检索结果-内蒙古大学图书馆

A Space-Efficient One-Pass Online SVM Algorithm

International Journal of Computational Geometry and Applications 2024年第1-2期34卷 63-79页

作者： Liu, Yangwei Huang, Ziyun Xu, Jinhui Department of Computer Science and Engineering State University of New York at Buffalo Buffalo NY United States Department of Computer Science and Software Engineering Penn State Erie The Behrend College Erie PA United States

In this paper we consider the problem of training a Support Vector Machine (SVM) online using a stream of data in random order. We provide a fast online training algorithm for general SVM on very large datasets. Based on the geometric interpretation of SVM known as the polytope distance, our algorithm uses a gradient descent procedure to solve the problem. With high probability our algorithm outputs an (ϵ, δ)-approximation result in constant time and space, which is independent of the size of the dataset, where (ϵ, δ)-approximation means that the separating margin of the classifier is almost optimal (with error ≤ ϵ), and the number of misclassified training points is very small (with error ≤ δ). Experimental results show that our algorithm outperforms most of existing online algorithms, especially in the space requirement aspect, while maintaining high accuracy. © 2024 World Scientific Publishing Company.

关键词： online algorithm SVM

来源：评论

学校读者我要写书评

暂无评论

Detection of Turkish Fraudulent Domain Names to Proactively Prevent Phishing Attacks Using A Character-Level Convolutional Neural Network

Detection of Turkish Fraudulent Domain Names to Proactively ...

引用

2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023

作者： Bozogullarindan, Ceylan Ozturk, Celal Erciyes University Computer Engineering Department Kayseri Turkey Erciyes University Software Engineering Department Kayseri Turkey

ISBN: (纸本)9798350306590

Phishing attacks, which aim to steal sensitive information by tricking users into fraudulent websites, continue to pose significant financial and operational threats to organizations and individuals. While various studies have focused on detecting phishing websites using different techniques, only a limited number of studies have addressed the proactive detection of attacks through the analysis of domain names. This paper introduces a novel and proactive approach for real-time detection of phishing websites solely based on their domain names by leveraging the characteristics of Turkish domain names. Detecting the legitimacy of a website based solely on its domain name presents a significant challenge due to the limited availability of features that can expose phishing attacks. To address this problem, the paper proposes the use of character-level embeddings and a convolutional neural network (CNN) to develop a specialized classifier. A new dataset consisting solely of Turkish domain names and their corresponding labels is constructed for training and evaluating the CNN model. The experimental results demonstrate that our proposed model achieves an accuracy of 90%, which is highly promising given the intricacies of the problem at hand. Our study contributes to the advancement of proactive phishing detection methods and underscores the significance of considering linguistic and regional factors in phishing attack analysis. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

A Model Driven Framework Enabling the Development of Standardized Text-Free User Interface for Smartphones 21

A Model Driven Framework Enabling the Development of Standar...

引用

21st International Bhurban Conference on Applied Sciences and Technology, IBCAST 2024

作者： Rasheed, Uzair Khalid, Sadia Mehmood, Rabia Ahmad, Muhammad Muneer, Mishal College of Electrical and Mechanical Engineering NUST Department of Computer and Software Engineering Islamabad Pakistan Lahore College for Women University Department of Computer Science Lahore Pakistan International Univesity of Rostock Department of Computer science Germany

ISBN: (纸本)9798331516680

Smartphones offer a wide range of applications globally, and usability is a key factor in their quality. Human-computer Interaction (HCI) continuously evolves to enhance usability by improving user interface (UI) components. However, most UI trends are designed for literate users, neglecting a significant portion of the population who cannot read or write. These users often rely on others for assistance with smartphone applications, and text-based UIs hinder their learning and usage, reducing overall usability. This research addresses the limitations of text-based standards by introducing a standardized framework for developing text-free user interfaces for smartphones. The framework utilizes static and dynamic images instead of text to convey widget or button functions, aiming to enhance usability for illiterate users, including preschoolers. Developed with Obeo Designer and Sirius, the framework's Platform Independent Metamodel (PIM) was validated through case studies representing the target user groups. Future work involves Model to Text (M2T) transformation, and results show the framework's potential for automating applications with text-free UIs. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Eye on the Future: Deep Learning with MobileNetV2 for Early Eye Disease Diagnosis 7

Eye on the Future: Deep Learning with MobileNetV2 for Early ...

引用

7th Edition Global Conference on Wireless and Optical Technologies, GCWOT 2024

作者： Noor, Shaheena Saleem, Muhammad Imran Ismat, Najma Siddiqui, Aneeta Minhas, Humera Noor Inam, Hamza Sir Syed University of Engineering & Technology Department of Computer Engineering Karachi Pakistan Ssuet Department of Software Engineering Karachi Pakistan Ssuet Department of Computer Engg. Karachi Pakistan Eyeo Quality Filtering Engineering Department Cologne Germany Avioinics Engineering Pakistan Air Force Islamabad Pakistan

ISBN: (纸本)9798331534271

MobileNetV2 represents a significant advancement in the design of efficient neural networks for mobile and embedded applications. Its innovative use of inverted residuals, linear bottlenecks, and depthwise separable convolutions makes it an ideal choice for developers seeking to deploy powerful AI models on resource-constrained devices. This paper presents an efficient algorithm leveraging the MobileNetV2 architecture for the classification of eye diseases, specifically targeting Normal, Cataract, Glaucoma, and Retina Disease categories. The proposed model is designed to perform with high accuracy on resource-constrained devices, making it suitable for mobile and embedded applications in telemedicine and ophthalmology. Extensive testing on a comprehensive dataset has demonstrated the model's effectiveness, achieving precision and accuracy of 96.15% and 97.39%, respectively. This research addresses the growing need for accessible and reliable diagnostic tools in eye care, particularly in remote and underserved regions. © 2024 IEEE.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Edge Cloud Selection in Mobile Edge Computing(MEC)-Aided Applications for Industrial Internet of Things(IIoT)Services

引用

computer Systems Science & engineering 2023年第11期47卷 2049-2060页

作者： Dae-Young Kim SoYeon Lee MinSeung Kim Seokhoon Kim Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Korea Department of Software Convergence Soonchunhyang UniversityAsan31538Korea

In many IIoT architectures,various devices connect to the edge cloud via gateway *** data processing,numerous data are delivered to the edge *** data to an appropriate edge cloud is critical to improve IIoT service *** are two types of costs for this kind of IoT network:a communication cost and a computing *** service efficiency,the communication cost of data transmission should be minimized,and the computing cost in the edge cloud should be also ***,in this paper,the communication cost for data transmission is defined as the delay factor,and the computing cost in the edge cloud is defined as the waiting time of the computing *** proposed method selects an edge cloud that minimizes the total cost of the communication and computing *** is,a device chooses a routing path to the selected edge cloud based on the *** proposed method controls the data flows in a mesh-structured network and appropriately distributes the data processing *** performance of the proposed method is validated through extensive computer *** the transition probability from good to bad is 0.3 and the transition probability from bad to good is 0.7 in wireless and edge cloud states,the proposed method reduced both the average delay and the service pause counts to about 25%of the existing method.

关键词： Industrial Internet of Things(IIoT)network IIoT service mobile edge computing(MEC) edge cloud selection MEC-aided application

来源：评论

学校读者我要写书评

暂无评论

Extended Reality and Digital Twin in the Oil and Gas Pipeline Industry: A Systematic Review on Applications, Trends, and Future Directions 23

Extended Reality and Digital Twin in the Oil and Gas Pipelin...

引用

23rd IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2024

作者： Sarvesh, Muskan Kang, Ryan Nam, Hyeongil Park, Simon Hugo, Ron Maurer, Frank Kim, Kangsoo University of Calgary Department of Electrical and Software Engineering Canada University of Calgary Department of Mechanical and Manufacturing Engineering Canada University of Calgary Department of Computer Science Canada

ISBN: (纸本)9798331516475

Immersive and simulation technologies, such as Augmented Reality (AR), Virtual Reality (VR), Mixed Reality (MR), and Digital Twins (DTs), have proven effective in enhancing decision-making, streamlining operations, and improving safety through intuitive visualizations. Unsurprisingly, the oil and gas (O&G) pipeline industry is increasingly turning to these technologies to tackle complex construction and resource management challenges. This paper reviews the applications, benefits, and future trends of these technologies, focusing on integration and emerging trends in monitoring, training, maintenance, and testing. It identifies potential gaps, offers guidance for future research, and emphasizes adapting to technological evolution, providing insights to improve system reliability and sustainability in O&G pipeline operations using immersion and simulation methods. © 2024 IEEE.

关键词： Gas pipelines

来源：评论

学校读者我要写书评

暂无评论

Entropy-based Selective Homomorphic Encryption for Smart Metering Systems 28

Entropy-based Selective Homomorphic Encryption for Smart Met...

引用

28th IEEE Pacific Rim International Symposium on Dependable Computing, PRDC 2023

作者： Xu, Weiyan Zhang, Yinghao Cardell-Oliver, Rachel Mian, Ajmal Hong, Jin B. The University of Western Australia Department of Computer Science and Software Engineering Australia

ISBN: (纸本)9798350358766

Smart metering systems (SMS) are popular in industrial and residential areas but can risk privacy by revealing user behaviors. Homomorphic encryption (HE) is a technique that protects data privacy by enabling calculations on encrypted data. However, the high computational costs of HE can hinder real-time or resource-constrained applications. Our paper presents a framework to encrypt only selected SMS data for improved efficiency without compromising privacy significantly. By encrypting data blocks with higher entropy values, we can mitigate the leakage of key information to adversaries who may conduct privacy attacks, such as membership inference attacks (MIA). We evaluate our framework using two real-world datasets (i.e., electricity and water) to assess privacy and performance trade-offs. The results indicate a 47% performance increase while still providing a sufficient level of privacy when adopting an encryption ratio of 0.4. They demonstrate the effectiveness of the proposed framework, considering the trade-off between privacy and performance, where the user can determine the appropriate security level for privacy protection and enhance the performance using HE in practical SMS settings. © 2023 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Security-Oriented Network Intent Placement using Particle Swarm Optimization 7

Security-Oriented Network Intent Placement using Particle Sw...

引用

7th Cyber Security in Networking Conference, CSNet 2023

作者： Landeau, Gabriel Avgeris, Marios Leivadeas, Aris Lambadaris, Ioannis Department of Software and It Engineering Montréal Canada Carleton University Department of Systems and Computer Engineering Ottawa Canada

ISBN: (纸本)9798350342871

As the network infrastructure grows, its configuration and service provisioning become a tedious process. Accordingly, new paradigms have emerged, such as the Intent-Based Networking (IBN), that envision the automation of the network configuration, while minimizing the human intervention. Specifically, IBN allows users to interact with the network through high-level and declarative requests, called intents, which later can be translated into low-level configurations. IBN can entail different scopes and target network infrastructures, while being domain specific, which can create several challenges in terms of the final activation of the requested intents. To this end, in this paper, we mainly focus on intents that are expressing security and Quality of Service (QoS) network services demands that can be translated into Service Function Chains (SFC) and automatically deployed over a campus network. Our work and depending on the security level expressed in the intent, tries to optimally decide the level of multi-tenancy or complete segregation of the users' services that can be achieved, while satisfying the network provider's objectives. In particular, an artificial intelligence inspired algorithm called Particle Swarm Optimization (PSO) is modeled that automatically tries to find the best placement of the intents, while satisfying the security and QoS requirements of the users issuing the intents. © 2023 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Drought Management System: A Turkish Case Study 4

AI-Driven Drought Management System: A Turkish Case Study

引用

4th International Informatics and software engineering Conference, IISEC 2023

作者： Sabamehr, Milad Ekin, Cansu Cigdem Atilim University Department of Software Engineering Ankara Turkey Atilim University Department of Computer Engineering Ankara Turkey

ISBN: (纸本)9798350318036

Nowadays, drought is one of the trending topics in the world that has turned into a challenge for the world. By developing countries and cities worldwide, especially in the economic aspect, governments started to damage the environment such as through the use of fossil fuels, pollution of the seas, unregulated use of fresh water also deforestation for personal purposes. The presented research aims to change the format of drought mitigation strategies from traditional ways into the up to date treats. Leveraging AI technologies, including machine learning algorithms and data analytics, a comprehensive AI-driven drought management system is designed and implemented. In this system, inconsistent data have been obtained from the Ministry of Agriculture and Forestry organization and transformed into insightful data and analyzed in real-Time style to provide the status of agricultural products in Turkey. This research contributes to the fields of environmental science and agriculture by innovatively augmenting traditional approaches with AI-driven solutions. Ultimately, our research offers a means to monitor weather conditions in different regions of Turkey, moving beyond manual drought prediction and guesswork that were prevalent in previous systems. Additionally, it facilitates the evaluation of vegetation health by considering precipitation and temperature averages in each area. © 2023 IEEE.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Role of Machine Learning in Power Analysis Based Side Channel Attacks on FPGA

Role of Machine Learning in Power Analysis Based Side Channe...

引用

2023 International Conference on Robotics and Automation in Industry, ICRAI 2023

作者： Hasnain, Ali Asfia, Yame Khawaja, Sajid Gul College of EME Department of Computer and Software Engineering NUST Islamabad Pakistan

ISBN: (纸本)9781665464727

The cloud-based devices face many threats these days due to shared resources like power. The attacker measures the power by using some remote sensors which are present in attacker tenants. These sensors get partial or full access to a power distribution network (PDN) and work as a backdoor for the attacker. In our research, we explored potential security issues which involved power analysis-based side-channel attacks (SCAs) on Field programmable Gate Arrays (FPGAs). We have made three major contributions to our research paper. First, we have discussed the power analysis or power profiling of FPGA, which is dependent upon voltage fluctuations' leakage while performing some encryption tasks. The voltage fluctuations of the cryptographic module are measured by some physical source like an oscilloscope or remote source like delay line sensors. Second, we have discussed potential power analysis-based SCAs that used these measurements of voltage fluctuations to extract the secret key. Third, we have designed a framework based on machine learning (ML) and deep learning (DL) models to perform secret key predictions and successful attacks. Firstly, our custom convolutional neural networks (CNN) model has revealed all 16 bytes of the secret key and performed a successful attack with only 570 attack power traces. Secondly, the multi-layer perceptron (MLP) model has successfully attacked only using 3200 traces using the same framework. Overall we have achieved a better performance in terms of the required number of power traces for a successful attack, training time, prediction time, and attack time. © 2023 IEEE.

关键词： Neural network models

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：