Derong Liu
YOU?
Author Swipe
View article: Compensating Distribution Drifts in Class-incremental Learning of Pre-trained Vision Transformers
Compensating Distribution Drifts in Class-incremental Learning of Pre-trained Vision Transformers Open
Recent advances have shown that sequential fine-tuning (SeqFT) of pre-trained vision transformers (ViTs), followed by classifier refinement using approximate distributions of class features, can be an effective strategy for class-increment…
View article: Magnetic resonance imaging-based radiomics of mesorectum for predicting extramural venous invasion in patients with rectal cancer: a bi-centric study
Magnetic resonance imaging-based radiomics of mesorectum for predicting extramural venous invasion in patients with rectal cancer: a bi-centric study Open
Objectives To develop and validate a magnetic resonance imaging (MRI)-based radiomics model of the mesorectum for predicting extramural venous invasion (EMVI) in patients with rectal cancer (RC). Methods A retrospective study included 238 …
View article: Development and Validation of a Predictive Model for Occult Liver Metastasis in Pancreatic Ductal Adenocarcinoma Using Subjective Imaging and Clinical Data
Development and Validation of a Predictive Model for Occult Liver Metastasis in Pancreatic Ductal Adenocarcinoma Using Subjective Imaging and Clinical Data Open
Background Pancreatic ductal adenocarcinoma (PDAC) is highly lethal, with liver metastases leading to poorer outcomes. Occult liver metastases (OLM), undetected by initial imaging, complicate treatment and diminish survival rates. We aimed…
View article: CLAD: Criterion Learner and Attention Distillation for Automated CNN Prunning
CLAD: Criterion Learner and Attention Distillation for Automated CNN Prunning Open
View article: Ferroptosis suppressor protein 1 regulated oligodendrocytes ferroptosis rescued by idebenone in spinal cord injury
Ferroptosis suppressor protein 1 regulated oligodendrocytes ferroptosis rescued by idebenone in spinal cord injury Open
Ferroptosis has been demonstrated to be involved in the progression of spinal cord injury (SCI). Ferroptosis suppressor protein 1 (FSP1) can inhibit ferroptosis in parallel with Glutathione peroxidase 4 (GPX4). However, the role of FSP1 in…
View article: Identifying individuals at risk for surgical supravalvar aortic stenosis by polygenic risk score with graded phenotyping
Identifying individuals at risk for surgical supravalvar aortic stenosis by polygenic risk score with graded phenotyping Open
In a previous pathway-based, extreme phenotype study, we identified 1064 variants associated with supravalvar aortic stenosis (SVAS) severity in people with Williams syndrome (WS) and either no SVAS or surgical SVAS. Here, we use those var…
View article: ROS-responsive nanoparticle delivery of ferroptosis inhibitor prodrug to facilitate mesenchymal stem cell-mediated spinal cord injury repair
ROS-responsive nanoparticle delivery of ferroptosis inhibitor prodrug to facilitate mesenchymal stem cell-mediated spinal cord injury repair Open
Spinal cord injury (SCI) is a traumatic condition that results in impaired motor and sensory function. Ferroptosis is one of the main causes of neural cell death and loss of neurological function in the spinal cord, and ferroptosis inhibit…
View article: Model based mapping of a novel prototype spark ignition opposed-piston engine
Model based mapping of a novel prototype spark ignition opposed-piston engine Open
Blower-scavenged opposed-piston two-stroke engines possess inherent thermodynamic advantages over four stroke engines. Increasingly well demonstrated in compression ignition form, they are less so in spark ignition form, where there is cle…
View article: Inside back cover
Inside back cover Open
View article: The joint-brain axis: evidence from a Mendelian randomization study of osteoarthritis and cortical structure
The joint-brain axis: evidence from a Mendelian randomization study of osteoarthritis and cortical structure Open
Background Osteoarthritis (OA) is a common joint disease that may affect brain function via a joint-brain axis, but its causal impact on brain cortical structures is unclear. Method We used Mendelian randomization (MR), a method that lever…
View article: Epigenetic regulation and factors that influence the effect of iPSCs-derived neural stem/progenitor cells (NS/PCs) in the treatment of spinal cord injury
Epigenetic regulation and factors that influence the effect of iPSCs-derived neural stem/progenitor cells (NS/PCs) in the treatment of spinal cord injury Open
Spinal cord injury (SCI) is a severe neurological disorder that causes neurological impairment and disability. Neural stem/progenitor cells (NS/PCs) derived from induced pluripotent stem cells (iPSCs) represent a promising cell therapy str…
View article: Self-Triggered Approximate Optimal Neuro-Control for Nonlinear Systems Through Adaptive Dynamic Programming
Self-Triggered Approximate Optimal Neuro-Control for Nonlinear Systems Through Adaptive Dynamic Programming Open
In this article, a novel self-triggered approximate optimal neuro-control scheme is presented for nonlinear systems by utilizing adaptive dynamic programming (ADP). According to the Bellman principle of optimality, the cost function of the…
View article: A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate
A Novel Online Adaptive Dynamic Programming Algorithm With Adjustable Convergence Rate Open
This article develops a novel online adaptive dynamic programming algorithm with adjustable convergence rate to address the optimal control problem of nonlinear systems. Relaxation factors are introduced to tune the convergence rate of val…
View article: Single-cell and genome-wide Mendelian randomization identifies causative genes for gout
Single-cell and genome-wide Mendelian randomization identifies causative genes for gout Open
Background Gout is a prevalent manifestation of metabolic osteoarthritis induced by elevated blood uric acid levels. The purpose of this study was to investigate the mechanisms of gene expression regulation in gout disease and elucidate it…
View article: Highly Lithiophilic Three-Dimension Framework of Vertical CuO Nanorod Arrays Decorated Carbon Cloth for Dendrite-Free Li Metal Anode
Highly Lithiophilic Three-Dimension Framework of Vertical CuO Nanorod Arrays Decorated Carbon Cloth for Dendrite-Free Li Metal Anode Open
An Li metal anode has been proposed as a promising candidate for high energy density electrode material. However, the direct use of Li metal can lead to uncontrollable dendrite growth and massive volume expansion, which generates severe sa…
View article: Neuro-Optimal Event-Triggered Impulsive Control for Stochastic Systems via ADP
Neuro-Optimal Event-Triggered Impulsive Control for Stochastic Systems via ADP Open
This article presents a novel neural-network-based optimal event-triggered impulsive control method. First, a novel general-event-based impulsive transition matrix (GITM) is constructed to represent the probability distribution evolving ch…
View article: Highly Efficient Electrocatalytic Treatment of High-Concentration 4-Chlorophenol Wastewater on Pd-Cu/Ppy/Nf Composite Cathode
Highly Efficient Electrocatalytic Treatment of High-Concentration 4-Chlorophenol Wastewater on Pd-Cu/Ppy/Nf Composite Cathode Open
View article: An Event-Triggered Adaptive Dynamic Programming Method for Large-Scale HVAC Systems*
An Event-Triggered Adaptive Dynamic Programming Method for Large-Scale HVAC Systems* Open
In this paper, an event-triggered adaptive dynamic programming (ADP) algorithm is developed for the temperature control of large-scale heating, ventilation, and air conditioning (HVAC) systems. First, the dynamic model of the system is est…
View article: A Significant Enhancement of Catalytic Activity in Pt/Fe2o3 Catalysts Via L-Histidine Decoration for Better Catalytic Hydrogenation Performance
A Significant Enhancement of Catalytic Activity in Pt/Fe2o3 Catalysts Via L-Histidine Decoration for Better Catalytic Hydrogenation Performance Open
View article: State of the Art of Adaptive Dynamic Programming and Reinforcement Learning
State of the Art of Adaptive Dynamic Programming and Reinforcement Learning Open
This article introduces the state-of-the-art development of adaptive dynamic programming and reinforcement learning (ADPRL). First, algorithms in reinforcement learning (RL) are introduced and their roots in dynamic programming are illustr…
View article: DNAD: Differentiable Neural Architecture Distillation
DNAD: Differentiable Neural Architecture Distillation Open
In order to satisfy the demand for designing efficient neural networks with an appropriate tradeoff between model performance (e.g., classifification accuracy) and computational complexity, the differentiable neural architecture distillati…
View article: DNAD: Differentiable Neural Architecture Distillation
DNAD: Differentiable Neural Architecture Distillation Open
In order to satisfy the demand for designing efficient neural networks with an appropriate tradeoff between model performance (e.g., classifification accuracy) and computational complexity, the differentiable neural architecture distillati…
View article: CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks
CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks Open
In neural architecture search (NAS) methods based on latent space optimization (LSO), a deep generative model is trained to embed discrete neural architectures into a continuous latent space. In this case, different optimization algorithms…
View article: Conference Committee
Conference Committee Open
View article: N6-methyladenosine modification: A potential regulatory mechanism in spinal cord injury
N6-methyladenosine modification: A potential regulatory mechanism in spinal cord injury Open
N6-methyladenosine (m6A), an essential post-transcriptional modification in eukaryotes, is closely related to the development of pathological processes in neurological diseases. Notably, spinal cord injury (SCI) is a serious traumatic dise…
View article: Pathway analysis identifies novel non-synonymous variants contributing to extreme vascular outcomes in Williams-Beuren syndrome
Pathway analysis identifies novel non-synonymous variants contributing to extreme vascular outcomes in Williams-Beuren syndrome Open
Supravalvar aortic stenosis (SVAS) is a characteristic feature of Williams-Beuren syndrome (WBS). SVAS is present in 67% of those with WBS, but severity varies; 21% have clinically significant SVAS requiring surgical intervention while 33%…
View article: Explainable Intelligent Fault Diagnosis for Nonlinear Dynamic Systems: From Unsupervised to Supervised Learning
Explainable Intelligent Fault Diagnosis for Nonlinear Dynamic Systems: From Unsupervised to Supervised Learning Open
The increased complexity and intelligence of automation systems require the development of intelligent fault diagnosis (IFD) methodologies. By relying on the concept of a suspected space, this study develops explainable data-driven IFD app…
View article: Bioinformatics analysis of ferroptosis in spinal cord injury
Bioinformatics analysis of ferroptosis in spinal cord injury Open
Ferroptosis plays a key role in aggravating the progression of spinal cord injury (SCI), but the specific mechanism remains unknown. In this study, we constructed a rat model of T10 SCI using a modified Allen method. We identified 48, 44, …
View article: Omics Imagification: Transforming High-throughput Molecular Representation of a Cell into an Image
Omics Imagification: Transforming High-throughput Molecular Representation of a Cell into an Image Open
Different omics profiles, depending on the underlying technology, encompass measurements of several hundred to several thousands of molecules in a biological sample or a cell. This study develops upon the concept of "omics imagification" a…
View article: Theoretical Model and Computer Simulation of Power Utility Matrix for the Integrated Distributed Energy Resources
Theoretical Model and Computer Simulation of Power Utility Matrix for the Integrated Distributed Energy Resources Open
In this article, the authors methodically study the optimized distributed energy resources (DER)/ systems in terms of energy generation, consumption, transaction, and scheduling. They discovered a mathematical model that allows the users/ …