A5055716987- Complex Network Analysis Techniques
- Opinion Dynamics and Social Influence
- Topic Modeling
- Natural Language Processing Techniques
- Speech Recognition and Synthesis
- Network Security and Intrusion Detection
- Evolutionary Game Theory and Cooperation
- Service-Oriented Architecture and Web Services
- Software System Performance and Reliability
- Metaheuristic Optimization Algorithms Research
- Advanced Text Analysis Techniques
- Sentiment Analysis and Opinion Mining
- Cloud Computing and Resource Management
- Software-Defined Networks and 5G
- Robotics and Sensor-Based Localization
- Gene Regulatory Network Analysis
- Civil and Geotechnical Engineering Research
- Insect and Arachnid Ecology and Behavior
- Circular RNAs in diseases
- Music and Audio Processing
- Advanced Multi-Objective Optimization Algorithms
- Advanced Image Fusion Techniques
- Robotic Path Planning Algorithms
- Cancer-related molecular mechanisms research
- Urban Heat Island Mitigation
Shenzhen University
2023-2025
Ludong University
2025
Sun Yat-sen University
2021-2024
Tiangong University
2010-2024
Shenzhen Research Institute of Big Data
2024
Beihang University
2019-2024
Nankai University
2024
Tsinghua University
2019-2024
Beijing Microelectronics Technology Institute
2024
Chinese University of Hong Kong, Shenzhen
2024
Abstract Long non-coding RNAs play critical roles in tumour progression. Through analysis of publicly available genomic datasets, we found that MIR22HG, the host gene microRNAs miR-22-3p and miR-22-5p, is ranked among most dysregulated long glioblastoma. The main purpose this work was to determine impact MIR22HG on glioblastoma growth invasion elucidate its mechanistic function. MIR22HG/miR-22 axis highly expressed as well glioma stem-like cells compared normal neural stem cells. In...
In order to find the nodes with better propagation ability, a large body of studies on influence maximization problem has been conducted. Several spreading models and corresponding optimization algorithms have proposed successfully identified infusive seeds in single isolated networks. However, as indicated by some recent online materials, modern networked systems tend more complicated structures multiple layers, which makes it difficult for existing seed determination techniques deal these...
Networked systems widely exist in the modern society, and these are always operated presence of attacks errors. The robustness a network indicates its tolerance against potential damages, which is crucial for network's normal functionalities. Damage models including malicious cascading failures have been considered previous studies. And mitigation on two destructive damages has attracted increasing attention, both single-objective multiobjective optimization techniques proposed to enhance...
Robust optimization of complex networks has attracted much attention in recent years. Although existing methods have been successful achieving promising results, the computational cost for robust tasks is extremely high, which prevents them from being further applied to large-scale networks. Thus, computationally efficient are high demand. This article proposes a low-cost method estimating robustness with help graph embedding techniques and surrogate models. An evolutionary algorithm then...
The robustness of complex networks is great significance. Great achievements have been made in optimization based on single measures, however, such may still be vulnerable to multiple attack scenarios. Therefore, recently, multiobjective has received increasing attention. Nevertheless, several challenges remain addressed, including the different computational complexities evaluating objectives, insufficient diversity obtained networks, and high costs search process. In this article, we...
Detecting what emotions are expressed in text is a well-studied problem natural language processing.However, research on finergrained emotion analysis such as causes an still its infancy.We present solutions that tackle both recognition and cause detection joint fashion.Considering common-sense knowledge plays important role understanding implicitly the reasons for those emotions, we propose novel methods combine via adapted models with multi-task learning to perform classification...
The double-layer one-time-paving technology for asphalt mixtures enhances the interlayer adhesion and stability of pavement by simultaneously laying compacting two layers mixture, demonstrating improvements over traditional layer-by-layer paving compaction methods. Based on this technology, effects techniques, mixture types, structural layer thickness low-temperature crack resistance at -10 °C were investigated. Results indicated that, compared to methods, maximum tensile strain bending...
Ocular images play an essential role in ophthalmological diagnoses. Having imbalanced dataset is inevitable issue automated ocular diseases diagnosis; the scarcity of positive samples always tends to result misdiagnosis severe patients during classification task. Exploring effective computer-aided diagnostic method deal with crucial. In this paper, we develop cost-sensitive deep residual convolutional neural network (CS-ResCNN) classifier diagnose ophthalmic using retro-illumination images....
Aspect sentiment classification (ASC) is a fundamental task in analysis. It aims at classifying the expressed on some target aspects/features of entities (e.g., products and services). Although great deal research has been done, this remains to be very challenging. Recently, memory networks, type neural model, have used for achieved state-of-the-art results. However, such models usually require large amount well-annotated training data producing reasonably good Unfortunately, ASC task,...
Event detection is a crucial and challenging sub-task of event extraction, which suffers from severe ambiguity issue trigger words. Existing works mainly focus on using textual context information, while there naturally exist many images accompanied by news articles that are yet to be explored. We believe not only reflect the core events text, but also helpful for disambiguation In this paper, we first contribute an image dataset supplement ED benchmarks (i.e., ACE2005) training evaluation....
This study is dedicated to developing an innovative method for evaluating spoken English by integrating large language models (LLMs) with effective space learning, focusing on the analysis and evaluation of emotional features in language. Addressing limitation current software that primarily focuses acoustic speech (such as pronunciation, frequency, prosody) while neglecting expression, this paper proposes a capable deeply recognizing speech. The core comprises three main parts: (1) creation...