检索结果-内蒙古大学图书馆

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

作者： Jia Zhang Gaetano Scebba Walter Karlen Mobile Health Systems Lab Institute of Robotics and Intelligent Systems ETH Zurich Zurich Switzerland

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Respiratory rate (RR) can be estimated from the photoplethysmogram (PPG) recorded by optical sensors in wearable devices. The fusion of estimates from different PPG features has lead to an increase in accuracy, but also reduced the numbers of available final estimates due to discarding of unreliable data. We propose a novel, tunable fusion algorithm using covariance intersection to estimate the RR from PPG (CIF). The algorithm is adaptive to the number of available feature estimates and takes each estimates' trustworthiness into account. In a benchmarking experiment using the CapnoBase dataset with reference RR from capnography, we compared the CIF against the state-of-the-art Smart Fusion (SF) algorithm. The median root mean square error was 1.4 breaths/min for the CIF and 1.8 breaths/min for the SF. The CIF significantly increased the retention rate distribution of all recordings from 0.46 to 0.90 (p

关键词： Estimation Benchmark testing Robustness Correlation Biomedical monitoring Feature extraction Indexes

来源：评论

学校读者我要写书评

暂无评论

Data generation method for learning a low-dimensional safe region in safe reinforcement learning

arXiv

引用

arXiv 2021年

作者： Zhou, Zhehua Oguz, Ozgur S. Ren, Yi Leibold, Marion Buss, Martin Technical University of Munich Munich Germany Max Planck Institute for Intelligent Systems University of Stuttgart Stuttgart Germany Tencent Robotics X Lab Tencent Shenzhen China

Safe reinforcement learning aims to learn a control policy while ensuring that neither the system nor the environment gets damaged during the learning process. For implementing safe reinforcement learning on highly nonlinear and high-dimensional dynamical systems, one possible approach is to find a low-dimensional safe region via data-driven feature extraction methods, which provides safety estimates to the learning algorithm. As the reliability of the learned safety estimates is data-dependent, we investigate in this work how different training data will affect the safe reinforcement learning approach. By balancing between the learning performance and the risk of being unsafe, a data generation method that combines two sampling methods is proposed to generate representative training data. The performance of the method is demonstrated with a three-link inverted pendulum example. Copyright © 2021, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Modeling sensory adaptation to peripheral nerve stimulation

Modeling sensory adaptation to peripheral nerve stimulation

引用

International IEEE/EMBS Conference on Neural Engineering, CNE

作者： J. Kljajic G. Valle S. Raspopovic Institute Mihajlo Pupin Belgrade Serbia and School of Electrical Engineering University of Belgrade Serbia Neuroengineering Lab Institute for Robotics and Intelligent Systems ETH Zürich Switzerland

Neural adaptation is a well-known phenomenon of the human sensory systems. Prolonged stimulation of the sensory system causes the adaptation (e.g. reduced neural activity) of the afferent sensory inputs. Interestingly, the use of direct nerve stimulation using implanted electrodes has been shown as the promise for providing sensory feedback to amputees. Although this technique is proven to be able to convey several sensory information, sensory adaptation to the neural stimulation can cause some unwanted behavior (e.g., disappearing of the artificial sensation after few minutes, changes in the perceptual intensity over time). Here we present a computational model of the sensory adaptation to direct electrical nerve stimulation. The model considers important biological parameters (i.e. synaptic processes) together with the different stimulation parameters (i.e. stimulation amplitude and frequency). The model was fitted on experimental data collected in two human transfemoral amputees, who were implanted with four transverse intrafascicular multichannel electrodes (TIME) in their residual tibial nerve. This model is not only used to better understand the mechanisms of sensory adaptation to different neural stimulation strategies, but it could also be exploited in future in neuroprosthetic applications to predict and control sensory adaptation.

关键词： Electrodes Adaptation models Biological system modeling Computational modeling Neural activity Neural engineering Predictive models

来源：评论

学校读者我要写书评

暂无评论

Wearable bioimpedance for continuous and context-aware clinical monitoring

Wearable bioimpedance for continuous and context-aware clini...

引用

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

作者： Abhilash Guru Dutt Michaela Verling Walter Karlen Mobile Health Systems Lab Institute of Robotics and Intelligent Systems ETH Zurich Zurich Switzerland

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

Bioimpedance monitoring provides a non-invasive, safe and affordable opportunity to monitor total body water for a wide range of clinical applications. However, the measurement is susceptible to variations in posture and movement. Existing devices do not account for these variations and are therefore unsuitable to perform continuous measurements to depict trend changes. We developed a wearable bioimpedance monitoring system with embedded real-time posture detection using a distributed accelerometer network. We tested the device on 14 healthy volunteers following a standardized protocol of posture change and evaluated the agreement with a commercial device. The impedance showed a high correlation (r>0.98), a bias of -4.5 Ω, and limits of agreement of -30 and 21 Ω. Context-awareness was achieved with an accuracy of 94.6% by classifying data from two accelerometers placed at the upper and lower leg. The calculated current consumption of the system was as low as 10 mA during continuous measurement operation, suggesting that the system can be used for continuous measurements over multiple days without charging. The proposed motion-aware design will enable the measurement of relevant bioimpedance parameters over long periods and support informed clinical decision making.

关键词： Bioimpedance Accelerometers Electrodes Performance evaluation Current measurement Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Sample Efficiency Improved Method via Hierarchical Reinforcement Learning Networks

A Sample Efficiency Improved Method via Hierarchical Reinfor...

引用

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Qinghua Chen Evan Dallas Pourya Shahverdi Jessica Korneder Osamah A. Rawashdeh Wing-Yue Geoffrey Louie Intelligent Robotics Laboratory Oakland University MI USA College of Electrical and Information Engineering Zhengzhou University of Light Industry Henan China Applied Behavior Analysis Clinic Oakland University MI USA Embedded Systems Research Lab Oakland University MI USA

ISBN: (数字)9781728188591

ISBN: (纸本)9781665406802

Learning from demonstration (LfD) approaches have garnered significant interest for teaching social robots a variety of tasks in healthcare, educational, and service domains after they have been deployed. These LfD approaches often require a significant number of demonstrations for a robot to learn a performant model from task demonstrations. However, requiring non-experts to provide numerous demonstrations for a social robot to learn a task is impractical in real-world applications. In this paper, we propose a method to improve the sample efficiency of existing learning from demonstration approaches via data augmentation, dynamic experience replay sizes, and hierarchical Deep Q-Networks (DQN). After validating our methods on two different datasets, results suggest that our proposed hierarchical DQN is effective for improving sample efficiency when learning tasks from demonstration. In the future, such a sample-efficient approach has the potential to improve our ability to apply LfD approaches for social robots to learn tasks in domains where demonstration data is limited, sparse, and imbalanced.

关键词： Social robots Education Reinforcement learning Medical services Task analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-Robot System for Autonomous Cooperative Counter-UAS Missions: Design, Integration, and Field Testing

Multi-Robot System for Autonomous Cooperative Counter-UAS Mi...

引用

IEEE International Workshop on Safety, Security, and Rescue robotics (SSRR)

作者： Antonella Barisic Marlan Ball Noah Jackson Riley McCarthy Nasib Naimi Luca Strässle Jonathan Becker Maurice Brunner Julius Fricke Lovro Markovic Isaac Seslar David Novick Jonathan Salton Roland Siegwart Stjepan Bogdan Rafael Fierro Laboratory for Robotics and Intelligent Control Systems (LAR-ICS) Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Electrical and Computer Engineering Department University of New Mexico Albuquerque NM USA ETH Zurich Autonomous Systems Lab (ASL) Zurich Switzerland Sandia National Laboratories Albuquerque New Mexico USA

ISBN: (纸本)9781665456814

With the rapid development of technology and the proliferation of uncrewed aerial systems (UAS), there is an immediate need for security solutions. Toward this end, we propose the use of a multi-robot system for autonomous and cooperative counter-UAS missions. In this paper, we present the design of the hardware and software components of different complementary robotic platforms: a mobile uncrewed ground vehicle (UGV) equipped with a LiDAR sensor, an uncrewed aerial vehicle (UAV) with a gimbal-mounted stereo camera for air-to-air inspections, and a UAV with a capture mechanism equipped with radars and camera. Our proposed system features 1) scalability to larger areas due to the distributed approach and online processing, 2) long-term cooperative missions, and 3) complementary multimodal perception for the detection of multirotor UAVs. In field experiments, we demonstrate the integration of all subsystems in accomplishing a counter-UAS task within an unstructured environment. The obtained results confirm the promising direction of using multi-robot and multi-modal systems for C-UAS.

关键词： Scalability Robot vision systems Autonomous aerial vehicles Cameras Software Safety Security

来源：评论

学校读者我要写书评

暂无评论

Dynamic modeling and vibration analysis of a 6-DOFs industrial robot considering joint flexibility

Dynamic modeling and vibration analysis of a 6-DOFs industri...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Shen, Guodong Xu, Sheng Chen, Chunjie Wang, Qiang Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781665436786

For the industrial robots, the vibration caused by the joint flexibility could affect the manipulator's performance significantly. Therefore, the modeling and vibration analysis of industrial robot considering joint flexibility has become an important topic in recent years. However, the research on flexible-joint manipulator is usually performed for planar robots, whereas the research on general spatial multi degrees of freedom (DOFs) industrial robots are still limited. In this paper, the dynamic modeling approach is developed for vibration analysis of the serial industrial robot having six DOFs. Firstly, based on the Spong's model of joint deformation, the flexibility of all joints is considered concurrently, and the partial velocity relationship between each link and the joint are deduced. Then, the dynamic model of the 6-DOFs flexible robot is derived according to the Kane equation. The results using the proposed Kane-based method are verified by several numerical simulations. Finally, vibration responses of the end-effector under different joint stiffness parameters are analyzed. The results in this study can offer some useful guidance for the path planning and control to suppress the vibration of the multi-DOFs industrial robots. © 2021 IEEE.

关键词： Vibration analysis

来源：评论

学校读者我要写书评

暂无评论

A data-driven shared control system for exoskeleton rehabilitation robot

A data-driven shared control system for exoskeleton rehabili...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Li, Feng He, Yong Li, Jinke Ni, Jiangpeng Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China

ISBN: (纸本)9781665436786

It is very important to establish a control operating system for rehabilitation robots, especially to improve the rehabilitation effect and human-machine interaction ability of patients. Exoskeletons have been proved to be effective in providing highly repeatable and accurate rehabilitation exercises, but most existing exoskeletons have inconsistent operating systems and data loss. This paper designed a novel data-driven shared control system(DDSCS) farmework, applied to different exoskeleton rehabilitation robots (ERR). Due to the unique physical characteristics of exoskeleton rehabilitation robots, it can't be adapt to different patients. Firstly, the DDSCS framework is established via the data-driven and shared technology, and the feasibility is analyzed. Secondly, to iterate the individualized gait trajectory, data-driven gait trajectory correction model is designed. Finally, the shared human-machine interface is developed, and the superiority and effectiveness of DDSCS framework are verified by the exoskeleton robot experiments. © 2021 IEEE.

关键词： Control systems

来源：评论

学校读者我要写书评

暂无评论

Transferability of a Sensing Mattress for Posture Classification from Research into Clinics

Transferability of a Sensing Mattress for Posture Classifica...

引用

IEEE International Conference on Rehabilitation robotics (ICORR)

作者： Oriella Gnarra Alexander Breuss Lorenzo Rossi Manuel Fujs Samuel E.J. Knobel Jan D. Warncke Stephan M. Gerber Claudio L.A. Bassetti Robert Riener Tobias Nef Markus H. Schmidt Department of Neurology Sleep-Wake Epilepsy Center University Hospital of Bern Switzerland Department of Health Sciences and Technology Sensory-Motor Systems Lab Institute of Robotics and Intelligent Systems ETH Zurich ETH Zurich Switzerland Gerontechnology Rehabilitation Group ARTORG Centre for Biomedical Engineering Research University of Bern Switzerland Spinal Cord Injury Center University Hospital Balgrist Zurich Switzerland Ohio Sleep Medicine Institute Dublin Ohio USA

Sleep is crucial in rehabilitation processes, promoting neural plasticity and immune functions. Nocturnal body postures can indicate sleep quality and frequent repositioning is required to prevent bedsores for bedridden patients after a stroke or spinal cord injury. Polysomnography (PSG) is considered the gold standard for sleep assessment. Unobtrusive methods for classifying sleep body postures have been presented with similar accuracy to PSG, but most evaluations have been done in research lab environments. To investigate the challenges in the usability of a previously validated device in a clinical setting, we recorded the sleep posture of 17 patients with a sensorized mattress. Ground-truth labels were collected automatically from a PSG device. In addition, we manually labeled the body postures using video data. This allowed us also to evaluate the quality of the PSG labels. We trained neural networks based on the VGG-3 architecture to classify lying postures and used a self-label correction method to account for noisy labels in the training data. The models trained with the video labels achieved a higher classification accuracy than those trained with the PSG labels (0.79 vs. 0.68). The self-label correction could further increase the models' scores based on video and PSG labels to 0.80 and 0.70, respectively. Unobtrusive sensors validated in clinics can, therefore, potentially improve the quality of care for bedridden patients and advance the field of rehabilitation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Dynamic Routing Network for Monocular Depth Estimation 12

A New Dynamic Routing Network for Monocular Depth Estimation

引用

12th International Conference on CYBER Technology in Automation, Control, and intelligent systems, CYBER 2022

作者： Luo, Zhehao Luo, Sijin Liang, Guoyuan Wu, Xinyu Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China University of Chinese Academy of Sciences Beijing China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Chinese Academy of Sciences Guangdong Province Shenzhen China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Province Shenzhen China

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Depth estimation is an essential task for understanding the geometry of 3D scenes. Compared with multi-view-based methods, monocular depth estimation is more challenging for the requirement of integrating not only global information but also local cues from various parts. Recently, numerous Convolutional Neural Networks (CNNs) based approaches relying on pre-defined static architectures have been reported. Although many of them have achieved remarkable improvements in accuracy, there remains problem with the generality of the static model when it comes to diverse scenes. In this paper, a novel deep network with dynamic routing architecture is proposed with a dynamically adjustable structure with respect to different inputs, therefore leading to not only improvements on both accuracy and generality but also decrease of the model parameters. Extensive experiments of monocular depth estimation have been conducted on two well-known challenging datasets (i.e., NYUD-v2 and Make3D) as well as the mixed dataset, and have verified the effectiveness of the proposed dynamic framework. © 2022 IEEE.

关键词： Deep neural networks

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：