检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Muratore, Fabio Ramos, Fabio Turk, Greg Yu, Wenhao Gienger, Michael Peters, Jan Intelligent Autonomous Systems Group Technical University of Darmstadt Germany Honda Research Institute Europe Offenbach Am Main Germany School of Computer Science University of Sydney Australia NVIDIA SeattleWA United States Georgia Institute of Technology AtlantaGA United States Robotics at Google Mountain ViewCA United States

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real). Despite becoming increasingly realistic, all simulators are by construction based on models, hence inevitably imperfect. This raises the question of how simulators can be modified to facilitate learning robot control policies and overcome the mismatch between simulation and reality, often called the 'reality gap'. We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named 'domain randomization' which is a method for learning from randomized simulations. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MoDL-QSM: Model-based deep learning for quantitative susceptibility mapping

arXiv

引用

arXiv 2021年

作者： Feng, Ruimin Zhao, Jiayi Wang, He Yang, Baofeng Feng, Jie Shi, Yuting Zhang, Ming Liu, Chunlei Zhang, Yuyao Zhuang, Jie Wei, Hongjiang School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China School of Psychology Shanghai University of Sport Shanghai China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA United States Helen Wills Neuroscience Institute University of California BerkeleyCA United States School of Information and Science and Technology ShanghaiTech University Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China

Quantitative susceptibility mapping (QSM) has demonstrated great potential in quantifying tissue susceptibility in various brain diseases. However, the intrinsic ill-posed inverse problem relating the tissue phase to the underlying susceptibility distribution affects the accuracy for quantifying tissue susceptibility. Recently, deep learning has shown promising results to improve accuracy by reducing the streaking artifacts. However, there exists a mismatch between the observed phase and the theoretical forward phase estimated by the susceptibility label. In this study, we proposed a model-based deep learning architecture that followed the STI (susceptibility tensor imaging) physical model, referred to as MoDL-QSM. Specifically, MoDL-QSM accounts for the relationship between STI-derived phase contrast induced by the susceptibility tensor terms (χ13, χ23 and χ33) and the acquired single-orientation phase. The convolution neural networks are embedded into the physical model to learn a regularization term containing prior information. χ33 and phase induced by χ13 and χ23 terms were used as the labels for network training. Quantitative evaluation metrics (RSME, SSIM, and HFEN) were compared with recently developed deep learning QSM methods. The results showed that MoDL-QSM achieved superior performance, demonstrating its potential for future applications. Copyright © 2021, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards to robust and generalized medical image segmentation framework

arXiv

引用

arXiv 2021年

作者： Chen, Yurong Zhang, Hui Wang, Yaonan Liu, Lizhu Wu, Q.M. Jonathan Yang, Yimin National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Hunan Changsha410082 China Department of Electrical and Computer Engineering University of Windsor WindsorONN9B3P4 Canada Department of Computer Science Lakehead University Vector Institute TorontoM5G 1M1 Canada

—To mitigate the radiologist’s workload, computer-aided diagnosis with the capability to review and analyze medical images is gradually deployed. Deep learning-based region of interest segmentation is among the most exciting use cases. However, this paradigm is restricted in real-world clinical applications due to the poor robustness and generalization. The issue is more sinister with a lack of training data. In this paper, we address the challenge from the representation learning point of view. We investigate that the collapsed representations, as one of the main reasons which caused poor robustness and generalization, could be avoided through transfer learning. Therefore, we propose a novel two-stage framework for robust generalized segmentation. In particular, an unsupervised Tile-wise AutoEncoder (T-AE) pretraining architecture is coined to learn meaningful representation. Furthermore, this learned prior knowledge is transferred to the segmentation benchmark. Coupled with an image reconstruction network, the representation keeps to be decoded, encouraging the model to capture more semantic features. Experiments of lung segmentation on multi chest X-ray datasets are conducted. Empirically, the comprehensive results demonstrate the superior generalization capability of the proposed framework on unseen domains in terms of high performance and robustness to corruption, especially under the scenario of the limited training data. © 2021, CC BY.

关键词： computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

DeepDA: LSTM-based deep data association network for multi-targets tracking in clutter

arXiv

引用

arXiv 2019年

作者： Liu, Huajun Zhang, Hui Mertz, Christoph School of Computer Science and Engineering Nanjing University of Science and Technology Robotics Institute Carnegie Mellon University School of Computer Science and Engineering Nanjing University of Science and Technology Robotics Institute Carnegie Mellon University

The Long Short-Term Memory (LSTM) neural network based data association algorithm named as DeepDA for multi-target tracking in clutter is proposed to deal with the NPhard combinatorial optimization problem in this paper. Different from the classical data association methods involving complex models and accurate prior knowledge on clutter density, filter covariance or associated gating etc, data-driven deep learning methods have been extensively researched for this topic. Firstly, data association mathematical problem for multitarget tracking on unknown target number, missed detection and clutter, which is beyond one-to-one mapping between observations and targets is redefined formally. Subsequently, an LSTM network is designed to learn the measurement-to-track association probability from radar noisy measurements and existing tracks. Moreover, an LSTM-based data-driven deep neural network after a supervised training through the BPTT and RMSprop optimization method can get the association probability directly. Experimental results on simulated data show a significant performance on association ratio, target ID switching and time-consuming for tracking multiple targets even they are crossing each other in the complicated clutter environment. Copyright © 2019, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

UAV-assisted Data Collection in Wireless Powered Sensor Networks over Multiple Fading Channels

UAV-assisted Data Collection in Wireless Powered Sensor Netw...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Tharindu D. Ponnimbaduge Perera Stephan Panic Dushantha Nalin K. Jayakody P. Muthuchidambaranathan School of Computer Science and Robotics National Research Tomsk Polytechnic University RUSSIA Centre for Telecommunications Research School of Engineering Sri Lanka Technological Campus Padukka SRI LANKA National Institute of Technology Tiruchirappalli INDIA

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186962

Radio frequency energy harvesting (RF-EH) offers an unorthodox solution to the painstaking energy constraint drawback in wireless sensor networks (WSNs). In this paper, a data-gathering scenario from a UAV assisted WSN that consists of multiple sensor nodes (SNs) and power beacons (PBs) is considered. All the SNs are remotely powered by the PBs via wireless power transfer (WPT). In the first phase, a cluster-head (CH) is selected from the powered-up SNs and each SN periodically sends its observations to the CH. In the second phase, UAV powers the CH and collects the aggregated sensor observations from the CH. Under the assumption of Rayleigh and Rician fading channels, the outage probability at the UAV is derived and identified the time ratio of the proposed time-block structure that minimizes the outage probability. Furthermore, an effective algorithm is proposed to generate a solution for the process of CH selection. Finally, the achievable outage probability, throughput and the service range of the UAV are demonstrated for a given random setup of WSN through the theoretical and simulation results obtained.

关键词： Wireless sensor networks Data collection Probability Signal to noise ratio Power system reliability Unmanned aerial vehicles Lead

来源：评论

学校读者我要写书评

暂无评论

DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter

DeepDA: LSTM-based Deep Data Association Network for Multi-T...

引用

International Conference on Information Fusion

作者： Huajun Liu Hui Zhang Christoph Mertz School of Computer Science and Engineering Nanjing University of Science and Technology Robotics Institute Carnegie Mellon University School of Computer Science and Engineering Nanjing University of Science and Technology Robotics Institute Carnegie Mellon University

ISBN: (数字)9780996452786

ISBN: (纸本)9781728118406

The Long Short-Term Memory (LSTM) neural network based data association algorithm named as DeepDA for multi-target tracking in clutter is proposed to deal with the NP-hard combinatorial optimization problem in this paper. Different from the classical data association methods involving complex models and accurate prior knowledge on clutter density, filter covariance or associated gating etc, data-driven deep learning methods have been extensively researched for this topic. Firstly, data association mathematical problem for multitarget tracking on unknown target number, missed detection and clutter, which is beyond one-to-one mapping between observations and targets is redefined formally. Subsequently, an LSTM network is designed to learn the measurement-to-track association probability from radar noisy measurements and existing tracks. Moreover, an LSTM-based data-driven deep neural network after a supervised training through the BPTT and RMSprop optimization method can get the association probability directly. Experimental results on simulated data show a significant performance on association ratio, target ID switching and time-consuming for tracking multiple targets even they are crossing each other in the complicated clutter environment.

关键词： Radar tracking Clutter Target tracking Optimization Radar measurements Laser radar

来源：评论

学校读者我要写书评

暂无评论

Orientation Control of an Electromagnetically Actuated Soft-Tethered Colonoscope Based on 2OR Pseudo-Rigid-Body Model

Orientation Control of an Electromagnetically Actuated Soft-...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Yehui Li Weibing Li Wenci Xin Xue Zhang Yitian Xian Philip Wai Yan Chiu Zheng Li The Chinese University of Hong Kong Hong Kong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Chow Yuk Ho Technology Centre for Innovative Medicine The Chinese University of Hong Kong Hong Kong Chow Yuk Ho Technology Centre for Innovative Medicine Li Ka Shing Institute of Health Science and Multi-Scale Medical Robotics Center Ltd The Chinese University of Hong Kong Hong Kong

Colorectal cancer incidence has been steadily rising worldwide. Magnetic colonoscopes provide new approaches to conduct colon inspection and treatment. This paper presents a novel electromagnetically actuated soft-tethered colonoscope to achieve precise and stable orientation control. An inflated balloon is designed to eliminate the unpredictable disturbance of the floating tether. A 2OR Pseudo-Rigid-Body (PRB) model of the soft tether is developed to analyze the relationship between the tether deflection and applied force and torque. A closed-loop control framework is constructed with visual position feedback. Experiments are first conducted to validate the assumption of the PRB model and the efficacy of the magnetic field model. Then, trajectory tracking tasks and disturbance rejection tests are performed to validate the feasibility of the proposed solution and closed-loop control. Results show that the colonoscope can stably and accurately orient to the desired orientation with an absolute mean position error of less than 0.5 mm and an average velocity of 3.5 mm/s. The distal tip can quickly re-stabilize to the desired orientation even when a large disturbance exists.

关键词： Location awareness Visualization Torque Trajectory tracking Biological system modeling Position control Medical services

来源：评论

学校读者我要写书评

暂无评论

Design of a Highly Reliable SRAM Cell with Advanced Self-Recoverability from Soft Errors

Design of a Highly Reliable SRAM Cell with Advanced Self-Rec...

引用

International Test Conference in Asia (ITC-Asia)

作者： Zhengda Dou Albin Yan Jun Zhou Yuanjie Hu Yan Chen Tianming Ni Jie Cui Patrick Girard Xiaoqing Wen School of Computer Science and Technology Anhui University/Anhui Engineering Laboratory of IoT Security Technologies Hefei China College of Electrical Engineering Anhui Polytechnic University Wuhu China Laboratory of Informatics Robotics and Microelectronics of Montpellier University of Montpellier/CNRS Montpellier France Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan

ISBN: (数字)9781728189444

ISBN: (纸本)9781728189451

In this paper, a highly reliable SRAM cell, namely SESRS cell, is proposed. Since the cell has a special feedback mechanism among its internal nodes and has more access transistors compared to a standard SRAM cell, the SESRS cell provides the following advantages: (1) it can self-recover from single node upsets (SNUs) and double-node upsets (DNUs); (2) it can reduce power consumption by 49.78% and silicon area by 7.92%, compared with the only existing SRAM cell which can self-recover from all possible DNUs. Simulation results validate the robustness of the proposed SESRS cell. Moreover, compared with the state-of-the-art hardened SRAM cells, the proposed SESRS cell can reduce read access time by 61.93% on average.

关键词： SRAM cells Transistors Integrated circuit reliability Logic gates Standards Robustness Reliability engineering

来源：评论

学校读者我要写书评

暂无评论

Multiple-object tracking based on monocular camera and 3-D lidar fusion for autonomous vehicles

Multiple-object tracking based on monocular camera and 3-D l...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Chen, Hao Xue, Chunyue Liu, Shoubin Sun, Yuxiang Chen, Yongquan Shenzhen Institute of Artificial Intelligence and Robotics for Society China Institute of Robotics and Intelligent Manufacturing Chinese University of Hong Kong Shenzhen China Harbin Institute of Technology School of Mechanical Engineering and Automation Shenzhen China School of Science and Engineering Chinese University of Hong Kong Shenzhen China Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong

ISBN: (纸本)9781728163215

This article describes a multi-object tracking method through sensor fusion with a monocular camera and a 3-D Lidar for autonomous vehicles. Specifically, several pairwise costs from information, such as locations, movements, and poses of 3-D cues, are designed for tracking. These costs can complement each other to reduce matching errors during the tracking process. Moreover, they are efficient to be on-line computed with embedded equipment. We feed the pairwise costs to the data-association framework, which is based on the Hungarian algorithm, and then do the back-end fusion for the tracking results. The experimental results on our autonomous sightseeing car demonstrate that our tracking method could achieve accurate and robust results in real-world traffic scenarios. © 2019 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Correction to: A survey on COVID-19 impact in the healthcare domain: worldwide market implementation, applications, security and privacy issues, challenges and future prospects

引用

Complex & intelligent systems 2023年第2期9卷 2205页

作者： Tanzeela Shakeel Shaista Habib Wadii Boulila Anis Koubaa Abdul Rehman Javed Muhammad Rizwan Thippa Reddy Gadekallu Mahmood Sufiyan School of System and Technology University of Management and Technology Lahore Pakistan. Robotics and Internet of Things Lab Prince Sultan University Riyadh 12435 Saudi Arabia. Department of Cyber Security PAF Complex E-9 Air University Islamabad Pakistan. Department of Computer Science Kinnaird College for Women Lahore Pakistan. School of Information Technology and Engineering Vellore Institute of Technology Vellore India.

[This corrects the article DOI: 10.1007/s40747-022-00767-w.].

关键词：

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：