检索结果-内蒙古大学图书馆

Room-Temperature Charge-to-Spin Conversion from Quasi-2D Electron Gas at SrTiO3-Based Interfaces

physica status solidi (RRL) – Rapid Research Letters 2023年第6期17卷

作者： Utkarsh Shashank Angshuman Deka Chen Ye Surbhi Gupta Rohit Medwal Rajdeep Singh Rawat Hironori Asada X. Renshaw Wang Yasuhiro Fukuma Department of Physics and Information Technology Faculty of Computer Science and System Engineering Kyushu Institute of Technology 680-4 Kawazu Iizuka 820-8502 Japan Birck Nanotechnology Center School of Electrical and Computer Engineering Purdue University West Lafayette IN 47907 USA School of Physical and Mathematical Sciences Nanyang Technological University 637616 Singapore Natural Sciences and Science Education National Institute of Education Nanyang Technological University 637616 Singapore Department of Physics Indian Institute of Technology Kanpur Kanpur 208016 India Graduate School of Sciences and Technology for Innovation Yamaguchi University 2-16-1 Tokiwadai Ube 755-8611 Japan School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore Research Center for Neuromorphic AI hardware Kyushu Institute of Technology Kitakyushu 808-0196 Japan

来源：评论

学校读者我要写书评

暂无评论

CRNN based jersey-bib number/text recognition in sports and marathon images 15

CRNN based jersey-bib number/text recognition in sports and ...

引用

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Nag, Sauradip Ramachandra, Raghavendra Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kankanhalli, Mohan Department of Computer Science & Engineering Kalyani Government Engineering College Kalyani India Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Norway Faculty of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9781728128610

The primary challenge in tracing the participants in sports and marathon video or images is to detect and localize the jersey/Bib number that may present in different regions of their outfit captured in cluttered environment conditions. In this work, we proposed a new framework based on detecting the human body parts such that both Jersey Bib number and text is localized reliably. To achieve this, the proposed method first detects and localize the human in a given image using Single Shot Multibox Detector (SSD). In the next step, different human body parts namely, Torso, Left Thigh, Right Thigh, that generally contain a Bib number or text region is automatically extracted. These detected individual parts are processed individually to detect the Jersey Bib number/text using a deep CNN network based on the 2-channel architecture based on the novel adaptive weighting loss function. Finally, the detected text is cropped out and fed to a CNN-RNN based deep model abbreviated as CRNN for recognizing jersey/Bib/text. Extensive experiments are carried out on the four different datasets including both bench-marking dataset and a new dataset. The performance of the proposed method is compared with the state-of-the-art methods on all four datasets that indicates the improved performance of the proposed method on all four datasets. © 2019 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity ensemble sample selection and label correction for classification with noisy labels

引用

Applied Soft Computing 2025年 180卷

作者： Kecan Cai Hongyun Zhang Witold Pedrycz Duoqian Miao Chaofan Chen Department of Computer Science and Technology Tongji University Shanghai 201804 PR China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 PR China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer/Istanbul Turkiye

Sample selection is crucial in classification tasks with noisy labels, yet most existing sample selection methods rely on a single criterion. These approaches often face challenges, including low purity of selected clean samples, and underfitting due to an insufficient number of selected clean training samples. To address these challenges, this paper proposes GNet-SSLC, a novel multi-granularity network framework that integrates multiple criteria ensemble sample selection (SS) and multiple views label correction (LC). In the SS phase, this paper proposes a metric learning-based dual k-Nearest Neighbor (k-NN) sample selection method. This method first uses corrected soft labels from the initial k-NN round to guide the selection of clean samples in the subsequent k-NN round. To further enhance selection accuracy, we combine this dual k-NN approach with a small loss sample selection technique through a voting mechanism. This multiple criteria ensemble method addresses the issues of low purity and instability inherent in single criterion approaches. In the LC phase, this paper designs a multiple views label correction framework that generates high-quality pseudo-labels for selected noisy samples. A key innovation of the framework is the design of a regularized contrastive learning loss, which optimizes the semi-supervised learning process by leveraging multiple views of training samples. The additional inclusion of training samples with high-quality pseudo-labels can effectively mitigate underfitting caused by a limited number of clean training samples. Experimental results on both synthetic and real-world noisy datasets indicate that GNet-SSLC enhances the purity and stability of the selected clean samples, and significantly improves classification performance. The enhancement is particularly notable with high noise rate dataset, such as CIFAR-100 dataset with 80% noise rate, achieving a 19.3% increase in classification accuracy compared to the baseline method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Rough Sets and Data Mining

引用

CAAI Transactions on Intelligence technology 2019年第4期4卷 201-202页

作者： HIROSHI SAKAI MICHINORI NAKATA WEI-ZHI WU DUOQIAN MIAO GUOYIN WANG Faculty of Engineering Kyushu Institute of TechnologySensuiTobataKitakyushu 804-8550Japan Faculty of Management and Information Science Josai International UniversityToganeChiba 283-0002Japan School of Mathematics Physics and Information ScienceZhejiang Ocean UniversityZhoushanZhejiang316022China Department of Computer Science and Technology Tongji UniversityShanghai201804China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqingChina

A rough set,first described by Polish computer scientist Zdzis?aw Pawlak,is a formal approximation of a crisp set,and it is now known as a new mathematical tool to process vague *** are used for machine learning,knowledge discovery,feature selection,etc.,and are applied to artificial intelligence,medical informatics,civil engineering,Kansei engineering,decision science,business administration,and so ***,research on data mining using rough sets is widely spreading,and the obtained association rules are applied to the characterisation of data and decision support.

关键词： Rough artificial computer

来源：评论

学校读者我要写书评

暂无评论

Toward Projection Learning between Sensor Data and Semantic Word Vector for Zero-shot Learning

Toward Projection Learning between Sensor Data and Semantic ...

引用

International Conference on Informatics, Electronics & Vision (ICIEV)

作者： Moe Matsuki Sozo Inoue Department of Applied Science for Integrated System Engineering Kyushu Institute of Technology Kitakyushu Japan Faculty of Engineering Kyushu Institute of Technology Kitakyushu Japan

In this paper, we compare 4 learning projection models between sensor domain and text domain for Zero-shot learning (ZSL). In traditional activity recognition with sensor data, the task of collecting training dataset is too tough and costly to apply for social. Our challenge is making the task efficient. The Zero-shot learning's purpose is to recognize the unknown activity which is activity class out of training dataset. In our previous research, we propose the Zero-shot learning method using the word vectors made from Wikipedia corpus for recognizing the human living activities like breakfast, watching TV, etc. We found that this method success to recognize unknown activities and need to improve the projection function for performance. In this paper, we construct 4 learning models for projection and evaluate them with accelerometer sensor data annotated simple activities. As a result, we realize that (1) the learning method with twice projection is useful for performance. (2) It is difficult to identify the two unknown activities whose distance from known activities is closer than that between other combination of two unknown activities and the known ones.

关键词： Semantics Training Learning systems Data models Activity recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Compact Low Power AI Module Mounted on Drone for Plant Monitor system 8

A Compact Low Power AI Module Mounted on Drone for Plant Mon...

引用

8th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2019

作者： Kobayashi, Tomoki Yokogawa, Tomoyuki Igawa, Nao Sato, Yoichiro Fujii, Satoshi Arimoto, Kazutami Graduate School of Computer Science and Systems Engineering Okayama Prefectural University Soja Okayama Japan Faculty of Computer Science and System Engineering Okayama Prefectural University Soja Okayama Japan Information and Communication Systems Engineering National Institute of Technology Okinawa College Nago Okinawa Japan

This paper describes the compact and low power AI DNN discriminator which is mounted on the small drone like a hobby type. By adopting this AI module, the effective plant monitoring system using the drone has been ach... 详细信息

ISBN: (纸本)9781728126272

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Preliminary Experiments of Series Elastic Actuator Prototype utilizing Mechanical Resonance

Preliminary Experiments of Series Elastic Actuator Prototype...

引用

International Conference on Control, Automation and systems ( ICCAS)

作者： Akihiro Yoshimi Tsuyoshi Mori Jun Kobayashi Graduate School of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan Faculty of Computer Science and Systems Engineering Kyushu Institute of Technology Iizuka Japan

This study proposes large force generation by a robotic manipulator by means of providing series elastic actuators exploiting mechanical resonance to it instead of powerful actuators. To this end, the authors designed and assembled a prototype of series elastic actuator that resonates at around 1.0 Hz on the basis of its model and identified parameters, and carried out preliminary experiments with it and a load. The prototype actuator consists of a geared DC motor with an encoder and an elastic element. The elastic element is made of two torsion springs so that it can generate torque in both directions. It was confirmed in the preliminary experiments that the prototype actuator resonated at around 0.7 Hz. In addition, in order to prove efficacy of mechanical resonance for large force generation, output torque of the prototype actuator with the elastic element and without it was estimated using their identified physical parameters and dynamics, and compared them. The estimation results showed that the prototype actuator exploiting mechanical resonance generated 2.24 times larger torque than the one without the elastic element.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Requirements, Deployments, and Challenges of LoRa technology: A Survey

引用

Computational intelligence and neuroscience 2023年第1期2023卷 5183062页

作者： Muhammad Ayoub Kamal Muhammad Mansoor Alam Aznida Abu Bakar Sajak Mazliham Mohd Su'ud Malaysian Institute of Information Technology (MIIT) Universiti Kuala Lumpur Kuala Lumpur 50250 Malaysia. Institute of Business and Management Karachi 75190 Pakistan. Riphah Institute of System Engineering (RISE) Faculty of Computing Riphah International University Islamabad 46000 Pakistan. Faculty of Computing and Informatics Multimedia University Cyberjaya Malaysia. Faculty of Engineering and Information Technology School of Computer Science University of Technology Sydney Australia. Malaysian France Institute (MFI) Universiti Kuala Lumpur Kuala Lumpur 50250 Malaysia.

LoRa is an ISM-band based LPWAN communication protocol. Despite their wide network penetration of approximately 20 kilometers or higher using lower than 14 decibels transmitting power, it has been extensively documented and used in academia and industry. Although LoRa connectivity defines a public platform and enables users to create independent low-power wireless connections while relying on external architecture, it has gained considerable interest from scholars and the market. The two fundamental components of this platform are LoRaWAN and LoRa PHY. The consumer LoRaWAN component of the technology describes the network model, connectivity procedures, ability to operate the frequency range, and the types of interlinked gadgets. In contrast, the LoRa PHY component is patentable and provides information on the modulation strategy which is being utilized and its attributes. There are now several LoRa platforms available. To create usable LoRa systems, there are presently several technical difficulties to be overcome, such as connection management, allocation of resources, consistent communications, and security. This study presents a thorough overview of LoRa networking, covering the technological difficulties in setting up LoRa infrastructures and current solutions. Several outstanding challenges of LoRa communication are presented depending on our thorough research of the available solutions. The research report aims to stimulate additional research toward enhancing the LoRa Network capacity and allowing more realistic installations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The effect of angle of attack in case of tandem buildings

引用

AIP Conference Proceedings 2023年 030023页

作者： Pavel Procházka Václav Svoboda Václav Uruba Renata Gnatowska Institute of Thermomechanics of the Czech Academy of Sciences Dolejškova 5 Praha 8 Czech Republic Faculty of Nuclear Sciences and Physical Engineering CTU in Prague Břehová 7 Praha 1 Czech Republic UWB Faculty of Mechanical Engineering Department of Power System Engineering Universitní 8 Plzeň Czech Republic Czestochowa University of Technology Faculty of Mechanical Engineering and Computer Science 21 Armii Krajowej Av Czestochowa Poland

The flow field between two tandem buildings will be investigated using PIV technique and the effect of various angles of incoming flow will be described. The 3D model is composed from two blocks of different size arrangement (ratio is 0.6) and it is subjugated to well-developed boundary layer. Experiments are conducted for many vertical and horizontal planes to study statistical features of the flow.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Digital Reference: A quasi-standard for digitalization in the domain of semiconductor supply chains 3

Digital Reference: A quasi-standard for digitalization in th...

引用

3rd IEEE Conference on Industrial Cyberphysical systems, ICPS 2020

作者： Ehm, Hans Schoitsch, Erwin Van Der Weit, Jan Wytze Ramzy, Nour Luo, Lanyingzhu Gruetzner, Daniel Louis Infineon Technologies Ag Supply Chain Innovations Munich Germany Austrian Institute of Technology Center for Digital Safety and Security Vienna Austria Philips Consumer Lifestyle Philips Drachten Netherlands Leibniz University Faculty of Electrical Engineering and Computer Science Hannover Germany The Technical University of Munich Faculty of Information System Munich Germany Epf École d'Ingénieur-e-s Formation Franco-Allemande Sceaux France

ISBN: (纸本)9781728163895

This paper is about the installation of trust in the Semantic Web content of the Digital Reference (DR). The DR was developed in H2020/ECSEL/Productive4.0, which contains ontologies to model production and Cyber Physical systems addressing the whole industrial automation and control area. It should serve as a quasi-standard for digitalization in the domain of semiconductors and corresponding supply chains to overcome the partial incompatibility problem of existing *** Web is a success story in the B2C (Business to consumer) environment as it is understandable for both humans and machines alike. To transfer this success of easy data exchange into the complex industrial B2B (Business to business) environment, a much higher quality is required-a standardization of the classes and properties. The confidence in standards usually comes from human verification, validation and confirmation, which has the disadvantage of being slow. Machine validation could be faster but often lacks confidence. Thus, how can trust be installed to ensure the "correctness"of the used classes and properties in a speedy process?We propose a human and machine blended approach based on peer review and Blockchain technology built on decentralized peer-to-peer networks to solve this problem. The consensus process combines transparency, traceability, immutability and speed of Blockchain with the fidelity of human experts. © 2020 IEEE.

关键词： Blockchain

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：