检索结果-内蒙古大学图书馆

International Conference on Information Fusion

作者： Md Asif Jalal Ruilong Chen Roger K Moore Lyudmila Mihaylova Department of Computer Science University of Sheffield UK Department of Automatic Control and Systems Engineering University of Sheffield UK

Sign language is a visually oriented, natural, nonverbal communication medium. Having shared similar linguistic properties with its respective spoken language, it consists of a set of gestures, postures and facial expressions. Though, sign language is a mode of communication between deaf people, most other people do not know sign language interpretations. Therefore, it would be constructive if we can translate the sign postures artificially. In this paper, a capsule-based deep neural network sign posture translator for an American Sign Language (ASL) fingerspelling (posture), has been presented. The performance validation shows that the approach can successfully identify sign language, with accuracy like 99%. Unlike previous neural network approaches, which mainly used fine-tuning and transfer learning from pre-trained models, the developed capsule network architecture does not require a pre-trained model. The framework uses a capsule network with adaptive pooling which is the key to its high accuracy. The framework is not limited to sign language understanding, but it has scope for non-verbal communication in Human-Robot Interaction (HRI) also.

关键词： Convolution Assistive technology Gesture recognition Feature extraction Neural networks Kernel Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Roadmap on Quantum Thermodynamics

arXiv

引用

arXiv 2025年

作者： Campbell, Steve D’Amico, Irene Ciampini, Mario A. Anders, Janet Ares, Natalia Artini, Simone Auffèves, Alexia Oftelie, Lindsay Bassman Bettmann, Laetitia P. Bonança, Marcus V.S. Busch, Thomas Campisi, Michele Cavalcante, Moallison F. Correa, Luis A. Cuestas, Eloisa Dag, Ceren B. Dago, Salambô Deffner, Sebastian Del Campo, Adolfo Deutschmann-Olek, Andreas Donadi, Sandro Doucet, Emery Elouard, Cyril Ensslin, Klaus Erker, Paul Fabbri, Nicole Fedele, Federico Fiusa, Guilherme Fogarty, Thomás Folk, Joshua Guarnieri, Giacomo Hegde, Abhaya S. Hernández-Gómez, Santiago Hu, Chang-Kang Iemini, Fernando Karimi, Bayan Kiesel, Nikolai Landi, Gabriel T. Lasek, Aleksander Lemziakov, Sergei Monaco, Gabriele Lo Lutz, Eric Lvov, Dmitrii Maillet, Olivier Mehboudi, Mohammad Mendonça, Taysa M. Miller, Harry J.D. Mitchell, Andrew K. Mitchison, Mark T. Mukherjee, Victor Paternostro, Mauro Pekola, Jukka Perarnau-Llobet, Martí Poschinger, Ulrich Rolandi, Alberto Rosa, Dario Sánchez, Rafael Santos, Alan C. Sarthour, Roberto S. Sela, Eran Solfanelli, Andrea Souza, Alexandre M. Splettstoesser, Janine Tan, Dian Tesser, Ludovico Van Vu, Tan Widera, Artur Halpern, Nicole Yunger Zawadzki, Krissia School of Physics University College Dublin Belfield Dublin 4 Ireland Centre for Quantum Engineering Science and Technology University College Dublin Dublin 4 Ireland School of Physics Engineering and Technology University of York York United Kingdom York Centre for Quantum Technologies University of York York United Kingdom Boltzmanngasse 5 ViennaA-1090 Austria Institute of Physics and Astronomy University of Potsdam Potsdam14476 Germany Department of Physics and Astronomy University of Exeter ExeterEX4 4QL United Kingdom Department of Engineering Science University of Oxford Parks Road OxfordOX1 3PJ United Kingdom Università degli Studi di Palermo Dipartimento di Fisica e Chimica - Emilio Segrè via Archirafi 36 PalermoI-90123 Italy MajuLab CNRS-UCA-SU-NUS-NTU International Joint Research Laboratory France Centre for Quantum Technologies National University of Singapore Singapore117543 Singapore NEST Istituto Nanoscienze-CNR and Scuola Normale Superiore Pisa56127 Italy School of Physics Trinity College Dublin College Green Dublin 2 Ireland Gleb Wataghin Physics Institute The University of Campinas Campinas São Paulo13083-859 Brazil Quantum Systems Unit OIST Graduate University Okinawa Onna904-0495 Japan Department of Physics University of Maryland Baltimore County BaltimoreMD21250 United States Quantum Science Institute University of Maryland Baltimore County BaltimoreMD21250 United States Universidad de La Laguna La Laguna38203 Spain Departamento de Física Universidad de La Laguna La Laguna38203 Spain Jülich54245 Germany Department of Physics Indiana University BloomingtonIN47405 United States Department of Physics Harvard University 17 Oxford Street CambridgeMA02138 United States National Quantum Laboratory College ParkMD20740 United States Department of Physics and Materials Science University of Luxembourg LuxembourgL-1511 Luxembourg Donostia International Physics Center San SebastianE-20018 Spain Au

The last two decades has seen quantum thermodynamics become a well established field of research in its own right. In that time, it has demonstrated a remarkably broad applicability, ranging from providing foundational advances in the understanding of how thermodynamic principles apply at the nano-scale and in the presence of quantum coherence, to providing a guiding framework for the development of efficient quantum devices. Exquisite levels of control have allowed state-of-the-art experimental platforms to explore energetics and thermodynamics at the smallest scales which has in turn helped to drive theoretical advances. This Roadmap provides an overview of the recent developments across many of the field’s sub-disciplines, assessing the key challenges and future prospects, providing a guide for its near term progress. Copyright © 2025, The Authors. All rights reserved.

关键词： Temperature

来源：评论

学校读者我要写书评

暂无评论

Motion Planning In High-Dimensional Spaces

arXiv

引用

arXiv 2018年

作者： Petrović, Luka University of Zagreb Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering Laboratory for Autonomous Systems Mobile Robotics

—Motion planning is a key tool that allows robots to navigate through an environment without collisions. The problem of robot motion planning has been studied in great detail over the last several decades, with researchers initially focusing on systems such as planar mobile robots and low degree-of-freedom (DOF) robotic arms. The increased use of high DOF robots that must perform tasks in real time in complex dynamic environments spurs the need for fast motion planning algorithms. In this overview, we discuss several types of strategies for motion planning in high dimensional spaces and dissect some of them, namely grid search based, sampling based and trajectory optimization based approaches. We compare them and outline their advantages and disadvantages, and finally, provide an insight into future research opportunities. Copyright © 2018, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Using AdaBoost-based Multiple Functional Neural Fuzzy Classifiers Fusion for Classification Applications

Using AdaBoost-based Multiple Functional Neural Fuzzy Classi...

引用

3rd International Conference on Inventions, ICI 2017

作者： Jhang, Jyun-Yu Lee, Chin-Ling Lin, Cheng-Jian Lin, Chin-Teng Young, Kuu-Young Institute of Electrical and Control Engineering National Chiao-Tung University Hsinchu300 Taiwan National Taichung University of Science and Technology Taichung411 Taiwan Department of Computer Science and Information Engineering National Chin-Yi University of Technology Taichung411 Taiwan Department of Electrical and Control Engineering National Chiao Tung University Hsinchu300 Taiwan Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia

In this study, two intelligent classifiers, the AdaBoost-based incremental functional neural fuzzy classifier (AIFNFC) and the AdaBoost-based fixed functional neural fuzzy classifier (AFFNFC), are proposed for solving the classification problems. The AIFNFC approach will increase the amount of functional neural fuzzy classifiers based on the corresponding error during the training phase;while the AFNFC approach is equipped with a fixed amount of functional neural fuzzy classifiers. Then, the weights of AdaBoost procedure are assigned for classifiers. The proposed methods are applied to different classification benchmarks. Results of this study demonstrate the effectiveness of the proposed AIFNFC and AFFNFC methods. © The Authors, published by EDP Sciences, 2018.

关键词： Adaptive boosting

来源：评论

学校读者我要写书评

暂无评论

Efficient On-Board Health Monitoring for Multicell Lithium-Ion Battery Systems Using Gaussian Process Clustering 10

Efficient On-Board Health Monitoring for Multicell Lithium-I...

引用

10th Annual IEEE Energy Conversion Congress and Exposition, ECCE 2018

作者： Kim, Taesic Kang, Daewook Oh, Chang-Yeol Kim, Myoungho Baek, Juwon Department of Electrical Engineering and Computer Science Texas AM University-Kingsville KingsvilleTX78363-8202 United States Korea Electrotechnology Research Institute Power Conversion Control Research Center Changwon51543 Korea Republic of

ISBN: (纸本)9781479973118

Accurately monitoring health condition of individual lithium-ion (Li-ion) cells such as state of charge (SOC) and state of health (SOH) in multicell batteries is crucial to build high-performance and safety-critical battery systems. However, this involves considerable computational burden to embedded battery management systems (BMSs), as number of battery cells increases. This paper proposes an efficient on-board health monitoring method for multicell Li-ion battery systems consisting of large number of cells using the proposed Gaussian process clustering. The Gaussian process clustering method first preprocesses all cell voltages using Z-score standardization and classifies a normal cell cluster and an abnormal cell cluster using outlier scoring vector. Then, a representative of the normal cell cluster and abnormal cells are carefully monitored using the threads of a condition monitoring algorithm. Instead of using cell-based method for all cells in a pack, the proposed method can significantly reduce the computation cost for onboard implementation. We show the usefulness of the proposed health monitoring algorithm through simulation results. © 2018 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic geometrical approach to model reduction

引用

IFAC-PapersOnLine 2017年第1期50卷 12905-12910页

作者： Soumelidis, Alexandros Bokor, József Schipp, Ferenc Szabó, Zoltán Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary Institute for Computer Science and Control Hungarian Academy of Sciences MTA-BME Control Engineering Research Group Hungary Department of Numerical Analysis Eötvös Loránd University Budapest Hungary

Model reduction of large scale systems is an actively researched area of modelling and control. The problem is more involved if uncertainties are also present and a computational tractable nominal model is needed for the design. Based on results of the Kolmogorov n-width theory the paper provides useful bounds for the worst case approximation error - both H2and H∞– in terms of the hyperbolic distance related to the sets of uncertain poles. A related model reduction strategy that uses only this a priori pole information is also proposed. The method is illustrated through numerical examples. © 2017

关键词： Numerical methods Computation theory Frequency domain analysis Large scale systems Poles Approximation errors Frequency domain identification Geometrical approaches Hyperbolic distances Identification for control Model reduction strategies Modelling and controls Nonparametric methods

来源：评论

学校读者我要写书评

暂无评论

Facility management outsourcing through multi-attribute auctions

引用

International Journal of Applied Decision Sciences 2017年第3期10卷 233-253页

作者： Avenali, Alessandro Matteucci, Giorgio Nonino, Fabio Reverberi, Pierfrancesco Department of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Ariosto 25 Roma00185 Italy

We introduce a multi-attribute auction-based mechanism with an endogenous score as a means to innovate the procurement of facility management (FM) activities in private and public sectors. The mechanism allows the procurer to request bids on several measurable technical and economic attributes of the supply of FM services. The procurer also assigns weights to such features to signal their importance to the sellers, while the score obtained with respect to each attribute is endogenously determined on the basis of the submitted offers for the attribute. The proposed mechanism mitigates the most relevant drawbacks due to the lack of skills and of crucial information on the outsourced non-core activities, while requiring the procurer very little auction design effort. On the one hand, the mechanism can extract from suppliers valuable private technical knowledge as well as the information on the supply cost. On the other hand, it saves the procurer from detailing ex ante both the score which will be assigned to any possible bid for every attribute and the exact value to require for any technical feature of the supply. © 2017 Inderscience Enterprises Ltd.

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

Monitoring human body motions during earthquakes 11

Monitoring human body motions during earthquakes

引用

11th National Conference on Earthquake engineering 2018: Integrating Science, engineering, and Policy, NCEE 2018

作者： Cimellaro, G.P. Domaneschi, M. Boroschek, R. Cardoni, A. Kammouh, O. Galdo, D. Apostoliti, C. Cares, D. Mahin, S. Dept. of Civil and Environmental Engineering University of California BerkeleyCA94720 United States Dept. of Civil Structural and Geotechnical Engineering Politecnico di Torino 10129 Italy Civil Engineering Department University of Chile Blanco Encalada Santiago2002 Chile Dept. of Control and Computer Engineering Politecnico di Torino 10129 Italy

ISBN: (纸本)9781510873254

This work aims at establishing laboratory requirements and testing conditions in order to understand the physical and emotional stability of people during a ground shaking. Several individuals with different human characteristics (gender, age, height, etc.) are considered in the test. Two different laboratory setups are presented. A position device (Kinect) and video targetless tracking algorithm has been used to collect the human body position during the shaking. A two and a three dimensional shaking tables are used to generate artificial earthquakes with different frequency bands. In addition, a well detailed virtual reality setting is applied to the testing site in order to illustrate the real environment. During the experiment, a special attention has been given to the factor of "surprise", which is necessary to ensure a natural reaction of the individuals. The result of the experiment proved common behaviors among the individual samples during the shaking. This work is considered a first step towards a large test campaign, which is necessary to obtain comprehensive statistics on this topic. Copyright © NCEE 2018: Integrating Science, engineering, and *** rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

SD-Unet: A Structured Dropout U-Net for Retinal Vessel Segmentation

SD-Unet: A Structured Dropout U-Net for Retinal Vessel Segme...

引用

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Changlu Guo Márton Szemenyei Yang Pei Yugen Yi Wei Zhou Department of Control Engineering and Information Technology Budapest University of Technology and Economics Budapest Hungary Budapest University of Technology and Economics Budapest Hungary School of Software Jiangxi Normal University Nanchang China College of Computer Science Shenyang Aerospace University Shenyang China

ISBN: (纸本)9781728146188

At present, artificial visual diagnosis of fundus diseases has low manual reading efficiency and strong subjectivity, which easily causes false and missed detections. Automatic segmentation of retinal blood vessels in fundus images is very effective for early diagnosis of diseases such as the hypertension and diabetes. In this paper, we utilize the U-shaped structure to exploit the local features of the retinal vessels and perform retinal vessel segmentation in an end-to-end manner. Inspired by the recently DropBlock, we propose a new method called Structured Dropout U-Net (SD-Unet), which abandons the traditional dropout for convolutional layers, and applies the structured dropout to regularize U-Net. Compared to the state-of-the-art methods, we demonstrate the superior performance of the proposed approach.

关键词： Image segmentation Biomedical imaging Blood vessels Training Retinal vessels Diseases

来源：评论

学校读者我要写书评

暂无评论

Hand Hygiene Auditing Algorithm using Image Processing for Hand Hygiene Evaluation Machine

Hand Hygiene Auditing Algorithm using Image Processing for H...

引用

International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON

作者： Kanabadee Srisomboon Kumthorn Malathum Sumawadee Skuntaniyom Jatepiya Duangthongkham Nattapong Phanthuna Department of Electrical and Computer Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Infection Prevention and Control Services Faculty of Medicine Ramathibodi Hospital Mahidol University Bangkok Thailand Rajamangala University of Technology Phra Nakhon Bangkok Thailand

Traditionally, hand hygiene performance of personnel is evaluated through human sight which does not meet the standard since the error may cause by human. Later, the hand hygiene auditing using image processing is proposed. The hand image is converted into grayscale and detected a clean/unclean area with a fixed threshold. In this paper, we propose a new hand hygiene auditing algorithm for hand hygiene evaluation machine by exploiting the image processing application. The objective of this work is to improve the performance and reduce a time of the traditional hand hygiene performance evaluation. In our proposed algorithm, the performance of hand hygiene is evaluated through color image by extracting the blue (B) component of image which is greatly influenced by the effect of ultraviolet (UV) light. Moreover, we detect clean/unclean area with an adaptive thresholds since the intensity of clean/unclean area for white and dark people is not the same. Therefore, the hand hygiene performance of personnel is evaluated accurately with less short consuming.

关键词：

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：