检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ma, Jun Cheng, Zilong Zhu, Haiyue Li, Xiaocong Tomizuka, Masayoshi Lee, Tong Heng Robotics and Autonomous Systems Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Singapore Institute of Manufacturing Technology Singapore138634 Singapore John A. Paulson School of Engineering and Applied Sciences Harvard University CambridgeMA02138 United States Department of Mechanical Engineering University of California BerkeleyCA94720 United States

Magnetic levitation positioning technology has attracted considerable research efforts and dedicated attention due to its extremely attractive features. The technology offers high-precision, contactless, dust/lubricant-free, multi-axis, and large-stroke positioning. In this work, we focus on the accurate and smooth tracking problem of a multi-axis magnetically levitated (maglev) planar positioning system for a specific S-curve reference trajectory. The floating characteristics and the multi-axis coupling make accurate identification of the system dynamics difficult, which lead to a challenge to design a high performance control system. Here, the tracking task is achieved by a 2-Degree of Freedom (DoF) controller consisting of a feedforward controller and a robust stabilizing feedback controller with a prescribed sparsity pattern. The approach proposed in this paper utilizes the basis of an H∞ controller formulation and a suitably established convex inner approximation. Particularly, a subset of robust stabilizable controllers with prescribed structural constraints is characterized in the parameter space, and so thus the re-formulated convex optimization problem can be easily solved by several powerful numerical algorithms and solvers. With this approach, the robust stability of the overall system is ensured with a satisfactory system performance despite the presence of parametric uncertainties. Furthermore, experimental results clearly demonstrate the effectiveness of the proposed approach. Copyright © 2021, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

One to many: Adaptive instrument segmentation via meta learning and dynamic online adaptation in robotic surgical video

arXiv

引用

arXiv 2021年

作者： Zhao, Zixu Jin, Yueming Lu, Bo Ng, Chi-Fai Dou, Qi Liu, Yun-Hui Heng, Pheng-Ann The Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong The T Stone Robotics Institute The Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China The Department of Surgery The Chinese University of Hong Kong Hong Kong

Surgical instrument segmentation in robot-assisted surgery (RAS) - especially that using learning-based models - relies on the assumption that training and testing videos are sampled from the same domain. However, it is impractical and expensive to collect and annotate sufficient data from every new domain. To greatly increase the label efficiency, we explore a new problem, i.e., adaptive instrument segmentation, which is to effectively adapt one source model to new robotic surgical videos from multiple target domains, only given the annotated instruments in the first frame. We propose MDAL, a meta-learning based dynamic online adaptive learning scheme with a two-stage framework to fast adapt the model parameters on the first frame and partial subsequent frames while predicting the results. MDAL learns the general knowledge of instruments and the fast adaptation ability through the video-specific meta-learning paradigm. The added gradient gate excludes the noisy supervision from pseudo masks for dynamic online adaptation on target videos. We demonstrate empirically that MDAL outperforms other state-of-the-art methods on two datasets (including a real-world RAS dataset). The promising performance on ex-vivo scenes also benefits the downstream tasks such as robot-assisted suturing and camera control. Copyright © 2021, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

An automatic approach for the classification of ancient clay statuettes based on heads features recognition

An automatic approach for the classification of ancient clay...

引用

2019 Eurographics Workshop on Graphics and Cultural Heritage, GCH 2019

作者： Scalas, A. Vassallo, V. Mortara, M. Spagnuolo, M. Hermon, S. Institute of Applied Mathematics and Information Technologies 'Enrico Magenes National Research Council Italy Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genova Italy Science and Technology for Archaeology Research Center Cyprus Institute Cyprus Department of Archaeology and Ancient History Lund University Sweden

ISBN: (纸本)9783038680826

In recent years, quantitative approaches based on mathematical theories and ICT tools, known under the terms of digital, computational, and virtual archaeology, are more and more involved in the traditional archaeological research. In this paper, we apply shape analysis techniques to 3D digital replicas of archaeological findings to support their interpretation. In particular, our study focuses on a collection of small terracotta figurines from the ancient sanctuary of Ayia Irini, Cyprus, and it aims at re-analysing the material utilising a quantitative approach. We experiment state of the art techniques (meshSIFT and DBSCAN) to cluster statuettes according to the similarity of their heads, to investigate their production process. © 2019 Eurographics Association.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Overcoming Data Scarcity in Speaker Identification: Dataset Augmentation with Synthetic MFCCs via Character-level RNN

Overcoming Data Scarcity in Speaker Identification: Dataset ...

引用

IEEE International Conference on Autonomous Robot systems and Competitions (ICARSC)

作者： Jordan J. Bird Diego R. Faria Cristiano Premebida Anikó Ekárt Pedro P. S. Ayrosa ARVIS Lab Aston University Birmingham UK Institute of Systems and Robotics University of Coimbra Coimbra Portugal School of Engineering and Applied Science Aston University Birmingham UK Department of Computer Science Universidade Estadual de Londrina Londrina Brazil

ISBN: (数字)9781728170787

ISBN: (纸本)9781728170794

Autonomous speaker identification suffers issues of data scarcity due to it being unrealistic to gather hours of speaker audio to form a dataset, which inevitably leads to class imbalance in comparison to the large data availability from non-speakers since large-scale speech datasets are available online. In this study, we explore the possibility of improving speaker recognition by augmenting the dataset with synthetic data produced by training a Character-level Recurrent Neural Network on a short clip of five spoken sentences. A deep neural network is trained on a selection of the Flickr8k dataset as well as the real and synthetic speaker data (all in the form of MFCCs) as a binary classification problem in order to discern the speaker from the Flickr speakers. Ranging from 2,500 to 10,000 synthetic data objects, the network weights are then transferred to the original dataset of only Flickr8k and the real speaker data, in order to discern whether useful rules can be learnt from the synthetic data. Results for all three subjects show that fine-tune learning from datasets augmented with synthetic speech improve the classification accuracy, F1 score, precision, and the recall when applied to the scarce real data vs non-speaker data. We conclude that even with just five spoken short sentences, data augmentation via synthetic speech data generated by a Char- RNN can improve the speaker classification process. Accuracy and related metrics are shown to improve from around 93% to 99% for three subjects classified from thousands of others when fine-tuning from exposure to 2500-1000 synthetic data points. High F1 scores, precision and recall also show that issues due to class imbalance are also solved.

关键词： Data models Mel frequency cepstral coefficient Recurrent neural networks Speech recognition Speaker recognition Human-robot interaction Autonomous systems

来源：评论

学校读者我要写书评

暂无评论

Variable Stiffness Control with Strict Frequency Domain Constraints for Physical Human-Robot Interaction

arXiv

引用

arXiv 2020年

作者： Zou, Wulin Duan, Pu Chen, Yawen Yu, Ningbo Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Xeno Dynamics Co. Ltd Shenzhen China Institute of Robotics and Automatic Information Systems Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China

Variable impedance control is advantageous for physical human-robot interaction to improve safety, adaptability and many other aspects. This paper presents a gain-scheduled variable stiffness control approach under strict frequency-domain constraints. Firstly, to reduce conservativeness, we characterize and constrain the impedance rendering, actuator saturation, disturbance/noise rejection and passivity requirements into their specific frequency bands. This relaxation makes sense because of the restricted frequency properties of the interactive robots. Secondly, a gain-scheduled method is taken to regulate the controller gains with respect to the desired stiffness. Thirdly, the scheduling function is parameterized via a nonsmooth optimization method. Finally, the proposed approach is validated by simulations, experiments and comparisons with a gain-fixed passivity-based PID method. Copyright © 2020, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Emergency Clinical Procedure Detection With Deep Learning

Emergency Clinical Procedure Detection With Deep Learning

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Lingfeng Li Richard A. Paris Conner Pinson Yan Wang Joseph Coco Jamison Heard Julie A. Adams Daniel V. Fabbri Bobby Bodenheimer Department of Electrical Engineering and Computer Science Vanderbilt University Nashville Tennessee Vanderbilt University Medical Center Nashville Tennessee Department of Electrical and Microelectronic Engineering Rochester Institute of Technology Rochester NY Collaborative Robotics and Intelligent Systems Institute Oregon State University Oregon

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Information about a patient's state is critical for hospitals to provide timely care and treatment. Prior work on improving the information flow from emergency medical services (EMS) to hospitals demonstrated the potential of using automated algorithms to detect clinical procedures. However, prior work has not made effective use of video sources that might be available during patient care. In this paper we explore the use convolutional neural networks (CNNs) on raw video data to determine how well video data alone can automatically identify clinical procedures. We apply multiple deep learning models to this problem, with significant variation in results. Our findings indicate performance improvements compared to prior work, but also indicate a need for more training data to reach clinically deployable levels of success.

关键词： Adaptation models Training Testing Machine learning Hospitals Cameras

来源：评论

学校读者我要写书评

暂无评论

Guest editorial: Image analysis in dermatology

引用

Medical Image Analysis 2022年第0期79卷 1页

作者： Celebi, M. Emre Barata, Catarina Halpern, Allan Tschandl, Philipp Combalia, Marc Liu, Yuan Department of Computer Science and Engineering University of Central Arkansas 201 Donaghey Ave. ConwayAR72035 United States Institute for Systems and Robotics University of Lisbon Av. Rovisco Pais 1 Torre Norte Lisbon1049-001 Portugal Dermatology Service Memorial Sloan Kettering Cancer Center 1275 York Ave. New York CityNY10065 United States Department of Dermatology Medical University of Vienna Spitalgasse 23 Vienna1090 Austria Hospital Clinic of Barcelona C. de Villarroel 170 Barcelona08036 Spain Google Health 3400 Hillview Ave. Palo AltoCA94304 United States

来源：评论

学校读者我要写书评

暂无评论

A Tendon-Driven Robotic Dexterous Hand Design for Grasping 4th

A Tendon-Driven Robotic Dexterous Hand Design for Grasping

引用

4th International Conference on Cognitive systems and Information Processing, ICCSIP 2018

作者： Xia, Ziwei Yuan, Jiahui Fang, Bin Sun, Fuchun Zhu, Chang Yang, Yiyong Min, Huasong State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science and Technology Tsinghua University Haidian District Beijing100083 China Beijing100083 China Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology Wuhan430081 China Beijing China

ISBN: (纸本)9789811379826

This paper focuses on the research of humanoid dexterous hand with tendon-driven. The structure of the dexterous hand is designed and its kinematics, dynamics and the relationship between the finger joints and the fingertip force are deduced. Then, based on the characteristics of the dexterous hand, a hierarchical control system is proposed and fuzzy adaptive PID is used as the motor control algorithm. The grasping experiments are implemented and the results indicate the hand has well performance. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Correction to: SleepBoost: a multi‑level tree‑based ensemble model for automatic sleep stage classification

引用

Medical & biological engineering & computing 2024年第9期62卷 2785页

作者： Akib Zaman Shiu Kumar Swakkhar Shatabda Iman Dehzangi Alok Sharma Computer Science and Artificial Intelligence Laboratory (CSAIL) Electrical Engineering and Computer Science Department Massachusetts Institute of Technology Cambridge MA USA. School of Electrical & Electronics Engineering Fiji National University Suva Fiji. shiu.kumar@fnu.ac.fj. Centre for Artificial Intelligence and Robotics (CAIR) United International University Dhaka Bangladesh. Department of Computer Science Rutgers University Camden NJ USA. Center for Computational and Integrative Biology Rutgers University Camden USA. Laboratory for Medical Science Mathematics RIKEN Center for Integrative Medical Sciences Yokohama 230‑0045 Japan. Institute for Integrated and Intelligent Systems Griffith University Nathan Brisbane QLD Australia.

来源：评论

学校读者我要写书评

暂无评论

A Survey on Deep Learning for Skin Lesion Segmentation

arXiv

引用

arXiv 2022年

作者： Mirikharaji, Zahra Abhishek, Kumar Bissoto, Alceu Barata, Catarina Avila, Sandra Valle, Eduardo Celebi, M. Emre Hamarneh, Ghassan Medical Image Analysis Lab School of Computing Science Simon Fraser University BurnabyV5A 1S6 Canada Institute for Systems and Robotics Instituto Superior Técnico Avenida Rovisco Pais Lisbon1049-001 Portugal RECOD.ai Lab Institute of Computing University of Campinas Av. Albert Einstein 1251 Campinas13083-852 Brazil RECOD.ai Lab School of Electrical and Computing Engineering University of Campinas Av. Albert Einstein 400 Campinas13083-952 Brazil Department of Computer Science and Engineering University of Central Arkansas 201 Donaghey Ave. ConwayAR72035 United States

Skin cancer is a major public health problem that could benefit from computer-aided diagnosis to reduce the burden of this common disease. Skin lesion segmentation from images is an important step toward achieving this goal. However, the presence of natural and artificial artifacts (e.g., hair and air bubbles), intrinsic factors (e.g., lesion shape and contrast), and variations in image acquisition conditions make skin lesion segmentation a challenging task. Recently, various researchers have explored the applicability of deep learning models to skin lesion segmentation. In this survey, we cross-examine 177 research papers that deal with deep learning-based segmentation of skin lesions. We analyze these works along several dimensions, including input data (datasets, preprocessing, and synthetic data generation), model design (architecture, modules, and losses), and evaluation aspects (data annotation requirements and segmentation performance). We discuss these dimensions both from the viewpoint of select seminal works, and from a systematic viewpoint, examining how those choices have influenced current trends, and how their limitations should be addressed. To facilitate comparisons, we summarize all examined works in a comprehensive table as well as an interactive table available online. Copyright © 2022, The Authors. All rights reserved.

关键词： computer aided diagnosis

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：