检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Orji, Ugochukwu Ukwandu, Elochukwu Department of Computer Science Faculty of Physical Science University of Nigeria Enugu State Nsukka Nigeria Department of Applied Computing and Engineering Cardiff School of Technologies Cardiff Metropolitan University Wales CardiffCF5 2YB United Kingdom

Predictive modeling in healthcare continues to be an active actuarial research topic as more insurance companies aim to maximize the potential of Machine Learning (ML) approaches to increase their productivity and efficiency. In this paper, the authors deployed three regression-based ensemble ML models that combine variations of decision trees through Extreme Gradient Boosting (XGBoost), Gradient-boosting Machine (GBM), and Random Forest (RF) methods in predicting medical insurance costs. Explainable Artificial Intelligence (XAi) methods SHapley Additive exPlanations (SHAP) and Individual Conditional Expectation (ICE) plots were deployed to discover and explain the key determinant factors that influence medical insurance premium prices in the dataset. The dataset used comprised 986 records and is publicly available in the KAGGLE repository. The models were evaluated using four performance evaluation metrics, including R-squared (R2), Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that all models produced impressive outcomes;however, the XGBoost model achieved a better overall performance although it also expanded more computational resources, while the RF model recorded a lesser prediction error and consumed far fewer computing resources than the XGBoost model. Furthermore, we compared the outcome of both XAi methods in identifying the key determinant features that influenced the PremiumPrices for each model and whereas both XAi methods produced similar outcomes, we found that the ICE plots showed in more detail the interactions between each variable than the SHAP analysis which seemed to be more high-level. It is the aim of the authors that the contributions of this study will help policymakers, insurers, and potential medical insurance buyers in their decision-making process for selecting the right policies that meet their specific needs. © 2023, CC BY-NC-SA.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The Summer Heat of Cryptojacking Season: Detecting Cryptojacking using Heatmap and Fuzzy

The Summer Heat of Cryptojacking Season: Detecting Cryptojac...

引用

Cyber Resilience (ICCR), International Conference on

作者： Ahmad Firdaus Ghassan Saleh AlDharhani Zahian Ismail Mohd Faizal Ab Razak Faculty of Computing College of Computing & Applied Sciences Universiti Malaysia Pahang Pekan Pahang Head of Department Digital Innovation Institute of Computer Science & Digital Innovation (ICSDI) UCSI University Kuala Lumpur Malaysia

ISBN: (数字)9781665461221

ISBN: (纸本)9781665461238

Cryptojacking is a subset of cybercrime in which hackers use unauthorised devices (computers, smartphones, tablets, and even servers) to mine cryptocurrencies. Similar to many other forms of cybercrime, the objective of cryptojacking is achieve profit illegally. It is also designed to remain entirely concealed from the victim's view. However, its attacks continue to evolve and spread, and their number continues to rise. Therefore, it is essential to detect cryptojacking malware, as it poses a significant risk to users. However, in machine learning intelligence detection, an excessive number of insignificant features will diminish the detection's accuracy. For machine learning-based detection, it's important to find important features in a minimal amount of data. This study therefore proposes the Pearson correlation coefficient (PMCC), a measure of the linear relationship between all features. After that, this study employs the heatmap method to visualise the PMCC value as a colour version of heat. We utilised The Fuzzy Lattice Reasoning (FLR) classifier for classification algorithms in machine learning. This experiment utilised actual cryptojacking samples and achieved a 100 percent detection accuracy rate in simulation.

关键词： Heating systems Correlation coefficient Lattices Machine learning Static analysis Feature extraction Cognition

来源：评论

学校读者我要写书评

暂无评论

EXISTENCE OF UNDERCOMPRESSIVE TRAVELLING WAVES OF A NON-LOCAL GENERALISED KORTEWEG-DE VRIES-BURGERS EQUATION

arXiv

引用

arXiv 2024年

作者： Achleitner, F. Cuesta, C.M. Diez-Izagirre, X. Vienna University of Technology Institute for Analysis and Scientific Computing Wiedner Hauptstrasse 8-10 Wien1040 Austria Faculty of Science and Technology Department of Mathematics Aptdo. 644 Bilbao48080 Spain Faculty of Economics and Business Department of Applied Economics Oñati plaza 1 Donostia-San Sebastian20018 Spain

We study travelling wave solutions of a generalised Korteweg-de Vries-Burgers equation with a non-local diffusion term and a concave-convex flux. This model equation arises in the analysis of a shallow water flow by performing formal asymptotic expansions associated to the triple-deck regularisation (which is an extension of classical boundary layer theory). The resulting non-local operator is a fractional type derivative with order between 1 and 2. Travelling wave solutions are typically analysed in relation to shock formation in the full shallow water problem. We show rigorously the existence of travelling waves that, formally, in the limit of vanishing diffusion and dispersion would give rise to non-classical shocks, that is, shocks that violate the Lax entropy condition. The proof is based on arguments that are typical in dynamical systems. The nature of the non-local operator makes this possible, since the resulting travelling wave equation can be seen as a delayed integro-differential equation. Thus, linearisation around critical points, continuity with respect to parameters and a shooting argument, are the main steps that we have proved and adapted for solving this *** Codes 47J35, 26A33, 35C07 © 2024, CC BY.

关键词： Korteweg-de Vries equation

来源：评论

学校读者我要写书评

暂无评论

Offline Writer Identification using Deep Convolution Neural Network 2

Offline Writer Identification using Deep Convolution Neural ...

引用

2nd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and Computer Engineering, MI-STA 2022

作者： Durou, Amal M. Aref, Ibrahim A. Erateb, Suleiman El-Mihoub, Tarek A. Ghalut, Tarik Emhemmed, Adel Saad University of Tripoli Faculty of Information Technology Tripoli Libya Lancaster University School of Computing and Comms Lancaster United Kingdom Coventry University Engineering and Digital Technologies Coventry United Kingdom Jade University of Applied Sciences Department of Engineering Science Wilhelmshaven Germany University of Tripoli Electrical Engineering Department Tripoli Libya

ISBN: (数字)9781665479189

ISBN: (纸本)9781665479189

Deep convolutional neural networks (DCNN) are efficient in solving different pattern recognition problems and have been applied to extract image features (IFs). This paper investigates using deep learning (DL) techniques to improve the performance of the writer identification (WI) process. This work presents a novel approach for WI tasks by combining a DL technique with machine learning (ML). A convolutional neural network (CNN) is employed as a feature extractor along with a ML algorithm to classify those features. The standard Alex-Net model is utilized to extract IFs that located in the fully connected layers (FCLs). The support vector machine (SVM) model is selected as the classifier due to its efficient capabilities to improve identification performance (IP). The proposed model is tested using various types of the datasets, namely the Islamic Heritage Project (IHP) and Clusius. Furthermore, IAM and ICFHR-2012 datasets have been employed for benchmarking the proposed model. The results demonstrate the model achieves superior performance. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Cutting-Edge Predictive Methods for Enhancing Short-Term Load Prediction

Cutting-Edge Predictive Methods for Enhancing Short-Term Loa...

引用

Electrical and Computer Engineering Researches (ICECER), International Conference on

作者： Taher M. Ghazal Jamshaid Iqbal Janjua Walid Abushiba Munir Ahmad Tahir Abbas Karamath Ateeq College of Arts & Science Applied Science University Manama Kingdom of Bahrain Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Selangor Malaysia Al-Khawarizimi Institute of Computer Science (KICS) University of Engineering & Technology (UET) Lahore Pakistan College of Engineering Applied Science University Bahrain College of Informatics Korea University Seoul Republic of Korea Department of Computer Science TIMES Institute Multan Pakistan School of Computing Skyline University College University City Sharjah Sharjah UAE

ISBN: (数字)9798331539733

ISBN: (纸本)9798331539740

Efficient management and cost-related factors in the power sector call for accurate short-term load forecasting as it enables better planning with the electric grid and achieving stability within it. This paper looks into the state-of-the-art forecasting strategies that enhance load forecasts made in shorter time frames. Such techniques include but are not limited to machine learning applications, effective data models, and multi-dimensional modeling leveraging historical, meteorological, and economic data. Their review is carried out in detail with their advantages and disadvantages and their application in practice. Furthermore, this study strives to understand the barriers that need to be overcome in the quest to increase the accuracy of the forecasting models especially concerning renewable energy sources. We illustrate how new trends relate to future developments of predictive models about supporting the decision-making in operating power systems and improving the reliability and sustainability of energy systems.

关键词： Renewable energy sources Accuracy Load forecasting Machine learning Predictive models Power system stability Data models Forecasting Sustainable development Load modeling

来源：评论

学校读者我要写书评

暂无评论

E-government and E-commerce issues in Malaysia 2

E-government and E-commerce issues in Malaysia

引用

2nd International Conference on Smart computing and Electronic Enterprise, ICSCEE 2021

作者： Baker El-Ebiary, Yousef A. Kanaan, Anas Ghassan Pathmanathan, P. Ravindran Alawi, Nahg Abdulmajid Hatamleh, Amer Jusoh, Julaily Aida Aledinat, Lowai Saleh Aseh, Khairi Bamansoor, Samer UniSZA Faculty of Informatics and Computing Malaysia Petra University Faculty of Managment and Financial Sciences Business and E-Commerce Depaetment Amman Jordan International Institute of Applied Science Swiss School of Management Netherlands Geomatika University College Malaysia University of Aden Yemen Irbid National University Faculty of Financial and Business Science Head of Management Information System Department Irbid Jordan UniSZA Faculty of Informatics and Computing Malaysia Faculty of Computer and Information Technology MEDIU Malaysia University of Aden Aden Yemen

ISBN: (纸本)9781665432221

In Malaysia, an e-commerce company is still considered a new middleman. As well as the development of information and communication technology strongly affects business companies at the present time in terms of management, business strategies, production, sales and marketing, and other aspects that underpin business profitability in general. E-commerce, known as e-commerce, refers to a general term for a commercial activity using modern technologies, or a commercial transaction that includes the exchange of data via electronic frameworks, especially the Internet, as well as many modern systems used in personal computers, smart phones, etc. It is not just limited to doing business between companies but also related to online services between governments and individuals. Various investigations related to e-commerce have identified obstacles related to information technology (IT) organization, internet use, financial situation, government and administrative activities as important determinants of doing business online. Information and Communication Technology (ICT) has revolutionized businesses around the world. In this paper, e-commerce practices in Malaysia are analyzed by their characteristics, drawbacks, openings and risks. This paper provides a general review of the current issues considered by e-commerce organizations today. It also suggests the challenges and problems facing e-commerce companies at the present time and how to solve them using e-commerce concepts. © 2021 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

An Overview of Tools and Techniques in Network Forensics

An Overview of Tools and Techniques in Network Forensics

引用

Information Technology (ACIT)

作者： Mahmoud Asassfeh Mohammad Rasmi Al-Mousa Hasan Al-Dweikat Malak Hamad Al-Mashagbeh Suha Afaneh Ghassan Samara Ali Abu Zaid Mohammed Khouj Essam Al Daoud Department of Cybersecurity Zarqa University Zarqa Jordan Cybersecurity and Cloud Computing Department Applied Science Private University Amman Jordan Department of Computer Science Zarqa University Zarqa Jordan Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia Faculty of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Network forensics pertains to a subfield of digital forensics that deals with network security. It is utilized in conjunction with computer network traffic monitoring and analysis, which acts as an intrusion detection system and firewall and facilitates the collection of data and digital proof for network security. This platform is designed to analyze and monitor data in a real-time network environment. It is a crucial instrument for identifying and resolving instances of real-time network misuse. This research shows the differences between network forensics and digital forensics as well as the tools and techniques used in network forensics. It also discusses building forensics platforms, developing network analysis methodologies, and talking about the future of network forensics.

关键词： Performance evaluation Digital forensics Intrusion detection Network analyzers Network security Search problems Real-time systems Logic Monitoring Stress

来源：评论

学校读者我要写书评

暂无评论

$k$kTCQ: Achieving Privacy-Preserving $k$k-Truss Community Queries Over Outsourced Data

引用

IEEE Transactions on Dependable and Secure computing 2023年第4期21卷 2750-2765页

作者： Yunguo Guan Rongxing Lu Songnian Zhang Yandong Zheng Jun Shao Guiyi Wei School of Information Security and Applied Computing Eastern Michigan University Ypsilanti MI USA Faculty of Computer Science University of New Brunswick Fredericton NB Canada State Key Laboratory of Integrated Services Networks Xidian University Xi’an China Zhejiang Gongshang University Hangzhou China

Community search over graphs, which is believed as a powerful tool for locating subgraphs of closely related vertices, has received considerable attention in recent years, and $k$ -truss is such a popular community search metric to obtain subgraphs in which every edge forms $(k-2)$ triangles. In this paper, we particularly consider $k$ -truss community query services, which will return all $k$ -truss communities containing a given query vertex. As is known, when the size of graph grows, for achieving better performance, it is natural for a service provider to outsource the services to a powerful cloud. However, this stresses the need for privacy-preserving $k$ -truss community query services, as the cloud server is not fully trustable. Over the past years, many schemes focusing on privacy-preserving graph computation have been put forth, but none of them can well support privacy-preserving $k$ -truss community queries. Aiming at this challenge, we first propose a privacy-preserving $k$ -truss community query scheme ( $k$ TCQ) by constructing boolean circuits with homomorphic encryption technique and a table-based index. After that, we also design an efficiency-enhanced version ( $k$ TCQ+) based on a stream cipher scheme to reduce the encrypted index's size and improve the query efficiency. Detailed security analysis shows that both $k$ TCQ and $k$ TCQ+ can well preserve data privacy and access pattern privacy, and extensive experimental results also demonstrate that $k$ TCQ+ can observably reduce the size of encrypted index and the query time by $12\times$ and $5.9\times$ , respectively.

关键词： Indexes Servers Cryptography Privacy Social networking (online) Homomorphic encryption Data privacy

来源：评论

学校读者我要写书评

暂无评论

Research on complex system fault prediction method for massive data 4

Research on complex system fault prediction method for massi...

引用

4th International Conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2021

作者： Niu, Wei Cheng, Juan Song, Xiaogang Xi'An Aeronautics Computing Technique Research Institute AVIC Xi'an China Xi'An Institute of Applied Optics Xi'an China Xi'an China Faculty of Computer Science and Engineering Xi'An University of Technology Xi an China

ISBN: (纸本)9781665415965

Fault prediction is a challenging problem of complex system. Furthermore, fault prediction plays a critical role in aircraft engines and the performance of their control systems. Using the robustness analysis of parametric uncertain systems, an improved algorithm is proposed for massive data. The algorithm takes the parametric uncertainties into consideration which can distinguish an actual fault from the model uncertainties. Application to an aircraft engine clearly illustrates the improved performance of the proposed method, the results show that the proposed method helps the system accommodate parametric uncertainties in the model and reduce false alarms and missed detection. © 2021 IEEE.

关键词： Aircraft engines

来源：评论

学校读者我要写书评

暂无评论

Improved Attentive Recurrent Network for applied Linguistics-Based Offensive Speech Detection

引用

Computer Systems science & Engineering 2023年第11期47卷 1691-1707页

作者： Manar Ahmed Hamza Hala J.Alshahrani Khaled Tarmissi Ayman Yafoz Amira Sayed A.Aziz Mohammad Mahzari Abu Sarwar Zamani Ishfaq Yaseen Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Applied Linguistics College of LanguagesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversityMakkahSaudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11835Egypt Department of English College of Science&HumanitiesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

applied linguistics is one of the fields in the linguistics domain and deals with the practical applications of the language studies such as speech processing,language teaching,translation and speech *** ever-growing Online Social Networks(OSNs)experience a vital issue to confront,i.e.,hate *** the OSN-oriented security problems,the usage of offensive language is the most important threat that is prevalently found across the *** on the group targeted,the offensive language varies in terms of adult content,hate speech,racism,cyberbullying,abuse,trolling and *** these,hate speech is the most intimidating form of using offensive language in which the targeted groups or individuals are intimidated with the intent of creating harm,social chaos or *** Learning(ML)techniques have recently been applied to recognize hate speech-related *** current research article introduces a Grasshopper Optimization with an Attentive Recurrent Network for Offensive Speech Detection(GOARN-OSD)model for social *** GOARNOSD technique integrates the concepts of DL and metaheuristic algorithms for detecting hate *** the presented GOARN-OSD technique,the primary stage involves the data pre-processing and word embedding ***,this study utilizes the Attentive Recurrent Network(ARN)model for hate speech recognition and *** last,the Grasshopper Optimization Algorithm(GOA)is exploited as a hyperparameter optimizer to boost the performance of the hate speech recognition *** depict the promising performance of the proposed GOARN-OSD method,a widespread experimental analysis was *** comparison study outcomes demonstrate the superior performance of the proposed GOARN-OSD model over other state-of-the-art approaches.

关键词： applied linguistics hate speech offensive language natural language processing deep learning grasshopper optimization algorithm

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：