检索结果-内蒙古大学图书馆

Action recognition through fusion of sEMG and skeletal data in feature level

Journal of Ambient Intelligence and Humanized Computing 2022年第9期13卷 4125-4134页

作者： Wang, Xinming Ding, Weili Bian, Shuangshuang Liu, Honghai Department of Automation Institute of Electrical Engineering Key Laboratory of Intelligent Rehabilitation and Neuromodulation of Hebei Province Yanshan University 438 West of Hebei Avenue Haigang District Qinhuangdao066004 China School of Mechanical Engineering and Automation State Key Laboratory of Robotics and Systems Harbin Institute of Technology Shenzhen Nanshan District Shenzhen518055 China

Human action can be recognized through a unimodal way. However, the information obtained from a single mode is limited due to the fact that a single mode contains only one type of physical attribute. Therefore, it is motivational to improve the accuracy of actions through fusion of two different complementary modality, which are the surface electromyography (sEMG) and the skeletal data. In this paper, we propose a general framework of fusion of sEMG signals and skeletal data. Firstly, vector of locally aggregated descriptor (VLAD) was extracted from sEMG sequences and skeletal sequences, respectively. Secondly, features obtained from sEMG and skeletal data are mapped through different weighted kernels using multiple kernel learning. Finally, the classification results are obtained through the model of multiple kernel learning. A dataset of 18 types of human actions is collected via KinectV2 and Thalmic Myo armband to verify our ideas. The experimental results show that the accuracy of human action recognition are improved by combining skeletal data with sEMG signals. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

An Effective Two-time Scale Composite Control Contraction Based Chaotic Trajectory Tracking of Two-link Flexible Manipulator

An Effective Two-time Scale Composite Control Contraction Ba...

引用

IEEE Conference on Decision and Control

作者： Kshetrimayum Lochan Asim Khan Binoy Krishna Roy Bidyadhar Subudhi Lakmal Seneviratne Irfan Hussain Department of Mechanical Engineering Khalifa University Center for Robotics and Autonomous Systems (KUCARS) Khalifa University United Arab Emirates Department of Electrical Engineering National Institute of Technology Silchar India Department of Electrical Engineering National Institute of Technology Warangal India

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

In this paper, a two-link flexible manipulator n-dimensional model is developed using the assumed modes method. Based on this model, the manipulator dynamics are segregated into two subsystems by the two-time scale decomposition method of singular perturbation. Subsequently, a contraction-based control theory and a backstepping control of composite controller are investigated for the desired chaotic trajectory tracking along with tip deflection vibration suppression. In the two subsystems, the slow subsystem is involved in the modelling of the joint angles, and the fast subsystem is for corrected flexible modes of vibration suppression. In order to guarantee strict stability, Lyapunov’s stability is realized for closed-loop system uniform boundedness. Thus, by choosing the control parameters appropriately, the system states converge to a neighborhood of asymptotic stability. Eventually, extensive validation by comparative simulations of the Quanser model of the two-link flexible manipulator is carried out to demonstrate and indicate the effectiveness of the proposed composite controller in terms of faster tip deflection vibration suppression and better trajectory tracking.

关键词： Vibrations Asymptotic stability Backstepping Trajectory tracking Perturbation methods Stability analysis Robustness Control theory Complexity theory Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

A New Approach for Long-Term Demand Forecasting

SSRN

引用

SSRN 2024年

作者： Paulos, José Pedro Azevedo, Filipe Fidalgo, José Nuno INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal The Department of Electrical Engineering ISEP IPP - School of Engineering Polytechnic Institute of Porto Portugal The Department of Electrical Engineering and Computers of the Faculty of Engineering of the University of Porto Portugal INESC TEC Porto Portugal

The methodology adopted in this article is based on the principle that load diagrams to be forecasted have two distinct components: shape and magnitude. The present work was focused on the shape component, which was essentially defined by historic data and calendar information. The implemented approach was applied to five European countries using four years for training and one year for testing. The goal was to forecast the hourly demand diagram for an entire future year. The forecasting models were based on three forecasting techniques: General Regression Neural Networks (GRNN), Multiple Linear Regression (MLR), and Artificial Neural Networks (ANN). The performance analysis showed a mean absolute percentage error roughly between 2% and 6%, depending on the country and year being forecasted. Investigating the effect of temperature on predictions was the aim of a second study, which allows us to define uncertainty margins around the forecasted demand curve. This outcome is an essential element for power system planning. © 2024, The Authors. All rights reserved.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Modular Cyber-Physical System for Smart Industry: A case study on energy load disaggregation

Modular Cyber-Physical System for Smart Industry: A case stu...

引用

2023 International Conference on Control, Automation and Diagnosis, ICCAD 2023

作者： Alves, Jorge Sousa, Pedro Matos, Barbara Mendes, Jerome Souza, Francisco Matias, Tiago University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal Oncontrol Technologies Coimbra3000-108 Portugal Radboud University Dept. Analytical Chemistry & Chemometrics AJ Nijmegen6525 Netherlands

ISBN: (纸本)9798350347074

Constant changes have marked the industry, and cyber-physical systems have offered great potential in Industry 4.0 on production processes, allowing the integration of computational intelligence and real-time processing. In this context, this paper proposes a modular hardware system for industrial applications according to a plug & play concept. The proposed system comprises a processing module (mPP) and specific expansion modules (mEXs). The mPP is responsible for administrating the network/communication. It collects data from the mEXs, extracts features, processes the features through artificial intelligence, and interacts with the production process. The mEXs comprise sensors, conditioning circuits, and an analog/digital converter. They are responsible for acquiring field signals and their transmission to the mPP. The proposed system is designed for operating with electrical protection, allowing reliable operation of the mPP and mEXs. For evaluating and demonstrating the proposed system in a real scenario, we applied it in a case study for non-intrusive energy load disaggregation. © 2023 IEEE.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

A Manta Ray-Inspired Biosyncretic Robot with Stable Controllability by Dynamic Electric Stimulation

引用

Cyborg and Bionic systems 2022年第1期2022卷 314-326页

作者： Chuang Zhang Yiwei Zhang Wenxue Wang Ning Xi Lianqing Liu State Key Laboratory of Robotics Shenyang Inst itute of AutomationChinese Academy of SciencesShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China School of Automation and Electrical Engineering Shenyang Ligong University Shenyang 110159China Emerging Technologies Institute Department of Industrial Manufacturing Systems Engineering University of Hong KongPokfulamChina

Biosyncretic robots,which are new nature-based robots in addition to bionic robots,that utilize biological materials to realize their core function,have been supposed to further promote the progress in *** as the main operation mechanism relates to the robotic overall ***,biosyncretic robots actuated by living biological actuators have attracted increasing ***,innovative propelling modes and control methods are still necessary for the further development of controllable motion performance of biosyncretic *** this work,a muscle tissue-based biosyncretic swimmer with a manta *** propelling mode has been *** is more,to improve the stable controllability of the biosyncretic swimmer,a dynamic control method based on circularly distributed multiple electrodes(CDME)has been *** this method,the direction of the electric field generated by the CDME could be real-time controlled to be parallel with the adtuation tissue of the dynamic ***,the instability of the tissue actuation induced by the dynamic included angle between the tissue axis and electric field direction could be ***,the biosyncretic robot has demonstrated stable,controllable,and efective swimming,by adjusting the electric stimulation pulse direction,amplitude,and *** work may be beneficial for not only the development of biosyncretic robots but also other related studies including bionic design of soft robots and muscle tissue engineering.

关键词： Robot robot Dynamic

来源：评论

学校读者我要写书评

暂无评论

Approaching Test Time Augmentation in the Context of Uncertainty Calibration for Deep Neural Networks

arXiv

引用

arXiv 2023年

作者： Conde, Pedro Barros, Tiago Lopes, Rui L. Premebida, Cristiano Nunes, Urbano J. The Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Portugal Critical Software South Africa

With the rise of Deep Neural Networks, machine learning systems are nowadays ubiquitous in a number of real-world applications, which bears the need for highly reliable models. This requires a thorough look not only at the accuracy of such systems, but also at their predictive uncertainty. Hence, we propose a novel technique (with two different variations, named M-ATTA and V-ATTA) based on test time augmentation, to improve the uncertainty calibration of deep models for image classification. By leveraging an adaptive weighting system, M/V-ATTA improves uncertainty calibration without affecting the model’s accuracy. The performance of these techniques is evaluated by considering diverse metrics related to uncertainty calibration, demonstrating their robustness. Empirical results, obtained on CIFAR-10, CIFAR-100, Aerial Image Dataset, as well as in two different scenarios under distribution-shift, indicate that the proposed methods outperform several state-of-the-art post-hoc calibration techniques. Furthermore, the methods proposed also show improvements in terms of predictive entropy on out-of-distribution samples. Code for M/V-ATTA available at: https://***/pedrormconde/MV-ATTA Copyright © 2023, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Improving Lidar Based Tracking of UAVs Using an Approach Based on Focusing

Improving Lidar Based Tracking of UAVs Using an Approach Bas...

引用

Iberian robotics Conference (ROBOT)

作者： Alberto Cerutti Sedat Dogru Lino Marques Department of Electronics and Telecommunications (DET) Polytechnic University of Turin Turin Italy Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal

ISBN: (数字)9798350376364

ISBN: (纸本)9798350376371

This paper presents a novel approach for detecting drones using a lidar sensor integrated on a robotic turret. The turret rotates allowing the sensor to scan the sky, and both hardware components communicate in real-time. When the lidar sensor detects a drone, the detection data is used to dynamically adjust the motion pattern of the turret, allowing the system to capture more data by orienting the lidar sensor towards the drone, eventually improving tracking accuracy thanks to the higher number of detections achieved in this manner. In this paper we also explore different motion patterns for the turret, comparing them on the field to track a drone using the built lidar-turret system.

关键词： Laser radar Accuracy Uncertainty Tracking Focusing Robot sensing systems Real-time systems Hardware Optimization Drones

来源：评论

学校读者我要写书评

暂无评论

Camera Lidar Fusion for Unmanned Aerial Vehicle Detection

Camera Lidar Fusion for Unmanned Aerial Vehicle Detection

引用

Iberian robotics Conference (ROBOT)

作者： Cosimo Leuci Sedat Dogru Lino Marques Department of Electronics and Telecommunications (DET) Polytechnic University of Turin Turin Italy Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Coimbra Portugal

ISBN: (数字)9798350376364

ISBN: (纸本)9798350376371

Due to their low-cost and ease of use, cameras are very popular for drone detection. Thanks to the feature reach images obtained from the cameras, it is possible to classify drones with a relatively high success ratio. However, cameras lack the means for accurate localization, allowing only a rough measure of the orientation of the target UAV. In order to better localize the UAV, in this study we fuse camera and lidar measurements, localizing UAVs accurately. This fusion was implemented using a Kalman filter, which enables integration of both sensor data, improving detection and tracking accuracy

关键词： Location awareness YOLO Laser radar Accuracy Robot vision systems Cameras Autonomous aerial vehicles Kalman filters Vehicle dynamics Drones

来源：评论

学校读者我要写书评

暂无评论

Multi-objective reinforcement learning framework for beneficent artificial intelligence

引用

Neural Computing and Applications 2025年 1-19页

作者： Nickelson, Anna Perkins, Russell London, Alex John Robinette, Paul Tumer, Kagan Collaborative Robotics and Intelligent Systems (CoRIS) Institute Oregon State University Corvallis USA Electrical and Computer Engineering University of Massachusetts Lowell Lowell USA Department of Philosophy Carnegie Mellon University Pittsburgh USA

As artificial intelligence (AI) systems are more widely deployed and utilized, they have greater potential to inflict harm or provide benefits to individuals. Designers must consider these concepts when building AI systems, but it is difficult to capture these notions in a mathematical framework. An ethical framework put forth by London and Heidari (Minds Mach, 2024. https://***/10.1007/s11023-024-09696-8 ) provides structure and formal definitions of benefits and harms in relation to an individual’s life plans. This leaves an open question of how these concepts impact the decision-making of an AI system. We leverage their work to provide a direct translation of these theoretical ethical concepts to a standard multi-objective reinforcement learning (MORL) decision model. Using this model, we show that multi-objective rewards are necessary to capture benefits and harms in accordance with their definitions. We demonstrate how to capture these concepts in a MORL system and provide scenarios to highlight the utility of this work.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Computation of Source, Target, and Mixed Strongly Connected Components in Multi-agent systems 16th

Distributed Computation of Source, Target, and Mixed Stron...

引用

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

作者： Ramos, Guilherme Pequito, Sérgio Department of Computer Science and Engineering Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal Instituto de Telecomunicações Lisbon1049-001 Portugal Department of Electrical and Computer Engineering Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal Institute for Systems and Robotics Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal

ISBN: (纸本)9783031817236

Strongly Connected Components (SCCs) play a crucial role in understanding the structural properties of directed graphs, with a plethora of applications across various domains including engineering, computer science and social sciences. In this paper, we propose a method for computing both the source SCCs and target SCCs in a distributed fashion. Our method leverages the decentralized nature of distributed systems to efficiently identify SCCs within large-scale graphs. We illustrate the proposed methods with examples. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Distributed computer systems

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：