A5111706869- Manufacturing Process and Optimization
- BIM and Construction Integration
- Digital Transformation in Industry
- Advanced Neural Network Applications
- Semantic Web and Ontologies
- AI in cancer detection
- Microgrid Control and Optimization
- Flexible and Reconfigurable Manufacturing Systems
- Electrostatic Discharge in Electronics
- Brain Tumor Detection and Classification
- Smart Grid Energy Management
- Solar Radiation and Photovoltaics
- ECG Monitoring and Analysis
- Rough Sets and Fuzzy Logic
- Quality and Supply Management
- Belt and Road Initiative
- Advanced Technologies in Various Fields
- Mobile and Web Applications
- Advanced Steganography and Watermarking Techniques
- Medical Image Segmentation Techniques
- Photovoltaic System Optimization Techniques
- Advanced Data Compression Techniques
- Engineering Technology and Methodologies
- Nonlinear Waves and Solitons
- Evaluation and Optimization Models
Aalto University
2020-2024
Xiamen University
2023-2024
SGIDI Engineering Consulting (China)
2023-2024
Hohai University
2014-2021
China Telecom
2020
China Telecom (China)
2020
Yunnan University
2020
Beijing Electronic Science and Technology Institute
2010
Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this generally can only capture small-range feature dependency for the convolutional layer local receptive field, which makes it difficult to learn global shape information from limited provided by scribble annotations. To address issue, paper proposes new CNN-Transformer hybrid solution medical image called ScribFormer. The proposed...
With ongoing advancements in information and communication technologies (ICTs) all stages of the construction lifecycle, from entities related to workflow (CW) can now be automatically collected. These implementations are point solutions, which require systematic integration combine their enable a holistic picture CW. The major barrier such is heterogeneity, where collected different systems under multiple contexts. Scholars domain have explored use ontology solve information-integration...
Industry 4.0 is helping to unleash a new age of digitalization across industries, leading data-driven, interoperable, and decentralized production process. To achieve this major transformation, one the main requirements interoperability various systems multiple devices. Ontologies have been used in numerous industrial projects tackle challenge digital manufacturing. However, there currently no semantic model literature that can be represent workflow comprehensively while also integrating...
Medical image segmentation plays a critical role in clinical decision-making, treatment planning, and disease monitoring. However, accurate of medical images is challenging due to several factors, such as the lack high-quality annotation, imaging noise, anatomical differences across patients. In addition, there still considerable gap performance between existing label-efficient methods fully-supervised methods. To address above challenges, we propose ScribbleVC, novel framework for...
Improved productivity and the elimination of waste are key goals for lean methods in construction production control. One such method is a kit-based logistics management which task-based materials delivered just-in-time aligned with assembly operations on-site. Digital platforms could enable situational awareness work material flows, potentially increasing benefit applicability kitting. The aim current research to utilize real-time indoor tracking labor flows evaluate an kit–based projects....
A Shared Ontology for Logistics Information Management in the Construction Industry Yuan Zheng, Müge Tetik, Seppo Törmä, Antti Peltokorpi and Olli Seppänen Pages 1278-1285 (2020 Proceedings of 37th ISARC, Kitakyushu, Japan, ISBN 978-952-94-3634-7) Abstract: management plays an essential role supporting primary activities manufacturing industries. Similarly, construction industry, logistics operations are a crucial part that directly influence operations. requires various stakeholders to...
In the shaft axis monitoring of hydrogenerating unit condition and fault diagnosis, orbit is intuitive comprehensively reflects operation state, different orbits correspond to types, which can accurately indicate a system vibration fault. Shaft identification has important significance for diagnosis. getting feature extraction pattern recognition orbit, Zernike moment better than Hu moment; it advantages small calculation error high rate. A rough set neural network (RS‐BP hybrid model)...
Abstract The era of knowledge economy puts forward new requirements for the management human resources in colleges and universities. system universities must be innovative order to promote development higher education. This article describes innovation resource mechanism based on computer-assisted technology, proposes measures establish a improve total talent College resources, optimization update existing universities, mechanism.
In order to effectively promote the goals of China's dual carbon strategy, accomplish energy conservation and reduction in municipal infrastructure, harness potential renewable sources, this paper presents a novel direct current (DC) power supply system for stormwater detention tank (SDT) based on photovoltaic storage DC technology. The provides fundamental design principles methods system. study, an analysis is initially conducted state, operational characteristics, consumption features...
In this paper, we derive the distribution of DCT coefficients for a fixed block variance, and invoke central limit theorem to show that is approximately Gaussian. Then, by allowing variance have statistical itself, analyze when would follow Laplacian distribution. Such knowledge be useful, instance, in quantizer design, information hiding capacity Watermark Detection.
Fault diagnosis is essentially a kind of pattern recognition. In this paper propose novel machinery fault method based on supervised locally linear embedding proposed first. The approach first performs the recently manifold learning algorithm high-dimensional signal samples to learn intrinsic embedded multiple features corresponding different modes. Supervised not only can map them into low-dimensional space achieve feature extraction, but also deal with new samples. Finally classification...
In this article, we obtain a class of tame maximal weights (Zhou weights), whose relative types numbers) satisfy the tropical multiplicativity and additivity, characterize multiplier ideal sheaves plurisubharmonic functions. Especially, to them are valuations valuations) on ring germs holomorphic functions, division relations ring. We consider global version these domains in $\mathbb{C}^n$, some properties them, including continuity approximation results.