Memory Flow-Controlled Knowledge Tracing with Three Stages

Academic Background With the rapid development of artificial intelligence (AI) technology, intelligent tutoring systems (ITS) such as Khan Academy and Coursera have made significant progress in personalized learning. Knowledge Tracing (KT), as a key technology in ITS, aims to infer students’ knowledge mastery and predict their future learning perfo...

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows

Continual Learning of Conjugated Visual Representations through Higher-Order Motion Flows: A Study on the CMOSFET Model Academic Background In the fields of artificial intelligence and computer vision, continual learning from continuous visual data streams has long been a challenge. Traditional machine learning methods typically rely on the assumpt...

Exploiting Instance-Label Dynamics through Reciprocal Anchored Contrastive Learning for Few-Shot Relation Extraction

Exploiting Instance-Label Dynamics through Reciprocal Anchored Contrastive Learning for Few-Shot Relation Extraction Academic Background In the field of Natural Language Processing (NLP), Relation Extraction (RE) is a fundamental task aimed at identifying and extracting relationships between entities in text. However, traditional supervised learnin...

Rise-Editing: Rotation-Invariant Neural Point Fields with Interactive Segmentation for Fine-Grained and Efficient Editing

Rise-Editing: Rotation-Invariant Neural Point Fields with Interactive Segmentation for Fine-Grained and Efficient Editing

Research on Efficient Fine-Grained 3D Scene Editing Based on Rotation-Invariant Neural Point Fields Academic Background In the fields of computer vision and graphics, modeling and rendering novel views of real scenes from multi-view images is a central problem. Neural Radiance Fields (NeRF) have recently demonstrated significant potential in genera...

Anxiety Disorder Identification with Biomarker Detection through Subspace-Enhanced Hypergraph Neural Network

Anxiety Disorder Identification with Biomarker Detection through Subspace-Enhanced Hypergraph Neural Network

Anxiety Disorder Identification and Biomarker Detection Based on Subspace-Enhanced Hypergraph Neural Network Academic Background Anxiety Disorders (ADs) are prevalent mental health issues globally, affecting approximately 7.3% of the population. Patients with anxiety disorders typically exhibit excessive fear, worry, and related behavioral abnormal...

Secure Finite-Time Filtering for Switched Fuzzy Systems with Scaling Attacks and Stochastic Sensor Faults

Research on Secure Finite-Time Filter Design for Switched Fuzzy Systems Academic Background In modern control systems, switched systems and fuzzy systems have garnered significant attention due to their effectiveness in handling complex nonlinear dynamics. However, with the proliferation of networked systems, these systems face threats from sensor ...

Nonlinear Displacement Control and Force Estimation in a Piezoelectric Robotic Manipulator

Academic Background In the fields of engineering and materials science, precise control of robotic manipulator displacement and force is crucial for studying the mechanical properties of materials, especially when dealing with objects exhibiting nonlinear viscoelastic deformation. For instance, in textiles, aerospace, medical, and energy production...

Hierarchical Non-Singular Terminal Sliding Mode Control for Constrained Under-Actuated Nonlinear Systems Against Sensor Faults

Background Introduction In modern engineering practices, under-actuated systems are widely used in fields such as overhead cranes, wheeled inverted pendulums, and snake robots due to their simple structure, low energy consumption, and high flexibility. However, the number of control inputs in under-actuated systems is less than the degrees of freed...

Fixed-Time Observation and Control for Network Systems: A Distributed Event-Based Saturation Adaptive Method

Academic Background Complex Networks (CNs) play a crucial role in fields such as sociology, engineering, and natural sciences, and are widely applied in scenarios like power distribution, traffic dispatching, and multi-agent collaboration. However, due to factors such as communication packet loss, sensor noise, and environmental uncertainties, obta...

Set-Membership Estimation for T–S Fuzzy Complex Networks: A Dynamic Coding-Decoding Mechanism

Academic Background In today’s complex network systems, state estimation is a critical issue, especially when dealing with uncertainties and noise. Complex networks typically consist of multiple interconnected nodes, and the dynamic behavior of each node may be influenced by nonlinear factors. The Takagi-Sugeno (T-S) fuzzy model has demonstrated si...