A5100387304- Energy Load and Power Forecasting
- Atmospheric and Environmental Gas Dynamics
- Meteorological Phenomena and Simulations
- Advanced Adaptive Filtering Techniques
- IoT-based Smart Home Systems
- Real-time simulation and control systems
- Grey System Theory Applications
- Coastal and Marine Dynamics
- Iterative Learning Control Systems
- Image and Signal Denoising Methods
- VLSI and Analog Circuit Testing
- Rock Mechanics and Modeling
- Advanced Algorithms and Applications
- Advanced Multi-Objective Optimization Algorithms
- Geological formations and processes
- Probabilistic and Robust Engineering Design
- Landslides and related hazards
- Electromagnetic Compatibility and Noise Suppression
- Radio Frequency Integrated Circuit Design
- Geoscience and Mining Technology
- VLSI and FPGA Design Techniques
- Model Reduction and Neural Networks
- Coastal wetland ecosystem dynamics
Dalian Polytechnic University
2022
Delft University of Technology
2020-2022
Ocean University of China
2020
North Carolina State University
2016-2020
North Central State College
2019-2020
Guizhou University
2017
Improving the accuracy of power system load forecasting is important for economic dispatch. However, a sequence highly nonstationary and hence makes accurate difficult. In this paper, method based on wavelet decomposition (WD) second-order gray neural network combined with an augmented Dickey-Fuller (ADF) test proposed to improve forecasting. First, decomposed by WD reduce sequence. Then, ADF adopted as stationary each component after in which results determine best level. Finally, because...
Machine learning, a powerful technique for building models, can rapidly provide accurate predictions. Since Integrated Circuit (IC) design and manufacturing have tremendously high complexity enormous data, there is surge in adapting machine learning approach IC Design stages, as fast Recently, has been used some stages (e.g. Physical Verification), but not Design. In this research, adapted to Surrogate Modeling implemented predict results after GR models predicting Detailed Route (DR) using...
The IBIS algorithmic modeling interface (IBIS-AMI) has become the standard methodology to model Serializer/Deserializer (SerDes) behavior for end-to-end high-speed serial link simulations. Meanwhile, machine learning (ML) techniques can mimic a black-box system behavior. This article proposes self-evolution cascade deep (SCDL) show parallel approach effectively adaptive SerDes Specifically, proposed self-guide uses its own failure experiences optimize future solution search according...
To speed up a serial link simulation, it is critical to model the Serializer/Deserializer (SerDes) circuit behavior accurately. In this research, we focus on building for high-speed SerDes receiver CTLE adaptation behavior, which has fast simulation and high-precision prediction. The proposed modeling method doesn't need any substantial domain knowledge. Deep neural networks will be used mimic of process in receiver. shows high correlations with codes.
Abstract As wind and solar power play increasingly important roles in the European energy system, unfavorable weather conditions, such as “Dunkelflaute” (extended calm cloudy periods), will pose ever greater challenges to transmission system operators. Thus, accurate identification characterization of events from open data streams (e.g., reanalysis, numerical prediction, climate projection) are going be crucial. In this study, we propose a two-step, unsupervised deep learning framework [wind...
It's crucial to build the SerDes behavioral models with high simulation speed and good hardware correlation. In this research, we focus on building a high-speed receiver model, which has fast excellent The proposed model doesn't need any substantial domain knowledge design process. Adaptive-ordered system identification will be used mimic behavior of receiver. modeling method shows high-correlation transient waveforms eye diagrams measured from on-die circuit.
Abstract In the coming decades, both wind and solar power production will be playing increasingly important roles in Europe’s energy economy. It is absolutely essential that grids are resilient against any unusual weather phenomena. One such meteorological phenomenon, “Dunkelflaute”, causing serious concern to renewable industry, which primarily characterized by calm winds overcast conditions. For example, a Dunkelflaute event happened Netherlands on 30th April 2018 leading significant...
Real-time monitoring of food freshness remains a challenge both for industry and consumers since no detection devices with portability, affordability efficiency has been commercialized to date. Here, we developed facile sensing platform based on smartphone application (APP) incorporation deeplearning model the real-time freshness. The colorimetric indicator bars cellulose paper were firstly constructed through gelatinization synthesized gelatin methacryloyl (GleMA) via UV-induced...