检索结果-内蒙古大学图书馆

Improving Common Spatial Patterns in Brain-Computer Interface Using Dynamic Time Warping and EEG Normalization

Improving Common Spatial Patterns in Brain-Computer Interfac...

Metrology for Extended Reality, Artificial Intelligence and Neural engineering (MetroXRAINE), IEEE International Conference on

作者： Mohamed A A Mohamed Salem Mansour Payam Soulatiantork Kai Keng Ang Phua Kok Soon Mahnaz Arvaneh Automatic control and Systems Engineering Department University of Sheffield Sheffield UK Institute for Infocomm Research Agency for Science Technology and Research (A*STAR) Singapore

Common spatial patterns (CSP) is widely employed for spatial filtering and feature extraction in electroencephalogram (EEG)-based brain-computer interfaces (BCIs), However, the non-stationary nature of EEG signals can lead to poor estimation of CSP. To address this drawback, this paper proposes a novel algorithm called scaled and warped CSP (SW-CSP). The proposed algorithm enhances the classical CSP by reducing within EEG class non-stationarity across both time and amplitude domains, followed by automatically selecting the most discriminative features. First, the maximum-minimum scaling is applied to align amplitude of each EEG trial to its class average. Next, dynamic time warping (DTW) temporally aligns each scaled EEG trial to its class average. Thereafter, the scaled and warped EEG trials are used to compute the CSP covariance matrices. Finally, the proposed Fisher's score is used to select most discriminative SW-CSP filters. The proposed SW-CSP algorithm is evaluated using two datasets, and compared with the CSP algorithm and the previously proposed DTW-CSP. The results showed that the SW-CSP significantly outperformed both CSP and DTW-CSP (p<0.003). Notably, an improvement above 10% was observed in 20 % of the participants.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation Analysis and Model Modification of the LWR Traffic Flow Theory

Simulation Analysis and Model Modification of the LWR Traffi...

引用

IEEE Workshop on Advanced robotics and its Social Impacts, ARSO

作者： Yang Chen Jun Fu Anton Selivanov State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China Department of Automatic Control and Systems Engineering University of Sheffield UK

ISBN: (数字)9798350344639

ISBN: (纸本)9798350344646

The surge in urbanization and ensuing traffic congestion underscores the imperative for contemporary traffic flow control models. This paper explores the Lighthill-Whitham-Richards (LWR) theory in the macroscopic domain of traffic flow control. It evaluates the accuracy and mathematical logic of simulation performance of related models, namely Greenshields, Newell-Daganzo, Greenberg, Underwood, and California. This paper employs thorough simulations that utilize a holistic three-dimensional(3D) analysis based on time, location, and density. It provides a comprehensive comparison and discusses specific features of each model. Additionally, a modification to the macroscopic model is proposed. The modified model overcomes the shortcomings of performing well only in some specific short ranges and achieves a full range of application effects. The study offers valuable guidance for real-life scenario selections and applications in the traffic domain.

关键词： Analytical models Accuracy Urban areas Transportation Predictive models Mathematical models Numerical models

来源：评论

学校读者我要写书评

暂无评论

RGB-D Image-Based Deep Neural Network Body Shape Classifier

RGB-D Image-Based Deep Neural Network Body Shape Classifier

引用

Data Science and engineering in Healthcare, Medicine and Biology, IEEE EMBS Special Topic Conference on

作者： Meng Xu Yuanhao Gong Sanja Dogramadzi Department of Automatic Control and Systems Engineering University of Sheffield S10 2TN Sheffield Faculty of Electronics and Information Engineering Shenzhen University

Leveraging the untapped potential of depth information in RGB-D images, this study introduces a deep neural network classifier for advanced body shape classification. Going beyond traditional RGB image analysis, our method innovatively employs multi-task learning, simultaneously performing body shape classification, posture estimation, and body part segmentation to achieve superior accuracy. This approach promises to revolutionize personalization avenues in healthcare, fashion, and entertainment industries, establishing a new benchmark in body shape analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MATLAB apps to support the learning and understanding of simple system dynamics

引用

IFAC-PapersOnLine 2022年第17期55卷 121-125页

作者： J.A. Rossiter Department of Automatic Control and Systems Engineering University of Sheffield Sheffield S1 3JD UK

This paper focuses on resources which enable students to be active rather than passive in their learning. Important underpinning skills for control engineering is a good understanding of basic models and the associated dynamics. This paper presents a small number of MATLAB APPs designed to bring dynamics to life by allowing an interactive and visual element relating the behaviours to real components and system architectures. The paper presents the APPs, shows how they are integrated into course delivery and also gives some concise student feedback.

关键词： Interaction within a lecture virtual laboratories independent learning

来源：评论

学校读者我要写书评

暂无评论

Combined Filters Design, Using the Principle of Internal Models

Combined Filters Design, Using the Principle of Internal Mod...

引用

International Russian Automation Conference (RusAutoCon)

作者： Anatoly Gaiduk Darya Denisenko Nikolay Prokopenko Department of Automatic Control Systems Southern Federal University Scientific Design Office Robotics and Control Systems Taganrog Rostov-on-Don Russia Department of scientific research Department of Automatic Control Systems Don State Technical University Southern Federal University Rostov-on-Don Russia Department of Information Systems and Radio Engineering Don State Technical University Rostov-on-Don Russia

ISBN: (数字)9798350349818

ISBN: (纸本)9798350349825

To design active analog, discrete-analog and digital filters a new method is suggested, taking into account the conditions of selective invariance and using the internal models principle of the dynamic systems. For this purpose, the structure of each basic filter ensures the presence of an explicit spectral model of the filtered signal. Such a filter is selectively invariant, and this property depend only on the spectrum-setting parameters and do not depend on other parameters. It is suggest-ed to carry out the design of the combined selective filters by integration of the suggested basic second-order filters, focusing on the log magnitude plot of the latter. This makes possible to minimize the order of the combined both analog and digital filters. The combined selective filters are distinguished by high stability of selective properties and can be used in the systems for measurement, signal processing, data transmission, as well as automatic and automated control of various social, production and special facilities.

关键词： Automation Filtering Focusing Production Signal processing Stability analysis Data communication Digital filters Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

A Novel Sensing Template Using Data Fusion for Large Volume Assembly

引用

IFAC-PapersOnLine 2022年第2期55卷 283-288页

作者： Ethan Canzini Marc Auledas Dominique Chasteau Ashutosh Tiwari Department of Automatic Control & Systems Engineering University of Sheffield UK Industrial Architecture & Manufacturing Research Airbus UK

The size of large components within manufacturing processes leads to complications with automating the processes required to assemble them into larger structures. In recent years, development of multi-sensor networks and breakthroughs in measuring algorithms have allowed for the creation of novel methods of mating large components. One major challenge with deploying sensor networks into production environments is the ability to attach sensors to large volume components. This can be remedied with the use of a sensing template that acts as a pseudo-virtual jig for the assembly process where sensors are embedded onto the template, thus not interfering with the physical assembly. The key step for this sensing template is creating an algorithmic process for accurate component localisation. This paper will introduce an innovative method of using data fusion attached to a sensing template embedded in an aerospace assembly process. A sensing algorithm utilising a Kalman filter allows for accurate component mating with a low error offset and high repeatability. The results of the sensing template show how it is capable of reducing the error offset and improves the repeatability of measurements.

关键词： Autonomy Manufacturing Automation Internet-of-Things Sensing Enterprise

来源：评论

学校读者我要写书评

暂无评论

A Learning Distributed Gaussian Process Approach for Target Tracking over Sensor Networks 25

A Learning Distributed Gaussian Process Approach for Target ...

引用

25th International Conference on Information Fusion, FUSION 2022

作者： Liu, Xingchi Lyu, Chenyi George, Jemin Pham, Tien Mihaylova, Lyudmila University of Sheffield Department of Automatic Control and Systems Engineering S1 3JD United Kingdom Us Army Research Laboratory AdelphiMD20783 United States

ISBN: (数字)9781737749721

ISBN: (纸本)9781737749721

Tracking manoeuvring targets often relies on complex models with non-stationary parameters. Gaussian process (GP) based model-free methods can achieve accurate performance in a data-driven manner but face scalability challenges. Aiming to address such challenges, this paper proposes a distributed GP-based tracking approach able to learn the kernel hyperparameters in an online manner, to improve the tracking performance and scalability. It caters to the inherent distributed feature of sensor networks and does not need measurements to be transmitted among sensors for target states predictions. Theoretical upper confidence bounds about the tracking error are derived within the regret bound setting. Through this theoretical analysis, the tracking error per time step is upper bounded as a function of predictive variances from local sensors. The theoretical results are supported by simulation based ones over a case study for tracking over wireless sensor networks. With evaluation on challenging target trajectories, a comparison on state-of-the-art centralised and distributed GP approaches, numerical results demonstrate that the proposed approach achieves competitively high and robust tracking performance. © 2022 International Society of Information Fusion.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Joint Sensor Scheduling and Target Tracking with Efficient Bayesian Optimisation

Joint Sensor Scheduling and Target Tracking with Efficient B...

引用

Sensor Signal Processing for Defence (SSPD)

作者： Xingchi Liu Chenyi Lyu Seyed Ahmad Soleymani Wenwu Wang Lyudmila Mihaylova Department of Automatic Control and Systems Engineering University of Sheffield Sheffield UK Centre for Vision Speech and Signal Processing (CVSSP) University of Surrey Guildford UK

The received signal strength measurement has been widely used in search and tracking applications and its benefit is linked with the distance between the transmitter and receiver. This paper proposes an online Bayesian optimisation-based approach that relies on signal strength measurements to schedule multiple sensors for searching and tracking a moving target, without any prior knowledge of the target’s state or motion model. A unique contribution lies in incorporating the Gaussian processes factorisation method into the Bayesian optimisation framework, which enhances the effectiveness of the proposed approach. Numerical results obtained from different sizes of measurements demonstrate that the proposed approach can efficiently schedule two unmanned aerial vehicles. Particularly, it achieves at most 21% lower computational time for deciding measurement locations and 79% lower time for updating the surrogate model as compared to the benchmark approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Wirelessly Actuated Rotation-free Magnetic Motor

Wirelessly Actuated Rotation-free Magnetic Motor

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Umur Ulas Harman Ahmed Hafez Cameron Duffield Zihan Zhao Luke Dixon Daniela Rus Shuhei Miyashita Automatic Control and Systems Engineering Department University of Sheffield Sheffield UK Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge MA USA Insigneo Institute for in Silico Medicine

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This paper addresses the challenge of actuating millimetre-sized motors, which are wirelessly driven by external magnetic fields. Traditional approaches, relying on rotating magnetic fields, often inadvertently cause the entire robot – especially if it is small and lightweight – to rotate, instead of a specified shaft in the motor. To overcome this issue, our study introduces a novel mechanism that leverages symmetrically configured magnetic motors to cancel out the torques, thus preventing unwanted rotation of the robot. This is achieved by utilizing a magnetic field along a single axis to induce rotational movement. The design features two millimetre-sized rotating magnets that interact to achieve a 90 ◦ rotation, complemented by an external magnetic field that accomplishes the remaining 270 ◦ , thus completing a full rotation. Furthermore, we demonstrate that applying a perpendicularly oriented magnetic field can inversely affect the motor’s rotation direction. A proof-of-concept experiment employing this mechanism successfully actuated a gripper in a water tank while it is free-floating, showcasing its potential for enhancing robotic applications at the sub-centimeter scale, where the small net torque of a miniature motor is essential.

关键词： Water Shafts Torque Gears Net zero Storage management Motors Permanent magnets Magnetic fields Grippers

来源：评论

学校读者我要写书评

暂无评论

Deformation Pattern Shape Sensing for Visuotactile Endoscope

Deformation Pattern Shape Sensing for Visuotactile Endoscope

引用

2024 IEEE International Conference on Real-Time Computing and robotics, RCAR 2024

作者： Yu, Yanzhe Tian, Yuan Cui, Shaowei Wang, Yupeng Wang, Rui Wang, Shuo Beijing University of Science and Technology Beijing100083 China The University of Sheffield Department of Automatic Control and Systems Engineering Sheffield United Kingdom Institute of Automation Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9798350372601

The integration of visuotactile sensor technology with endoscopy enables the provision of tactile information for minimally invasive surgeries and other operations. This paper proposes a real-time sensing framework for contact deformation pattern shape, providing a foundation for precise perception in miniaturized visuotactile sensors. Specifically, we first construct a Deformation Pattern shape Descriptor (DPSD) and then track the key points in the descriptor using optical flow to obtain contact deformation shape information. Through extensive qualitative and quantitative experiments, our proposed algorithm achieves an average perception accuracy of around 83.81% for contact pattern shapes. It demonstrates consistent perception accuracy across various contact force magnitudes, directions, and scenarios, highlighting its robustness. Additionally, compared to traditional marker-level methods, it achieves a notable 46.5% improvement in displacement field perception accuracy. This research elevates tactile perception to the dimension of contact pattern shape sensing and has the potential for application in miniaturized visual tactile sensors. © 2024 IEEE.

关键词： Endoscopy

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：