检索结果-内蒙古大学图书馆

ZND-ZeaD Models and Theoretics Including Proofs for Takagi Factorization of Complex Time-Dependent Symmetric Matrix

学校读者我要写书评

暂无评论

ZND-ZeaD Models and Theoretics Including Proofs for Takagi F...

第33届中国控制与决策会议

作者： Zhuosong Fu Min Yang Jinjin Guo Jianrong Chen Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangdong Key Laboratory of Modern Control Technology Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education School of Electronics and Information Technology Sun Yat-sen University School of Public Health and Management Youjiang Medical University for Nationalities

Takagi factorization(TF) is a kind of matrix factorization(also termed,decomposition) *** this paper,the problem of TF for complex time-dependent symmetric matrix(simply termed,time-dependent Takagi factorization)is presented and theoretically *** simplify the tough problem,we first consider converting it into an equivalent equation ***,a continuous-time(CT) TF(CTTF) model is presented and derived theoretically,by adopting ZND(Zhang neural dynamics,or termed,Zhang neural network) method and a dimensional reduction *** order to facilitate the implementation on digital hardware platforms,the corresponding discrete-time(DT) ZND solution models(or termed,algorithms) with different discretization precisions of the CTTF model are presented and taken into theoretical ***,we present and investigate a discrete-time TF(DTTF) model,termed eight-instant DTTF(8IDTTF) model,by using a new eight-instant Zhang et al discretization(ZeaD,also termed,Zhang time discretization,ZTD) formula to discretize the CTTF ***,two other DTTF models,termed four-instant DTTF(4IDTTF) and six-instant DTTF(6IDTTF) models,are presented respectively,on the basis of two corresponding multiinstant ZeaD ***,the effective solution step-size intervals of the three DTTF models are further presented and proved.

关键词： Time-dependent Takagi factorization Dimensional reduction Zhang neural dynamics(ZND) Kronecker product Zhang et al discretization(ZeaD) formulas

Pro-UIGAN: Progressive Face Hallucination from Occluded Thumbnails

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Yang Yu, Xin Lu, Xiaobo Liu, Ping The Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Australian Institute of Artificial Intelligence University of Technology Sydney UltimoNSW2007 Australia The School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Singapore138634 Singapore

In this paper, we study the task of hallucinating an authentic high-resolution (HR) face from an occluded thumbnail. We propose a multi-stage Progressive Upsampling and Inpainting Generative Adversarial Network, dubbed Pro-UIGAN, which exploits facial geometry priors to replenish and upsample (8×) the occluded and tiny faces (16×16 pixels). Pro-UIGAN iteratively (1) estimates facial geometry priors for low-resolution (LR) faces and (2) acquires non-occluded HR face images under the guidance of the estimated priors. Our multi-stage hallucination network upsamples and inpaints occluded LR faces via a coarse-to-fine fashion, significantly reducing undesirable artifacts and blurriness. Specifically, we design a novel cross-modal attention module for facial priors estimation, in which an input face and its landmark features are formulated as queries and keys, respectively. Such a design encourages joint feature learning across the input facial and landmark features, and deep feature correspondences will be discovered by attention. Thus, facial appearance features and facial geometry priors are learned in a mutually beneficial manner. Extensive experiments show that our Pro-UIGAN attains visually pleasing completed HR faces, thus facilitating downstream tasks, i.e., face alignment, face parsing, face recognition as well as expression classification. Copyright © 2021, The Authors. All rights reserved.

关键词： Generative adversarial networks

MODELING AND FUZZY control OF PERMANENT MAGNET SYNCHRONOUS MOTORS

学校读者我要写书评

暂无评论

MODELING AND FUZZY CONTROL OF PERMANENT MAGNET SYNCHRONOUS M...

The 10th International Conference on Power Electronics, Machines and Drives (PEMD 2020)

作者： D.-K. Jukić T. Varga T. Benšić V. J. Štil M. Barukčić Automation and Control Institute TU Wien Vienna Austria Faculty of Electrical Engineering Computer Science and Information Technology Osijek Josip Juraj Strossmayer University of Osijek Osijek Croatia

This paper deals with Permanent Magnet Synchronous Motor modeling and control. The derived nonlinear dq model is a combination of Finite Element Method simulation data with the classical dq model. The so derived model keeps the precision of the Finite Element Method simulations and also the fast execution times of the dq model. The Finite Element Method data is included in the dq model using Artificial Neural Networks. The derived model is also used for controller design. The chosen controller is a PI like Fuzzy Logic controller, which is tuned using Genetic Algorithm optimization. The Permanent Magnet Synchronous Motor with Fuzzy Logic controller operation is tested using Real-Time (Model-in-the-Loop) simulations.

关键词： fuzzy control finite element analysis genetic algorithms neural nets permanent magnet motors machine control synchronous motors nonlinear control systems PI control electric machine analysis computing

Ensemble CNN and Uncertainty Modeling to Improve Automatic Identification/Segmentation of Multiple Sclerosis Lesions in Magnetic Resonance Imaging

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Placidi, Giuseppe Cinque, Luigi Iacoviello, Daniela Mignosi, Filippo Polsinelli, Matteo A2VI-lab Department of MeSVA University of LAquila Via Vetoio Coppito 2 L'Aquila67100 Italy Department of Computer Science Sapienza University of Rome Via Salaria 113 Roma00198 Italy Department of Computer Control and Management Engineering Sapienza University of Rome Rome Italy Department of DISIM University of LAquila Via Vetoio Coppito L'Aquila67100 Italy

To date, several automated strategies for identification/segmentation of Multiple Sclerosis (MS) lesions with the use of Magnetic Resonance Imaging (MRI) have been presented, but they are outperformed by human experts, from whom they act very differently. This is mainly due to: the ambiguity originated by MRI instabilities;peculiar variability of MS;non specificity of MRI regarding MS. Physicians partially manage the uncertainty generated by ambiguity relying on radiological/clinical/anatomical background and experience. To emulate human diagnosis, we present an automated framework for identification/segmentation of MS lesions from MRI based on three pivotal concepts: 1. the modelling of uncertainty;2. the proposal of two, separately trained, CNN, one optimized for lesions and the other for lesions with respect to the environment surrounding them, respectively repeated for axial, coronal and sagittal directions;3. the definition of an ensemble classifier to merge the information collected by different CNN. The proposed framework is trained, validated and tested on the 2016 MSSEG benchmark public data set from a single imaging modality, the FLuid-Attenuated Inversion Recovery (FLAIR). The comparison with the ground-truth and with each of 7 human raters, proves that there is no significant difference between the automated and the human raters. © 2021, CC BY.

关键词： Magnetic resonance imaging

RAPTOR: Robust and Perception-aware Trajectory Replanning for Quadrotor Fast Flight

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhou, Boyu Pan, Jie Gao, Fei Shen, Shaojie Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Industrial Control and Technology Zhejiang University Hangzhou310007 China

—Recent advances in trajectory replanning have enabled quadrotor to navigate autonomously in unknown environments. However, high-speed navigation still remains a significant challenge. Given very limited time, existing methods have no strong guarantee on the feasibility or quality of the solutions. Moreover, most methods do not consider environment perception, which is the key bottleneck to fast flight. In this paper, we present RAPTOR, a robust and perception-aware replanning framework to support fast and safe flight, which addresses these issues systematically. A path-guided optimization (PGO) approach that incorporates multiple topological paths is devised, to ensure finding feasible and high-quality trajectories in very limited time. We also introduce a perception-aware planning strategy to actively observe and avoid unknown obstacles. A risk-aware trajectory refinement ensures that unknown obstacles which may endanger the quadrotor can be observed earlier and avoid in time. The motion of yaw angle is planned to actively explore the surrounding space that is relevant for safe navigation. The proposed methods are tested extensively through benchmark comparisons and challenging indoor and outdoor aggressive flights. We will release our implementation as an open-source package1 for the community. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion planning

Mode-dependent seamless transfer control strategy of a microgrid via a small-signal stability approach

学校读者我要写书评

暂无评论

Mode-dependent seamless transfer control strategy of a micro...

作者： Wu, Ying Guerrero, Josep M. Wu, Yanpeng School of Computer Science Xi'an Shiyou University China Department of Energy Technology Aalborg University Denmark School of Information and Control Engineering Xi'an University of Architecture and Technology China

A microgrid is an effective solution to enhance the integration of distributed renewable energy resources, which can operate both in grid connected mode and islanded mode. In order to reduce the jumps of the system variables within acceptable limits to ensure the system has good transient performance and power quality in multiple operating modes, seamless transfer is the key problem to be considered. In this paper, due to the different multiple equilibrium points for the two operating modes, the dynamics of every operating mode re modeled as a subsystem with all the variables that are needed to be synchronized. Linearization is carried out respectively for the two operation modes on the different equilibriums in a state-space form based on the small-signal stability method. To reduce the conservatism of the unified controller, the concept of the relative Lyapunov function is introduced to derive a multiple segmental Lyapunov method and a robust feedback mode-dependent switching controller is designed to achieve smooth transfer by making the deviation energy of the two modes both converge to the zero point. To rapidly detect the switching signal, a sparse communication network is introduced by the use of low bandwidth communication links to broadcast the switching signal to each distributed controller. Finally, two microgrid test systems were built in SIMULINK to show the feasibility and effectiveness of the proposed seamless transfer control strategies. © 2019 Chinese Automatic control Society and John Wiley & Sons Australia, Ltd

关键词： controllers

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wu, Qiong Li, Jiahan Dai, Pingyang Ye, Qixiang Cao, Liujuan Wu, Yongjian Ji, Rongrong Institute of Artificial Intelligence The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221000 China The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Peng Cheng Laboratory Shenzhen518066 China The School of Electronics Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Media Analytics and Computing Lab Department of Computer Science School of Informatics Xiamen University Xiamen361005 China The Youtu Laboratory Tencent Shanghai200233 China The Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application Institute of Artificial Intelligence Xiamen University Xiamen361005 China

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

Think too fast nor too slow: The computational trade-off between planning and reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Moerland, Thomas M. Deichler, Anna Baldi, Simone Broekens, Joost Jonker, Catholijn M. Interactive Intelligence Tu Delft Leiden Institute of Advanced Computer Science Leiden University School of Cyberscience and Engineering Southeast University Delft Center for Systems and Control Tu Delft

Planning and reinforcement learning are two key approaches to sequential decision making. Multistep approximate real-Time dynamic programming, a recently successful algorithm class of which AlphaZero [Silver et al., 2018] is an example, combines both by nesting planning within a learning loop. However, the combination of planning and learning introduces a new question: how should we balance time spend on planning, learning and acting? The importance of this trade-off has not been explicitly studied before. We show that it is actually of key importance, with computational results indicating that we should neither plan too long nor too short. Conceptually, we identify a new spectrum of planning-learning algorithms which ranges from exhaustive search (long planning) to modelfree RL (no planning), with optimal performance achieved midway. Copyright © 2020, The Authors. All rights reserved.

关键词： Reinforcement learning

EMDS-5: Environmental Microorganism Image Dataset Fifth Version for Multiple Image Analysis Tasks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Zihan Li, Chen Yao, Yudong Zhang, Jinghua Rahaman, Md Mamunur Xu, Hao Kulwa, Frank Lu, Bolin Zhu, Xuemin Jiang, Tao Microscopic Image and Medical Image Analysis Group MBIE College Northeastern University Shenyang110169 China Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07030 United States School of Biomedical Engineering Huazhong University of Science and Technology Wuhan430074 China Whiting School of Engineering Johns Hopkins University 500 W University Parkway MD21210 United States School of Control Engineering Chengdu University of Information Technology Chengdu610225 China

Environmental Microorganism Data Set Fifth Version (EMDS-5) is a microscopic image dataset including original Environmental Microorganism (EM) images and two sets of Ground Truth (GT) images. The GT image sets include a single-object GT image set and a multi-object GT image set. The EMDS-5 dataset has 21 types of EMs, each of which contains 20 original EM images, 20 single-object GT images and 20 multi-object GT images. EMDS-5 can realize to evaluate image preprocessing, image segmentation, feature extraction, image classification and image retrieval functions. In order to prove the effectiveness of EMDS-5, for each function, we select the most representative algorithms and price indicators for testing and evaluation. The image preprocessing functions contain two parts: image denoising and image edge detection. Image denoising uses nine kinds of filters to denoise 13 kinds of noises, respectively. In the aspect of edge detection, six edge detection operators are used to detect the edges of the images, and two evaluation indicators, peak-signal to noise ratio and mean structural similarity, are used for evaluation. Image segmentation includes single-object image segmentation and multi-object image segmentation. Six methods are used for single-object image segmentation, while k-means and U-net are used for multi-object *** extract nine features from the images in EMDS-5 and use the Support Vector Machine classifier for testing. In terms of image classification, we select the VGG16 feature to test different classifiers. We test two types of retrieval approaches: texture feature retrieval and deep learning feature retrieval. We select the last layer of features of these two deep learning networks as feature vectors. We use mean average precision as the evaluation index for retrieval. © 2021, CC BY.

关键词： Image segmentation