检索结果-内蒙古大学图书馆

2nd International Conference on Business Analytics for technology and Security, ICBATS 2023

作者： Bharany, Salil Taleb, Nasser Sadiq, M. Tariq Kanwal, Nayab Abdelhakim, Mohamed Ghazal, Taher M. Pradhan, Manas Rehman, Ateeq Ur Tech Amritsar India CET Department United Kingdom Canadian University Dubai Faculty of Management Dubai United Arab Emirates University of Brighton School of Architecture Engineering United Kingdom NCBA&E School of Computer Science Lahore Pakistan Applied Science Private University Applied Science Research Center Amman11937 Jordan University of Dubai College of Engineering and IT United Arab Emirates Skyline University College School of Information Technology Sharjah United Arab Emirates Department of Electrical Engineering GCU Lahore Pakistan

ISBN: (纸本)9798350335644

Increased hardware capability has allowed many businesses to store massive amounts of data in the previous few years. Streams of data may go on forever, so they are used in so many different applications. Analyzing and querying these streams is challenging for a stream of dynamic information. The term "big data"refers to a collection of methods and tools that must be combined in novel ways to unearth the vast amounts of previously unseen information buried within vast, diverse, and intricate databases. There are several ways to obtain, organize and analyze data in the big data world. In order to deal with streaming data, efficient data mining procedures must be in place. In this article, we examine a variety of Big Data-related concerns and challenges. This paper introduces the features, and challenges of managing big data. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

LanCOPE: Language-Guided Category-Level Object Pose Estimation from a Single RGB Image

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 7555-7562页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Dai, Zhenqi Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha 410082 China Central South University School of Architecture and Art Changsha 410082 China The University of Western Australia Department of Computer Science and Software Engineering 6009 WA Australia

Monocular RGB-based category-level object pose estimation is more practical and cost-effective for robotics. However, existing methods do not fully exploit the rich semantic and contextual information in multimodal data (e.g. language) that provides additional object attributes to guide the model in extracting category features more reliably. We propose a language-guided category-level object pose estimation method (LanCOPE), taking a single RGB image as input. Our method uses DINOv2 to recover depth from a single RGB image and converts it into point cloud to perceive the object's geometry. We then introduce language descriptions for the RGB image, estimated point cloud and overall scene to better guide the point cloud encoder and image encoder in learning category features. We develop a cross-modal differential perception feature fusion network to fuse multimodal features. This network employs a differential perception module to eliminate redundant information across different modalities, highlighting signifcant semantic differences and similarities. Furthermore, it uses a cross-attention mechanism to fuse the semantic information of the language and vision features, improving the overall perception. Finally, we design a denoising network based on the skip fusion transformer to recover the object pose accurately. Extensive experiments on REAL275 and Wild6D datasets show that LanCOPE achieves state-of-the-art performance. Our code is available at LanCOPE. © 2016 IEEE.

关键词： category-level object pose estimation languag RGB image

来源：评论

学校读者我要写书评

暂无评论

P4toNFV: Offloading from P4 switches to NFV in programmable data planes

引用

International Journal of Communication Systems 2024年第5期37卷 e5687-e5687页

作者： Pekar, Adrian Makara, Laszlo A. Lai, Yuan-Cheng Lin, Ying-Dar Seah, Winston Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Budapest Hungary HUN-REN-BME Information Systems Research Group Budapest University of Technology and Economics Budapest Hungary Department of Information Management National Taiwan University of Science and Technology Taipei Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

P4 combines the benefits of hardware-based networking with the adaptability of software-based network operations. However, when faced with intricate network functions, P4 switches reveal constraints in memory and processing primitives. To address these, we advocate offloading traffic demanding intricate processing from the programmable data plane to network function virtualization (NFV). By leveraging this approach, P4 switches handle the core data plane, ensuring maximum performance, whereas virtualized network functions (VNF) cater to the intricate processing. Central to our research is the optimization of this offloading process, specifically considering delay constraints. We developed an analytical model that examines a P4 switch overseen by an SDN controller, integrating an offloading capability to NFV. The principal objective was to determine an offloading rate that minimizes packet processing delay. To this end, we employed a Bounded method, an advancement from Brent's method, to determine this optimal rate. The findings indicate that offloading approximately 66% of packets to the VNF achieves the lowest total delay, registering at 0.1505 (Formula presented.) s. This strategy of optimal offloading can notably reduce the system's average delay as the demand for network functions increases. The optimization technique we adopted exhibited rapid convergence in our experiments, reflecting the method's efficacy. Furthermore, a rigorous parametric sensitivity analysis spanning no offloading, full offloading, and optimal offloading strategies underscores that optimal offloading to NFV consistently augments system performance, particularly in terms of delay reduction. Conclusively, our study furnishes valuable insights into offloading strategies, augmenting the narrative on resource allocation in both PNFs and VNFs. © 2023 The Authors. International Journal of Communication Systems published by John Wiley & Sons Ltd.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Implicit Relative Labeling-Importance Aware Multi-Label Metric Learning 39

Implicit Relative Labeling-Importance Aware Multi-Label Metr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Mao, Jun-Xiang Rui, Yong Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China Information Technology and Data Management Department China Mobile Communications Group Zhejiang Co. Ltd. China Lenovo Research Lenovo Group Ltd. Beijing China

ISBN: (纸本)157735897X

Multi-label metric learning, as an extension of metric learning to multi-label scenarios, aims to learn better similarity metrics for objects with rich semantics. Existing multi-label metric learning approaches employ the common assumption of equal labeling-importance, i.e., all associated labels are considered relevant to the training instance, while there is no differentiation in the relative importance of their semantics. However, this common assumption does not reflect the fact that the importance of each relevant label is generally different, even though such importance information is not directly accessible from the training examples. In this paper, we claim that it is beneficial to leverage the implicit Relative Labeling-Importance (RLI) information to facilitate multi-label metric learning. Specifically, the manifold structure within the feature space is exploited by local linear reconstruction, and then the RLIs are recovered by transferring such structure to the label space. Subsequently, a discrimiative multi-label metric learning framework is introduced to align the predictive modeling outputs with the recovered RLIs, under which instances with similar RLI are implicitly pulled closer to each other, while those with dissimilar RLI are pushed further apart. Comprehensive experiments on benchmark multi-label datasets validate the superiority of our proposed approach in learning effective similarity metrics between multi-label examples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Nameplates

来源：评论

学校读者我要写书评

暂无评论

Comparison Model for Forecasting the Total Population in Bangkok 9

Comparison Model for Forecasting the Total Population in Ban...

引用

Joint 9th International Conference on Digital Arts, Media and technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Tipwong, Nattanicha Jitpattanakul, Anuchit Phaphan, Wikanda Nontapa, Chalermrat Mekruksavanich, Sakorn King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand Chiang Mai University Faculty of Science Department of Statistics Chiang Mai50200 Thailand Research Group in Statistical Learning and Inference Thailand University of Phayao School of Information and Communication Department of Computer Engineering Phayao56000 Thailand

ISBN: (纸本)9798350318241

The primary aim of this article is to investigate, contrast, and formulate a time series model to predict Bangkok's overall population. In this study, we intend to propose a hybrid model that combines the Autoregressive Moving Integrated Average (ARIMA) model and machine learning techniques, utilizing a Multilayer Perceptron (MLP). Our data source comprises monthly data from 2002 to 2022, totaling 252 data points, obtained from the official registration statistics system of the Registration Administration Office, Department of Provincial Administration. This dataset has been divided into two subsets: the first subset covers the years from 2002 to 2021, encompassing 240 data points, which will be used for constructing predictive models. The second subset consists of the data for the year 2022, comprising 12 data points, which will serve as a means to compare the accuracy of various forecasting methods. The evaluation criteria employed for this purpose are the minimum mean absolute error (MAE), the mean square error (MSE) and the mean absolute percentage error (MAPE). Furthermore, we will utilize the Python programming language to facilitate data analysis. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

A Cactus-Inspired Biomimicry Shading Device for Office Building Typologies

SSRN

引用

SSRN 2024年

作者： Fattah, Twana Rasool Jalal, Shazad Jamal Katona, Tamás János Baranyai, Bálint Marcel Breuer Doctoral School Faculty of Engineering and Information Technology University of Pécs Boszorkány Street 2-E81 Pécs7624 Hungary College of Engineering University of Sulaimani Sulaimani46001 Iraq Department of Building Structures and Energy Design Institute of Architecture Faculty of Engineering and Information Technology University of Pécs Boszorkány Street 2 Pécs7624 Hungary Energy Design Research Group Institute of Architecture Faculty of Engineering and Information Technology University of Pécs Hungary

Highlights• Utilised a novel biomimetic approach to save energy in office buildings in Iraq• This novel approach achieved varied energy savings in various typologies• Devised a novel approach to simulate curvilinear shading by IDA ICE software• These plant-inspired shading devices can save cooling energy up to 31%• These practical findings can be effective in temperate and desert climate zones © 2024, The Authors. All rights reserved.

关键词： Office buildings

来源：评论

学校读者我要写书评

暂无评论

Novel heuristics for Stock portfolio optimization using machine learning and Modern Portfolio Theory

Novel heuristics for Stock portfolio optimization using mach...

引用

Business Analytics for technology and Security (ICBATS), International Conference on

作者： Bristo Joemon Mustansar Ali Ghazanfar Muhammad Awais Azam N. Z Jhanjhi Arshad Ali Khan Department of Engineering & Computing University of East London London UK Technology Innovation Research Group School of Information Technology Whitecliffe NZ School of Computer Science SCS Taylor's University Malaysia Malaysia Elm Research & Innovation ELM Riyadh KSA

Stock market portfolio optimization is a very important aspect for stock market trading. Various techniques have been proposed in the literature ranging from technical indicator-based methods to statistical methods and machine learning for portfolio optimization. However, there has been lack of effort to find the impact of machine learning along with technical indicators to build optimal stock portfolios for trading. From this line of research, this paper focusses on the use of deep learning-based LSTM (Long Short Term Memory) models along with Ichimoku cloud indicators to build optimal portfolios, which can be used in a practical stock market environment. This model is developed with combining the above prediction models such as LSTM and Ichimoku Cloud Indicators with Modern Portfolio Theory and Sharpe Ratio to optimize the model by reducing the risk to reward ratio. The model is tested with real life data of London Stock Exchange and Bombay Stock Exchange. By doing extensive experimental analysis, it was found that, the model combining LSTM network and Ichimoku Indicator, paired with Modern Portfolio Theory and Sharpe Ratio giving consistent performance in the market despite volatility.

关键词： Statistical analysis Machine learning Predictive models Distance measurement Data models Security Stock markets

来源：评论

学校读者我要写书评

暂无评论

Intelligent Internet of Things Attack Detection: Novel Approaches and Technologies

Intelligent Internet of Things Attack Detection: Novel Appro...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Bakhtawar Saeed Sobia Arshad Sanay Muhammad Umar Saeed Muhammad Awais Azam Adeel Akram Shehla Gul Computer Engineering Department University of Engineering and Technology Taxila Taxila Pakistan Deep Packet Inspection Lab (DPI) National Center of Cyber Security (NCCS) UET Taxila Pakistan Technology Innovation Research Group School of Information Technology Whitecliffe NZ

The Internet of Things (IoT) influences numerous facets of our daily lives, and artificial intelligence (AI)-based programs and applications are rapidly gaining popularity. Due to the vast adaptability of the IoT and the escalating data privacy concerns, classical AI algorithms may not be applicable in certain practical application domains. Federated learning (FL) has emerged as a viable technique for training distributed machine learning (ML) models while maintaining data privacy and security. In recent years, it has gained attention in the context of IoT security, particularly for detecting attacks on IoT devices and networks. In this article, we examine ML and DL in the context of the IoT and IoT attack detection. Then, we evaluate the most recent FL applications in IoT networks and IoT attack detection, investigating their potential to deliver a variety of IoT services, including security and privacy. Our work on detecting FL-IoT attacks has taught us a lot, and at the end, we suggest some directions for future research in this quickly growing field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time Workflow Scheduling in Hybrid Clouds with Privacy Protection

MARS: Multi-Agent Deep Reinforcement Learning for Real-Time ...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Long Cheng Haoyang He Yan Gu Qingzhi Liu Zhiming Zhao Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Information Technology Group Wageningen University and Research Netherlands Research Group of Multi-Scale Networked Systems University of Amsterdam Netherlands

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Scheduling workflows in hybrid cloud environments presents significant challenges due to the inherent complexity of workflows and the dynamic nature of cloud resources. This complexity is further increased when attempting to balance workflow performance with privacy protection. Recent efforts have leveraged deep reinforcement learning (DRL) to address these challenges. However, most of these approaches rely on single-agent models, which can lead to security issues and scalability problems due to their centralized processing. Specifically, the properties of workflows are transferred to the single agent, which risks leaking privacy information. Our paper addresses these issues by introducing MARS, a real-time workflow scheduling method that prioritizes privacy protection in hybrid clouds. MARS leverages multi-agent deep reinforcement learning (MADRL) to optimize the workflow scheduling of cloud virtual machines (VMs). The benefit of our solution is that it relies on the collaborative learning of multi-agents on multiple VMs, which could assign user data to specific cloud servers for privacy protection while sharing training experiences between agents. In our implementation, MARS aims to reduce workflow completion time and operational costs while complying with strict privacy protection guidelines. The experimental results demonstrate that MARS can significantly surpass existing methods, reducing makespan by an average of $53.18 \%$ and costs by $61.98 \%$ compared to basic techniques, and achieving $20.26 \%$ and $25.71 \%$ improvements over the latest advanced methods, respectively.

关键词： Training Cloud computing Privacy Costs Scalability Deep reinforcement learning Dynamic scheduling Real-time systems Complexity theory Protection

来源：评论

学校读者我要写书评

暂无评论

Non-Orthogonal Multiple Access Based Multi-Objective Optimization in Emergency Task Offloading

Non-Orthogonal Multiple Access Based Multi-Objective Optimiz...

引用

2025 IEEE Wireless Communications and Networking Conference, WCNC 2025

作者： Chen, Caijuan Zhang, Chaofeng Li, Gaolei Liu, Yuchen National Institute of Informatics The Information Systems Architecture Science Research Division Tokyo Japan Advanced Institute of Industrial Technology Tokyo Japan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Nc State University Department of Computer Science NC United States

ISBN: (纸本)9798350368369

The escalating frequency of geological disasters, local conflicts, and public health crises necessitates robust emergency communication systems within Internet of Things (IoT) frameworks to ensure public safety. Employing Power-Domain NOMA (PD-NOMA) and Successive Interference Cancellation (SIC) enables effective multi-device communication that is crucial for emergency responses. However, the practical implementation of NOMA technologies in emergency scenarios is hindered by existing resource constraints and the requirement of prioritizing critical emergency information. To address these limitations, we propose a multi-objective optimization-based NOMA framework to maximize network throughput while ensuring quality of service (QoS) and energy efficiency. This framework incorporates a novel communication grouping algorithm based on queue penalty optimization and an Actor-Critic-based dynamic updating algorithm for multiple resource allocation. Our study proposes a practical approach to enhance emergency communication in disaster areas, ensuring efficient and reliable network performance under various constraints. © 2025 IEEE.

关键词： Multiobjective optimization

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：