A5101829260- Data Mining Algorithms and Applications
- Natural Language Processing Techniques
- Topic Modeling
- Semantic Web and Ontologies
- Advanced Graph Neural Networks
- Mental Health via Writing
- Advanced Database Systems and Queries
- Service-Oriented Architecture and Web Services
- Data Management and Algorithms
- Imbalanced Data Classification Techniques
- Endometriosis Research and Treatment
- Reproductive System and Pregnancy
- Network Security and Intrusion Detection
- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Aviation Industry Analysis and Trends
- Oil Spill Detection and Mitigation
- Rough Sets and Fuzzy Logic
- Advanced Neural Network Applications
- Robotics and Sensor-Based Localization
- Multimodal Machine Learning Applications
- Complex Network Analysis Techniques
- Hand Gesture Recognition Systems
- Atmospheric and Environmental Gas Dynamics
- Multi-Agent Systems and Negotiation
Second Institute of Oceanography
2021-2025
Ministry of Natural Resources
2021-2025
State Key Laboratory of Satellite Ocean Environment Dynamics
2024-2025
Agency for Integrated Care
2025
Huazhong University of Science and Technology
2025
Union Hospital
2025
University of Iowa
2025
Academy of Military Medical Sciences
2025
Yunnan Normal University
2024
Wuhan University
2023-2024
Over last two decades, numerous studies have used remotely sensed data from the Advanced Very High Resolution Radiometer (AVHRR) sensors to map land use and cover at large spatial scales, but achieved only limited success. In this paper, we employed an approach that combines both AVHRR images geophysical datasets (e.g. climate, elevation). Three are in study: annual mean temperature, precipitation, elevation. We first divide China into nine bio-climatic regions, using long-term climate data....
Most data mining algorithms and tools stop at the delivery of patterns satisfying expected technical interestingness. There are often many mined but business people either not interested in them or do know what follow-up actions to take support their decisions. This issue has seriously affected widespread employment advanced techniques greatly promoting enterprise operational quality productivity. In this paper, we present a formal view actionable knowledge discovery (AKD) from system...
Abstract Background Querying drug-induced gene expression profiles with machine learning method is an effective way for revealing drug mechanism of actions (MOAs), which strongly supported by the growth large scale and high-throughput databases. However, due to lack code-free user friendly applications, it not easy biologists pharmacologists model MOAs state-of-art deep approach. Results In this work, a newly developed online collaborative tool, Genetic profile-activity relationship (GPAR)...
Automatic identification systems (AIS) can record a large amount of navigation information about ships, including abnormal or illegal ship movement information, which plays an important role in supervision. To distinguish the trajectories ships and analyze behavior this paper adopts method supervised learning to classify ships. First, AIS data for were marked divided into five types tracks. The Tsfresh module was then used extract various trajectory features, new ensemble classifier based on...
Lithium (Li)-rich Manganese (Mn)-based cathode materials are considered to be the most hopeful for next-generation high-energy-density Li metal batteries. However, rapid capacity fading and voltage decaying derived from phase transformation still hinder their practical application. Herein, we developed a cation/anion dual-doping strategy by synchronically incorporating Zr4+ cation F- anion boost structural stability of Li-rich Mn-based cathode. The strengthened transition metal-oxygen bonds...
Perceptual constancy is the ability to maintain stable perceptions of objects despite changes in sensory input, such as variations distance, angle, or lighting. This crucial for recognizing visual information a dynamic world, making it essential Vision-Language Models (VLMs). However, whether VLMs are currently and theoretically capable mastering this remains underexplored. In study, we evaluated 33 using 253 experiments across three domains: color, size, shape constancy. The included...
Despite excelling in high-level reasoning, current language models lack robustness real-world scenarios and perform poorly on fundamental problem-solving tasks that are intuitive to humans. This paper argues both challenges stem from a core discrepancy between human machine cognitive development. While systems rely increasing representational power, the absence of knowledge-foundational structures humans-prevents developing robust, generalizable abilities, where complex skills grounded...
Endometriosis is a common chronic neuroinflammatory disease with poorly understood pathogenesis. Molecular changes and specific immune cell infiltration in the eutopic endometrium are critical to progression. This study aims explore mechanisms molecular differences proliferative of endometriosis by integrating bulk RNA-seq single-cell RNA sequencing (scRNA-seq) data, develop diagnostic predictive models for disease. Gene expression profiles from patients healthy controls were obtained...
Listeners adapt to diverse cues in real-time language processing. While younger adults can learn and complex multitalker settings, it remains uncertain whether this ability persists older adults, especially when they must accumulate auditory inputs novel statistics. We examined talker-specific patterns using paralinguistic such as disfluency. In two experiments, listened instructions from talkers: one used disfluency predictively (e.g., always referring objects following disfluency) the...
Undiagnosed cognitive impairment is a pervasive global issue, often due to subtle nature of early symptoms, necessitating the use brief tests for detection. However, most are not scalable (requiring trained professionals), and designed lower literacy groups (e.g. in underserved communities). Here, we developed PENSIEVE-AITM, drawing-based digital test that less dependent on literacy, can be self-administered <5 min. In prospective study involving 1758 community-dwelling individuals aged 65...
Drug-target interaction prediction is critical for drug development. Through the integration of structural and transcriptional signature information, molecules both binding to target inducing therapeutic activities could be found out improve targeted prediction. Therefore, approaches that integrate two types data are worth exploring. Here, we present an integrated method named Data Integration Oriented Repurposing Strategy (DIORS) combining molecular docking gene-signature matching enhance...
Reliable chronologies are prerequisites when interpreting proxy records in terrestrial archives of Quaternary climate and environmental change. Optically stimulated luminescence (OSL) dating accelerator mass spectrometry radiocarbon (AMS 14 C) commonly used to date late loess deposits the Chinese Loess Plateau, but range reliability two methods Central Asia still debated. In this study, we investigate both fine‐grained quartz OSL AMS C a section located at northern piedmont South Tianshan...
Abstract In the realm of social media, users frequently convey personal sentiments, with some potentially indicating cognitive distortions or suicidal tendencies. Timely recognition such signs is pivotal for effective interventions. response, we introduce two novel annotated datasets from Chinese focused on and risk classification. We propose a comprehensive benchmark using both supervised learning large language models, especially GPT series, to evaluate performance these datasets. To...
Colorectal cancer (CRC) is one of the most common tumors digestive tract, with third-highest incidence and second-highest mortality rate among all malignant worldwide. However, treatment options for CRC remain limited. As a complementary therapy, acupuncture or electro-acupuncture (EA) has been widely applied in various inflammation-related diseases, such as obesity, ulcerative colitis tumors. Although numerous pre-clinical clinical studies have investigated beneficial effects on CRC,...
Multi-task learning aims at multiple related but different tasks. In general, there are two ways for multi-task learning. One is to exploit the small set of labeled data from all tasks learn a shared feature space knowledge sharing. this way, focus on training samples while large amount unlabeled not sufficiently considered. Another way has how share model parameters among based original features space. Here, question whether it possible combine advantages both approaches and develop method,...