A5100653275- Machine Learning in Materials Science
- Computational Drug Discovery Methods
- Protein Structure and Dynamics
- Various Chemistry Research Topics
- X-ray Diffraction in Crystallography
- Advanced Neural Network Applications
- Membrane-based Ion Separation Techniques
- Advanced oxidation water treatment
- Fire Detection and Safety Systems
- Covalent Organic Framework Applications
- Metal-Organic Frameworks: Synthesis and Applications
- Membrane Separation Technologies
- Photoreceptor and optogenetics research
- Advanced Condensed Matter Physics
- Video Surveillance and Tracking Methods
Chuzhou University
2023
Carnegie Mellon University
2023
South China University of Technology
2022
Abstract Accurate and efficient prediction of polymer properties is great significance in design. Conventionally, expensive time-consuming experiments or simulations are required to evaluate functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance natural language processing. However, such methods not been investigated sciences. Herein, we report TransPolymer, a Transformer-based model for property prediction. Our proposed...
Developing a general, facile, and direct strategy for synthesizing thin films of covalent organic frameworks (COFs) is major challenge in this field. Herein, we report an unprecedented electrocleavage synthesis to produce imine-linked COF directly on electrodes from electrolyte solutions at room temperature. This enables the cathodic exfoliation powders nanosheets by electrochemical reduction protonation, followed migrating anode reproducing structures anodic oxidation. Our method adaptable...
Recent advances in equivariant graph neural networks (GNNs) have made deep learning amenable to developing fast surrogate models expensive
Person re-identification (Re-ID) aims to identify the same pedestrian from a surveillance video in various scenarios. Existing Re-ID models are biased learn background appearances when there many variations training set. Thus, pedestrians with identity will appear different backgrounds, which interferes performance. This paper proposes swin transformer based on two-fold loss (TL-TransNet) pay more attention semantic information of pedestrian’s body and preserve valuable information, thereby...
Heat-activated persulfate preoxidation was recently proposed as a potential approach to mitigate membrane fouling in distillation (MD) for treating actual water. However, the possible mitigation mechanism involved has not yet been elucidated. In this study, we explored relationship between and pretreatment of natural organic matter (NOM) solutions with peroxymonosulfate (PMS). Individual humic acid (HA), bovine serum albumin (BSA), sodium alginate (SA) contaminants were chosen model NOM...
Accurate and efficient prediction of polymer properties is great significance in design. Conventionally, expensive time-consuming experiments or simulations are required to evaluate functions. Recently, Transformer models, equipped with self-attention mechanisms, have exhibited superior performance natural language processing. However, such methods not been investigated sciences. Herein, we report TransPolymer, a Transformer-based model for property prediction. Our proposed tokenizer...
Recent advances in equivariant graph neural networks (GNNs) have made deep learning amenable to developing fast surrogate models expensive ab initio quantum mechanics (QM) approaches for molecular potential predictions. However, building accurate and transferable using GNNs remains challenging, as the data is greatly limited by computational costs level of theory QM methods, especially large complex systems. In this work, we propose denoise pretraining on nonequilibrium conformations achieve...
Recently, the remarkable capabilities of large language models (LLMs) have been illustrated across a variety research domains such as natural processing, computer vision, and molecular modeling. We extend this paradigm by utilizing LLMs for material property prediction introducing our model Materials Informatics Transformer (MatInFormer). Specifically, we introduce novel approach that involves learning grammar crystallography through tokenization pertinent space group information. further...