检索结果-内蒙古大学图书馆

15th Federated Conference on Computer Science and Information Systems, FedCSIS 2020

作者： Li, Yuanyuan Fadda, Edoardo Manerba, Daniele Tadei, Roberto Terzo, Olivier Links Foundation-Advanced Computing and Applications Torino10138 Italy Politecnico di Torino Department of Control and Computer Engineering Torino10129 Italy University of Brescia Department of Information Engineering Brescia25123 Italy

ISBN: (纸本)9788395541674

Online scheduling has been an attractive field of research for over three decades. Some recent developments suggest that Reinforcement Learning (RL) techniques have the potential to deal with online scheduling issues effectively. Driven by an industrial application, in this paper we apply four of the most important RL techniques, namely Q-learning, Sarsa, Watkins's Q(lambda), and Sarsa(lambda), to the online single-machine scheduling problem. Our main goal is to provide insights on how such techniques perform. The numerical results show that Watkins's Q(lambda) performs best in minimizing the total tardiness of the scheduling process. © 2020 Polish Information Processing Society - as it is since 2011.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Diff9D: Diffusion-Based Domain-Generalized Category-Level 9-DoF Object Pose Estimation

arXiv

引用

arXiv 2025年

作者： Liu, Jian Sun, Wei Yang, Hui Deng, Pengchao Liu, Chongpei Sebe, Nicu Rahmani, Hossein Mian, Ajmal National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering School of Robotics State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Hunan University Changsha410082 China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China Department of Information Engineering and Computer Science University of Trento Trento38123 Italy School of Computing and Communications Lancaster University LA1 4YW United Kingdom Department of Computer Science The University of Western Australia WA6009 Australia

Nine-degrees-of-freedom (9-DoF) object pose and size estimation is crucial for enabling augmented reality and robotic manipulation. Category-level methods have received extensive research attention due to their potential for generalization to intra-class unknown objects. However, these methods require manual collection and labeling of large-scale real-world training data. To address this problem, we introduce a diffusion-based paradigm for domain-generalized category-level 9-DoF object pose estimation. Our motivation is to leverage the latent generalization ability of the diffusion model to address the domain generalization challenge in object pose estimation. This entails training the model exclusively on rendered synthetic data to achieve generalization to real-world scenes. We propose an effective diffusion model to redefine 9-DoF object pose estimation from a generative perspective. Our model does not require any 3D shape priors during training or inference. By employing the Denoising Diffusion Implicit Model, we demonstrate that the reverse diffusion process can be executed in as few as 3 steps, achieving near real-time performance. Finally, we design a robotic grasping system comprising both hardware and software components. Through comprehensive experiments on two benchmark datasets and the real-world robotic system, we show that our method achieves state-of-the-art domain generalization performance. Our code will be made public at https://***/CNJianLiu/Diff9D. Copyright © 2025, The Authors. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Experiences with Postdoctoral Training in Human Factors: Mentor and Trainee Perspectives

引用

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2023年第1期67卷 265 - 269页

作者： Kelly Caine Ken Catchpole Farzan Sasangohar Karen B. Chen Sudeep Hegde Dustin Souders Anthony McDonald Elease J. McLaurin Clemson University School of Computing Clemson SC USA Medical University of South Carolina Clinical Practice and Human Factors Charleston SC USA Texas A&M University Industrial and Systems Engineering Central SC USA North Carolina State University Edward P. Fitts Department of Industrial and Systems Engineering Raleigh NC USA Clemson University Department of Industrial Engineering Central SC USA Clemson University Psychology Department Clemson SC USA University of Wisconsin-Madison Department of Industrial and Systems Engineering Madison WI USA Oak Ridge Institute for Science & Education Fellowship Program Centers for Disease Control & Prevention Philadelphia PA USA

Postdoctoral training positions are becoming more common in the human factors and ergonomics (HFE) discipline. However, conversations related to training in the HFE discipline have largely focused on undergraduate and graduate education. This panel assembles both postdoctoral mentors and former trainees who collectively have a diverse set of HFE-related postdoctoral experiences. By panelists discussing their experiences, observations, and recommendations related to postdoctoral training with the audience, the panel session will support HFE faculty and students in making more informed decisions about if and how a postdoctoral experience (either as a mentor or trainee) could be a part of their career development in HFE.

关键词： education postdoctoral training human factors mentorship

来源：评论

学校读者我要写书评

暂无评论

Quantum advantage for differential equation analysis

引用

Physical Review A 2022年第2期105卷 022415-022415页

作者： Bobak Toussi Kiani Giacomo De Palma Dirk Englund William Kaminsky Milad Marvian Seth Lloyd Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Research Laboratory of Electronics Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Giacomo De Palma Scuola Normale Superiore 56126 Pisa Italy QuEra Computing Boston Massachusetts 02143 USA Department of Mechanical Engineering Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Electrical and Computer Engineering Center for Quantum Information and Control University of New Mexico Albuquerque New Mexico 87131 USA

Quantum algorithms for differential equation solving, data processing, and machine learning potentially offer an exponential speedup over all known classical algorithms. However, there also exist obstacles to obtaining this potential speedup in useful problem instances. The essential obstacle for quantum differential equation solving is that outputting useful information may require difficult postprocessing, and the essential obstacle for quantum data processing and machine learning is that inputting the data is a difficult task just by itself. In this study, we demonstrate that, when combined, these difficulties solve one another. We show how the output of quantum differential equation solving can serve as the input for quantum data processing and machine learning, allowing dynamical analysis in terms of principal components, power spectra, and wavelet decompositions. To illustrate this, we consider continuous-time Markov processes on epidemiological and social networks. These quantum algorithms provide an exponential advantage over existing classical Monte Carlo methods.

关键词： Machine learning Quantum algorithms Quantum computation Markovian processes Numerical techniques

来源：评论

学校读者我要写书评

暂无评论

Normal Dynamics: Solving Newton's Equations of Motion in the Reciprocal Space

SSRN

引用

SSRN 2023年

作者： Cammarata, Antonio Dašić, Miljan Nicolini, Paolo Department of Control Engineering Faculty of Electrical Engineering Czech Technical University in Prague Technicka 2 Prague16627 Czech Republic Scientific Computing Laboratory Center for the Study of Complex Systems Institute of Physics Belgrade University of Belgrade Pregrevica 118 Belgrade11080 Serbia Institute of Physics Czech Academy of Sciences Na Slovance 2 Prague18200 Czech Republic

We here present the Normal Dynamics technique, which provides a way to integrate the Newton's equations of motion by sampling the reciprocal space. We discuss the sampling strategy and show how it is capable to produce dynamical trajectories at the ab initio level on an ordinary desktop computer. The reciprocal space sampling allows to i) obtain a systematic improvement of the results accuracy and a fine control of the computational load, and ii) account for distortions realized across large atomic distances without the use of large unit cells. We present three case studies: the first two are aimed to show the capabilities of the method while in the latter we investigate on the characterization of Raman spectra at different temperatures in MoS2/MX2 transition metal dichalcogenide heterostructures. Finally, we discuss how the sampling procedure is general and can be used to simulate periodic, semiperiodic and finite systems such as crystals, slabs, nanoclusters or molecules. © 2023, The Authors. All rights reserved.

关键词： Equations of motion

来源：评论

学校读者我要写书评

暂无评论

Faster Randomized Dynamical Decoupling

arXiv

引用

arXiv 2024年

作者： Yi, Changhao Kim, Leeseok Marvian, Milad Center for Quantum Information and Control University of New Mexico NM87131 United States Department of Physics and Astronomy University of New Mexico NM87131 United States State Key Laboratory of Surface Physics Department of Physics Fudan University Shanghai200433 China Institute for Nanoelectronic Devices and Quantum Computing Fudan University Shanghai200433 China Department of Electrical and Computer Engineering University of New Mexico NM87131 United States

We present a randomized dynamical decoupling (DD) protocol that can substantially improve the performance of any given deterministic DD, by using no more than two additional pulses. Our construction is implemented by probabilistically applying sequences of pulses, which, when combined, effectively eliminate the error terms that scale linearly with the system-environment coupling strength. As a result, we show that a randomized protocol using a few pulses can outperform deterministic DD protocols that require considerably more pulses. Furthermore, we prove that the randomized protocol provides an improvement compared to deterministic DD sequences that aim to reduce the error in the system’s Hilbert space, such as Uhrig DD, which had been previously regarded to be optimal. To rigorously evaluate the performance, we introduce new analytical methods suitable for analyzing higher-order DD protocols that might be of independent interest. We also present numerical simulations confirming the significant advantage of using randomized protocols compared to widely used deterministic protocols. Copyright © 2024, The Authors. All rights reserved.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Teeth Segmentation from Bite-Wing X-Ray Images by Integrating Nested Dual UNet with Swin Transformers

Teeth Segmentation from Bite-Wing X-Ray Images by Integratin...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yubo Li Yibin Tian Zhiyuan Zhang Xueyang Zhang Bingran Du Zhi Zeng School of Computer and Information Science Chongqing Normal University Chongqing CN College of Mechatronics and Control Engineering Shenzhen University Shenzhen CN Litemaze Technology Shenzhen CN School of Computing and Information Systems Singapore Management University Singapore SG Department of Stomatology Shunde Hospital Southern Medical University (The First People's Hospital of Shunde) Foshan CN

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In medical practice, the precision of image segmentation is crucial for diagnosis and treatment evaluations. Specifically, in dentistry, accurate teeth segmentation from bite-wing images is important for automatic and objective evaluations of root canal treatments. This study introduces $\text{Swin}-\mathrm{U}^{2} \text{Net}$ , a model merging the nested dual UNet with residual U-block and Swin Transformers. It combines the local feature extraction capability of the former and the global attention and context understanding of the latter. It has been evaluated for tooth root segmentation using 500 bite-wing dental x-ray images obtained from a root canal treatment clinic. It achieved the best segmentation outcome in terms of Intersection over Union (IOU) and the third best result in terms of Dice Similarity Coefficient (DSC) with the second least amount of network parameters among six UNet-like models, thus it is effective and efficient.

关键词： Image segmentation Irrigation Accuracy Merging Teeth Transformers Feature extraction Dentistry X-ray imaging Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Research on fault diagnosis method and application of gas turbine based on acoustic imaging technology

Research on fault diagnosis method and application of gas tu...

引用

CSAA/IET International Conference on Aircraft Utility Systems (AUS 2024)

作者： Wen Yan Mingliang Hu Fei Wen Peipei Guo Ziang Guo AVIC Shanghai Aviation Measurement & Control Technology Research Institute Shanghai 201601 People's Republic of China Xi'an Aeronautics Computing Technique Research Institute AVIC Xi'an 710068 People's Republic of China Department of Electronics College of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai 200240 People's Republic of China

ISBN: (数字)9781837242108

Gas turbine health management is of great significant for enhancing flight safety and reducing maintenance costs. Based on the architecture of gas turbine fault identification system, a multi-arm spiral microphone array with high positioning accuracy, high beam resolution, and strong anti-interference capability is designed in this paper with simulation and experiment. On this basis, by utilizing multi-channel acoustic digital acquisition and analysis equipment, high-precision, wide dynamic range, and high-real-time acquisition of audio data from the combustion chamber of gas turbines are achieved. An audio data analysis strategy based on feature extraction and an autoencoder network construction strategy are proposed, fulfilling the imaging of audio data from the combustion chamber of gas turbines, which can effectively identify gas turbine faults. Experiments conducted on the platform of the multi-arm spiral microphone array indecates that the proposed fault detection strategy has an accuracy rate of over 98%. This is of great theoretical significance and practical value for enhancing the level of gas turbine fault detection, and improving the performance, reliability, and lifespan of gas turbine systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Reconstruction of CT Images Based on AA-R2Unet in Inferior Mesenteric Artery Classification 7th

Research on Reconstruction of CT Images Based on AA-R2Unet i...

引用

7th International Conference on Life System Modeling and Simulation, LSMS 2021, and 7th International Conference on Intelligent computing for Sustainable Energy and Environment, ICSEE 2021

作者： Xu, Peixia Wang, Meirong Han, Yu Chen, Jinghao Zhu, YuanFan Zhang, Kun He, Bosheng School of Electrical Engineering Nantong University Nantong China Department of Radiology The Second Affiliated Hospital of Nantong University Nantong China Nantong Key Laboratory of Intelligent Medicine Innovation and Transformation Nantong China Nantong Key Laboratory of Intelligent Control and Intelligent Computing Nantong China School of Management Science and Engineering ChongqingTechnology and Business University Chongqing China

ISBN: (纸本)9789811672064

In the process of colorectal cancer surgery, dispute on whether to retain the left colonic artery continues to this day. The classification of the inferior mesenteric artery has instructional significance for clinic which has been proved. Therefore, realizing relative position among vessels is an essential step for the diagnosis and therapy of colorectal cancer disease. The method of 3D reconstruction based on CT sequence images in hospital is time-consuming and laborious. In this paper, we propose a kind of AA-R2Unet based on Unet to realize automatic segmentation of the inferior mesenteric artery. We use attention augment rather than the convolution to achieve the global feature, stacking predictions with 2D features to achieve the function of 3D visualization. The improved Focal Loss function we proposed focuses more on our target vessel. AA-R2Uet achieved a per case precision of 93.34%, recall of 90.28%, and 90.06% of F1 score. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Remanufacturing Scheme Design for Used Parts Based on Incomplete Information Reconstruction

引用

Chinese Journal of Mechanical engineering 2020年第3期33卷 72-85页

作者： Wenhao Huang Zhigang Jiang Teng Wang Yan Wang Xiaoli Hu Hubei Key Laboratory of Mechanical Transmission and Manufacturing Engineering Wuhan University of Science&TechnologyWuhan 430081China Key Laboratory of Metallurgical Equipment and Control Technology Wuhan University of Science&TechnologyWuhan 430081China Department of Computing Engineering and MathematicsUniversity of BrightonBrighton BN24GJUK School of Mechanical Engineering Shanghai Dianji UniversityShanghai 201306China.

The different conditions of use of a component result in a variety of damage ***,excluding differences in shape and size,used parts show a high degree of uncertainty regarding failure characteristics,quality conditions,and remaining life,which seriously affects the efficiency of a remanufacturing scheme *** to address this problem,a remanufacturing scheme design method based on the reconstruction of incomplete information of used parts is ***,the remaining life of the reconstructed model is predicted by finite element analysis,and the demand for the next life cycle is ***,the scanned 3D damage point cloud data are registered with the original point cloud data using the integral iterative method to construct a missing point cloud model to achieve the restoration of geometric ***,according to reverse engineering and laser cladding remanufacturing,the tool remanufacturing process path can be generated by the tool contact point path section line ***,the proposed method is adopted for turbine blades to evaluate the effectiveness and feasibility of the proposed *** study proposes a remanufacturing scheme design method based on the incomplete reconstruction of used part information to solve the uncertain and highly personalized problems in remanufacturing.

关键词： Remanufacturing Incomplete information Unit-step integration iteration method

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：