Cost-Efficient Feature Selection for Horizontal Federated Learning

Information Science, Computer Science, Artificial Intelligence,
Federated Learning   Feature Selection   Multiobjective Optimization   Mutual Information   Clustering  

Research on Cost-Efficient Feature Selection in Horizontal Federated Learning Background and Motivation As Federated Learning (FL) is increasingly recognized as a distributed machine learning paradigm that safeguards data privacy, its application to multi-client scenarios has garnered significant attention. In Horizontal Federated Learning (HFL), a...

Self-Model-Free Learning versus Learning with External Rewards in Information-Constrained Environments

Information Science, Computer Science, Artificial Intelligence,
Reinforcement Learning   Information Loss   Adversarial Learning   Jamming Attacks   Autonomous Decision Making  

Self-Model-Free Learning vs. Learning with External Rewards in Information-Constrained Environments: A New Reinforcement Learning Framework In recent years, with the development of networks and artificial intelligence systems, networked learning mechanisms face significant security challenges. In the domain of reinforcement learning (RL), the loss ...

Spatio-Temporal Graph-Based Generation and Detection of Adversarial False Data Injection Evasion Attacks in Smart Grids

Engineering, Electrical Engineering, Information Science, Computer Science, Artificial Intelligence,
smart grids   false data injection attacks   adversarial attacks   spatio-temporal graphs   graph neural networks   machine learning   cybersecurity  

Title: Generating and Detecting Spatio-Temporal Graph-Based Adversarial False Data Injection Evasion Attacks in Smart Grids Background With the continuous development of modern smart grids, the grid, as a typical Cyber-Physical System (CPS), faces numerous security threats due to the extensive exchange of data between its components. Among these, F...

Partial Domain Adaptation for Building Borehole Lithology Model Under Weaker Geological Prior

Earth Sciences, Geochemistry, Geology, Geophysics, Information Science, Automation, Artificial Intelligence,
lithology identification   partial domain adaptation   sample transferability weighting   convolutional neural network   channel attention mechanism   target sample reconstruction   geological exploration  

Report on the Paper: “Partial Domain Adaptation for Building Borehole Lithology Model Under Weaker Geological Prior” Background and Research Problem Lithology identification plays a critical role in stratigraphic characterization and reservoir exploration. However, existing AI and machine learning-based lithology identification methods face substan...

Simplified Kernel-Based Cost-Sensitive Broad Learning System for Imbalanced Fault Diagnosis

Engineering, Mechanical Engineering, Information Science, Computer Science, Artificial Intelligence,
fault diagnosis   imbalanced data   broad learning system   cost-sensitive learning   kernel mapping  

Research Report on the Simplified Kernel-Based Cost-Sensitive Broad Learning System (SKCSBLS) for Imbalanced Fault Diagnosis Research Background and Significance With the advent of Industry 4.0, smart manufacturing increasingly relies on industrial big data analytics. By extracting critical insights from machine operation data, the effectiveness of...

Event-Triggered Fuzzy Adaptive Stabilization of Parabolic PDE–ODE Systems

Mathematics, Engineering, Electrical Engineering, Information Science, Automation, Artificial Intelligence,
Event-Triggered Control   Fuzzy Logic Systems   Parabolic PDE-ODE Systems   Stabilization Control   Adaptive Backstepping  

Scientific Report: On “Event-Triggered Fuzzy Adaptive Stabilization of Parabolic PDE–ODE Systems” Research Background and Significance In modern engineering systems, such as flexible manipulators, heat transfer devices, and reactor controllers, many complex systems must be modeled using partial differential equations (PDEs). Due to their unique rea...

Optimal Control of Stochastic Markovian Jump Systems with Wiener and Poisson Noises: Two Reinforcement Learning Approaches

Mathematics, Engineering, Information Science, Computer Science, Artificial Intelligence,
Stochastic Markovian Jump Systems   Wiener Noise   Poisson Noise   Reinforcement Learning   Optimal Control   Policy Iteration Algorithm   Numerical Verification  

Optimal Control of Stochastic Markovian Jump Systems with Wiener and Poisson Noises: Two Reinforcement Learning Approaches Academic Context In modern control theory, optimal control is a crucial research field, aiming to design an optimal control strategy under various constraints for dynamic systems to minimize a given cost function. For stochasti...

Integration of High-κ Native Oxides of Gallium for Two-Dimensional Transistors

Chemistry, Nanoscience, Engineering, Electrical Engineering, Materials Science, Information Science, Semiconductors and Information Devices,
2D semiconductors   gallium oxide   high-κ dielectric   transistors   surface-tension-driven method   ultrathin layer   interface quality  

Report on the Integration of High-κ Gallium Oxide in 2D Transistors Academic Background With the continuous advancement in semiconductor technology, 2D materials (such as molybdenum disulfide, MoS₂) are considered promising candidates for next-generation transistor channel materials due to their unique electrical properties and atomic-scale thickne...

Rapid Cryogenic Characterization of 1,024 Integrated Silicon Quantum Dot Devices

Physics, Quantum Physics, Engineering, Electrical Engineering, Information Science, Semiconductors and Information Devices,
quantum dots   silicon quantum dots   cryogenic characterization   quantum computing   semiconductor manufacturing   radio-frequency reflectometry   automated machine learning  

Rapid Cryogenic Characterization of 1,024 Integrated Silicon Quantum Dot Devices: A Review Background Quantum computing, as a disruptive technology in computing, holds the promise of far surpassing traditional high-performance computers in areas such as materials science, drug discovery, and big data search. Silicon-based quantum dots (Quantum Dot,...

An N-Doped Capacitive Transparent Conductor for All-Polymer Electrochromic Displays

Chemistry, Polymer Chemistry, Materials Chemistry, Materials Science, Organic Polymeric Materials, Information Science, Semiconductors and Information Devices,
transparent conductor   electrochromic display   polymer   low power consumption   flexible display   full-color display   capacitive material  

Progress in All-Polymer Electrochromic Displays: Innovative Applications of N-Doped Transparent Conductive Polymer Background and Significance Display technology is omnipresent in modern society, spanning applications from consumer electronics to medical devices and wearable technology. Although traditional emissive displays (e.g., OLEDs and LCDs) ...