检索结果-内蒙古大学图书馆

RLCFormer: Automatic roadside LiDAR-Camera calibration framework with transformer

Heliyon 2024年第20期10卷 e38506页

作者： Tian, Rui Bao, Xuefeng Chen, Yunli Liu, Feng Zhen, Yiqiang Li, Yong Faculty of Information Technology Beijing University of Technology Beijing 100124 China School of Software Engineering Beijing Jiaotong University Beijing 100044 China DFH Satellite Co. Ltd. Beijing 100094 China

LiDAR-Camera fusion is pivotal for perceiving and understanding complex traffic environments, particularly valuable in autonomous driving and traffic monitoring. Traditional calibration algorithms, primarily designed for onboard sensors, are inadequate for roadside setups where sensors are positioned higher and more dispersed. To address this challenge, we introduce the RLCFormer, a Transformer-based network specifically tailored for precise calibration of roadside sensors. This method innovatively integrates depth and RGB features, utilizing correlation layers and a Transformer decoder to accurately match features across modalities. Evaluated on the DAIR-V2X-I Roadside 3D detection dataset, the RLCFormer achieves an average translation error of 3.3187 cm and a rotation error of 0.0469°, surpassing existing methods. Our approach significantly enhances scene representation and calibration precision, offering a robust solution for roadside sensor calibration and advancing the state of the art in sensor fusion technology. © 2024 The Authors

关键词： Calibration and identification Computer vision for transportation LiDAR-camera systems Roadside traffic monitoring Sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Graph Learning: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2021年第2期2卷 109-127页

作者： Xia, Feng Sun, Ke Yu, Shuo Aziz, Abdul Wan, Liangtian Pan, Shirui Liu, Huan School of Engineering IT and Physical Sciences Federation University Australia BallaratVIC3353 Australia School of Software Dalian University of Technology Dalian116620 China Faculty of Information Technology Monash University MelbourneVIC3800 Australia School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

Graphs are widely used as a popular representation of the network structure of connected data. Graph data can be found in a broad spectrum of application domains such as social systems, ecosystems, biological networks, knowledge graphs, and information systems. With the continuous penetration of artificial intelligence technologies, graph learning (i.e., machine learning on graphs) is gaining attention from both researchers and practitioners. Graph learning proves effective for many tasks, such as classification, link prediction, and matching. Generally, graph learning methods extract relevant features of graphs by taking advantage of machine learning algorithms. In this survey, we present a comprehensive overview on the state-of-the-art of graph learning. Special attention is paid to four categories of existing graph learning methods, including graph signal processing, matrix factorization, random walk, and deep learning. Major models and algorithms under these categories are reviewed, respectively. We examine graph learning applications in areas such as text, images, science, knowledge graphs, and combinatorial optimization. In addition, we discuss several promising research directions in this field. Impact Statement—Real-world intelligent systems generally rely on machine learning algorithms handling data of various types. Despite their ubiquity, graph data have imposed unprecedented challenges to machine learning due to their inherent complexity. Unlike text, audio and images, graph data are embedded in an irregular domain, making some essential operations of existing machine learning algorithms inapplicable. Many graph learning models and algorithms have been developed to tackle these challenges. This article presents a systematic review of the state-of-the-art graph learning approaches as well as their potential applications. The article serves multiple purposes. First, it acts as a quick reference to graph learning for researchers and practitioners in differe

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Analysis of android applications permissions 3

Analysis of android applications permissions

引用

3rd International Conference on Data Science, E-Learning and information Systems, DATA 2021

作者： Saif, Amal Al-Kilani, Hamzeh Qasaimeh, Malik Al-Refai, Abdullah Computer Science Department King Hussein School of Computing Sciences Princess Sumaya University for Technology Amman Jordan Software Engineering Department Faculty of Computer and Information Technology Jordan University of Science and Technology Irbid Jordan

ISBN: (纸本)9781450388382

As Android is one of the most popular mobile open-source platforms, it is very important to ensure the security and privacy of Android apps. Android has an authorization system that allows developers to announce their applications requiring essential services, and when running such applications, users need to comply with these requirements. Users frequently download applications, giving them infinite permissions easily without thinking about the impact on their privacy. In this paper, we analyze 222 applications manually to grant these permissions to see how they are compatible with user privacy depending on many criteria. © 2021 Association for Computing Machinery.

关键词： Android (operating system)

来源：评论

学校读者我要写书评

暂无评论

The Essence of Perceived Compatibility and Behavioral Intention in Mobile Money Use

The Essence of Perceived Compatibility and Behavioral Intent...

引用

2024 International Conference on Advanced information Scientific Development, ICAISD 2024

作者： Susanti, Leni Mohamad, Siti Hajar Savitri, Mila Andria Saputra, Karen Etania Alamsyah, Doni Purnama Setiadi, Ahmad Bina Nusantara University Binus Business School Entrepreneurship Department Jakarta Indonesia Management and Science University Department of Business Management and Law Selangor Malaysia Bina Nusantara University School of Design Interior Design Department Jakarta Indonesia Bina Nusantara University School of Computer Science Computer Science Department Jakarta Indonesia Universitas Bina Sarana Informatika Faculty of Information Technology Software Engineering Department Jakarta Indonesia

ISBN: (纸本)9798350392036

Today, financial technology is a part of consumer needs. Mobile payments are used to support daily transactions, so a study of factors that can support behavioral intention and mobile money use is conducted. This study examines the support of digital literacy, perceived security, and perceived compatibility of mobile payments in increasing behavioral intention and mobile money use. The research was conducted on mobile payment users in Bandung City (Indonesia), and 416 research participants were asked using a questionnaire. The research was conducted using a quantitative survey and was processed using the SmartPLS tool. Two tests, namely, the PLS Algorithm and Bootstrapping, were used to test the research model. Next, the research hypothesis testing was used to explain the results. The research results found positive support from digital literacy, perceived security, and perceived compatibility on mobile payment behavioral intention. However, only perceived compatibility can directly increase the use of mobile money. In line with the hypothesis test, behavioral intention can support increased mobile money use by digital payment users. The research findings explain the ability of behavioral intention to mediate support for digital literacy, perceived security, and perceived compatibility in mobile money use. © 2024 IEEE.

关键词： Mobile commerce

来源：评论

学校读者我要写书评

暂无评论

Development of a Control System for a Lower Limb Exoskeleton Rehabilitation Robot for Stroke Patients with Standing Instability

Development of a Control System for a Lower Limb Exoskeleton...

引用

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Muxin Du Qingqing Wang Liucun Zhu Zhen Liu Lei Shi Yudong Fang Yinxi Gu School of Mechanical and Marine Engineering Beibu Gulf University Qinzhou China School of Electric and Information Engineering Beibu Gulf University Qinzhou China Sentinel Institute of Science and Technology Beibu Gulf University Qinzhou China School of Information Nagasaki Institute of Applied Science Nagasaki Japan Guangzhou Shiyuan Electronic Technology Company Limited Qinzhou China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huai'an China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

Lower-limb exoskeleton robots can medically assist stroke patients in standing and walking, but there is little research on lower-limb exoskeleton robots that assist in standing balance. In this paper, we design the system of a lower limb exoskeleton rehabilitation robot that can assist in standing balance. We performed kinematic modeling with OpenSim and forward dynamics simulation with SCONE. Having identified the muscle groups and joints that affect standing balance more significantly. This paper focuses on the effects of the hip and iliopsoas muscles on standing balance. We have developed a control system for a lower-limb exoskeleton rehabilitation robot that realizes: when inputting a hip joint change angle signal, an opposite moment and angle are output to control the lower limb exoskeleton rehabilitation robot to assist the patient to achieve standing balance. The robotic system was simulated and analyzed using Matlab and the results showed the effectiveness of the system to keep the patient in standing balance.

关键词： Legged locomotion Limbs Exoskeletons Stroke (medical condition) Muscles Assistive robots Control systems MATLAB Robots Hip

来源：评论

学校读者我要写书评

暂无评论

Everything you wanted to know about ChatGPT: Components, capabilities, applications, and opportunities

引用

Internet technology Letters 2024年第6期7卷

作者： Heidari, Arash Navimipour, Nima Jafari Zeadally, Sherali Chamola, Vinay Department of Software Engineering Haliç University Istanbul Turkey Department of Computer Engineering Faculty of Engineering and Natural Science İstanbul Atlas University Istanbul Turkey Department of Computer Engineering Faculty of Engineering and Natural Sciences Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Douliou Taiwan College of Communication and Information University of Kentucky LexingtonKY United States Pilani India

Conversational Artificial Intelligence (AI) and Natural Language Processing have advanced significantly with the creation of a Generative Pre-trained Transformer (ChatGPT) by OpenAI. ChatGPT uses deep learning techniques like transformer architecture and self-attention mechanisms to replicate human speech and provide coherent and appropriate replies to the situation. The model mainly depends on the patterns discovered in the training data, which might result in incorrect or illogical conclusions. In the context of open-domain chats, we investigate the components, capabilities constraints, and potential applications of ChatGPT along with future opportunities. We begin by describing the components of ChatGPT followed by a definition of chatbots. We present a new taxonomy to classify them. Our taxonomy includes rule-based chatbots, retrieval-based chatbots, generative chatbots, and hybrid chatbots. Next, we describe the capabilities and constraints of ChatGPT. Finally, we present potential applications of ChatGPT and future research opportunities. The results showed that ChatGPT, a transformer-based chatbot model, utilizes encoders to produce coherent responses. © 2024 John Wiley & Sons Ltd.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Artificial Intelligence in Cybersecurity: Integrating Advanced Technologies to Improve Threat Detection and Response

Research on the Application of Artificial Intelligence in Cy...

引用

Global Conference for Advancement in technology (GCAT)

作者： T.S.Balaji R.Nadanasabai Rajesh Jagadeesan Ravikumar S.Sharanyaa R.Meenal Nandigam Poornima Deepthi Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai Department of MBA St.Josephs College of Engineering Chennai Software Engineering Senior Advisor Evernorth Health Services Chattanooga TN Department of Information Technology Panimalar Engineering College Chennai Tamil Nadu India Department of Electrical and Electronics Engineering V.S.B Engineering College India Department of ECE MLR Institute of Technology Hyderabad

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

In the current age of digital change, the field of cybersecurity is faced with progressively advanced and enduring dangers. Conventional security measures are finding it difficult to keep up with the fast-changing nature of cyber threats. Artificial intelligence (AI) offers a significant chance to enhance threat detection and response systems by leveraging its sophisticated data processing and pattern recognition abilities. This study explores the incorporation of artificial intelligence (AI) technology in the field of cybersecurity, specifically aiming to improve the effectiveness of systems that identify and respond to threats. The paper commences by examining the present difficulties encountered by cybersecurity experts, which encompass the large number and diverse range of potential threat vectors, the covert and flexible nature of contemporary malware, and the limitations imposed by resource constraints on the efficacy of human-driven analysis. The text explores the current cutting-edge AI strategies used to tackle these difficulties, including anomaly identification through machine learning algorithms, predictive analysis using deep learning models, and threat intelligence collecting through natural language processing. The research also examines the distinct factors of AI in the cybersecurity field, such as the requirement for immediate decision-making, the significance of comprehending the model, and the possibility of hostile attacks on AI systems. This study seeks to analyse current literature and emerging trends to gain a deep understanding of how artificial intelligence (AI) can enhance cybersecurity. Additionally, it aims to identify the obstacles and deficiencies that must be overcome to effectively incorporate AI technologies into this crucial domain. To summarise, the research highlights the considerable capacity of AI to transform cybersecurity practices, providing a way to develop more robust and flexible defence methods against the numerous danger

关键词： Deep learning Ethics Machine learning algorithms Transforms Semisupervised learning Threat assessment Vectors Safety Artificial intelligence Computer security

来源：评论

学校读者我要写书评

暂无评论

Early Fault Detection in Rolling Element Bearings Using Signal Processing Techniques

Early Fault Detection in Rolling Element Bearings Using Sign...

引用

International Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Ali Saeed M. Usman Akram Muazzam A. Khan M. Belal Afsar Department of Computer Science ICESCO Chair Big Data Analytics and Edge Computing Quaid-i-Azam University Islamabad Pakistan Department of Computer and Software Engineering National University of Sciences & Technology Islamabad Pakistan Faculty of Electrical Engineering and Information Technology Otto-von-Guericke University Maddeburg DE

ISBN: (数字)9798350378078

ISBN: (纸本)9798350378085

Many studies show that bearings are the most vulnerable components in low-voltage motors. While advanced bearing diagnostic systems exist, their cost can be a barrier for non-critical machinery due to the potential wait time to see a return on investment. This research explores the feasibility of using basic signal processing techniques on vibration data for bearing condition monitoring. The primary goal is to analyze benchmark data from the Case Western Reserve University (CWRU) dataset and establish a baseline performance for this data-driven approach. The results suggest that, with appropriate signal processing, it's possible to achieve early detection of bearing faults, leading to more efficient time-to-fault identification with higher detection accuracies ranging from 83 % to 100 % for each method.

关键词： Vibrations Fault diagnosis Low voltage Smart cities Rolling bearings Signal processing Motors Robots Monitoring Investment

来源：评论

学校读者我要写书评

暂无评论

Quantum computation on a 19-qubit wide 2d nearest neighbour qubit array

arXiv

引用

arXiv 2022年

作者： Shaw, Alexis T.E. Bremner, Michael J. Paler, Alexandru Herr, Daniel Devitt, Simon J. Centre for Quantum Computation and Communication Technology Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology SydneyNSW2007 Australia Aalto University Espoo02150 Finland d-fine GmbH An der Hauptwache 7 Frankfurt60213 Germany Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology SydneyNSW2007 Australia

In this paper, we explore the relationship between the width of a qubit lattice constrained in one dimension and physical thresholds for scalable, fault-tolerant quantum computation. To circumvent the traditionally low thresholds of small fixed-width arrays, we deliberately engineer an error bias at the lowest level of encoding using the surface code. We then address this engineered bias at a higher level of encoding using a lattice-surgery surface code bus that exploits this bias, or a repetition code to make logical qubits with unbiased errors out of biased surface code qubits. Arbitrarily low error rates can then be reached by further concatenating with other codes, such as Steane J7, 1, 3K code and the J15, 7, 3K CSS code. This enables a scalable fixed-width quantum computing architecture on a square qubit lattice that is only 19 qubits wide, given physical qubits with an error rate of 8.0 × 10−4. This potentially eases engineering issues in systems with fine qubit pitches, such as quantum dots in silicon or gallium arsenide. Copyright © 2022, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Application of Nonlinear Gaussian Process Regression Models for CO2 Emissions Prediction

Application of Nonlinear Gaussian Process Regression Models ...

引用

International Conference on Innovations in information technology

作者： Ahmed Abdelhadi Ahmed Yousif Badri Asaad Shamseldin Department of Computer Science & Software Engineering College of Information Technology (CIT) United Arab Emirates University Al Ain UAE Department of Mechanical and Mechatronics Engineering Faculty of Engineering University of Auckland Auckland New Zealand Department of Civil and Environmental Engineering Faculty of Engineering University of Auckland Auckland New Zealand

The growing concern over climate change led to a massive corpus of literature addressing the impact of various factors in terms of carbon dioxide (CO2) emissions levels. However, the majority of existing literature employs linear models to a singular factor, neglecting the relation of these factors and their impact in conjunction on CO2 emissions levels. To answer this question, this study conducted an intensive literature review to identify proper factors to deduce parameters that influence CO2 emissions levels. These parameters, derived from data spanning from 1965 to 2021 in the United Arab Emirates, underwent thorough analysis using Dominance Analysis to establish their significance in relation to CO2 emissions levels. Subsequently, we employed nonparametric nonlinear Gaussian Process Regression (GPR) models with diverse kernels to assess their performance against traditional parametric linear models. The results showed that nonparametric nonlinear GPR models provide the most accurate predictions for CO2 emissions, with the GPR-Matern kernel outperforming all other models, achieving an R-squared value of 98.1%. Our findings highlight the importance of adopting a nonlinear approach for predicting and forecasting CO2 emissions levels when considering the interplay of driving factors.

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：