检索结果-内蒙古大学图书馆

A cloud service composition method using a fuzzy-based particle swarm optimization algorithm

Multimedia Tools and Applications 2024年第19期83卷 56275-56302页

作者： Nazif, Habibeh Nassr, Mohammad Al-Khafaji, Hamza Mohammed Ridha Jafari Navimipour, Nima Unal, Mehmet Department of Mathematics Payame Noor University Tehran Iran Communication Technology Engineering Department Tartous University Tartus Syria Dpartment of Mathematics and Natural Sciences Gulf University for Science and Technology Mishref Campus Mubarak Al-Abdullah Kuwait Biomedical Engineering Department College of Engineering and Technologies Al-Mustaqbal University Babil Hillah51001 Iraq 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 Yunlin Douliou64002 Taiwan Department of Computer Engineering Nisantasi University Istanbul Turkey

In today's dynamic business landscape, organizations heavily rely on cloud computing to leverage the power of virtualization and resource sharing. Service composition plays a vital role in cloud computing, combining multiple cloud services to fulfill complex user requests. Service composition in cloud computing presents several challenges. These include service heterogeneity, dynamic service availability, QoS (Quality of Service) constraints, and scalability issues. Traditional approaches often struggle to handle these challenges efficiently, leading to suboptimal resource utilization and poor service performance. This work presents a fuzzy-based strategy for composing cloud services to overcome these obstacles. The fact that service composition is NP-hard has prompted the use of a range of metaheuristic algorithms in numerous papers. Therefore, Particle Swarm Optimization (PSO) has been applied in this paper to solve the problem. Implementing a fuzzy-based PSO for service composition requires defining the fuzzy membership functions and rules based on the specific service domain. Once the fuzzy logic components are established, they can be integrated into the PSO algorithm. The simulation results have shown the high efficiency of the proposed method in decreasing the latency, cost, and response time. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Monitoring and detection of NEFT fraudulent requests: A comparative analysis of machine learning models 15

Monitoring and detection of NEFT fraudulent requests: A comp...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bhowmik, Somnath Howlader, Jaydeep National Institute of Technology Department of Computer Science and Engineering West Bengal Durgapur India

ISBN: (纸本)9798350370249

The world is going through a fast pace of 'digital disruption' in business driven by 'technology transformation.' Similar to the global trend, the Indian banking industry is experiencing a major digital explosion, especially in the post-demonetization era, and accelerated further with the COVID19 pandemic. Digital channel services create massive volumes of electronic transactions and are automatically processed from end to end. With the increasing use of digital banking and online payments, cyberattacks, money laundering, and other fraudulent activities are rising in frequency and intensity. Frauds are dynamic, show irregular patterns, and are difficult to identify accurately. Cyberattackers use innovative technologies to find the existing systems' vulnerabilities and siphon millions of rupees. This means traditional fraud monitoring and detection methods are inadequate to meet the challenges that banks and financial institutions face today. This study aims to analyze the results of applying Machine Learning (ML) algorithms to digital payment transactions and measure the accuracy of segregating valid and abnormal transactions. The methods used are Logistic Regression (LR), k-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes (NB), and Decision Tree (DT). The datasets used are the National Electronic Fund Transfer (NEFT) N02 messages. We analyze five evaluation metrics - Precision, F-Score, Accuracy, Misclassification Error, and Area Under the Receiver Operating Characteristic Curve (AUC). The results propose the models in online payment systems for continuous monitoring and early detection of possible fraudulent transactions. © 2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Face Tracking using Deep Reinforcement Learning on Zenbo Junior

Face Tracking using Deep Reinforcement Learning on Zenbo Jun...

引用

2024 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2024

作者： Tseng, Shih-Huan Lin, De-Yu Huang, Shih-Shinh National Kaohsiung University of Science and Technology Department of Computer and Communication Engineering Kaohsiung Taiwan

ISBN: (纸本)9798350389210

This paper aims to develop a deep reinforcement learning-based face tracking system for Zenbo Jr. As robots become increasingly integrated into daily life, human-robot interaction (HRI) has emerged as a critical research area, especially in adhering to social norms. This project combines deep learning with visual servo systems to enhance the accuracy and response speed of robotic face tracking. The primary objectives of the study include: adjusting robot movements based on face position, designing a virtual environment using OpenAI Gym that matches Zenbo Jr.'s perspective for model training, and testing and validating the model on Zenbo Jr. The research methods involve designing the virtual environment, establishing reward functions, and constructing and training the DQN model. Experimental results compare the training outcomes of Q-Learning and Deep Q-Learning, confirming that Q-Learning leads to an excessively large Q-table in scenarios with numerous state-action combinations, making effective training impossible, whereas Deep Q-Learning achieves stable convergence and good results. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Review on Image Processing for MRI-Focused Brain Tumor Identification Using Machine Learning 7

Review on Image Processing for MRI-Focused Brain Tumor Ident...

引用

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

作者： Agha, Dur-E-Shawar Qazi, Farheen Rasheed, Rohail Ali Khan, M. Sadiq Naseem, Muhammad Mubeen, Tauseef Sir Syed University of Engineering & Technology Software Engineering Department Karachi Pakistan Computer Science Department Karachi Pakistan

ISBN: (纸本)9798331534271

Today, image processing plays a significant role in early disease detection, allowing doctors to treat conditions like breast, lung, and brain malignancies. A brain tumor is a serious condition that can be fatal. Brain tumor diagnosis is the most important task for early therapy, and automatic visual classification might be extremely important. It is essential to classify brain cancers in order to assess the tumor's and determine the best course of treatment for each class. To find brain tumors, numerous imaging modalities are used. However, MRI is frequently utilized since it produces superior images and uses no ionizing radiation. This research aims to provide a review of different Machine Learning (ML) techniques for detection and classification of brain tumor. Also, different feature extraction techniques are analyzed and their benefits are discussed. This review is conducted by different research papers which helps new researchers to start immediately a literature review and knowing different machine learning techniques their advantages and disadvantages to classify brain tumor through MRI. Also, they know the accuracy of each algorithm which leads them to directly target the problem not implementing the existing techniques. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions 38

Decentralized Noncooperative Games with Coupled Decision-Dep...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yan, Wenjing Cao, Xuanyu Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Distribution variations in machine learning, driven by the dynamic nature of deployment environments, significantly impact the performance of learning models. This paper explores endogenous distribution shifts in learning systems, where deployed models influence environments, which in turn alters the data distributions that the learning models rely on. This phenomenon is formulated by a decision-dependent distribution mapping within the recently introduced framework of performative prediction (PP) (Perdomo et al., 2020). Our study investigates the performative effect in a decentralized noncooperative game, where players aim to minimize private cost functions while simultaneously managing coupled inequality constraints. In this context, we examine two equilibrium concepts for the studied game: performative stable equilibrium (PSE) and Nash equilibrium (NE), and establish sufficient conditions for their existence and uniqueness. Notably, we provide the first upper bound on the distance between the PSE and NE in the literature, which is challenging to evaluate due to the absence of strong convexity on the joint cost function. Furthermore, we develop a decentralized stochastic primal-dual algorithm for efficiently computing the PSE point. By rigorously bounding the performative effect, we prove that the proposed algorithm achieves sublinear convergence rates for both performative regret and constraint violations and maintains the same order of convergence rate as the case without performativity. Numerical experiments further confirm the effectiveness of our algorithm and theoretical results. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secured Data Storage Using OAuth and Encryption of Data Using AES with Patterns and Hidden Layer

Secured Data Storage Using OAuth and Encryption of Data Usin...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer engineering, ICSSEEC 2024

作者： Vilasini, V. Hariharan, K. Chezhian, Nethra Kaviyarasu, D. PSG Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350378177

In today's digital era, the use of data is becoming more day by day. Data is serving as a main source for all the applications we rely on. As the volume of data rapidly increases, the need for security also increases in the same phase. This brings the need for securing the data in a more effective manner. The need to protect sensitive data is underscored by the increasing intricacy of cyberattacks and the expansion of virtual commerce. It is imperative to rely on several legal and regulatory requirements for the need for data security. The failure to do so may result in severe penalties. In order to maintain trust in digital interactions, data security during transmission and storage is becoming more important as the world gets smaller. If the data is not secured in an effective manner, the growth of the companies and several other technologies may collapse and result in higher threats to the world. Both firms and governments are required to preserve intellectual property and information related to national security. The availability, confidentiality, and integrity of data are critical for sustaining innovation, trust, and business continuity. This project focusses on the two-level authentication of the system where the users are allowed to store the sensitive data. The first level authentication is provided using OAuth where it is a single sign on mechanism which is advantageous to the users to access it easily. The second level authentication is provided using the encryption technique where the Advanced Encryption Standard is used along with the creative usage of user-generated patterns as a hidden layer in the encryption process. Here a symmetric key is used for the encryption to make it more secure. The two-level authentication brings high level security for the stored data. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Modelling Smart Grid Instability Against Cyber Attacks in SCADA System Networks

Lecture Notes on Data Engineering and Communications Technol...

引用

Lecture Notes on Data engineering and Communications Technologies 2023年 180卷 239-250页

作者： Efiong, John E. Akinyemi, Bodunde O. Olajubu, Emmanuel A. Ibrahim, Isa A. Aderounmu, Ganiyu A. Degila, Jules Department of Computer Science and Engineering Obafemi Awolowo University Ile-Ife Nigeria Department of Cybersecurity Federal University of Technology Owerri Nigeria Department of Computer Science Institute of Mathematics and Physics University of Abomey Calavi Benin

The SCADA systems in the Smart Grid Network (SGN) are increasingly facing cyber threats and divers attacks due to their known proprietary vulnerabilities, most often leading to power instability and cascading failures in the Grid. This paper associates the SGN’s instability with cyberattacks and models intrusions into SCADA systems using the Decentral Smart Grid Control (DSGC) model on the Stability dataset. The Time-Synchronization Attack was modelled with its effects on Transmission Line Fault Detection, Voltage Stability Monitoring and Event Locating. Classification and prediction were done on WEKA using a number of Machine Learning Algorithms and performances evaluated. Random Forest (RF) classifier was found to be more promising in all the benefit metrics yielding 92.0%, 91.9%, 92.0%, and 91.9% for Accuracy, Precision, Recall and F-measure, respectively. An ensemble classifier – Bagging, performed significantly well after the RF with 90.0%, 89.9%, 90.0% and 89.9%. The ROC Area under Curve also showed RF having 97% and Bagging 96.7%. 100 trees were constructed for the RF while considering 4 random features, and the out-of-bag error was 0.0084. RF had a TPR of 92.0%, which is the highest and an FPR of 0.11. These results provide insights into identifying appropriate ML techniques and models for the Grid’s instability problem vis-à-vis modelling attacks. This is expected to help in effective security planning, threats detection, attack mitigation and risk management. © The Author(s).

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Securing Health Monitoring in IOT with Blockchain-Based Proxy Re-Encryption

Securing Health Monitoring in IOT with Blockchain-Based Prox...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： George, Jerlin Chitra, R. Karunya Institute of Technology and Sciences Department of Computer Science and Engineering Tamil Nadu India

ISBN: (纸本)9798331517953

The devices with sensors that can monitor your temperature, heart rate, and other vital signs and link to the internet, known as the Internet of Things (IoT), have completely transformed the way we control health. Providing real time health data, these sensors improve diagnostics and treatment outcomes. Security and privacy matters when IoT comes into play in healthcare. Cyberattacks on centralized database systems are also a problem. To solve these challenges, the study uses blockchain technology coupled with proxy re-encryption to secure health data. ThingSpeak IoT cloud analyzes the collected data and turns them into blockchain transactions which are safely kept on the DriveHQ cloud. Transparency and data integrity are ensured by blockchain, and secure data sharing among authorized users is made possible by proxy re-encryption. This results in a health monitoring system that preserves the accuracy and confidentiality of data while reducing the safety risks of IoT driven healthcare applications. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Proficiency in Spark Configuration Tuning: An Empirical Study using Execution Time Metrics across Varied Workloads 2

Algorithmic Proficiency in Spark Configuration Tuning: An Em...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Sewal, Piyush Singh, Hari Computer Science & Engineering Department Jaypee University of Information Technology Solan173234 India

In the realm of big data, where datasets of immense scale pose processing challenges, distributed processing platforms like open-source Apache Spark have emerged to address these issues. Spark's internal configuration parameters exert varying impacts on execution times based on job characteristics, making manual optimization daunting. The core focus of this study lies in optimizing Spark's internal configurations, with specific attention directed towards three types of workloads: Iterative-intensive, Memory-intensive, and CPU-intensive. Employing Grid Search, Random Search, and Evolutionary Optimization algorithms yields substantial execution time reductions: 23.24% with Grid Search, 19.71% with Random Search, and 23.06% with Evolutionary Optimization. Notably, Evolutionary Optimization achieves optimal configurations approximately 29% faster than Grid Search. While Random Search and Evolutionary Optimization share similar time requirements, Random Search's execution time reduction for a given Spark workload is relatively lower. This research sheds light on algorithmic configuration tuning intricacies and its influence on Spark workload execution times, contributing to the exploration of optimizing big data processing platforms. © 2024 Elsevier B.V.. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Analysis of various Classification Techniques using CNN models for the Detection of Alzheimer's Disease using MRI images 14

Analysis of various Classification Techniques using CNN mode...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Hemkiran, S. Sudha Sadasivam, G. Pradeepa, T. Samukthaa, R.S. Ajay Raj, R. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Psg College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

Alzheimer's disease (AD) is a brain disorder that is associated with memory loss and is typically observed in elderly and aging individuals. This condition is irreversible in nature. Neural networks have shown better performance than traditional machine learning algorithms when it comes to analyzing high-dimensional data from Magnetic Resonance Images (MRI) brain images. This is an approach for processing such data. Detection of Alzheimer's disease is essential because the early treatment can control the progression of the disease in a slower pace. In this work, the proposed model used different models of convolutional neural networks (CNN) techniques to process the MRI images of the brain and classified them into different classes. The proposed model detects AD using neural network feature extraction and classification methods based on the pre-processed datasets. Here, in the proposed model, various algorithms such as Resnet-50, DenseNet-169 and Hyperparameter tuning of Convolutional Neural Network are utilized to find the better performing model in terms of accuracy when compared with other traditional techniques. © 2023 IEEE.

关键词： Image classification

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：