A5101480388- Chemical Synthesis and Analysis
- Machine Learning in Bioinformatics
- Computational Drug Discovery Methods
- Speech and dialogue systems
- Video Analysis and Summarization
- Text and Document Classification Technologies
- Digital Games and Media
- Composite Structure Analysis and Optimization
- Microbial Metabolic Engineering and Bioproduction
- Biochemical effects in animals
- Antimicrobial Peptides and Activities
- Biochemical Acid Research Studies
- Gaze Tracking and Assistive Technology
- Numerical methods in engineering
- Elasticity and Wave Propagation
- Circular RNAs in diseases
- Cellular Mechanics and Interactions
- Advanced Fluorescence Microscopy Techniques
- Intracranial Aneurysms: Treatment and Complications
- Language, Metaphor, and Cognition
- Neural Networks and Applications
- Multimodal Machine Learning Applications
- Virtual Reality Applications and Impacts
- Subtitles and Audiovisual Media
- Structural Analysis and Optimization
University of Chinese Academy of Sciences
2024-2025
Hefei Institutes of Physical Science
2024
Institute of Plasma Physics
2024
Chinese Academy of Sciences
2024
First Affiliated Hospital of Bengbu Medical College
2024
State Key Laboratory of Turbulence and Complex Systems
2023
Peking University
2022-2023
Jiangnan University
2022
China West Normal University
2022
Cornell University
2021
Lysine acetylation in protein is one of the most important post-translational modifications (PTMs). It plays an role essential biological processes and related to various diseases. To obtain a comprehensive understanding regulatory mechanism lysine acetylation, key identify sites. Previously, several shallow machine learning algorithms had been applied predict modification sites proteins. However, has some disadvantages. For instance, it not as effective deep for processing big data. In this...
As cracks are unavoidable and always reduce structural local stiffness strength, this paper pays attention to the effect of on stability cracked functionally graded (FG) graphene-nanoplates reinforced composite (GRC) beam covered with piezoelectric layers. Both critical buckling loads postbuckling paths novel structures considered. The massless rotational spring model is employed calculate bending section. Three different graphene platelets (GPLs) distribution patterns along thickness...
Abstract Instability-induced wrinkle patterns of thin sheets are ubiquitous in nature, which often result origami-like that provide inspiration for the engineering origami designs. Inspired by instability-induced patterns, we propose a computational design method based on nonlinear analysis loaded and topology optimization. The bar-and-hinge model is employed structural analysis, added with displacement perturbation strategy to initiate out-of-plane buckling. Borrowing ideas from...
Deep learning-based information processing consumes long time and requires huge computing resources, especially for dense prediction tasks which require an output each pixel, like semantic segmentation salient object detection. There are mainly two challenges quantization of tasks. Firstly, directly applying the upsampling operation that is extremely crude causes unacceptable accuracy reduction. Secondly, complex structure networks means it difficult to maintain a fast speed as well high...
Air-writing is a challenging task that combines the fields of computer vision and natural language processing, offering an intuitive approach for human-computer interaction. However, current air-writing solutions face two primary challenges: (1) their dependency on complex sensors ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">e.g</i> ., Radar, EEGs others) capturing precise handwritten trajectories, (2) absence video-based dataset covers...
Lysine lipoylation which is a rare and highly conserved post-translational modification of proteins has been considered as one the most important processes in biological field. To obtain comprehensive understanding regulatory mechanism lysine lipoylation, key to identify lipoylated sites. The experimental methods are expensive laborious. Due high cost complexity methods, it urgent develop computational ways predict sites.In this work, predictor named LipoSVM developed accurately overcome...
Abstract Propelling the future of space exploration, electric propulsion stands as a transformative force, showcasing high efficiency, reliability, and environmental consciousness in comparison to conventional chemical propulsion. The applied field MPD thruster, an device, can produce thrust impulse, provided that some known issues (such cathode lifespan, cooling system, payload, theoretical challenges) hindering efficiency are addressed. At vanguard our breakthroughs is introduction...
Visual Language Tracking (VLT) enhances single object tracking (SOT) by integrating natural language descriptions from a video, for the precise of specified object. By leveraging high-level semantic information, VLT guides tracking, alleviating constraints associated with relying on visual modality. Nevertheless, most benchmarks are annotated in granularity and lack coherent framework to provide scientific guidance. Moreover, coordinating human annotators high-quality annotations is...
<title>Abstract</title> Objective: This retrospective study evaluated the safety and effectiveness of pure endoscopic clipping for anterior circulation aneurysms through supraorbital keyhole approach pterional approach. Methods: We included 92 patients with aneurysms, all treated surgery at The First Affiliated Hospital Bengbu Medical University. Patients were divided into neuroendoscopic microscopic groups, based on whether or techniques used clipping. analyzed baseline patient...
Visual language tracking (VLT) has emerged as a cutting-edge research area, harnessing linguistic data to enhance algorithms with multi-modal inputs and broadening the scope of traditional single object (SOT) encompass video understanding applications. Despite this, most VLT benchmarks still depend on succinct, human-annotated text descriptions for each video. These often fall short in capturing nuances content dynamics lack stylistic variety language, constrained by their uniform level...
Visual Language Tracking (VLT) enhances tracking by mitigating the limitations of relying solely on visual modality, utilizing high-level semantic information through language. This integration language enables more advanced human-machine interaction. The essence interaction is cognitive alignment, which typically requires multiple exchanges, especially in sequential decision-making process VLT. However, current VLT benchmarks do not account for multi-round interactions during tracking. They...
Vision-language tracking (VLT) extends traditional single object by incorporating textual information, providing semantic guidance to enhance performance under challenging conditions like fast motion and deformations. However, current VLT trackers often underperform compared single-modality methods on multiple benchmarks, with information sometimes becoming a "distraction." To address this, we propose VLTVerse, the first fine-grained evaluation framework for that comprehensively considers...
Air-writing is a challenging task that combines the fields of computer vision and natural language processing, offering an intuitive approach for human-computer interaction. However, current air-writing solutions face two primary challenges: (1) their dependency on complex sensors (e.g., Radar, EEGs others) capturing precise handwritten trajectories, (2) absence video-based dataset covers comprehensive vocabulary range. These limitations impede practicality in various real-world scenarios,...
With the rapid development of biological research, microRNAs (miRNAs) have increasingly attracted worldwide attention. The increasing studies and scientific experiments proven that miRNAs are related to occurrence a large number key processes which cause complex human diseases. Thus, identifying association between disease is helpful diagnose Although some found considerable associations diseases, there still lot need be identified. Experimental methods uncover miRNA-disease time-consuming...