检索结果-内蒙古大学图书馆

Combining Autoencoders and Deep Learning for Effective Fraud Detection in Credit Card Transactions

Operations Research Forum 2025年第1期6卷 1-30页

作者： Tayebi, Mohammed El Kafhali, Said Computer Networks Modeling and Mobility Laboratory (IR2M) Faculty of Sciences and Techniques Hassan First University of Settat Settat Morocco

The advancement of technologies and the proliferation of new payment services have improved our lives, offering limitless opportunities for individuals and companies in each country to develop their businesses through credit card transactions as a payment method. Consequently, continuous improvement is crucial for these systems, particularly in the classification of fraud transactions. Numerous studies are required in the realm of automated and real-time fraud detection. Due to their advantageous properties, recent studies have utilized different deep learning architectures to create well-fitting models to identify fraudulent transactions. Our proposed solution aims to exploit the robust capabilities of deep learning approaches to identify abnormal transactions. The solution can be presented as follows: To address the imbalanced data set issue, we applied an autoencoder combined with the support vector machine model (ASVM). For the classification phase, we utilize an attention-long short-term memory neural network as a weak learner for the gradient boosting algorithm (GB_ALSTM), comparing it with various techniques, including artificial neural networks (ANNs), convolutional neural networks (CNNs), long short-term memory neural networks (LSTMs), attention-long short-term memory neural networks (ALSTMs), and bidirectional long short-term memory neural networks (BLSTMs). We conducted several experiments on a real-world dataset, revealing promising results in detecting abnormal transactions and highlighting the dominance of our suggested solution over competing models. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Attention mechanism Attention-long short-term memory neural networks Autoencoder Deep learning Fraud transactions detection Gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Stacking Approach for Detecting Arabic Fraudulent Reviews in E-Commerce Platforms

引用

Procedia computer Science 2025年 257卷 1251-1256页

作者： Marouane Dirchaoui Abdallah Abarda Abdeljalil El Ouardighi Abdallah Maiti Laboratoire de Modelisation Mathematiques et de Calculs Economiques Hassan First University of Settat Settat Morocco Computer Networks Mobility and Modeling laboratory Hassan First University of Settat Settat Morocco

Fake online reviews pose a significant threat to the growth of e-commerce, as they are used not only to unethically promote products and services, but also to commit fraud. The aim of this study is to explore the potential of stacking machine learning models in the detection of Arabic fake reviews on e-commerce platforms. Using the Arabic Fake Reviews Detection dataset, this study developed three stacking models: RLGM, RLGGM, and GAM, using basic learners such as Random Forest, Multilayer Perceptron, and Gradient Boosting, with a logistic regression model as the meta-learner. The performance of these models was compared with traditional machine learning models in three domains, namely hotel, product and restaurant. The developed models achieved an accuracy of 87.41% in detecting fake Arabic reviews in the Restaurant domain, 82.27% in the Product domain, 87.1% in the Hotel domain, and 83.53% in all three domains combined. The results showed that stacking machine learning models generally improves performance, with the RLGGM stacking model outperforming the advanced deep learning architectures developed in a previous study in the product domain.

关键词： Arabic Fake reviews Stacking models Financial cybercrime Machine learning Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Stacking Approach for Detecting Arabic Fraudulent Reviews in E-Commerce Platforms 16

Stacking Approach for Detecting Arabic Fraudulent Reviews in...

引用

16th International Conference on Ambient Systems, networks and Technologies networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： Dirchaoui, Marouane Abarda, Abdallah El Ouardighi, Abdeljalil Maiti, Abdallah Laboratoire de Modelisation Mathematiques et de Calculs Economiques Hassan First University of Settat Settat Morocco Computer Networks Mobility and Modeling Laboratory Hassan First University of Settat Settat Morocco

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

A Study of the Main Factors Affecting Wireless Sensor networks 3

A Study of the Main Factors Affecting Wireless Sensor Networ...

引用

3rd International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2019

作者： Hamami, Loubna Nassereddine, Bouchaib Computer Networks Mobility and Modeling Laboratory Hassan 1st University Faculty of Sciences and Technology Department of Mathematics and Computer Settat Morocco

ISBN: (数字)9781728143651

ISBN: (纸本)9781728143651

In the last years, the enormous advance in wireless technologies and the proliferation of MEMS (MicroElectroMechanical) systems technology have facilitated the development of smart sensors at low cost and low energy consumption. This development has led to a major shift in wireless sensor network (WSN) technology. The wireless sensor network is considered an exciting and economical technology for widespread use in various areas of life, including military, agriculture, environment, medical, and industry, for multiple reasons, such as monitoring, detection, and tracking. However, this type of network poses a range of problems such as security, deployment, architecture, location, and energy consumption. This paper describes the main factors affecting wireless sensor networks. © 2019 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Integration of irrigation system with wireless sensor networks: Prototype and conception of intelligent irrigation system

Integration of irrigation system with wireless sensor networ...

引用

2018 World Congress on Engineering and computer Science, WCECS 2018

作者： Hamami, Loubna Nassereddine, Bouchaib Computer Networks Mobility and Modeling Laboratory Department of Mathematics and Computer Faculty of Sciences and Technology Hassan 1st University Settat Morocco

ISBN: (纸本)9789881404909

In recent years, precision agriculture and Wireless Sensor Network (WSN) technology have attracted great attention and concentration in industrial and academic levels. The combination between WSNs and the agricultural sector will be beneficial to solve several issues and challenges. This combination can realize a set of benefits such as improving the quality of the agricultural product, increasing the efficiency of production, improving the efficiency of crop, and conserving energy and water resources. Precision agriculture manages a set of different services (e.g., irrigation, fertilization), especially irrigation systems. The irrigation system is considered one of the most critical factors for successful agricultural production and development of the agriculture. However, the current irrigation systems are characterized by poor performance and a significant increase in demand for agricultural productivity. In addition, these current systems are affected by many factors and problems such as the water scarcity, drought, and waste of limited water resources. To correct these problems, we propose a prototype for an intelligent irrigation system that is based on the integration of a drip irrigation technique with the wireless sensor network. In this paper, we develop an automated and intelligent irrigation technique using a WSN and ZigBee wireless communication technology for saving water and increasing the performance and efficiency of irrigation systems and we present the operation and design of this system. The proposed system controls irrigation water through the detection of temperature and soil moisture and other environmental parameters;the data is measured using several special sensors deployed near the root part of plants. This system also allows an analysis and checks the measured data with a developed base of threshold values for each measured parameter in order to activate or deactivate the irrigation mechanism. The main aims of our proposed system are savi

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Towards a smart irrigation system based on wireless sensor networks (WSNs) 1

Towards a smart irrigation system based on wireless sensor n...

引用

1st International Conference of computer Science and Renewable Energies, ICCSRE 2018

作者： Hamami, Loubna Nassereddine, Bouchaib Computer Networks Mobility and Modeling laboratory Department of Mathematics and Computer Faculty of Sciences and Technology Hassan 1st University Settat Morocco

ISBN: (纸本)9789897584312

Due to the evolution of technologies and need to observe and manage hostile environments, Wireless Sensor networks (WSNs) are becoming essential and implicated in most fields of life. The agricultural sector is one of such sectors where WSNs are successfully utilized to achieve many benefits. For successful agriculture, the irrigation is one of the most important factors, where it plays a tactical role in the process of agriculture but is considered one of the world's largest freshwater consumers. Besides, the water scarcity, drought, and irrational wastage of water resources are among the critical issues that touch almost all sectors, notably agricultural services, and especially irrigation. These facts lead all governments around the world to rethink about saving water and reducing the amount of water used in irrigation;this requires the development of irrigation practices in order to obtain a complete and independent system for the management of irrigation more efficient. Consequently, selection of using WSNs in irrigation system will be a benefit for developing the agriculture, and thus saving water and improving and increasing production. In this work, we propose a new model of a complete and smart irrigation system based on wireless sensor networks, and we introduce and discuss our proposed system. The suggested system controls and regulates irrigation system by monitoring a set of environmental parameters, i.e., soil and weather properties, using soil and weather sensor nodes and improving techniques of decision-making to estimate requirements of each crop (e.g., amount of water required), and therefore can make the decision to activate or disable irrigation. Copyright © 2020 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.

关键词： Irrigation

来源：评论

学校读者我要写书评

暂无评论

A novel approach based on XGBoost classifier and Bayesian optimization for credit card fraud detection

Cyber Security and Applications

引用

Cyber Security and Applications 2025年 3卷

作者： Mohammed Tayebi Said El Kafhali Computer Networks Modeling and Mobility Laboratory (IR2M) Faculty of Sciences and Techniques Hassan First University of Settat Settat 26000 Morocco

Nowadays, detecting fraudulent transactions has become increasingly important due to the rise of online businesses and the increasing use of sophisticated techniques by fraudsters to make fraudulent transactions appear similar to genuine ones. Researchers have explored a lot of machine learning classifiers, such as random forest, decision tree, support vector machine, logistic regression, artificial neural network, and recurrent neural network, to secure these systems. This study proposes an enhanced XGBoost algorithm for detecting fraudulent transactions using an intelligent technique that tunes the hyperparameters of the algorithm through Bayesian optimization. To test the performance of our solution, several experiments are conducted on two credit card datasets consisting of both legitimate and fraudulent transactions. To prevent overfitting on imbalanced datasets, we employed cross-validation, SMOTE, and Random under-sampling techniques. For Data 1, the best performance using SMOTE achieved an accuracy of 0.9996, precision of 0.9406, recall of 0.8740, F-measure of 0.8740, and AUC of 0.9879. For Data 2, the Random Under-sampling technique yielded the highest performance with an accuracy of 0.8325, precision of 0.8294, recall of 0.8378, F-measure of 0.8336, and AUC of 0.9088. Our proposed solution outperforms other machine learning models, as demonstrated by these experimental results.

关键词： XGBoost algorithm Hyperparameters optimization Bayesian optimization Fraud detection Credit card transactions Cross-validation Imbalanced datasets

来源：评论

学校读者我要写书评

暂无评论

Non-cooperative game for admission control and bandwidth allocation in WiMAX networks

Non-cooperative game for admission control and bandwidth all...

引用

International Conference on Innovative Computing Technology (INTECH)

作者： Abdelali El Bouchti Abdelkrim Haqiq Ali Benjelloun Computer Networks Mobility and Modeling laboratory FST Settat Morocco

In this paper, we propose an adaptive bandwidth allocation (BA) and connection admission control (CAC) mechanism based on game theory for polling services in IEEE 802.16 broadband wireless networks. A noncooperative two-person general-sum game is formulated where the base station and a new connection are the players of this game. The game formulation provides not only the decision on accepting or rejecting a connection, but also the amount of bandwidth allocated to a new connection (if admitted). A queuing model considering adaptive modulation and coding (AMC) in the physical layer is used to analyze quality of service (QoS) performances, namely, delay and throughput performances, respectively, for real-time and non-real-time polling services. This queuing model is used by the proposed bandwidth allocation and admission control game to ensure that the payoffs for both the base station and the new connection are maximized. The performance of the proposed scheme is evaluated by simulation and compared with that of traditional admission control with static and adaptive bandwidth allocation.

关键词： Bandwidth Base stations Admission control Channel allocation Games Delays Throughput

来源：评论

学校读者我要写书评

暂无评论

Stochastic modeling and analysis of feedback control on the QoS VoIP traffic in a single cell IEEE 802.16e networks

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2017年第1期44卷 19-28页

作者： El Kafhali, Said Hanini, Mohamed Computer Networks Mobility and Modeling laboratory National School of Applied Sciences Hassan 1st Univ Morocco Computer Networks Mobility and Modeling laboratory Faculty of Sciences and Technology Hassan 1st Univ Morocco

One of the major challenges in the next generation networks is maintaining the Quality of Service (QoS) for different users who use the services of such a technology. The problem increases when the flows that traverse the wireless link belong to classes with different requirements of QoS. In this case, the network services face several disadvantages caused by the unreliability of wireless channel and the channel sharing by several users. In this paper, we consider a single-cell IEEE 802.16e environment in which the base station allocates subchannels to the subscriber stations in its coverage area. Therefore, two systems are compared. In the first system, called system without Feedback Control, for each uplink subchannel, a separate single queue is used for buffering the VoIP packets from Subscriber Station (SS) to Base Station (BS). However, in the second system, called system with Feedback Control, an Active Queue Managment (AQM) is used to control the VoIP packets. Two thresholds are used in the queue in an effort to control the arrival rate of the VoIP packets. The VoIP arrivals are modeled by a two-state Markov Modulated Poisson Process (MMPP) process. A queuing analytical model is presented to evaluate the performance of both systems. Numerical results obtained show the positive impact of the AQM added to the second system on the performance parameters of VoIP packets compared to the first system.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Dynamic resource allocation for service in mobile cloud computing with Markov modulated arrivals

引用

International Journal of modeling, Simulation, and Scientific Computing 2021年第5期12卷 97-117页

作者： Munatel Mohammed Abdelkrim Haqiq Hassan First University of Settat Faculty of Sciences and Techniques Computer Networks Mobility and Modeling Laboratory:IR2M Settat 26000Morocco

Mobile Cloud Computing (MCC) is a modern architecture that brings together cloudcomputing, mobile computing and wireless networks to assist mobile devices in storage,computing and communication. A cloud environment is developed to support a widerange of users that request the cloud resources in a dynamic environment with possible constraints. Burstiness in users service requests causes drastic and unpredictableincreases in the resource requests that have a crucial impact on policies of resourceallocation. How can the cloud system efficiently handle such burstiness when the cloudresources are limited? This problem becomes a hot issue in the MCC research area. Inthis paper, we develop a system model for the resource allocation based on the SemiMarkovian Decision Process (SMDP), able of dynamically assigning the mobile servicerequests to a set of cloud resources, to optimize the usage of cloud resources and maximize the total long-term expected system reward when the arrival process is a finitestate Markov-Modulated Poisson Process (MMPP). Numerical results show that ourproposed model performs much better than the Greedy algorithm in terms of achievinghigher system rewards and lower service requests blocking probabilities, especially whenthe burstiness degree is high, and the cloud resources are limited.

关键词： Mobile cloud computing resource allocation burstiness Markov decision process

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：