检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Duan, Wenying Guo, Shujun Zhou, Zimu Huang, Wei Rao, Hong He, Xiaoxi Jiangxi Provincial Key Laboratory of Intelligent Systems and Human-Machine Interaction Nanchang University Nanchang China School of Mathematics and Computer Sciences Nanchang University Nanchang China School of Data Science City University of Hong Kong Hong Kong School of Software Nanchang University Nanchang China Faculty of Science and Technology University of Macau China

Spatial-temporal data, fundamental to many intelligent applications, reveals dependencies indicating causal links between present measurements at specific locations and historical data at the same or other locations. Within this context, adaptive spatial-temporal graph neural networks (ASTGNNs) have emerged as valuable tools for modelling these dependencies, especially through a data-driven approach rather than pre-defined spatial graphs. While this approach offers higher accuracy, it presents increased computational demands. Addressing this challenge, this paper delves into the concept of localisation within ASTGNNs, introducing an innovative perspective that spatial dependencies should be dynamically evolving over time. We introduce DynAGS, a localised ASTGNN framework aimed at maximising efficiency and accuracy in distributed deployment. This framework integrates dynamic localisation, time-evolving spatial graphs, and personalised localisation, all orchestrated around the Dynamic Graph Generator, a light-weighted central module leveraging cross attention. The central module can integrate historical information in a node-independent manner to enhance the feature representation of nodes at the current moment. This improved feature representation is then used to generate a dynamic sparse graph without the need for costly data exchanges, and it supports personalised localisation. Performance assessments across two core ASTGNN architectures and nine real-world datasets from various applications reveal that DynAGS outshines current benchmarks, underscoring that the dynamic modelling of spatial dependencies can drastically improve model expressibility, flexibility, and system efficiency, especially in distributed settings. © 2025, CC BY-NC-ND.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Comments on "An Efficient and Provably Secure Authenticated Key Agreement Protocol for Fog-Based Vehicular Ad-Hoc Networks"

Comments on "An Efficient and Provably Secure Authenticated ...

引用

IEEE International Conference on Electronics and Communication Engineering (ICECE)

作者： Syed Muhammad Awais Wu Yucheng Khalid Mahmood Rupak Kharel School of Microelectronics and Communication Engineering Chongqing University Chongqing China School of Psychology and Computer Science and Graduate School of Intelligent Data Science University of Central Lancashire and National Yunlin University of Science and Technology Preston United Kingdom Yunlin Taiwan School of Psychology and Computer Science and Faculty of Electrical and Electronics Engineering University of Central Lancashire and Ton Duc Thang University Preston United Kingdom Ho Chi Minh City Vietnam

Vehicle ad-hoc networks (VANETs) have experienced rapid growth due to the advancement of cloud computing, IoT technologies, and intelligent transportation systems (ITS). Vehicles are required to have enhanced storage capacity, onboard computing capabilities, improved sensing power, and communication systems. To address real-world demands like low latency, affordable storage, and mobility in VANET deployments, There have been efforts to integrate fog computing with VANETs in a practical implementation. "An Efficient and Provably Secure Authenticated Key Agreement Protocol for Fog-Based Vehicular Ad-Hoc Networks" was proposed by Ma et al. (IEEE Internet of Things Journal, pp 8065–8075, 10.1109/JIOT.2019.2902840). According to their claims, the use of their secure authentication technique can help prevent security threats. However, after careful investigation, we discovered that their authentication protocol is susceptible to vehicle user impersonation attacks and also does not provide vehicle anonymity. In light of this, we have provided some recommendations to address the current flaws in the protocol developed by Ma et al.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Pre Shoplifting Suspicious Behavior Using Deep Learning

Detection of Pre Shoplifting Suspicious Behavior Using Deep ...

引用

IIAI International Conference on Advanced Applied Informatics (IIAIAAI)

作者： Sujan Shrestha Yoji Taniguchi Tetsuo Tanaka Course of Information and computer sciences Graduate school of Engineering Kanagawa Institute of Tehnology Atsugi Japan Department of Information Artificial Intelligence and Data Science Daiichi Institute of Technology Tokyo Japan Dept. of Information and Computer Sciences Faculty of Information Technology Kanagawa Institute of Technology Atsugi Japan

ISBN: (数字)9798350377903

ISBN: (纸本)9798350377910

Shoplifting presents a significant challenge for retailers, leading to substantial financial losses and security concerns. Current surveillance systems effectively identify shoplifting incidents postoccurrence; however, the capability to detect and prevent such activities preemptively remains limited. This research focuses on identifying behaviors that likely precede shoplifting events. To this end, we introduce a novel benchmark dataset, specifically designed for the early detection of suspicious behavior that may lead to shoplifting. This dataset is curated by selecting and segmenting relevant sequences from the UCF101-Crime dataset, encompassing suspicious behavior, actual shoplifting incidents, and normal activities. Our approach addresses the limitations of existing datasets where the brief duration of shoplifting events may skew neural network performance. The dataset includes clips of only a few seconds each, for which we propose a robust neural network architecture combining the strengths of convolutional neural networks (CNN) for efficient feature extraction and Bidirectional long short-term memory (BiLSTM) networks for capturing temporal dependencies within action sequences. Our model achieves an impressive classification accuracy of 86.21 % on the newly created dataset.

关键词： Deep learning Recurrent neural networks Accuracy Surveillance Benchmark testing Feature extraction Convolutional neural networks Security Informatics Long short term memory

来源：评论

学校读者我要写书评

暂无评论

HSR-Diff: Hyperspectral Image Super-Resolution via Conditional Diffusion Models

HSR-Diff: Hyperspectral Image Super-Resolution via Condition...

引用

International Conference on computer Vision (ICCV)

作者： Chanyue Wu Dong Wang Yunpeng Bai Hanyu Mao Ying Li Qiang Shen National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Laboratory of Speech & Image Information Processing School of Computer Science Northwestern Polytechnical University China Department of Computer Science Faculty of Business and Physical Sciences Aberystwyth University U.K.

Despite the proven significance of hyperspectral images (HSIs) in performing various computer vision tasks, its potential is adversely affected by the low-resolution (LR) property in the spatial domain, resulting from multiple physical factors. Inspired by recent advancements in deep generative models, we propose an HSI Super-resolution (SR) approach with Conditional Diffusion Models (HSR-Diff) that merges a high-resolution (HR) multispectral image (MSI) with the corresponding LR-HSI. HSR-Diff generates an HR-HSI via repeated refinement, in which the HR-HSI is initialized with pure Gaussian noise and iteratively refined. At each iteration, the noise is removed with a Conditional Denoising Transformer (CDFormer) that is trained on denoising at different noise levels, conditioned on the hierarchical feature maps of HR-MSI and LR-HSI. In addition, a progressive learning strategy is employed to exploit the global information of full-resolution images. Systematic experiments have been conducted on four public datasets, demonstrating that HSR-Diff outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Payment Channel Network Optimization Composed of Merkle Tree with Election Mechanism

Payment Channel Network Optimization Composed of Merkle Tree...

引用

Blockchain Technology and Information Security (ICBCTIS), International Conference on

作者： Zuobin Ying Wenqi Li Chiawei Chu Jiawei Zang Chen Deng Shengmin Xu Faculty of Data Science City University of Macau Macau China National Institute of Education (NIE) Nanyang Technological University Singapore College of Computer and Cyber Security Fujian Normal University Fuzhou China

On-chain methods fail to improve the scalability of cryptocurrencies since they are constrained by block size and block creation rate. As a result, Payment Channel Networks (PCNs) have surfaced as a vital off-chain alternative for achieving scalability. In our prior research, we introduced a scheme called Accountable Assertions Performance optimization (A 2 PO) designed to identify malicious users in PCNs while optimizing computational efficiency and maintaining security. The original A 2 PO scheme assumed the third-party supervisor to be trustworthy; however, the potential for malicious behavior exists in reality. Consequently, we present an improved A 2 PO framework that incorporates an election mechanism. Supervisors for each transaction are automatically elected by calculating user balances. We offer a thorough security analysis, as well as the results of our evaluation show that the suggested scheme keeps the original A 2 PO’s benefits in terms of computing performance while enhancing security to thwart hostile supervisor operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

How can artificial intelligence help customer intelligence for credit portfolio management? A systematic literature review

引用

International Journal of Information Management data Insights 2024年第2期4卷

作者： Amato, Alessandra Osterrieder, Joerg R. Machado, Marcos R. University of Twente Faculty of Electrical Engineering Mathematics and Computer Science AE Enschede 7500 Netherlands University of Twente Faculty of Behavioural Management and Social Sciences Department of High-Tech Business and Entrepreneurship AE Enschede 7500 Netherlands Bern Business School Institute of Finance and Applied Data Science Bern 3005 Switzerland

In this era of Big data and the advancement of sophisticated analytical techniques, the financial industry has the capacity to implement innovative technologies within their systems to derive crucial insights about their clientele and vigilantly monitor their activities. This landscape has seen the emergence and rise of two significant applications, namely, customer segmentation systems and early warning systems. Therefore, this study presents a systematic literature review on the automation of customer segmentation and early warning techniques with a focus on managing credit portfolio entities. The research delves into a multitude of scholarly articles from three distinct perspectives: charting the dominant trends within the literature, unpacking the overarching themes, and critically examining the integration of early warning signals within customer clustering applications. Furthermore, the review reveals a noticeable dearth of studies probing the synergistic application of these two systems. Despite their independent effectiveness in risk management and targeted marketing strategies respectively, an integrated approach holds potential for bolstering financial stability and tailoring customer service. Thus, this review stands as a significant academic contribution, advocating an integrated application of these systems within the financial industry. The findings provide a novel foundation for future research and practical applications, potentially redefining strategies within the financial sector. © 2024 The Author(s)

关键词： Customer segmentation Early warning systems Lending settings Systematic literature review Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Personal Radiation Exposure from Wireless Signals in Indoor and Outdoor Environments

引用

IEEE Access 2025年 13卷 106489-106510页

作者： Ruijie, Pan Sali, Aduwati Li, Lu Mohyedin, Muhammad Zamir Qahtan, Sangin Universiti Putra Malaysia (UPM) WiPNET Research Centre Department of Computer and Communication Systems Engineering Faculty of Engineering Selangor Serdang 43400 Malaysia Universiti Putra Malaysia (UPM) Institute for Mathematical Research (INSPEM) Selangor Serdang 43400 Malaysia Anhui University of Technology School of Microelectronics and Data Science Maanshan 243002 China

With the development of wireless technology, the public is exposed to electromagnetic fields (EMF), which has led to concerns about the potential health effects of EMF exposures. This paper aims to evaluate personal EMF exposures from wireless signals in indoor and outdoor micro-environments in Malaysia. According to the influencing factors, four different types of micro-environments are selected. A radiation exposure meter called ExpoM-RF 4 is used to measure the electric field strength across these micro-environments. From the measurement campaigns, three machine learning (ML) techniques are simulated to model the Electric Field Strength in each micro-environment. The ML techniques are Fully connected neural network (FCNN), eXtreme Gradient Boosting (XG Boost), and Linear Regression (LR) to predict the RMS and Maximum radiation exposure. From the ML models, Total Emission Ratio (TER), Root Mean Square Error (RMSE) and Coefficient of Determination (R2) are evaluated to measure the performance of ML. By comparison, it is found that LR performs well with single and simple data set, while XG Boost and FCNN demonstrate superior capabilities in handling multiple types of data sets. The FCNN model provides the most accurate predictions, particularly in urban and suburban areas where extreme values are observed. Finally, the measured data and the predicted radiation exposure levels are compared against public exposure limit by International Commission on Non-Ionizing Radiation Protection (ICNIRP), Malaysian Communications and Multimedia Commission (MCMC) and Federal Communications Commission (FCC). The results demonstrate that typically personal radiation exposure is lower than the exposure limit (61.4 V/m), which is similar to the most research results. However, in areas with dense population and numerous base stations, the maximum exposure can approach 56.7365 V/m (measured data), which is close to the exposure limit. © 2013 IEEE.

关键词： Electromagnetic Fields (EMF) ExpoM-RF 4 Exposure Limit Indoor and Outdoor Environment Machine Learning (ML) Micro-Environments Personal Radiation Exposure

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Robotic Arm Efficiency: Evaluating PID and Fuzzy-PID Control using Printed Mechanical Structure and ESP8266 Integration

Comparative Analysis of Robotic Arm Efficiency: Evaluating P...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Padma Nyoman Crisnapati I Made Darma Susila I Komang Agus Ady Aryanto Jaturapith Krohkaew Ricky Aurelius Nurtanto Diaz I Made Suandana Astika Pande Department of Information Systems Faculty of Informatics and Computers Institute Technology and Business STIKOM Bali Denpasar Indonesia Department of Computer Systems Faculty of Informatics and Computers Institute Technology and Business STIKOM Bali Denpasar Indonesia Dept. of Big Data Management and Analytics Faculty of Science and Technology Rajamangala University of Technology Thanyaburi Thanyaburi Thailand

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

This study investigates the comparative effectiveness of manual PID tuning versus Fuzzy-PID control in enhancing the performance of a robot arm with two degrees of freedom (2-DOF). The experimental approach involves conducting two scenarios: manual tuning of PID parameters in Scenario 1 and utilizing a fuzzy algorithm for PID parameter tuning in Scenario 2. The novelty of this research lies in the new 3D mechanical design of the 2-DOF robot arm and the utilization of the ESP8266 microcontroller for implementing Fuzzy-PID control. Performance evaluation is conducted using Root Mean Square Error (RMSE) and Root Mean Square Percentage Error (RMSPE) calculations. The results reveal that Fuzzy-PID control significantly reduces errors compared to manual PID tuning, with lower RMSE and RMSPE values indicating more precise and stable control. These findings underscore the potential of integrating fuzzy logic with PID control to enhance system adaptability and flexibility. Additionally, the ESP8266 is capable of handling the computations required for fuzzy-PID control while being cost-effective.

关键词： Fuzzy logic PI control Microcontrollers 2-DOF Manuals Manipulators Three-dimensional printing PD control Root mean square Tuning

来源：评论

学校读者我要写书评

暂无评论

Python package for causal discovery based on LiNGAM

引用

The Journal of Machine Learning Research 2023年第1期24卷 483-490页

作者： Takashi Ikeuchi Mayumi Ide Yan Zeng Takashi Nicholas Maeda Shohei Shimizu SCREEN Advanced System Solutions Co. Ltd. Japan Department of Computer Science and Technology Tsinghua University China School of System Design and Technology Tokyo Denki University Japan and Center for Advanced Intelligence Project RIKEN Japan Faculty of Data Science Shiga University Japan and Center for Advanced Intelligence Project RIKEN Japan

Causal discovery is a methodology for learning causal graphs from data, and LiNGAM is a well-known model for causal discovery. This paper describes an open-source Python package for causal discovery based on LiNGAM. The package implements various LiNGAM methods under different settings like time series cases, multiple-group cases, mixed data cases, and hidden common cause cases, in addition to evaluation of statistical reliability and model assumptions. The source code is freely available under the MIT license at https://***/cdt15/lingam.

关键词： causal structure learning statistical reliability model evaluation

来源：评论

学校读者我要写书评

暂无评论

E-Learning: A Successful Learning Environment

E-Learning: A Successful Learning Environment

引用

computer science and Emerging Technologies (CSET), International Conference on

作者： Fayiz Momani Amer Ahmad Hatamleh Wan Mohd Amir Fazamin Wan Hamzah Julaily Aida Jusoh Muhammad D. Zakaria Sunanda Das E-business & Commerce Department Faculty of Management and Financial Sciences University of Petra (UOP) Jordan Head of Departments Faculty of Business and Financial Science MIS BI and Data Analysis Irbid National University Irbid Jordan Faculty of Informatics and Computing (UniSZA) Malaysia Faculty of Informatics and Computing UniSZA Malaysia Cyber Security School of Computer Science and Engineering Jain University Bangalore India

Education is developing with the economy. This led to the creation of e-Iearning tools for instructors and students. In e-learning, electronic resources are used to teach. E-learning can be taught in or out of school, but computers and the Internet are essential. That is, e-learning involves delivering education to a big group of people at once or over time. So, overall, in this research is about E-learning that make a successful environment. We chose this term since it is widely used in E-learning research to improve student academic achievement. Due to the difficulties of accessing adequate study materials during the Covid-19 epidemic, distance learning has grown more popular among students. This study proposes a unique learning technique that involves choosing and organizing important learning items using a recommender system. We also studied our method's efficacy. Using a recommended system to help online learning activities was proven to be effective. Software development methodology is a collection of principles and processes used to build software. Systematic software development is the goal. The research approach utilized for this topic is Lean Development Methodology. We also examine the advantages and disadvantages of e-learning. This research also introduces various new strategies and methodologies that may be employed in the future to improve system-learning. It also presents system that we choose and why we choose it. So, it aims to eliminate waste and increase production. Following the principles can help developers avoid nonproductive chores while still producing high-quality results. The ultimate objective is to develop an efficient and error-free system. Finally, E-learning is a social revolution. It's part of a bigger rethinking of how we teach future employees and students. The eLearning platform enabled the learning data visualization dashboard beautifully. User-centered design lets the dashboard adapt to its users' demands.

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：