Han Liu
YOU?
Author Swipe
View article: Targeting Ferroptosis in Sensorineural Hearing Loss: A Mechanistic Review of Therapeutic Opportunities
Targeting Ferroptosis in Sensorineural Hearing Loss: A Mechanistic Review of Therapeutic Opportunities Open
Ferroptosis, an iron-dependent form of regulated cell death, is emerging as a critical pathogenic mechanism and a highly promising therapeutic target in sensorineural hearing loss (SNHL). The irreversible loss of auditory hair cells, the h…
View article: Genome-Wide Identification, Evolution, and Expression Analysis of the DMP Gene Family in Peanut (Arachis hypogaea L.)
Genome-Wide Identification, Evolution, and Expression Analysis of the DMP Gene Family in Peanut (Arachis hypogaea L.) Open
Peanut (Arachis hypogaea L.) is a globally important oilseed cash crop, yet its limited genetic diversity and unique reproductive biology present persistent challenges for conventional crossbreeding. Traditional breeding approaches are oft…
View article: Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey
Data Augmentation for Time-Series Classification: An Extensive Empirical Study and Comprehensive Survey Open
Background: Data Augmentation (DA) has become a critical approach in Time Series Classification (TSC), primarily for its capacity to expand training datasets, enhance model robustness, introduce diversity, and reduce overfitting. However, …
View article: Cross-Domain Conditional Diffusion Models for Time Series Imputation
Cross-Domain Conditional Diffusion Models for Time Series Imputation Open
Cross-domain time series imputation is an underexplored data-centric research task that presents significant challenges, particularly when the target domain suffers from high missing rates and domain shifts in temporal dynamics. Existing t…
View article: Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers
Surrogate Signals from Format and Length: Reinforcement Learning for Solving Mathematical Problems without Ground Truth Answers Open
Large Language Models have achieved remarkable success in natural language processing tasks, with Reinforcement Learning playing a key role in adapting them to specific applications. However, obtaining ground truth answers for training LLM…
View article: Light sensor based on carbon tetrachloride-infiltrated side-hole fiber
Light sensor based on carbon tetrachloride-infiltrated side-hole fiber Open
We propose a high-sensitivity light sensor based on side-hole optical fiber filled with carbon tetrachloride. Using a fusion splicer, we employed a selective glue coating method to fill one of the air holes with liquid. Coupling occurs bet…
View article: Evaluating disability, comorbidities and risk factors after TB treatment: an 18–24 month follow-up
Evaluating disability, comorbidities and risk factors after TB treatment: an 18–24 month follow-up Open
BACKGROUNDSeveral countries have developed national strategic plans to address post-TB disability and comorbidities. However, their feasibility and added value within routine programmatic settings remain undocumented.METHODSWe followed up …
View article: An Optimized Power Load Forecasting Algorithm Based on VMD‐SMA‐LSTM
An Optimized Power Load Forecasting Algorithm Based on VMD‐SMA‐LSTM Open
Accurate load forecasting can scientifically guide the optimal operation and scheduling of urban power grids. This study introduces an enhanced power load forecasting algorithm, integrating slime mould algorithm (SMA) and long short‐time m…
View article: A Study on the Application of Intelligent Algorithms in the Detection and Classification of Malicious Traffic
A Study on the Application of Intelligent Algorithms in the Detection and Classification of Malicious Traffic Open
In order to solve the problem of insufficiently accurate attack model training due to the lack of samples of certain attack steps in the attack detection in the current network big data environment, the research on the application of intel…
View article: Expression Patterns of Cav1.3 in the Developing Stria Vascularis of Sprague–Dawley Rats
Expression Patterns of Cav1.3 in the Developing Stria Vascularis of Sprague–Dawley Rats Open
Background: Although multiple functions of Cav1.3 in adult rat cochlea have been explored, its role in developing stria vascularis (SV) ofSprague–Dawley (SD) rats has rarely been reported.Methods: Sprague–Dawley rats from postnatal 0 to 21…
View article: A Dual-Branch Network of Strip Convolution and Swin Transformer for Multimodal Remote Sensing Image Registration
A Dual-Branch Network of Strip Convolution and Swin Transformer for Multimodal Remote Sensing Image Registration Open
Multimodal remote sensing image registration aims to achieve effective fusion and analysis of information by accurately aligning image data obtained by different sensors, thereby improving the accuracy and application value of remote sensi…
View article: A study on the causes of viewers’ non-continuous following intention in tourism live streaming
A study on the causes of viewers’ non-continuous following intention in tourism live streaming Open
View article: Hybrid Linking Sites Constructed Non‐Fully Conjugated Asymmetric Dimerized Giant Molecule Acceptors for Organic Solar Cells with an Efficiency of ≈20%
Hybrid Linking Sites Constructed Non‐Fully Conjugated Asymmetric Dimerized Giant Molecule Acceptors for Organic Solar Cells with an Efficiency of ≈20% Open
Linking‐site engineering, used to graft two or more monomers, is crucial for achieving high‐performance Y‐series giant molecule acceptors (Y‐GMAs). However, the reported Y‐GMAs all use a single‐typed linking site, making it difficult to fi…
View article: Application of PDCA cycle management in outpatient nursing management under the background of New Quality Productive Forces
Application of PDCA cycle management in outpatient nursing management under the background of New Quality Productive Forces Open
Objective To explore the effect of PDCA cycle management on outpatient nursing management under the background of New Quality Productive Forces. Methods The PDCA cycle management was adopted, and targeted interventions on outpatient treatm…
View article: Automating RT Planning at Scale: High Quality Data For AI Training
Automating RT Planning at Scale: High Quality Data For AI Training Open
Radiotherapy (RT) planning is complex, subjective, and time-intensive. Advances with artificial intelligence (AI) promise to improve its precision and efficiency, but progress is often limited by the scarcity of large, standardized dataset…
View article: HDCTfusion: Hybrid Dual-Branch Network Based on CNN and Transformer for Infrared and Visible Image Fusion
HDCTfusion: Hybrid Dual-Branch Network Based on CNN and Transformer for Infrared and Visible Image Fusion Open
The purpose of infrared and visible image fusion is to combine the advantages of both and generate a fused image that contains target information and has rich details and contrast. However, existing fusion algorithms often overlook the imp…
View article: One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context Open
Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, they are still able to solve unseen tasks well purely based on…
View article: Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory Open
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is modeled as a stream of tasks drawn from a task distributio…
View article: Global Convergence in Training Large-Scale Transformers
Global Convergence in Training Large-Scale Transformers Open
Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in train…
View article: ALDH2 mediates the effects of sodium-glucose cotransporter 2 inhibitors (SGLT2i) on improving cardiac remodeling
ALDH2 mediates the effects of sodium-glucose cotransporter 2 inhibitors (SGLT2i) on improving cardiac remodeling Open
View article: MDSCNN: Remote Sensing Image Spatial–Spectral Fusion Method via Multi-Scale Dual-Stream Convolutional Neural Network
MDSCNN: Remote Sensing Image Spatial–Spectral Fusion Method via Multi-Scale Dual-Stream Convolutional Neural Network Open
Pansharpening refers to enhancing the spatial resolution of multispectral images through panchromatic images while preserving their spectral features. However, existing traditional methods or deep learning methods always have certain disto…
View article: Influence of Early through Late Fusion on Pancreas Segmentation from Imperfectly Registered Multimodal MRI
Influence of Early through Late Fusion on Pancreas Segmentation from Imperfectly Registered Multimodal MRI Open
Multimodal fusion promises better pancreas segmentation. However, where to perform fusion in models is still an open question. It is unclear if there is a best location to fuse information when analyzing pairs of imperfectly aligned images…
View article: Pretrained subtraction and segmentation model for coronary angiograms
Pretrained subtraction and segmentation model for coronary angiograms Open
This study introduces a novel self-supervised learning method for single-frame subtraction and vessel segmentation in coronary angiography, addressing the scarcity of annotated medical samples in AI applications. We pretrain a U-Net model …
View article: An Improved Detail-Enhancement CycleGAN Using AdaLIN for Facial Style Transfer
An Improved Detail-Enhancement CycleGAN Using AdaLIN for Facial Style Transfer Open
The rise of comics and games has led to increased artistic processing of portrait photos. With growing commercial demand and advancements in deep learning, neural networks for rapid facial style transfer have become a key research area in …
View article: ODNet: A High Real-Time Network Using Orthogonal Decomposition for Few-Shot Strip Steel Surface Defect Classification
ODNet: A High Real-Time Network Using Orthogonal Decomposition for Few-Shot Strip Steel Surface Defect Classification Open
Strip steel plays a crucial role in modern industrial production, where enhancing the accuracy and real-time capabilities of surface defect classification is essential. However, acquiring and annotating defect samples for training deep lea…
View article: A Forest Fire Smoke Monitoring System Based on a Lightweight Neural Network for Edge Devices
A Forest Fire Smoke Monitoring System Based on a Lightweight Neural Network for Edge Devices Open
Forest resources are one of the indispensable resources of the earth, which are the basis for the survival and development of human society. With the swift advancements in computer vision and artificial intelligence technology, the utiliza…
View article: MDC-RHT: Multi-Modal Medical Image Fusion via Multi-Dimensional Dynamic Convolution and Residual Hybrid Transformer
MDC-RHT: Multi-Modal Medical Image Fusion via Multi-Dimensional Dynamic Convolution and Residual Hybrid Transformer Open
The fusion of multi-modal medical images has great significance for comprehensive diagnosis and treatment. However, the large differences between the various modalities of medical images make multi-modal medical image fusion a great challe…
View article: Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods
Communication-Efficient Adaptive Batch Size Strategies for Distributed Local Gradient Methods Open
Modern deep neural networks often require distributed training with many workers due to their large size. As the number of workers increases, communication overheads become the main bottleneck in data-parallel minibatch stochastic gradient…
View article: Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation
Enhancing Single-Slice Segmentation with 3D-to-2D Unpaired Scan Distillation Open
2D single-slice abdominal computed tomography (CT) enables the assessment of body habitus and organ health with low radiation exposure. However, single-slice data necessitates the use of 2D networks for segmentation, but these networks oft…
View article: Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation
Adversarial Robustness Enhancement for Deep Learning-Based Soft Sensors: An Adversarial Training Strategy Using Historical Gradients and Domain Adaptation Open
Despite their high prediction accuracy, deep learning-based soft sensor (DLSS) models face challenges related to adversarial robustness against malicious adversarial attacks, which hinder their widespread deployment and safe application. A…