检索结果-内蒙古大学图书馆

Classification of Hyperspectral and LiDAR Data Using Coupled CNNs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hang, R. Li, Z. Ghamisi, P. Hong, D. Xia, G. Liu, Q. Jiangsu Key Laboratory of Big Data Analysis Technology School of Automation Nanjing University of Information Science and Technology Nanjing210044 China Department of Computer Science and Electrical Engineering University of Missouri Kansas CityMO64110 United States Exploration FreibergD-09599 Germany Wessling82234 Germany Munich80333 Germany Jiangsu Key Laboratory of Big Data Analysis Technology School of Automation Nanjing University of Information Science and Technology Nanjing210044 China

This paper has been accepted by IEEE Transactions on Geoscience and Remote Sensing. In this paper, we propose an efficient and effective framework to fuse hyperspectral and Light Detection And Ranging (LiDAR) data using two coupled convolutional neural networks (CNNs). One CNN is designed to learn spectral-spatial features from hyperspectral data, and the other one is used to capture the elevation information from LiDAR data. Both of them consist of three convolutional layers, and the last two convolutional layers are coupled together via a parameter sharing strategy. In the fusion phase, feature-level and decision-level fusion methods are simultaneously used to integrate these heterogeneous features sufficiently. For the feature-level fusion, three different fusion strategies are evaluated, including the concatenation strategy, the maximization strategy, and the summation strategy. For the decision-level fusion, a weighted summation strategy is adopted, where the weights are determined by the classification accuracy of each output. The proposed model is evaluated on an urban data set acquired over Houston, USA, and a rural one captured over Trento, Italy. On the Houston data, our model can achieve a new record overall accuracy of 96.03%. On the Trento data, it achieves an overall accuracy of 99.12%. These results sufficiently certify the effectiveness of our proposed model. Copyright © 2020, The Authors. All rights reserved.

关键词： Optical radar

On diffusive non-reciprocity and thermal diode

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Ying Li, Jiaxin Qiu, Cheng-Wei Department of Electrical and Computer Engineering National University of Singapore Kent Ridge17583 Singapore State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China

Wave propagation and diffusion in linear materials preserve local reciprocity in terms of a symmetric Green's function. For wave propagations, people usually focus on the signals entering and leaving a system, and do not need detailed information about the fields inside it. In such cases, the global reciprocity of the scattering off a system through several ports is more important, which is defined as the symmetric transmission between the scattering channels. When a two-port system supports non-reciprocal (electromagnetic, acoustic) wave propagation, it is a (optical, phonon) diode directly following the definition. However, to date no clear definition or discussion has been made on the global reciprocity of diffusive processes through a system. It thus remains a question whether diffusive non-reciprocity is related with diode for diffusive fields, say, a thermal diode. Here, we provide theoretical analysis based on local reciprocity and define the global reciprocity of diffusion through a two-port system. We further prove the equivalence between a non-reciprocal heat transfer system and a thermal diode, and discuss some methods to realize it. Our results set a general background for future studies on symmetric and asymmetric diffusive processes. Copyright © 2019, The Authors. All rights reserved.

关键词： Acoustic wave propagation

CholecTriplet2021: A benchmark challenge for surgical action triplet recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nwoye, Chinedu Innocent Alapatt, Deepak Yu, Tong Vardazaryan, Armine Xia, Fangfang Zhao, Zixuan Xia, Tong Jia, Fucang Yang, Yuxuan Wang, Hao Yu, Derong Zheng, Guoyan Duan, Xiaotian Getty, Neil Sanchez-Matilla, Ricardo Robu, Maria Zhang, Li Chen, Huabin Wang, Jiacheng Wang, Liansheng Zhang, Bokai Gerats, Beerend Raviteja, Sista Sathish, Rachana Tao, Rong Kondo, Satoshi Pang, Winnie Ren, Hongliang Abbing, Julian Ronald Sarhan, Mohammad Hasan Bodenstedt, Sebastian Bhasker, Nithya Oliveira, Bruno Torres, Helena R. Ling, Li Gaida, Finn Czempiel, Tobias Vilaça, João L. Morais, Pedro Fonseca, Jaime Egging, Ruby Mae Wijma, Inge Nicole Qian, Chen Bian, Guibin Li, Zhen Balasubramanian, Velmurugan Sheet, Debdoot Luengo, Imanol Zhu, Yuanbo Ding, Shuai Aschenbrenner, Jakob-Anton van der Kar, Nicolas Elini Xu, Mengya Islam, Mobarakol Seenivasan, Lalithkumar Jenke, Alexander Stoyanov, Danail Mutter, Didier Mascagni, Pietro Seeliger, Barbara Gonzalez, Cristians Padoy, Nicolas ICube University of Strasbourg CNRS France IHU Strasbourg France Department of Computer Science University of Chicago United States Lab for Medical Imaging and Digital Surgery Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China School of Management Hefei University of Technology Hefei China Institue of Medical Robotics Shanghai Jiao Tong University Shanghai China Argonne National Laboratory 9700 S Cass Ave LemontIL60439 United States Digital Surgery A Medtronic Company London United Kingdom Institute of Automation Chinese Academy of Sciences China Department of Computer Science School of Informatics Xiamen University Xiamen China Johnson & Johnson Meander Medical Centre Netherlands Indian Institute of Technology Kharagpur India Muroran Institute of Technology Japan Department of Biomedical Engineering National University of Singapore Singapore Department for Translational Surgical Oncology National Center for Tumor Diseases Partner Site Dresden Germany 2Ai School of Technology IPCA Barcelos Portugal School of Medicine University of Minho Braga Portugal Algoritimi Center School of Engineering University of Minho Guimeraes Portugal Technical University of Munich Germany Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Wellcome EPSRC Center for Interventional and Surgical Science University College London United Kingdom Fondazione Policlinico Universitario Agostino Gemelli IRCCS Rome Italy University Hospital of Strasbourg France

Context-aware decision support in the operating room can foster surgical safety and efficiency by leveraging real-time feedback from surgical workflow analysis. Most existing works recognize surgical activities at a coarse-grained level, such as phases, steps or events, leaving out fine-grained interaction details about the surgical activity;yet those are needed for more helpful AI assistance in the operating room. Recognizing surgical actions as triplets of combination delivers comprehensive details about the activities taking place in surgical videos. This paper presents CholecTriplet2021: an endoscopic vision challenge organized at MICCAI 2021 for the recognition of surgical action triplets in laparoscopic videos. The challenge granted private access to the large-scale CholecT50 dataset, which is annotated with action triplet information. In this paper, we present the challenge setup and assessment of the state-of-the-art deep learning methods proposed by the participants during the challenge. A total of 4 baseline methods from the challenge organizers and 19 new deep learning algorithms by competing teams are presented to recognize surgical action triplets directly from surgical videos, achieving mean average precision (mAP) ranging from 4.2% to 38.1%. This study also analyzes the significance of the results obtained by the presented approaches, performs a thorough methodological comparison between them, in-depth result analysis, and proposes a novel ensemble method for enhanced recognition. Our analysis shows that surgical workflow analysis is not yet solved, and also highlights interesting directions for future research on fine-grained surgical activity recognition which is of utmost importance for the development of AI in surgery. © 2022, CC BY-NC-SA.

关键词： Deep learning

Adaptive frequency-limited H2-model order reduction

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zulfiqar, Umair Sreeram, Victor Du, Xin School of Mechatronic Engineering and Automation Shanghai Key Laboratory of Power Station Automation Technology Shanghai University Shanghai China Department of Electrical Electronics and Computer Engineering The University of Western Australia WA Australia Key Laboratory of Knowledge Automation for Industrial Processes Ministry of Education Beijing China Jilin China

In this paper, we present an adaptive framework for constructing a pseudo-optimal reduced model for the frequency-limited H2-optimal model order reduction problem. We show that the frequency-limited pseudo-optimal reduced-order model has an inherent property of monotonic decay in error if the interpolation points and tangential directions are selected appropriately. We also show that this property can be used to make an automatic selection of the order of the reduced model for an allowable tolerance in error. The proposed algorithm adaptively increases the order of reduced model such that the frequency-limited H2-norm error decays monotonically irrespective of the choice of interpolation points and tangential directions. The stability of the reduced-order model is also guaranteed. Additionally, it also generates the approximations of the frequency-limited system Gramians that monotonically approach the original solution. Further, we show that the low-rank alternating direction implicit iteration method for solving large-scale frequency-limited Lyapunov equations implicitly performs frequency-limited pseudo-optimal model order reduction. We consider two numerical examples to validate the theory presented in the paper. Copyright © 2019, The Authors. All rights reserved.

关键词： Errors

Representative task self-selection for flexible clustered lifelong learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sun, Gan Cong, Yang Wang, Qianqian Zhong, Bineng Fu, Yun State Key Laboratory of Robotics Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States Xidian University. Xian Shanxi710071 China Huaqiao University Xiamen Fujian361021 China Department of Electrical and Computer Engineering Khoury College of Computer and Information Sciences Northeastern University BostonMA02115 United States

Consider the lifelong machine learning paradigm whose objective is to learn a sequence of tasks depending on previous experiences, e.g., knowledge library or deep network weights. However, the knowledge libraries or deep networks for most recent lifelong learning models are with prescribed size, and can degenerate the performance for both learned tasks and coming ones when facing with a new task environment (cluster). To address this challenge, we propose a novel incremental clustered lifelong learning framework with two knowledge libraries: feature learning library and model knowledge library, called Flexible Clustered Lifelong Learning (FCL3). Specifically, the feature learning library modeled by an autoencoder architecture maintains a set of representation common across all the observed tasks, and the model knowledge library can be self-selected by identifying and adding new representative models (clusters). When a new task arrives, our proposed FCL3 model firstly transfers knowledge from these libraries to encode the new task, i.e., effectively and selectively soft-assigning this new task to multiple representative models over feature learning library. Then, 1) the new task with a higher outlier probability will be judged as a new representative, and used to redefine both feature learning library and representative models over time;or 2) the new task with lower outlier probability will only refine the feature learning library. For model optimization, we cast this lifelong learning problem as an alternating direction minimization problem as a new task comes. Finally, we evaluate the proposed framework by analyzing several multi-task datasets, and the experimental results demonstrate that our FCL3 model can achieve better performance than most lifelong learning frameworks, even batch clustered multi-task learning models. Copyright © 2019, The Authors. All rights reserved.

关键词： Libraries

Predictive Identification of Electromagnetic Micro-mirrors*

学校读者我要写书评

暂无评论

Predictive Identification of Electromagnetic Micro-mirrors*

IEEE Conference on Cybernetics and Intelligent Systems

作者： Qingmei Cao Yonghong Tan Ruili Dong Qingyuan Tan Institute of Robotics and Automation Nankai University Tianjin China College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai China College of Information Science and Technology Donghua University Shanghai China Department of Electrical and Computer Engineering University of Windsor Windsor Canada

ISBN: (数字)9781728134581

ISBN: (纸本)9781728134598

This paper presents an identification approach for electromagnetic micro-mirrors using data-driven model with hysteresis. Usually, linear models are applied to modeling of electromagnetic micro-mirrors. However, from the experimental results, it can find that hysteresis phenomenon exists in the electromagnetic micro-mirror. Thus, it is not proper for using the linear model for modeling of electromagnetic micro-mirror. In this paper, a data-driven model with hysteresis is proposed for modeling the performance of electromagnetic micro-mirrors. In this model, a linear dynamic submodel is employed to model the deflection mechanism, whilst a dynamic hysteresis submodel is used to describe the hysteresis phenomenon in the electromagnetic actuating mechanism of the micro-mirror. One of the challenges of identification for electromagnetic micro-mirror is the electromagnetic torque cannot be measured directly. For handling this problem, a so-called predictive identification algorithm is applied to parameter estimation of the model. The effect of random noise on the identification is also considered. Then, the paper also presents the experimental results of modeling an electromagnetic micro-mirror.

关键词： Conferences Cybernetics Intelligent systems Robots automation Mechatronics Random access memory

Distributed Localization without Direct Communication Inspired by Statistical Mechanics

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Jingxian Wang, Tianye Wang, Wei Dong, Xiwang Wang, Yandong School of Physics Peking University Beijing100871 China Department of Urban Studies and Planning Massachusetts Institute of Technology CambridgeMA02139 United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

Distributed localization is essential in many robotic collective tasks such as shape formation and self-assembly. Inspired by the statistical mechanics of energy transition, this paper presents a fully distributed localization algorithm named as virtual particle exchange (VPE) localization algorithm, where each robot repetitively exchanges virtual particles (VPs) with neighbors and eventually obtains its relative position from the virtual particle (VP) amount it owns. Using custom-designed hardware and protocol, VPE localization algorithm allows robots to achieve localization using sensor readings only, avoiding direct communication with neighbors and keeping anonymity. Moreover, VPE localization algorithm determines the swarm center automatically, thereby eliminating the requirement of fixed beacons to embody the origin of coordinates. Theoretical analysis proves that the VPE localization algorithm can always converge to the same result regardless of initial state and has low asymptotic time and memory complexity. Extensive localization simulations with up to 10000 robots and experiments with 52 low-cost robots are carried out, which verify that VPE localization algorithm is scalable, accurate and robust to sensor noises. Based on the VPE localization algorithm, shape formations are further achieved in both simulations and experiments with 52 robots, illustrating that the algorithm can be directly applied to support swarm collaborative tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： Statistical mechanics

A Situation-Aware Collision Avoidance Strategy for Car-Following

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2018年第5期5卷 1012-1016页

作者： Li Li Fellow IEEE Xinyu Peng Fei-Yue Wang ieee department of automation bnristtsinghua universityBeijing l00084China the department of automation tsinghua universityBeijing l00084China state key laboratory of management and control for complex systems institute of automationchinese academy of sciencesBeijing 100080China the driver cognition and automated driving laboratory university of waterlooWaterloo N2L 3GlCanada the department of electrical and computer engineering purdue school of engineering and technologyindiana university-purdue university indianapolisIndiana 46202-5l32USA

Abstract--In this paper, we discuss how to develop an appropriate collision avoidance strategy for car-following. This strategy aims to keep a good balance between traffic safety and efficiency while also taking into consideration the unavoidable uncertainty of position/speed perception/measurement of vehicles and other drivers. Both theoretical analysis and numerical testing results are provided to show the effectiveness of the proposed strategy. Index Terms--Collision avoidance, safety, traffic efficiency, uncertainty.

关键词： Collision avoidance safety traffic efficiency uncertainty

Secure Edge Caching for Layered Multimedia Contents in Heterogeneous Networks

学校读者我要写书评

暂无评论

Secure Edge Caching for Layered Multimedia Contents in Heter...

2019 IEEE Global Communications Conference (GLOBECOM)

作者： Qichao Xu Zhou Su Ying Wang Kuan Zhang School of Mechatronic Engineering and Automation Shanghai University China Department of Computer Science and Technology MOEKLINNS Laboratory Xian Jiaotong University China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China Electrical and Computer Engineering Department University of Nebraska-Lincoln USA

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

To meet the exponentially increasing mobile services and applications, heterogenous networks (HetNets) have been envisioned as a promising technology. In HetNets, multiple caching-enabled small-cell based stations (SBSs) are deployed within the coverage of a macro-cell base station (MBS) to cache multimedia contents for mobile users. However, due to security threats of untrusted SBSs, the cached contents may be illegally accessed by owners of these untrusted SBSs, resulting in the content privacy leakage. To tackle this problem, we propose a secure edge caching scheme for layered multimedia contents in HetNets. Specifically, considering the layered features of contents, we first develop a secure edge caching framework based on the cooperations of SBSs and MBS. In this framework, the critical base layer subfile of the content are directly delivered by the trusted MBS, whereas the enhancement layer subfiles are cached on untrusted SBSs. Furthermore, according to the limited caching capacities of SBSs and dynamic content demands of mobile users, we formulate the enhancement layer subfile caching problem as a non-convex 0-1 integer programming problem. To solve this problem, we devise a distributed alternating direction method of multipliers (ADMM) and secure the edge caching for each SBS to iteratively search the optimal caching strategy. Simulation results show that the proposed scheme provides secure and efficient multimedia content caching for mobile users.

关键词： Streaming media Interference Base stations Privacy Encoding Servers Static VAr compensators