检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Hua, Yilei Wu, Wenhan Zheng, Ce Lu, Aidong Liu, Mengyuan Chen, Chen Wu, Shiqian School of Information Science and Engineering Wuhan University of Science and Technology China University of North Carolina at Charlotte United States Center for Research in Computer Vision University of Central Florida United States Peking University Shenzhen Graduate School China

In recent years, remarkable results have been achieved in self-supervised action recognition using skeleton sequences with contrastive learning. It has been observed that the semantic distinction of human action features is often represented by local body parts, such as legs or hands, which are advantageous for skeleton-based action recognition. This paper proposes an attention-based contrastive learning framework for skeleton representation learning, called SkeAttnCLR, which integrates local similarity and global features for skeleton-based action representations. To achieve this, a multi-head attention mask module is employed to learn the soft attention mask features from the skeletons, suppressing non-salient local features while accentuating local salient features, thereby bringing similar local features closer in the feature space. Additionally, ample contrastive pairs are generated by expanding contrastive pairs based on salient and non-salient features with global features, which guide the network to learn the semantic representations of the entire skeleton. Therefore, with the attention mask mechanism, SkeAttnCLR learns local features under different data augmentation views. The experiment results demonstrate that the inclusion of local feature similarity significantly enhances skeleton-based action representation. Our proposed SkeAttnCLR outperforms state-of-the-art methods on NTURGB+D, NTU120-RGB+D, and PKU-MMD *** code and settings are available at this repository: https://***/GitHubOfHyl97/SkeAttnCLR Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

International Seminar on Research of information Technology and Intelligent Systems (ISRITI)

作者： Jia Hao Loo Veronica Lestari Jauw Chin Seong Lim Khairul-Rijal Sarmin Nunung Nurul Qomariyah Ahmad Nurul Fajar Department of Mechanical Materials and Manufacturing Engineering University of Nottingham Malaysia Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Computer Science Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Information System Management Department BINUS Graduate Program-Master Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%.

关键词： Accuracy Optical character recognition Text categorization Lighting Transforms US Department of Transportation Cameras Tires Internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive active-powering pressure sensor enabled by integration of double-rough surface hydrogel and flexible batteries

引用

npj Flexible Electronics 2022年第1期6卷 908-916页

作者： Yuan Huang Binbin Liu Wenyue Zhang Gangrui Qu Shunyu Jin Xianbo Li Zanxiang Nie Hang Zhou School of Microelectronics Science and Technology Sun Yat-Sen UniversityGuangzhouP.R.China School of Electronic and Computer Engineering Peking University Shenzhen Graduate SchoolShenzhen 518055P.R.China School of Electronics and Information Technology Sun Yat-Sen UniversityGuangzhouP.R.China Hefei National Research Center for Physical Sciences at the Microscale University of Science and Technology of ChinaHefei 23000P.R.China Zinergy Shenzhen Ltd. Floor 6Building HGangzhilong Science ParkLonghuaShenzhen 518109P.R.China

A conductive,elastic,and biocompatible hybrid network hydrogel was prepared by cross-linking of locust bean gum,polyvinyl alcohol,and carbon nanotubes,yielding a rough top surface and smooth bottom *** merging of the two pieces of hydrogel flat face to flat face forms a highly elastic hydrogel with double-rough surfaces.A piezoresistive sensor assembled with the double-rough surface hydrogel sandwiched between two carbon cloth electrodes exhibits a high sensitivity(20.5 kPa^(-1),0-1kPa),a broad detection range(0.1-100 kPa)and a reliable response for 1000 *** rough contact area between the hydrogels and the carbon cloth is found critical in achieving ultra-high sensitivities in the low-pressure ***,further monolithic integration of the sensor with a flexible solid-state zinc ion battery ensures the self-powering of the sensor for various human motions detection applications.

关键词： hydrogel double integration

来源：评论

学校读者我要写书评

暂无评论

A Framework for Digital Twin-Based Deterministic Communication in Satellite Time Sensitive Networks

A Framework for Digital Twin-Based Deterministic Communicati...

引用

IEEE International Conference on Communications (ICC)

作者： Yinzhi Lu Guofeng Zhao Chuan Xu Muhammad Imran Keping Yu Joel J.P.C. Rodrigues School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing China College of Applied Computer Science Saud University Riyadh Saudi Arabia Graduate School of Science and Engineering Hosei University Tokyo Japan College of Computer Science and Technology China University of Petroleum Qingdao China Instituto de Telecomunicações Covilhã Portugal

With the explosive growth of real-time applications in satellite systems, Time Sensitive Networking (TSN) is explored to be introduced to provide bounded low latency network services. Nevertheless, some efforts in delay ensuring techniques are ongoing, guaranteeing deterministic low latency communication in satellite networks is still a significant problem. In the article, we first present a Digital Twin-based TSN framework in which digital twin technology is introduced for the purpose of reducing the management cost and optimizing the performance of satellite networks. The virtual model of the scheduling method working in satellite systems is explored and created for the simulation and prediction of the forwarding delay results. Deep convolution generative adversarial network (DCGAN) is adopted to train the scheduling model. The simulation experiments verified that the digital twin could mirror the scheduling behavior and predict the delay in dynamic environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ECG signals-based security and steganography approaches in WBANs: A comprehensive survey and taxonomy

引用

Sustainable Computing: Informatics and Systems 2024年 41卷

作者： Masdari, Mohammad Band, Shahab S. Qasem, Sultan Noman Sayed, Biju Theruvil Pai, Hao-Ting Department of Computer Engineering Urmia Branch Islamic Azad University Urmia Iran Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Riyadh11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz6803 Yemen Department of Computer Science Dhofar University PO Box 2509 SalalahPCode 211 Oman Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan

Wireless Body Area Networks (WBANs) are integral components of e-healthcare systems, responsible for monitoring patients' physiological states through intelligent implantable or wearable sensor nodes. These nodes collect medical data, which is then transmitted to remote healthcare facilities for thorough evaluation. Securing medical data within WBANs is paramount due to its central role in preserving patient privacy and confidentiality. Notably, Electrocardiogram (ECG) signals have recently gained prominence as pivotal elements within diverse security frameworks. Incorporating ECG signals strategically enhances the security and reliability of WBANs and broader e-healthcare systems, instilling greater trustworthiness. This survey article provides an in-depth exploration of contemporary ECG-based security schemes, adding to the scholarly discourse. The imperative to categorize these security paradigms revolves around their use of ECG signals. This categorization identifies three key domains: the first involves schemes that utilize ECG signals for cryptographic operations, encompassing key generation, agreement, management, and authentication. The second category employs steganography-based techniques, using ECG signals to conceal patients' sensitive medical data. The third category focuses on enhancing ECG signal security during data transmission. Each category is meticulously elaborated, detailing architectural foundations, notable contributions, and intrinsic security services. Furthermore, each section presents a comprehensive overview of the attributes characterizing ECG-based security frameworks. This includes insights into employed datasets, simulation environments, evaluation metrics, and inherent advantages and limitations. Expanding on this, a thorough analysis of distinctive attributes underpinning these security frameworks concludes by shedding light on potential directions for future research. © 2023 Elsevier Inc.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

CompAct: Designing Interconnected Compliant Mechanisms with Targeted Actuation Transmissions 25

CompAct: Designing Interconnected Compliant Mechanisms with ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Yang, Humphrey Shen, I-Chao Martelaro, Nikolas Zhu, Bo Xie, Haoran Igarashi, Takeo Yao, Lining Human-Computer Interaction Institute Carnegie Mellon University PittsburghPA United States The University of Tokyo Graduate School of Information Science and Technology Tokyo Japan Georgia Institute of Technology AtlantaGA United States JAIST Ishikawa Japan The University of Tokyo Tokyo Japan Mechanical Engineering Department University of California Berkeley BerkeleyCA United States

ISBN: (纸本)9798400713941

Compliant mechanisms enable the creation of compact and easy-to-fabricate devices for tangible interaction. This work explores interconnected compliant mechanisms consisting of multiple joints and rigid bodies to transmit and process displacements as signals that result from physical interactions. As these devices are difficult to design due to their vast and complex design space, we developed a graph-based design algorithm and computational tool to help users program and customize such computational functions and procedurally model physical designs. When combined with active materials with actuation and sensing capabilities, these devices can also render and detect haptic interaction. Our design examples demonstrate the tool's capability to respond to relevant HCI concepts, including building modular physical interface toolkits, encrypting tangible interactions, and customizing user augmentation for accessibility. We believe the tool will facilitate the generation of new interfaces with enriched affordance. © 2025 Copyright held by the owner/author(s).

关键词： Haptic interfaces

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Location information Fusion for Secure Localization in Cyber-Physical Social Systems: A Case of Consumer's Trustworthy Personalized Recommendation

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Medhane, Darshan Vishwasrao Sangaiah, Arun Kumar Fan, Chun-I National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804 Taiwan SPPU K. K. Wagh Institute of Engineering Education and Research Department of Information Technology Maharashtra Nashik India National Yunlin University of Science and Technology International Graduate School of AI Douliu64002 Taiwan Sunway University School of Engineering and Technology Selangor Petaling Jaya47500 Malaysia Chandigarh University Punjab 140413 India National Sun Yat-sen University Department of Computer Science and Engineering Information Security Research Center Intelligent Electronic Commerce Research Center Kaohsiung804 Taiwan

Cyber-physical social systems (CPSS) have developed significantly in the last decade as a result of their effective computing and communication capabilities. Security and safety concerns, yet continue to be the biggest obstacle to the wider acceptance of CPSS in spite of all technological developments. In this work, we investigate the problem of secure localization of roaming users along with preserving their privacy in CPSS through location information fusion. We present a novel idea of privacy preserving location information fusion based on linear combination aggregation and extend it for its use in CPSS ensuring the privacy of anchor's locations and dimensions, and target's location while roaming in CPSS environment. Furthermore, a privacy-preserving secure localization scheme is offered, together with the necessary cryptographic support to ensure the ultimate aim of privacy. In CPSS contexts where real-time location information is crucial for participant's safety, the proposed privacy-preserving secure localization scheme can be implemented. The proposed scheme is assessed through the implementation of a trustworthy personalized consumer recommendation system. The experimental results demonstrate that the proposed method can guarantee high recommendation accuracy and achieve the accuracy and diversity of personalized recommendations under varying recommendation list lengths when compared to other reliable methods for personalized consumer recommendations. © 1975-2011 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Time Series Forecasting for Coronavirus (COVID-19) 1

引用

3rd International Conference on Futuristic Trends in Network and Communication Technologies, FTNCT 2020

作者： Sobti, Priyal Nayyar, Anand Nagrath, Preeti Computer Science and Engineering Bharati Vidyapeeth’s College of Engineering New Delhi110063 India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam

ISBN: (数字)9789811614804

ISBN: (纸本)9789811614798

The upsurge of the novel coronavirus has spread to many countries and has been declared a pandemic by WHO. It has shaken the most powerful countries across the world like the USA, UK, and has affected economies of various countries. The coronavirus or the 2019-nCoV causes the disease that has been named COVID-19. This disease transmits by inhaling droplets that are expelled by an infected person. It has been affecting people in different ways and has been found to be threatening for the older population or people with comorbidities. It has been seen that the virus 2019-nCoV spreads faster than the two of its antecedents namely severe acute respiratory syndrome coronavirus (SARS-CoV) and Middle East respiratory syndrome coronavirus (MERS-CoV). No cure or vaccine has been discovered as of now and taking precautions like staying at home are the only possible solutions. Our study analyzes the current trend of the disease in India and predicts future trends using time series forecasting. The official dataset provided by John Hopkins University through a GitHub repository has been used for the research for the time period of 22 January 2020 to 31 May 2020. The trend in cases, fatalities, and the people who have recovered until the date of 31 May 2020 has been discussed in the paper. It has been seen through the findings that the total number of cases is expected to rise to 2,15,000 by the end of May 2020 i.e. 31 May 2020 as per the AR (Autoregression) model. ARIMA (Autoregressive Integrated Moving Average) model predicts the number of cases to be 2,05,000 until the same date. Actual data has shown that the number of confirmed cases is 1,90,609 as on 31 May 2020 giving a percentage error of 7.57% and 12.85% for ARIMA and AR model respectively. Comparison between the findings of the two models has been shown later in the paper. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

Neural Machine Translation Approach for Low-resource Languages using Long Short-term Memory Model

Neural Machine Translation Approach for Low-resource Languag...

引用

computer science, information Technology and engineering (ICCoSITE), International Conference on

作者： Yaya Heryadi Bambang Dwi Wijanarko Dina Fitria Murad Cuk Tho Kiyota Hashimoto Computer Science Department BINUS Graduate Program – Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Information Systems Department BINUS Online Learning Bina Nusantara University Jakarta Indonesia Interdisciplinary Graduate School or Earth System Science and Andaman Natural Disaster Management Prince of Songkla University Phuket Thailand

Communication is a form of translation that human learns naturally since early childhood. Translating a language to another language has become instrumental when peoples interact with other people who speak a different language. One example of high-impact language translation is translating health protocols from the World Health Organization to many national languages to prevent the spread of the Covid-19 virus. However, the language translation is not an easy computation task when there is a language-resource gap. This paper presents empirical results on the performance of the Long Short-term Memory model as a machine translation involving Bahasa Indonesia and the Sundanese languages. Performance of the Sundanese language to Indonesian language translation is 0.93 average training and validation accuracy and 0.91 average testings BLEU score. Whilst, Indonesian language to Sundanese language translation is 0.92 average training and validation accuracy and 0.88 average testings BLEU score. Both models achieve 0.39 average training loss and 0.38 average validation loss.

关键词： Training Pediatrics Protocols Computational modeling Instruments Organizations Machine translation

来源：评论

学校读者我要写书评

暂无评论

Gamification in the Learning Community for Culinary Basics Course at Higher Education 8

Gamification in the Learning Community for Culinary Basics C...

引用

8th International Conference on ICT for Smart Society, ICISS 2021

作者： Winanti Meyliana Sestri Goestjahjanti, Francisca Lumban Gaol, Ford Prabowo, Harjanto Ferdiyatmoko Cahya Kumoro, Dwi STMIK Insan Pembangunan Information System Departement Tangerang15810 Indonesia Bina Nusantara University School of Information Systems Information Systems Department 11480 Indonesia STIE Insan Pembangunan Management Departement Banten Tangerang15810 Indonesia Bina Nusantara University BINUS Graduate Program-Computer Science Computer Science Department Jakarta11480 Indonesia Computer Science Department Doctor of Computer Science Bina Nusantara University 11480 Indonesia

ISBN: (纸本)9781665416979

This paper discusses basic culinary learning in universities using gamification techniques. The learning objectives are carried out to improve maximum learning outcomes, create a sense of pleasure and joy (satisfaction), and increase motivation. Although the author realizes that gamification is not the only learning technique that must be applied. The success of learning can be influenced by various factors including the internal factors of students and lecturers which until now have become the most important factors. Apart from the curriculum, social environment, and methods used, gamification is an alternative to produce maximum value, satisfaction, and motivation. The gamification technique is done by dividing students into several groups, each group consisting of 4 to 6 students. Each half-semester group is given learning by conventional methods and the next half-semester is given learning by gamification. Both will be evaluated through the results of the assessment in the form of statistics. The results obtained by using gamification on average have 10 to 20 points better than conventional methods. Students and lecturers become satisfied, motivated and get maximum test scores and they become more creative and innovative due to direct student involvement and fast interaction between lecturers and students. © 2021 IEEE.

关键词： Students

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：