A5043607756- Hydrogen embrittlement and corrosion behaviors in metals
- Microstructure and Mechanical Properties of Steels
- Metal Alloys Wear and Properties
- Welding Techniques and Residual Stresses
- Additive Manufacturing Materials and Processes
- Machine Learning in Materials Science
- Non-Destructive Testing Techniques
- Multimodal Machine Learning Applications
- Impact of Light on Environment and Health
- Building Energy and Comfort Optimization
- Advanced Neural Network Applications
- Speech and dialogue systems
- High Entropy Alloys Studies
- Subtitles and Audiovisual Media
- Image Enhancement Techniques
- High-Temperature Coating Behaviors
- Color perception and design
- Speech Recognition and Synthesis
Chengdu University
2023-2024
University of Missouri
2006
High entropy alloys (HEAs) have excellent properties because they can form simple solid solution (SS) phases, including body-centered cubic (BCC) phase, face-centered (FCC) or FCC + BCC so phase prediction is the first step in alloy design. In current research, machine learning (ML) approach had been widely used to guide discovery and design of materials. The HEAs structure based on a hot topic. this work, five ML algorithms were utilized predict for SS amorphous (AM) phases 399 collected...
In this paper, we present a first exposition of an automatic closed captioning system designed to assist hearing impaired users in telemedicine. This automatically separates telehealth conversation speech between health care provider and client into two streams provides real-time captions provider's client. The is based on the state-of-the-art technology large vocabulary conversational recognition, encompassing stream separation, acoustic modeling, language decoding, confidence annotation,...
The purpose of this study is to explore the composition space Fe–C–Mn–Al steel using machine learning in order identify materials with high-strength mechanical properties.
Steel used in the automotive industry requires a favorable combination of strength and ductility to maintain structural integrity automobiles achieve complex shapes. Traditional approaches weight reduction from high-strength low-carbon steels have several limitations. Therefore, novel dual-phase lightweight steel with austenite-ferrite structure composition (mass fraction, %) Fe-0.52C-11Mn-5.14Al-1Cr was designed. The relationship between microstructure mechanical properties under different...
Low Dynamic Range (LDR) to High (HDR) image translation is an important computer vision problem. There a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using single-exposed multi-exposed LDR for HDR reconstruction. However, most current state-of-the-art require high-quality paired {LDR,HDR} datasets model training. In addition, there limited literature unpaired this task where the learns mapping between domains,...
Deep learning framework for austenitic ferrite segmentation using electron microscope images. Preprocessing and data enhancement enable accurate grain detection in Fe–C–Mn–Al alloys with a novel quantification method.