检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Goswami, Dipam Liu, Yuyang Twardowski, Bartlomiej van de Weijer, Joost Department of Computer Science Universitat Autònoma de Barcelona Spain Computer Vision Center Barcelona Spain University of Chinese Academy of Sciences China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM. © 2023, CC BY.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Clustering-Based Resource Management for Consumer Cost Optimization in IoT Edge Computing Environments

引用

IEEE Transactions on Consumer Electronics 2024年 1-1页

作者： Denden, Mohsen Jemmali, Mahdi Boulila, Wadii Soni, Mukesh Khan, Faheem Ahmad, Jawad Department of Computer and Information Technologies College of Telecommunication and Information CTI Riyadh Saudi Arabia Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah UAE Robotics and Internet-of-Things Laboratory Prince Sultan University Riyadh Saudi Arabia Department of CSE University Centre for Research and Development Chandigarh University Mohali Punjab- India Department of Computer Engineering Gachon University Seongnam-si South Korea School of Computing Engineering and the Built Environment Edinburgh Napier University U.K

Edge computing emerges as a pivotal model in the era of next-generation consumer electronics and the emerging challenges of multimodal data-driven decision-making. Specifically, edge computing offers an open computing architecture for the vast and diverse consumer multimodal data generated by mobile computing and Internet of Things (IoT) technologies. While edge computing is instrumental in optimizing latency and bandwidth control in processing consumer multimodal data, the viability of employing edge resources is complicated by high service costs and the complexities of managing multimodal data diversity. This study introduces an innovative optimization method for distributing multimodal data on edge storage, considering both the I/O (input/output) speed and the overall distribution cost. The core part of our approach is the deployment of intelligent algorithms that ensure equitable data distribution across storage servers, thus eliminating unused space and reducing extra costs. Given the complexity of this NP-hard (non-deterministic polynomial-time) challenge, our study reveals a unique model incorporating an edge-broker component in combination with novel algorithms. The proposed algorithms aim to harmonize data distribution and reduce resource allocation expenses in a multimodal edge environment. Our proposed approach achieves excellent results, highlighting the efficacy of the proposed algorithms in several parameters such as makespan, cost, multimodal data security, and total processing time. Empirical tests reveal that the BCA (Best Clustering Algorithm) performs best, achieving a minimum load balancing rate of 92.2%, an average variance of 0.04, and an average run time of 0.56 seconds. IEEE

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Tactile Sensor-Based Detection of Partial Foothold for Balance Control in Humanoid Robots

Tactile Sensor-Based Detection of Partial Foothold for Balan...

引用

IEEE-RAS International Conference on Humanoid Robots

作者： Taro Tako Rafael Cisneros-Limón Hiroshi Kaminaga Kenji Kaneko Masaki Murooka Iori Kumagai Hiroaki Masuzawa Yohei Kakiuchi Department of Computer Science and Engineering Toyohashi University of Technology Toyohashi Japan CNRS-AIST JRL (Joint Robotics Laboratory) UMI3218/IRL National Institute of Advanced Industrial Science and Technology (AIST) Tsukuba Japan IRES2 Toyohashi University of Technology Toyohashi Japan

ISBN: (数字)9798350373578

ISBN: (纸本)9798350373585

This paper proposes a tactile sensor array to detect partial footholds and a wrench control method for biped humanoid robots using detected partial footholds. The proposed tactile sensor adopts a high-density FSR (Force Sensitive Resistor) array. It can read data within milliseconds. Filtering methods for its high-speed data which provide accurate estimation of contact areas are also proposed. They enable the computation of optimal contact forces. A wrench control method for biped humanoid robots, based on contact area information from detected partial footholds, enables stable force control even in partial foothold situations. The effectiveness of this advanced control system is evaluated through stabilizing and climbing stepladder experiments on partial footholds using an actual humanoid robot.

关键词： Legged locomotion Torque Force measurement Force Tactile sensors Humanoid robots Estimation Torque measurement Foot Sensor arrays

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2024年

作者： Lin, Zhenchao He, Li Yang, Hongqiang Sun, Xiaoqun Zhang, Guojin Chen, Weinan Guan, Yisheng Zhang, Hong School of Electromechanical Engineering Guangdong University of Technology Guangzhou China Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China Meituan Technology Co. Ltd Shenzhen China

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling Transformer to deal with large-scale point cloud. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently. The code is available at https://***/Sylva-Lin/SWCF-Net Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fetal Ultrasound Standard Plane Extraction using Orthogonal Triple-slice Deep Reinforcement Learning Agent

Fetal Ultrasound Standard Plane Extraction using Orthogonal ...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Baichuan Jiang Keshuai Xu Ernest Graham Russell H. Taylor Jeeun Kang Mathias Unberath Emad M. Boctor Department of Computer Science Johns Hopkins University Baltimore Maryland Department of Gynecology and Obstetrics Johns Hopkins Medical Institute Baltimore Maryland Department of Anesthesiology and Critical Care Medicine Johns Hopkins Medical Institute Baltimore Maryland Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore Maryland

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Using ultrasound for fetal anatomical survey and fetal growth monitoring can be challenging and tedious as sonographers need to manually search for a set of standard planes (SPs) using a 2D ultrasound probe. A desirable alternative is using a 3D ultrasound device, either hand-held or wearable, to capture large field-of-view volumetric images and apply an image analysis algorithm to automatically extract the target SPs. Prior work has been conducted to formulate this problem as iteratively moving a 6-degree-of-freedom 2D resampling plane toward the target viewing pose. However, views with insufficient anatomical information can lead to incorrect actions thus poor results for SP *** this work, we propose to extend the 6-degree-of-freedom plane agent and leverage the two other resampling views orthogonal to the original plane to incorporate more context information for adaptive action prediction based on the most informative view. Experiments have been conducted on a preliminary clinical ultrasound dataset and the results show that with adaptive view selection, our algorithm can extract fetal biparietal diameter plane with an average plane localization error of 7.09 mm and 8.01 deg, comparing to the error of 25.35 mm and 35.15 deg when using a single view.

关键词： Surveys Location awareness Ultrasonic imaging Three-dimensional displays Image analysis Prediction algorithms Probes Standards Monitoring Frequency control

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of a Fiber Bragg Grating Shape Sensor for Shape Reconstruction of a Continuum Manipulator

arXiv

引用

arXiv 2023年

作者： Amirkhani, Golchehr Goodridge, Anna Esfandiari, Mojtaba Phalen, Henry Ma, Justin H. Iordachita, Iulian Armand, Mehran Department of Mechanical Engineering Johns Hopkins University BaltimoreMD21218 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States Department of orthopaedic Surgery The Department of Mechanical Engineering The Department of Computer Science

Continuum dexterous manipulators (CDMs) are suitable for performing tasks in a constrained environment due to their high dexterity and maneuverability. Despite the inherent advantages of CDMs in minimally invasive surgery, real-time control of CDMs’ shape during non-constant curvature bending is still challenging. This study presents a novel approach for the design and fabrication of a large deflection fiber Bragg grating (FBG) shape sensor embedded within the lumens inside the walls of a CDM with a large instrument channel. The shape sensor consisted of two fibers, each with three FBG nodes. A shape-sensing model was introduced to reconstruct the centerline of the CDM based on FBG wavelengths. Different experiments, including shape sensor tests and CDM shape reconstruction tests, were conducted to assess the overall accuracy of the shape sensing. The FBG sensor evaluation results revealed the linear curvature-wavelength relationship with the large curvature detection of 0.045 mm at a 90◦ bending angle and a sensitivity of up to 5.50 nm/mm in each bending direction. The CDM’s shape reconstruction experiments in a free environment demonstrated the shape tracking accuracy of 0.216±0.126 mm for positive/negative deflections. Also, the CDM shape reconstruction error for three cases of bending with obstacles were observed to be 0.436±0.370 mm for the proximal case, 0.485±0.418 mm for the middle case, and 0.312±0.261 mm for the distal case. This study indicates the adequate performance of the FBG sensor and the effectiveness of the model for tracking the shape of the large-deflection CDM with nonconstant-curvature bending for minimally-invasive orthopaedic applications. © 2023, CC BY.

关键词： Fiber Bragg gratings

来源：评论

学校读者我要写书评

暂无评论

Effective Imaging Window Analysis for Wearable Ultrasound Device Using Fetal MRI

Effective Imaging Window Analysis for Wearable Ultrasound De...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Baichuan Jiang Keshuai Xu Yunpu Zhang Ernest Graham Russell H. Taylor Mathias Unberath Jeeun Kang Emad M. Boctor Department of Computer Science Johns Hopkins University Baltimore Maryland Department of Gynecology and Obstetrics Johns Hopkins Medical Institute Baltimore Maryland Department of Anesthesiology and Critical Care Medicine Johns Hopkins Medical Institute Baltimore Maryland Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore Maryland

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Wearable ultrasound devices can play a key role and enable revolutionary workflows in fetal monitoring applications in both antepartum and intrapartum phase of pregnancy. However, the fundamental question for developing wearable fetal monitoring solutions is whether the sensor is capable of performing continuous monitoring while being placed at a fixed location with minimum instruction to the user. Therefore, in this work, we developed a validation workflow using fetal MRI images to virtually place the wearable ultrasound scanner and examine the feasible placement window given the scanner design. This allows any scanner design being validated and optimized even before production. We showed that a scanner with a cone-shaped field-of-view with 18cm imaging depth can successfully monitor both the key heart and brain features throughout the critical period of delivery for fetal hypoxic-ischemic encephalopathy detection.

关键词： Pregnancy Performance evaluation Heart Ultrasonic imaging Magnetic resonance imaging Production Feature extraction Biomedical monitoring Monitoring Frequency control

来源：评论

学校读者我要写书评

暂无评论

Optical tomography-guided system for pre-clinical radiotherapy research

Optical tomography-guided system for pre-clinical radiothera...

引用

2023 Digital Holography and Three-Dimensional Imaging, DH 2023 in Optica Imaging Congress - Part of Imaging and Applied Optics Congress 2023

作者： Wang, Ken Kang-Hsin Xu, Xiangkun Deng, Zijian Tong, Zhishen Tsai, Yupei Iordachita, Iulian Dehghani, Hamid Wong, John W. Department of Radiation Oncology University of Texas Southwestern Medical Center DallasTX75390 United States Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD21218 United States School of Computer Science University of Birmingham Edgbaston BirminghamB15 2TT United Kingdom Department of Radiation Oncology and Molecular Radiation Sciences Johns Hopkins University BaltimoreMD21287 United States

We advance the in vivo cancer imaging capability of small animal irradiators to include bioluminescence and fluorescence tomography. The imaging system is expected to enhance preclinical radiation guidance and assessm... 详细信息

ISBN: (纸本)9781957171289

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

Adaptive Generalized Social Space Delimitation for Human-Robot Interaction Tasks

Adaptive Generalized Social Space Delimitation for Human-Rob...

引用

IEEE Latin American robotics Symposium, LARS

作者： Manuela M. F. Silva Aline F. F. Silva Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Belo Horizonte MG Brazil Laboratório de Inteligência Computacional e Robótica (LICRo) Instituto Federal do Triângulo Mineiro (IFTM) Campus Patrocínio Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

Human-Robot Interaction (HRI) research is of paramount importance as it addresses the rapidly evolving landscape where robots are increasingly integrated into everyday life. Social spaces refer to the invisible zones that individuals maintain around themselves, dictating appropriate distances for various types of interactions. This concept is pivotal in HRI, as it ensures that robots engage with humans in ways that are both comfortable and respectful of personal boundaries. In this paper, we propose a novel social space delimitation approach based on deformable elastic bands. Our method leverages the flexibility and adaptability of elastic band theory to dynamically define and adjust social spaces around individuals and groups. The results, based on both static and dynamic cases as well as a real-world dataset, show that our approach achieves a responsive and accurate representation of social spaces, that can accommodate varying group configurations and environmental conditions.

关键词： Accuracy Human-robot interaction Robots

来源：评论

学校读者我要写书评

暂无评论

Study of Helicopter Optimal Autorotation Landing Procedure in Tail Rotor Drive Failure

Study of Helicopter Optimal Autorotation Landing Procedure i...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Yan, Xufei Chen, Renliang Zhu, Shiqiang Xie, Anhuan Gu, Jason Research Center for Intelligent Robotics Zhejiang Lab Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China National Key Laboratory of Science and Technology on Rotorcraft Aeromechanics College of Aeronautics Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

This paper investigates the optimal landing trajectory and control procedure when a helicopter undergoes autorotation due to tail rotor drive failure (TRDF), in which an optimal control methodology is proposed. First, a helicopter flight dynamics model with TRDF was developed. Then, the autorotation in TRDF was converted to be a nonlinear optimal control problem, solved by direct node collocation method and sequential quadratic programming algorithm. Finally, a model helicopter (Z11) with single main rotor and tail rotor was used to demonstrate the proposed approach. An optimal autorotation landing procedure in TRDF was determined accordingly. Results indicate that the airframe will immediately respond to the excess torque generated by the main rotor via yawing, sideslip and rolling when TRDF occurs. The pilot is recommended to shut down the engine and perform a series of critical operations to stabilize the violent yaw and roll movements. In addition, flight test data were used to validate the numerical simulations of autorotation landing. The proposed optimal control approach provides a useful tool to investigate helicopter TRDF autorotation landing procedure. © 2022 IEEE.

关键词： Helicopters

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：