检索结果-内蒙古大学图书馆

Performance analysis for a degrading system with Markov model 32nd

学校读者我要写书评

暂无评论

Performance analysis for a degrading system with Markov mode...

32nd European Safety and Reliability Conference, ESREL 2022

作者： Zhang, Aibo Wu, Zhiying Wang, Yukun Xie, Min Center for Intelligent Multidimensional Data Analysis Hong Kong Science Park Shatin Hong Kong Department of Advanced Design and Systems Engineering City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong School of Economics and Management Tianjin Chengjian University Tianjin300384 China

ISBN: (纸本)9789811851834

Most mechanical engineering systems experience deterioration due to several practical factors such as aging, usage etc. This results in the degradation of its performance. Although the deterioration is continuous in nature, it is not always practically possible to measure the deterioration especially in the case of subsea systems. In such cases the performance of these systems is represented by multiple finite states in their lifetimes where various levels of degradation are represented by these states. Generally, the degradation process is divided into two stages, i.e., the normal and defective stages. Thus, there are three possible states for the system: normal, defective, and failed. The Markov approach has been utilized heavily for reliability analysis of such systems. However, most of the Markov models rely on an accurately exponentially distributed transition rate, which is unrealistic in certain cases. In reality, there are some uncertainties in the transition rates thanks to the limits of prior knowledge. This paper presents a multi-phase Markov model-based performance evaluation model for a three-state system with uncertainties in transition rates. The transition rates are assumed following Beta distribution with known lower and upper bounds. The average system unavailability in a given life cycle is employed to quantify system performance. © 2022 ESREL2022 Organizers. Published by Research Publishing, Singapore.

关键词： Reliability analysis

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： de Curtò, J. de Zarzà, I. Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Hong Kong Universitat Politècnica de València València Spain The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature1 as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization. © 2022, CC BY.

关键词： Generative adversarial networks

Learning with Signatures

学校读者我要写书评

暂无评论

arXiv 2022年

作者： de Curtò Díaz, J. de Zarzà, I. Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Shatin Hong Kong Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong Department of Computer Engineering Universitat Politècnica de València València Spain

In this work we investigate the use of the Signature Transform in the context of Learning2. Under this assumption, we advance a supervised framework that potentially provides state-of-the-art classification accuracy with the use of few labels without the need of credit assignment and with minimal or no overfitting. We leverage tools from harmonic analysis by the use of the signature and log-signature, and use as a score function RMSE and MAE Signature and log-signature. We develop a closed-form equation to compute probably good optimal scale factors, as well as the formulation to obtain them by optimization. Techniques of Signal Processing are addressed to further characterize the problem. Classification is performed at the CPU level orders of magnitude faster than other methods. We report results on AFHQ, MNIST and CIFAR10, achieving 100% accuracy on all tasks assuming we can determine at test time which probably good optimal scale factor to use for each category. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

Efficient CUR decomposition for interpretable low-rank approximations and imaging applications

学校读者我要写书评

暂无评论

Neurocomputing 2025年 645卷

作者： Abdelgawad, Muhammad A.A. Cheung, Ray C.C. Yan, Hong Department of Electrical Engineering and Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Hong Kong Department of Electrical Engineering Faculty of Engineering Minia University El-Minia 61517 Egypt

Low-rank approximations based on the selected columns and rows from a given matrix are an alternative approach to singular value decomposition (SVD) and offer more interpretable outputs. They have been successfully used in pattern recognition, recommendation systems, bioinformatics, and social network analysis. One popular approach is CUR matrix decomposition, which represents the data matrix using three small matrices and can be achieved through randomized or deterministic approaches. Deterministic algorithms yield higher approximation accuracy than randomized ones. However, they are highly computationally expensive, especially with large datasets. To address these limitations, we introduce a new method for efficiently computing the CUR matrix decomposition called HyCUR. It incorporates a deterministic sampling strategy based on guided information of the singular vectors and a randomized sampling to select rows and columns for efficient CUR low-rank approximation. HyCUR overcomes the main drawbacks of deterministic methods and can estimate the approximation rank using an incremental QR factorization approach, which also approximates the SVD of the data matrix instead of the classical method. Therefore, HyCUR is suitable for applications with unknown data rank. Experimental results on synthetic and real datasets of varying sizes demonstrate that HyCUR achieves comparable accuracy to recent deterministic approaches while significantly improving computational efficiency for large low-rank datasets. We validate the proposed method in two real imaging applications: simultaneous sample and feature extraction from large datasets and hyperspectral unmixing to extract endmember signatures and estimate their fractions from hyperspectral image datasets (HSIs). The experiment results show promising performance in both applications. © 2025 Elsevier B.V.

关键词： Feature Selection

Unsupervised Domain Adaptation for Low-dose CT Reconstruction via Bayesian Uncertainty Alignment

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Kecheng Liu, Jie Wan, Renjie Lee, Victor Ho-Fun Vardhanabhuti, Varut Yan, Hong Li, Haoliang The Department of Electrical Engineering The Center for Intelligent Multidimensional Data Analysis City University of Hong Kong Hong Kong The Department of Computer Science Hong Kong Baptist University Hong Kong The Department of Clinical Oncology School of Clinical Medicine LKS Faculty of Medicine The University of Hong Kong Hong Kong The Department of Diagnostic Radiology School of Clinical Medicine LKS Faculty of Medicine The University of Hong Kong Hong Kong

Low-dose computed tomography (LDCT) image reconstruction techniques can reduce patient radiation exposure while maintaining acceptable imaging quality. Deep learning is widely used in this problem, but the performance of testing data (a.k.a. target domain) is often degraded in clinical scenarios due to the variations that were not encountered in training data (a.k.a. source domain). Unsupervised domain adaptation (UDA) of LDCT reconstruction has been proposed to solve this problem through distribution alignment. However, existing UDA methods fail to explore the usage of uncertainty quantification, which is crucial for reliable intelligent medical systems in clinical scenarios with unexpected variations. Moreover, existing direct alignment for different patients would lead to content mismatch issues. To address these issues, we propose to leverage a probabilistic reconstruction framework to conduct a joint discrepancy minimization between source and target domains in both the latent and image spaces. In the latent space, we devise a Bayesian uncertainty alignment to reduce the epistemic gap between the two domains. This approach reduces the uncertainty level of target domain data, making it more likely to render well-reconstructed results on target domains. In the image space, we propose a sharpness-aware distribution alignment to achieve a match of second-order information, which can ensure that the reconstructed images from the target domain have similar sharpness to normal-dose CT images from the source domain. Experimental results on two simulated datasets and one clinical low-dose imaging dataset show that our proposed method outperforms other methods in quantitative and visualized performance. © 2023, CC BY.

关键词： Uncertainty analysis

Minimax principle for right eigenvalues of dual quaternion matrices and their generalized inverses

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ling, Chen Qi, Liqun Yan, Hong Department of Mathematics Hangzhou Dianzi University Hangzhou310018 China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Department of Electrical Engineering Centre for Intelligent Multidimensional Data Analysis City University of Hong Kong Kowloon Hong Kong

Dual quaternions can represent rigid body motion in 3D spaces, and have found wide applications in robotics, 3D motion modelling and control, and computer graphics. In this paper, we introduce three different right linear independency concepts for a set of dual quaternion vectors, and study some related basic properties for dual quaternion vectors and dual quaternion matrices. We present a minimax principle for eigenvalues of dual quaternion Hermitian matrices. Based upon a newly established Cauchy-Schwarz inequality for dual quaternion vectors and singular value decomposition of dual quaternion matrices, we propose an inequality for singular values of dual quaternion matrices. Finally, we introduce the concept of generalized inverses of dual quaternion matrices, and present necessary and sufficient conditions for a dual quaternion matrix to be one of four types of generalized inverses of another dual quaternion matrix. © 2022, CC BY.

关键词： Singular value decomposition

An effective model for quantification of cell 3Dshape in early embryogenesis

学校读者我要写书评

暂无评论

Research Square

Research Square 2021年

作者： Li, Zelin Cao, Jianfeng Zhao, Zhongying Yan, Hong Center for Intelligent Multidimensional Data Analysis and Department of Electrical Engineering City University of Hong Kong Kowloon Tong Hong Kong Department of Biology Hong Kong Baptist University Kowloon Tong Hong Kong

Background: The cell developmental process is featured by fabulous morphogenesis in multicellular organisms. Describing morphological changes quantitatively concretes the way to investigating both intra and inter cell regulations on cell fate. While Caenorhabditis elegans has been used as a model for cell development studies for a long time, the research of how cell shape is precisely controlled remains obscure by the lack of methods to model morphological features. Currently, in order to characterize the features of cell shape involved in cell migration and differentiation, there is an increasing demand in analyzing cell shape systematically, especially when many works have contributed to cell reconstruction. Results: In this work, Spherical harmonics and Principal component analysis integrated Cell Shape quantification Models (SPCSMs) is proposed to represent cell shapes in a low-dimensional shape space. SPCSMs incorporates a complete pipeline to quantify cell shapes and analyze their morphological phenotypes in three dimensional (3D) reconstructions. Based on the framework, we extract biologically meaningful patterns in the lineage of C. elegans embryo before 350-cell stage, during which all hypodermis cells deformed like a funnel and can be recognized based on these shape patterns. Finally, SPCSMs is compared with two cell shape representation methods, which substantiates the effectiveness and robustness of our method. Conclusion: SPCSMs provides a general method to decribe shapes in low-dimensional shape space with compact parameters. It can quantify the shapes of cells from single-cell resolution images obtained over one-minute intervals, making it possible to recognize developmental patterns in cell lineages. SPCSMs is expected to be an effective model for biologists to explore the relationships between the shapes of cells and their fates. © 2021, CC BY.

关键词： Cells

A regularization-patching dual quaternion optimization method for solving the hand-eye calibration problem

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Zhongming Ling, Chen Qi, Liqun Yan, Hong Department of Mathematics School of Science Hangzhou Dianzi University Hangzhou310018 China Department of Applied Mathematics The Hong Kong Polytechnic University Hung Hom Kowloon Hong Kong Center for Intelligent Multidimensional Data Analysis Science Park Shatin Hong Kong Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

The hand-eye calibration problem is an important application problem in robot research. Based on the 2-norm of dual quaternion vectors, we propose a new dual quaternion optimization method for the hand-eye calibration problem. The dual quaternion optimization problem is decomposed to two quaternion optimization subproblems. The first quaternion optimization subproblem governs the rotation of the robot hand. It can be solved efficiently by the eigenvalue decomposition or singular value decomposition. If the optimal value of the first quaternion optimization subproblem is zero, then the system is rotationwise noiseless, i.e., there exists a "perfect" robot hand motion which meets all the testing poses rotationwise exactly. In this case, we apply the regularization technique for solving the second subproblem to minimize the distance of the translation. Otherwise we apply the patching technique to solve the second quaternion optimization subproblem. Then solving the second quaternion optimization subproblem turns out to be solving a quadratically constrained quadratic program. In this way, we give a complete description for the solution set of hand-eye calibration problems. This is new in the hand-eye calibration literature. The numerical results are also presented to show the efficiency of the proposed method. © 2022, CC BY.

关键词： Numerical methods

Signature and Log-signature for the Study of Empirical Distributions Generated with GANs

学校读者我要写书评

暂无评论

arXiv 2022年

作者： de Curtò, Joaquim de Zarzà, Irene Yan, Hong Calafate, Carlos T. Centre for Intelligent Multidimensional Data Analysis HK Science Park Hong Kong Universitat Politècnica de València València Spain Universitat Oberta de Catalunya Barcelona Spain The Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong

In this paper, we bring forward the use of the recently developed Signature Transform as a way to measure the similarity between image distributions and provide detailed acquaintance and extensive evaluations. We are the first to pioneer RMSE and MAE Signature, along with log-signature as an alternative to measure GAN convergence, a problem that has been extensively studied. We are also forerunners to introduce analytical measures based on statistics to study the goodness of fit of the GAN sample distribution that are both efficient and effective. Current GAN measures involve lots of computation normally done at the GPU and are very time consuming. In contrast, we diminish the computation time to the order of seconds and computation is done at the CPU achieving the same level of goodness. Lastly, a PCA adaptive t-SNE approach, which is novel in this context, is also proposed for data visualization. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning