A5108949296- RNA modifications and cancer
- Hate Speech and Cyberbullying Detection
- Advanced Steganography and Watermarking Techniques
- Genetic Associations and Epidemiology
- 3D Modeling in Geospatial Applications
- Advanced Computing and Algorithms
- Internet Traffic Analysis and Secure E-voting
- Industrial Vision Systems and Defect Detection
- Brain Tumor Detection and Classification
- Geographic Information Systems Studies
- Medical Image Segmentation Techniques
- 3D Surveying and Cultural Heritage
- Image Retrieval and Classification Techniques
- Speech Recognition and Synthesis
- Silicon and Solar Cell Technologies
- Remote Sensing and LiDAR Applications
- Cancer-related molecular mechanisms research
- Remote Sensing and Land Use
- Handwritten Text Recognition Techniques
Shanghai Maritime University
2024-2025
Southeast University
2024
Beijing University of Civil Engineering and Architecture
2022
Harbin Medical University
2013
With the widespread use of social media, user-generated content has surged on online platforms. When such includes hateful, abusive, offensive, or cyberbullying behavior, it is classified as toxic speech, posing a significant threat to ecosystem's integrity and safety. While manual moderation still prevalent, overwhelming volume psychological strain human moderators underscore need for automated speech detection. Previously proposed detection methods often rely large annotated datasets;...
ABSTRACT Alzheimer's disease (AD) and mild cognitive impairment (MCI) are common disorders. Research has shown that decline is closely related to abnormal connections between different functional areas of the brain. However, research on brain network (BFN) mainly focused individual topological structures, seldom considering sparsity BFNs complexity multi‐level interactions among regions. To tackle this problem, in article, we propose a multi‐view bilinear aggregation attention model...
Abstract Autism Spectrum Disorder (ASD) is a complex neurodevelopmental disorder, and structural magnetic resonance imaging (sMRI) functional (fMRI) provide information about brain structure function, aiding in objective ASD diagnosis. However, existing classification methods face challenges such as sample scarcity, inter‐imaging center variations, insufficient single‐modality information, inconsistent feature dimensions. This study introduced method based on the Local Global Multimodal...
Currently, most methods for text steganalysis are based on deep neural networks (DNNs). However, in real-life scenarios, obtaining a sufficient amount of labeled stego-text correctly training using large number parameters is often challenging and costly. Additionally, due to phenomenon known as dataset bias or domain shift, recognition models trained exhibit poor generalization performance novel datasets tasks. Therefore, address the issues missing data inadequate model steganalysis, this...
Abstract. Indoor point cloud data is easy to obtain and contains a large amount of data, but there no connectivity, structural attributes, semantic information between clouds. It very difficult extract interior components. In order solve the problem that it closed door in indoor cloud, scanning noisy redundant, segmentation method proposed reduce impact noise. Because most components are not on same horizontal plane, different component can be obtained by slicing at heights. these slices,...
Abstract. This paper presents a multi-source POI matching method with multi feature similarity, which can effectively solve the problem of low accuracy data from different sources. The spherical distance method, editing and Jaro Winkler are combined to calculate distance, name, address other main attributes data. Then importance each index is analyzed by using analytic hierarchy process, weight similarity obtained. candidate objects screened according total determine final object. Finally,...
Tissue-specific expression quantitative trait loci (eQTLs) are always linked to specific diseases.In this study, we focused on eQTLs common multiple tissues and explored their functional mechanisms in disease for the first time.We found 11 eQTL genes among tissues.Five were validated through a genome-wide association 3 using Online Mendelian Inheritance Man database, others text mining.Most of these disorders related systemic immune system.In analyses Gene Ontology Kyoto Encyclopedia Genes...