检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Scherp, Ansgar Groener, Gerd Škoda, Petr Hose, Katja Vidal, Maria-Esther Ulm University Germany Carl Zeiss SMT GmbH Germany Department of Software Engineering Faculty of Mathematics and Physics Charles University Prague Czech Republic TU Wien Austria Leibniz University of Hannover TIB-Leibniz Information Centre for Science and Technology Germany

Ever since the vision was formulated, the Semantic Web has inspired many generations of innovations. Semantic technologies have been used to share vast amounts of information on the Web, enhance them with semantics to give them meaning, and enable inference and reasoning on them. Throughout the years, semantic technologies, and in particular knowledge graphs, have been used in search engines, data integration, enterprise settings, and machine learning. In this paper, we recap the classical concepts and foundations of the Semantic Web as well as modern and recent concepts and applications, building upon these foundations. The classical topics we cover include knowledge representation, creating and validating knowledge on the Web, reasoning and linking, and distributed querying. We enhance this classical view of the so-called "Semantic Web Layer Cake" with an update of recent concepts that include provenance, security and trust, as well as a discussion of practical impacts from industry-led contributions. We conclude with an outlook on the future directions of the Semantic Web. Copyright © 2024, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

H2P×PKD: Progressive Training Pipeline with Knowledge Distillation for Lightweight Backbones in Pedestrian Detection

H2P×PKD: Progressive Training Pipeline with Knowledge Disti...

引用

International Conference on Multimedia Analysis and Pattern Recognition (MAPR)

作者： Duc-Nhuan Le Hoang-Phuc Nguyen Vinh-Toan Vong Nguyen-Khoa Luong Trong-Le Do Faculty of Information Technology University of Science VNU-HCM Ho Chi Minh City Vietnam Vietnam National University Ho Chi Minh City Vietnam Software Engineering Laboratory University of Science VNU-HCM Ho Chi Minh City Vietnam

ISBN: (数字)9798350368437

ISBN: (纸本)9798350368444

Pedestrian Detection, an instance of Object Detection, has many applications, especially in autonomous driving and surveillance. While many methods are tailored for pedestrian detection, studies suggest that general object detection approaches can also be effective with the appropriate training settings. The large domain unsimilarity between general object data and pedestrian-specific data is a significant challenge. To address this, Pedestron introduces a progressive training pipeline that begins with pre-training on a large and diverse general human dataset, followed by fine-tuning on pedestrian-specific data. However, this transition remains too abrupt. Additionally, the model’s size and computational cost are also not receiving much attention. Therefore, we propose H2P, a new training pipeline based on Pedestron. The pipeline includes IDSS, an intermediate training step for detecting general humans in traffic-related contexts before fine-tuning on pedestrian datasets. Moreover, we leverage PKD, a knowledge distillation method via Pearson Correlation Coefficient, to improve lightweight models using FPN features from large-scale, general teacher models. To evaluate the effectiveness of our H2P with PKD approach, we experiment on two lightweight backbones: a traditional MobileNetV2 and a downscaled variant of InternImage, named InternImage-M. Our best result is 8.59% MR −2 on CityPersons’ validation set. Our lightweight InternImage-M backbone gives the promising result of 11.53% MR −2 .

关键词： Training Correlation coefficient Pedestrians Surveillance Multimedia systems Pipelines Object detection

来源：评论

学校读者我要写书评

暂无评论

Image-based Freeform Handwriting Authentication with Energy-oriented Self-Supervised Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Mou, Luntian Zheng, Changwen Gao, Wen The University of Chinese Academy of Sciences Beijing100049 China The National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing100086 China Beijing Institute of Artiicial Intelligence Faculty of Information Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing100124 China The School of Electronics Engineering and Computer Science Peking University Beijing100871 China

Freeform handwriting authentication verifies a person’s identity from their writing style and habits in messy handwriting data. This technique has gained widespread attention in recent years as a valuable tool for various fields, e.g., fraud prevention and cultural heritage protection. However, it still remains a challenging task in reality due to three reasons: (i) severe damage, (ii) complex high-dimensional features, and (iii) lack of supervision. To address these issues, we propose SherlockNet, an energy-oriented two-branch contrastive self-supervised learning framework for robust and fast freeform handwriting authentication. It consists of four stages: (i) pre-processing: converting manuscripts into energy distributions using a novel plug-and-play energy-oriented operator to eliminate the influence of noise;(ii) generalized pre-training: learning general representation through two-branch momentum-based adaptive contrastive learning with the energy distributions, which handles the high-dimensional features and spatial dependencies of handwriting;(iii) personalized fine-tuning: calibrating the learned knowledge using a small amount of labeled data from downstream tasks;and (iv) practical application: identifying individual handwriting from scrambled, missing, or forged data efficiently and conveniently. Considering the practicality, we construct EN-HA, a novel dataset that simulates data forgery and severe damage in real applications. Finally, we conduct extensive experiments on six benchmark datasets including our EN-HA, and the results prove the robustness and efficiency of SherlockNet. We will release our code and dataset at https://***/WangJingyao07/SherlockNet. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

The Low-Cost IoT Mornitoring the Quality of River: A Case Study of Wang River in Lampang Municipality

The Low-Cost IoT Mornitoring the Quality of River: A Case St...

引用

International Computer Science and engineering Conference (ICSEC)

作者： Narong Krueganta Oran Chieochan Anukit Saokaew Ekkachai Yana Chaowoot Singkaew Weerachai Sawangtook Ekkarat Boonchieng Warakhom Wongchai Sakchai Srimakorn Faculty of Industrial Technology School of Industrial Technology Lampang Rajabhat University Lampang Thailand Faculty of Sciences School of Information Technology Lampang Rajabhat University Lampang Thailand Faculty of Science School of Environmental innovation Lampang Rajabhat University Lampang Thailand Faculty of Industrial Technology School of Computer Engineering Lampang Rajabhat University Lampang Thailand Department of Computer Sciences Faculty of Sciences Chiang Mai University Chiang Mai Thailand Faculty of Industrial Technology School of Industrial Electrical Engineering Lampang Rajabhat University Lampang Thailand Faculty of Industrial Technology School of Software Engineering Lampang Rajabhat University Lampang Thailand

The research project focuses on prototyping an IoT (Internet of Things) system for measuring and monitoring the quality of the Wang River in Lampang Municipality. The system utilizes EC (Electrical Conductivity), pH, and temperature sensors connected to an ESP32 microcontroller with a custom-developed board. Additionally, the IoT system is supported by a solar cell system to provide power. The software programming is implemented using Arduino C++ on the PlatformIO platform, which is integrated with Visual Studio code. The IoT platform chosen for this project is ThingsBoard, specifically the community version. The research findings indicate that the utilization of IoT technology combined with the sensors has improved the prototype of a low-cost IoT monitoring system for assessing the quality of the Wang River in Lampang Municipality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and development of two-factor authentication methods using neural networks

Research and development of two-factor authentication method...

引用

Smart information Systems and Technologies (SIST), IEEE International Conference on

作者： Temirkhan Darbek Assel Mukasheva Alibek Bissembayev Sergiy Gnatyuk Dinargul Mukammejanova Department of Information Systems and Cybersecurity Almaty University of Power Engineering and Telecommunications Almaty Kazakhstan School of Information Technology and Engineering Kazakh-British Technical University Almaty Kazakhstan Faculty of Cybersecurity Computer and Software Engineering National Aviation University National Aviation University Kyiv Ukraine Department of Artificial Intelligence and Big Data Kazakh National University named after Al-Farabi Almaty Kazakhstan

ISBN: (数字)9798350374865

ISBN: (纸本)9798350374872

This article is devoted to the research and development of innovative two-factor authentication (2FA) methods using neural networks. 2FA plays a key role in ensuring the security of data and accounts in the modern digital world, and the use of neural networks opens up new prospects in strengthening protection and improving the user experience. The article presents an analysis of existing 2FA methods, identifies their limitations, and discusses the advantages of using neural networks in this area. The main focus is on the development of new authentication algorithms based on deep learning, providing effective anomaly detection and support for a dynamic adaptive approach. In the context of the article, the issues of privacy and data security are also considered, as well as the possibilities of applying the developed methods in various fields, including finance, medicine and the Internet of Things. The results of the study represent a significant contribution to the field of digital

关键词： Codes Face recognition Heuristic algorithms Data security Neural networks Authentication Chatbots

来源：评论

学校读者我要写书评

暂无评论

Beyond Data, Towards Sustainability: A Sydney Case Study on Urban Digital Twins

SSRN

引用

SSRN 2023年

作者： Sohail, Ammar Shen, Bojie Cheema, Muhammad Aamir Ali, Mohammed Eunus Ulhaq, Anwaar Babar, Muhammad Ali Qureshi, Asama Faculty of Information Technology Monash University ClaytonVIC3800 Australia Dhaka1000 Bangladesh School of Engineering and Technology Central Queensland University Australia SydneyNSW2000 Australia Centre for Research on Engineering Software Technologies University of Adelaide North Terrace SA5005 Australia

As urban areas grapple with unprecedented challenges stemming from population growth and climate change, the emergence of urban digital twins offers a promising solution. This paper presents a case study focusing on Sydney's urban digital twin, a virtual replica integrating diverse real-time and historical data, including weather, crime, emissions, and traffic. Through advanced visualization and data analysis techniques, the study explores some applications of this digital twin in urban sustainability, such as spatial ranking of suburbs and automatic identification of correlations between variables. Additionally, the research delves into predictive modeling, employing machine learning to forecast traffic crash risks using environmental data, showcasing the potential for proactive interventions. The contributions of this work lie in the comprehensive exploration of a city-scale digital twin for sustainable urban planning, offering a multifaceted approach to data-driven decision-making. © 2023, The Authors. All rights reserved.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sovereign Allocation of Resources in Cloud Milieus Using a Causal Dilated Geometric Algebra Approach for Dynamic Scalability

Enhancing Sovereign Allocation of Resources in Cloud Milieus...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： Chandrasekhar Rao Katru Sathish Srinivasan Mohan Kumar T G Sunita Yadwad G. Satish Ramya Maranan Lead Software Engineer Indian Land SC USA Oracle Cloud Infrastructure Division Machine Learning & AI Development San Francisco Bay Area California USA Department of Information Science and Engineering Nitte Meenakshi Institute of Technology Bengaluru Karnataka Computer science and Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Post Limda Gujarat Department of Electrical and Electronics Engineering Sree Dattha Institute of Engineering and Science Sheriguda Telangana Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance.

关键词： Cloud computing Energy consumption Algebra Scalability Quality of service Transformers Real-time systems Resource management Time factors Service level agreements

来源：评论

学校读者我要写书评

暂无评论

A Novel Trust Assessment System for Online Social Networking Environment Using Learning Assisted Classification Model

A Novel Trust Assessment System for Online Social Networking...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： S. Nithya D. Deepa Vunnava Dinesh Babu Pallavi G Hamed Fawareh R. D. Kayalvizhy Department of Computer Science Engineering Saveetha Engineering College Chennai Department of CSE St. Joseph's College of Engineering Chennai Department of CSE RV Institute of Technology Guntur Department of Civil Engineering Laxminarayan Innovation Technological University Nagpur India Software Engineering Dept Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia Department of Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai Tamil Nadu

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Trust is essential in the constantly developing environment of online social networks. The Nexus Terroism Impact and Intro Trust facilitate the communication, decision-making, and maintenance of digital communities among individuals. Trust-based Learning with Classification Principle (TLCP) is introduced in this research to improve the assessment of trust in social networks. To ascertain its efficacy, our proposed methodology undergoes a 10-fold cross-validation against the Trust Assessment Methodology (TAM). The traditional Trust Assessment Model (TAM) evaluates and regulates trust in Internet social networking. This method incorporates trust assessment factors to generate a user dependability judgment that is both discriminatory and dynamic. The Trustworthy Account Management (TAM) challenge is designed to enhance digital trust by addressing disinformation, deception, and hostile conduct. The TLCP is able to accurately evaluate trust by utilizing reputation scoring, community analysis, and user behavior metrics. Trust levels are dynamically adjusted as a result of the identification of trustworthy behavioral patterns and danger indicators by machine learning algorithms and social media data. This research examines the connections between trust management and digital interactions and suggests a general solution to alleviate specific trust evaluation issues across online social networks.

关键词： Measurement Machine learning algorithms Social networking (online) Privacy breach Real-time systems Hazards Maintenance Internet Fake news Trust management

来源：评论

学校读者我要写书评

暂无评论

Light-weight Sketch Recognition with Knowledge Distillation

Light-weight Sketch Recognition with Knowledge Distillation

引用

International Conference on Multimedia Analysis and Pattern Recognition (MAPR)

作者： Viet-Tham Huynh Tam.V Nguyen Minh-Triet Tran Software Engineering Laboratory and Faculty of Information Technology University of Science VNU-HCM Vietnam Vietnam National University Ho Chi Minh City Vietnam Department of Computer Science University of Dayton U.S.A.

Recognizing hand-drawn sketches is a promising starting point for various applications, such as assisting artists in creating 3D environments for games or virtual environment scenes quickly and efficiently from concept arts. In addition, by understanding drawings, we can generate 3D models that can be used for further design and development. Thus, in this paper, we aim to develop a novel lightweight network that can accurately recognize sketch drawings. We propose a lightweight-yet-efficient neural network based on MobileNetV2 for sketch recognition and employ knowledge distillation to train the proposed model from EfficientNet-B4. To evaluate the accuracy of the proposed method, we collect a dataset of sketches comprising 1800 drawings in 12 categories, ranging from furniture to animals. The experimental results show that our network model achieves an accuracy of 96.7%, with 96.9% precision, 96.7% recall, and 96.7% F1-score. These results demonstrate that the proposed approach has great potential for practical sketch recognition applications, such as interior design or VR scene generation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EPPR: Blockchain for educational record sharing and recommendation using the Ethereum platform

EPPR: Blockchain for educational record sharing and recommen...

引用

作者： Alkouz, Akram HajYasien, Ahmed Alarabeyyat, Abdulsalam Samara, Khalid Al-Saleh, Mohammed I. Computer Information Sciences Higher Colleges of Technology Abu Dhabi United Arab Emirates Software Engineering Department Faculty of Prince Abdullah Bin Ghazi of Information Technology Al-Balqa' Applied University As-Salt Jordan Department of Computer Science Jordan University of Science and Technology Al Ramtha Irbid Jordan

There has been a great deal of discussion of the challenges on privacy of Educational Professional Personal Record (EPPR). Therefore, it is required to reassess the current models, in which various parties generate, exchange and observe a huge amount of personal data with regard to EPPR. Ethereum blockchain has shown that trusted, auditable transactions are detectible using a decentralised network of nodes. In this paper, we propose a novel decentralised framework to manage EPPR using Ethereum blockchain. The framework provides the owner of the EPPR a comprehensive immutable log and accessibility to their educational records across the educational record editors and consumers. Furthermore, it provides a recommender engine to endorse skills and competencies to the education record owners and similar candidates for educational records editors and consumers. The aim of the proposed framework is to enable educational stakeholders to participate in the network as blockchain miners rewarded by pseudonymised data. Copyright © 2021 Inderscience Enterprises Ltd.

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：