HSI super-resolution (SR). Previous studies have mainly concentrated on est…
View article: DAPE: Data-Adaptive Positional Encoding for Length Extrapolation
DAPE: Data-Adaptive Positional Encoding for Length Extrapolation Open
Positional encoding plays a crucial role in transformers, significantly impacting model performance and length generalization. Prior research has introduced absolute positional encoding (APE) and relative positional encoding (RPE) to disti…
View article: Data Valuation by Fusing Global and Local Statistical Information
Data Valuation by Fusing Global and Local Statistical Information Open
Data valuation has garnered increasing attention in recent years, given the critical role of high-quality data in various applications. Among diverse data valuation approaches, Shapley value-based methods are predominant due to their stron…
View article: A New Cross-Space Total Variation Regularization Model for Color Image Restoration with Quaternion Blur Operator
A New Cross-Space Total Variation Regularization Model for Color Image Restoration with Quaternion Blur Operator Open
The cross-channel deblurring problem in color image processing is difficult to solve due to the complex coupling and structural blurring of color pixels. Until now, there are few efficient algorithms that can reduce color artifacts in debl…