A5103265617- Advanced Surface Polishing Techniques
- Advanced machining processes and optimization
- Time Series Analysis and Forecasting
- Advanced Machining and Optimization Techniques
- Advanced Text Analysis Techniques
- Electrical Fault Detection and Protection
- Structural Integrity and Reliability Analysis
- Service-Oriented Architecture and Web Services
- Data Management and Algorithms
- Stock Market Forecasting Methods
- Nonlinear Waves and Solitons
- Traffic Prediction and Management Techniques
- Software System Performance and Reliability
- Cloud Computing and Resource Management
- Machine Fault Diagnosis Techniques
- Fractional Differential Equations Solutions
- Hydrogen embrittlement and corrosion behaviors in metals
- Forecasting Techniques and Applications
- Integrated Circuits and Semiconductor Failure Analysis
- Corrosion Behavior and Inhibition
- Nonlinear Photonic Systems
Beijing University of Posts and Telecommunications
2023-2024
Switch
2023-2024
Shandong University of Technology
2024
Southeast University
2019-2023
Nanjing University of Aeronautics and Astronautics
2021
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal data, using a fixed-length window for training prediction single dataset, cannot adapt different scenarios. The powered pre-trained large language model has introduced new opportunities series analysis. Yet, existing methods are either inefficient in training, incapable of handling information, or lack zero-shot...
Machine learning-based fault detection technology has gained significant attention in recent years. However, the practical implementation of such technologies often encounters challenges selecting appropriate characteristics and network parameters. This study proposes a novel method for series arc based on combined approach complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) improved fireworks algorithm-1D convolutional neural (IFWA-1DCNN). Following CEEMDAN...
Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate. Due to the abundant seasonal information they contain, timestamps possess potential offer robust global guidance for techniques. However, existing works primarily focus on local observations, with being treated merely as an optional supplement that remains underutilized. When data gathered from real world is polluted, absence of will damage...
Human experts typically integrate numerical and textual multimodal information to analyze time series. However, most traditional deep learning predictors rely solely on unimodal data, using a fixed-length window for training prediction single dataset, cannot adapt different scenarios. The powered pre-trained large language model has introduced new opportunities series analysis. Yet, existing methods are either inefficient in training, incapable of handling information, or lack zero-shot...
Recent graph-based methods achieve significant success in multivariate time series modeling and forecasting due to their ability handle relationships among variables. However, only pairwise are considered most existing works. They ignore beyond-pairwise potential categories practical scenarios, which leads incomprehensive relationship learning for forecasting. In this paper, we present ReMo, a Relational Modeling-based method, promote fine-grained relational data. Firstly, by treating...
Abstract High-aspect-ratio (HAR) micro-structures of harden steel (SKD11) are widely used in the national defense and electronic fields. Micro-milling is a suitable method for machining HAR micro structures, however inevitable generation burrs deteriorates machined surface. Previous studies have mostly focused on burr formation process shallow grooves, but ignored grooves. This paper investigated mechanism (2:1) grooves (SKD11). Due to fact that was difficult be observed actual micro-milling...