A5046080277- Manufacturing Process and Optimization
- Simulation Techniques and Applications
- Industrial Technology and Control Systems
- Product Development and Customization
- Design Education and Practice
- Fault Detection and Control Systems
- Business Process Modeling and Analysis
- Simulation and Modeling Applications
- Service-Oriented Architecture and Web Services
- Mineral Processing and Grinding
- Bioinformatics and Genomic Networks
- Digital Transformation in Industry
- Modeling and Simulation Systems
- Multimodal Machine Learning Applications
- Collaboration in agile enterprises
- Advanced Computational Techniques and Applications
- BIM and Construction Integration
- Genomics and Phylogenetic Studies
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Face recognition and analysis
- Computational Drug Discovery Methods
- Functional Brain Connectivity Studies
- Additive Manufacturing and 3D Printing Technologies
- Quality Function Deployment in Product Design
Xi'an Technological University
2025
Tsinghua University
2015-2024
Air Force Medical University
2020-2024
Washington University in St. Louis
2020-2024
University of Tsukuba
2019-2024
Xi'an Medical University
2020-2024
Anyang Tumor Hospital
2024
Zhong Ke San Huan (China)
2024
University of Electronic Science and Technology of China
2019-2023
State Key Laboratory of Digital Manufacturing Equipment and Technology
2023
Deep neural networks (DNNs) often suffer from "catastrophic forgetting" during incremental learning (IL) — an abrupt degradation of performance on the original set classes when training objective is adapted to a newly added classes. Existing IL approaches tend produce model that biased towards either old or new classes, unless with help exemplars data. To address this issue, we propose class-incremental paradigm called Model Consolidation (DMC), which works well even data not available. The...
While smart city initiatives have characterized global urbanization from the 1990s to 2020s, nowadays a novel artificial intelligence (AI) enabled approach urban governance is rapidly emerging, thereby shaping and planning of present future cities. This phenomenon can be understood theoretically through notion anticipatory governance, empirically so-called City Brain systems. particularly evident in China where wide range AI solutions are being experimented at different scales which this...
Fault diagnosis in an open world refers to the tasks that need cope with previously unknown faults online stage. It faces a great challenge yet be addressed—that is, data of may classified as normal samples high probability. In this article, we develop effective solution for by using supervised contrastive learning learn discriminative and compact embedding known situation fault situations. Specifically, addition contrasting given sample other instances is case conventional methods, our...
Abstract: To address the complex interactions between humans and wildlife habitat, we developed a conceptual framework that links human factors with forested landscapes habitat. All components in are integrated into systems models analyze effects of project how habitat would change under different policy scenarios. As case study, applied this to Wolong Nature Reserve Sichuan Province (southwestern China), largest home giant panda ( Ailuropoda melanoleuca ). We collected ecological...
Individuals with low socioeconomic status (SES) are at a higher risk of developing depression. However, evidence on the role cardiovascular health (CVH) in this chain is sparse and limited. The purpose research was to assess mediating Life's Essential 8 (LE8), recently updated measurement CVH, association between SES depression according nationally representative sample adults.
Cloud computing technologies have enabled a new paradigm for advanced product development powered by the provision and subscription of computational services in multi-tenant distributed simulation environment. The description resources their optimal allocation among tenants with different requirements holds key to implementing effective software systems such paradigm. To address this issue, systematic framework monitoring, analyzing improving system performance is proposed research....
Stroke remains a leading cause of adult disability and the demand for stroke rehabilitation services is growing, Astragaloside IV (As IV), primary bioactive compound Radix Astragali : Astragalus mongholicus Bunge (Fabaceae), may be promising therapy.To access effect As on mice after ischemic stroke, photochemical ischemia model was established C57BL/6 mice, which were intravenously administered three consecutive days later. And then cognitive benefits hippocampal neurogenesis evaluated by...
Thanks to the availability of multiomics data individual cancer patients, precision medicine or personalized is becoming a promising treatment for patients. However, association patterns, that is, mechanism response (MoR) between large-scale features and drug are complex heterogeneous remain unclear. Although there existing computational models predicting using high-dimensional features, it remains challenging uncover molecular responses. To reduce number predictors/features make model more...
Conventional crop height measurements performed using aerial drone images require 3D reconstruction results of several obtained through structure from motion. Therefore, they extensive computation time and their measurement accuracy is not high; if the result fails, photos must be captured again. To overcome these challenges, this study proposes a high-precision method that uses equipped with monocular camera real-time kinematic global navigation satellite system (RTK-GNSS) for processing....
The independent dietary shift from carnivore to herbivore with over 90% being bamboo in the giant and red pandas is of great interests biologists. Although previous studies have shown convergent evolution at both morphological molecular level, gut microbiota these remains largely unknown. goal this study was determine whether converged due same diet, or diverged. We characterized fecal two species by pyrosequencing 16S V1-V3 hypervariable regions using 454 GS FLX Titanium platform. also...
In this article, a new fault diagnosis problem is formulated, which involves large number of normal samples and in almost all the classes are few-shot classes. Although common many industrial scenarios, it remains challenge overlooked previous studies. To develop novel solution for addressing challenge, we employ long-tailed distribution work name task accordingly. Specifically, divide procedure into representation learning classification. On basis, propose method using progressively...
This study investigated the hydrochar-based porous carbon prepared by combining technical route of hydrothermal carbonization (HTC) + chemical activation. The hydrochar morphology was adjusted changing activation reaction conditions and adding metal salts. Experiments showed that KHCO3 significantly increased specific surface area pore size hydrochar. Besides, oxygen-rich groups on activated interacted with heavy ions to achieve efficient adsorption. adsorption capacity for Pb2+ Cd2+ reached...
Improving the performance of human–computer interaction systems is an essential indicator aircraft intelligence. To address limitations single-modal methods, a multimodal model based on gaze and EEG target selection proposed using deep learning technology. This consists two parts: classification intention recognition. The long short-term memory networks established trained by combining eye movement information operator. recognition transformers constructed operator’s information. In...