A5100359613- Advanced Vision and Imaging
- Advanced Image Processing Techniques
- Quantum-Dot Cellular Automata
- Advanced Image Fusion Techniques
- Advanced Causal Inference Techniques
- Quantum Computing Algorithms and Architecture
- Educational Technology and Assessment
- Educational Technology and Pedagogy
- Education and Learning Interventions
- Image Enhancement Techniques
- Coding theory and cryptography
- Quantum Information and Cryptography
- Metaheuristic Optimization Algorithms Research
- Educational Systems and Policies
- IoT and Edge/Fog Computing
- Health Systems, Economic Evaluations, Quality of Life
- Machine Learning in Bioinformatics
- Distributed and Parallel Computing Systems
- Image Retrieval and Classification Techniques
- Virtual Reality Applications and Impacts
- Augmented Reality Applications
- Advanced Data Storage Technologies
- Image and Signal Denoising Methods
- Advanced Multi-Objective Optimization Algorithms
- Economic Policies and Impacts
Shandong University
2025
First Hospital of China Medical University
2024
China Medical University
2024
Lanzhou University
2022-2024
Huazhong University of Science and Technology
2023
Beijing Automation Control Equipment Institute
2023
Chinese Academy of Agricultural Mechanization Sciences
2023
Zhejiang Police College
2023
Central China Normal University
2022
University of Amsterdam
2022
Taking photos by mobile phones has become an indispensable part of people's daily life with the popularity smartphones. However professional photography content is also needed for taking high-quality as ones taken cameras. Existing learning tools can't provide photographic practice while presenting theoretical content, nor give real-time guidance according to environment. Mobile augmented reality (AR) technology provides a new way solve these problems creating real situation. Therefore,...
The class imbalance problem usually occurs in real applications. is that the amount of one may be much less than another training set. Under-sampling a very popular approach to deal with this problem. efficient, it only using subset majority class. drawback under-sampling throws away many potentially useful examples. To overcome drawback, we adopt an unsupervised learning technique for supervised learning. We proposes cluster-based approaches selecting representative from Compared...
High-resolution (HR) medical imaging data provide more anatomical details of human body, which facilitates early-stage disease diagnosis. But it is challenging to get clear HR images because the limiting factors, such as systems, environments, and factors. This work presents a novel image super-resolution (SR) method via high-resolution representation learning based on generative adversarial network (GAN), namely, Med-SRNet. We use GAN backbone SR considering advantages that can...
Accurate and automated segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a critical role computer-aided diagnosis treatment cancer. However, this task is challenging, due to random variation tumor sizes, shapes, appearances, blurred boundaries caused by inherent heterogeneity Moreover, the presence ill-posed artifacts DCE-MRI further complicate process region annotation. To address challenges above, we propose scheme (named SwinHR)...
The reasonable scheduling of agricultural machinery can avoid their purposeless flow during the operational service and reduce cost centers. In this research, a multiregional model with time window was established considering timeliness operation. This divided into two stages: first stage, regions were through Voronoi diagram, farmlands distributed to intraregional second solved using hybrid particle swarm optimization (HPSO). algorithm improves performance by introducing crossover,...
Image decolorization is used to realize the color-to-gray conversion, which widely in black-and-white printing, digital-ink display, photo stylization, etc. contrast fidelity preservation key issue during this conversion process. We present a parametric model combining image entropy and Canny edge retention ratio (CERR). Maximizing keeps global content, while maximizing CERR enhances local contrast, mainly along edges. The weighting parameter λ can be robustly estimated. Experimental results...
Locally recoverable codes are very important due to their applications in distributed storage systems. In this paper, by using cyclic codes, we construct two classes of optimal q-ary (r, δ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> ) locally with parameters [2(q + 1), 2(q 1) - 2δ , 2]q, where q is an odd prime power and r 1 = 1, xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> 4δ 2, ≥ 7 power, ≡ 3 (mod 4) q+1 2 . Compared the...
New families of subsystem codes are constructed. Furthermore, these new optimal. Finally, asymmetric which derived from cyclic presented.
In cases of non-compliance with a prescribed treatment, estimates causal effects typically rely on instrumental variables. However, when participation is also misreported, this approach can be severely biased. We provide an variable method that researchers use to identify the true heterogeneous treatment in data include both and misclassification status. Our used regardless whether misclassified because it missing at random, not or was generally mismeasured. conclude dedicated Stata command,...
For the properties of polymer are relative to its structure, main purpose present work is investigate mechanical aeronautical PMMA which has been treated by directional tensile technology. Isodyne images reveal stress state in PMMA. And then, an anisotropic model established. Furthermore, all parameters measured digital image correlation method. Finally, based on and parameters, FEM numerical simulation experimental methods applied analyze fracture along different directions.
Color-to-gray conversion is popularly used in black and white printing other image processing tasks. In this paper, we propose an adaptive linear weighting algorithm based on the boundary points to realize decolorization. First, develop a new for detection of color by Sobel operator. Secondly, parametric model with discrete searching employed get optimal grayscale image, which aiming at maximally preserving image. Finally, linearly stretch all gray values into intensities. Experimental...
This paper provides a framework for the policy relevant treatment effects using instrumental variables. In framework, selection may or not satisfy classical monotonicity condition and can accommodate multidimensional unobserved heterogeneity. We bound target parameter by extracting information from identifiable estimands. also provide more conservative yet computationally simpler applying convex relaxation method. Linear shape restrictions be easily incorporated to further improve bounds....
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Drilling safety and efficiency are greatly impacted by kick, a major problem that is hard to diagnose, assess, predict due the complexity high uncertainty of deep water drilling formation pressure system. This article forms pre-drilling well kick probability prediction method establishing calculation model for wellbore ECD using numerical solution Monte Carlo simulation algorithm. The bottomhole range gradually increases with depth, according calculations, decreases fluid volume....
The firefly algorithm is a stochastic meta-heuristic that incorporates randomness into search process. In essence, the useful when determining next point in space and therefore has crucial impact exploring new solution. Simultaneously, randomized mechanism plays an important role balance exploration exploitation during this paper, extensive comparison made between 8 different probability distributions can be used for randomizing algorithm's attractive mechanism, e.g., Uniform distribution,...
Entanglement-assisted quantum error-correcting codes are not only theoretically interesting, but also of great importance in practical physically applications. In this work, two class entanglement-assisted constructed. The first is minimal ebits codes, which require one copy maximally entangled state no matter how large the code length is. second maximal entanglement can achieve hashing bound asymptotically.