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

A renewal theory based performance and configuration framework of the IEEE 802.11ah RAW mechanism

引用

Digital Communications and networks 2023年第1期9卷 236-251页

作者： Hamid Taramit Luis Orozco-Barbosa Abdelkrim Haqiq Hassan First University of Settat Faculty of Sciences and TechniquesComputerNetworksMobility and Modeling Laboratory:IR2M26000 SettatMorocco Albacete Research Institute of Informatics Universidad de Castilla-La Mancha02006 AlbaceteSpain

IEEE 802.11ah is a new Wi-Fi standard for sub-1Ghz communications,aiming to address the challenges of the Internet of Things(IoT).Significant changes in the legacy 802.11 standards have been proposed to improve the network performance in high contention scenarios,the most important of which is the Restricted Access Window(RAW)*** mechanism promises to increase the throughput and energy efficiency by dividing stations into different *** this scheme,only the stations belonging to the same group may access the channel,which reduces the collision probability in dense ***,the standard does not define the RAW grouping *** this paper,we develop a new mathematical model based on the renewal theory,which allows for tracking the number of transmissions within the limited RAW slot contention period defined by the *** then analyze and evaluate the performance of RAW *** also introduce a grouping scheme to organize the stations and channel access time into different groups within the ***,we propose an algorithm to derive the RAW configuration parameters of a throughput maximizing grouping *** additionally explore the impact of channel errors on the contention within the time-limited RAW slot and the overall RAW optimal *** presented analytical framework can be applied to many other Wi-Fi standards that integrate periodic channel *** simulations using the MATLAB software validate the analytical model and prove the effectiveness of the proposed RAW configuration scheme.

关键词： IEEE 802.11ah Performance evaluation Renewal theory RAW mechanism Internet of things

来源：评论

学校读者我要写书评

暂无评论

Fog Computing Model Based on Queuing Theory 1

引用

International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2022

作者： Mohtadi, Hibat Eallah Hanini, Mohamed Haqiq, Abdelkrim Faculty of Sciences and Techniques Computer Networks Mobility and Modeling Laboratory: IR2M Hassan First University of Settat Settat26000 Morocco

ISBN: (数字)9783031352515

ISBN: (纸本)9783031352508

To overcome the limitations of Cloud server that does not fit well for vehicles needing high-speed processing, low latency, and more security;Fog computing was evolved, extending the functionality of cloud computing model to the edge of the network. Therefore, the idea of utilizing vehicles as the infrastructures, named Vehicular Fog Computing (VFC) is proposed. The VFC is an architecture that utilizes a collaborative multitude of end-user clients or near-user edge devices to carry out communication and computation, based on better utilization of individual communication and computational resources of each vehicle. In this work, we will try to determine the Qos performances in different scenarios. We will as well, try to give a mathematical model by formulating the vehicular fog computing system using the queuing theory, in order to find out and evaluate the QoS parameters such as the mean throughput, the mean number of requests, the service utilisation.., than we will implement our analytical results to try to find out the effect of the mobility on the fog computing;We consider that the service time in our mathematical model is the key factor of the mobility which means that each vehicle had a service time so when the vehicles move the service time changes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Quality of Service Analysis in a Fog Computing Network with Breakdown and Vacation Interruption

Quality of Service Analysis in a Fog Computing Network wi...

引用

International Conference on Business Intelligence and Information Technology, BIIT 2022

作者： Mohtadi, Hibat Eallah Hanini, Mohamed Haqiq, Abdelkrim Faculty of Sciences and Techniques Computer Networks Mobility and Modeling laboratory: IR2M Hassan First University of Settat Settat26000 Morocco

ISBN: (纸本)9789819934157

Fog computing was developed to expand cloud computing’s computation, storage, and networking capabilities to the network’s edge, therefore reducing latency and improving the quality of service. In fact, it produces a little cloud at the network’s edge by utilizing a huge number of community and geo-distributed network equipments called as fog nodes (FN), such as routers, switches, and access points. Fog computing raises concerns about offloading tasks for remote processing, such as the loss of a node in a computer network, whether due to unforeseeable causes such as system failure, breakdowns, or scheduled outages such as vacations taken by the fog node. These concerns can result in reduced computer network performance in a fog environment or loss of redundancy. This work provides an analytical model based on queening theory for investigating the quality of service in a fog computing network where the fog nodes could break down or go on vacation. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Solving the 0/1 Knapsack Problem Using Metaheuristic and Neural networks for the Virtual Machine Placement Process in Cloud Computing Environment

引用

Mathematical Problems in Engineering 2023年第1期2023卷

作者： Abid, Mohamed El Kafhali, Said Amzil, Abdellah Hanini, Mohamed Faculty of Sciences and Techniques Computer Networks Mobility and Modeling Laboratory IR2M Hassan First University of Settat Settat26000 Morocco

Virtual machine placement (VMP) is carried out during virtual machine migration to choose the best physical computer to host the virtual machines. It is a crucial task in cloud computing. It directly affects data center performance, resource utilization, and power consumption, and it can help cloud providers save money on data center maintenance. To optimize various characteristics that affect data centers, VMs, and their runs, numerous VMP strategies have been developed in the cloud computing environment. This paper aims to compare the accuracy and efficiency of nine distinct strategies for treating the VMP as a knapsack problem. In the numerical analysis, we test out various conditions to determine how well the system works. We first illustrate the rate of convergence for algorithms, then the rate of execution time growth for a given number of virtual machines, and lastly the rate of development of CPU usage rate supplied by the nine methods throughout the three analyzed conditions. The obtained results reveal that the neural network algorithm performs better than the other eight approaches. The model performed well, as shown by its ability to provide near-optimal solutions to test cases. © 2023 Mohamed Abid et al.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Random Access Mechanism Enhancement Based on a Hybrid ALOHA Protocol Using an Analytical Model

Journal of ICT Standardization

引用

Journal of ICT Standardization 2022年第3期10卷 383-410页

作者： Bellouch, Abdessamad Zaaloul, Abdellah Haqiq, Abdelkrim Hassan First University of Settat Faculty of Sciences and Techniques Computer Networks Mobility and Modeling laboratory: IR2M Settat26000 Morocco Agadir Morocco Washington United States

In this paper, we present a new MAC (Medium Access Control) protocol, called Hybrid ALOHA (H-ALOHA), which is a combination of two existing protocols: Pure ALOHA (P-ALOHA) protocol and Slotted ALOHA (S-ALOHA) protocol. The idea behind it is to design a MAC protocol that could meet some specific requirements in wireless networks, such as reducing energy consumption, delay minimization, and increasing the throughput. To the best of our knowledge, the S-ALOHA protocol is an improved version of P-ALOHA. However, during one single transmission scenario, P-ALOHA works better than S-ALOHA in terms of energy consumption and packet delivery. Motivated by that fact, we combine these two protocols, resulting in a hybrid ALOHA. A finite-state Markovian model is proposed to study the steady-state performance of H-ALOHA including normalized throughput, backlogged throughput, access delay, backlogged delay, and energy consumption. The proposed hybrid protocol has been compared with the S-ALOHA protocol. The simulation results show that the proposed hybrid protocol outperforms all ALOHA protocols. On average, the proposed protocol outperforms the S-ALOHA protocol by 60% in terms of normalized throughput, by 15% in terms of access delay, and by 23% in terms of total energy consumed during the transmission process. © 2022 River Publishers.

关键词： Medium access control

来源：评论

学校读者我要写书评

暂无评论

Optimizing Resource Allocation in 5G networks: An Integrated Approach with Mobile Edge Computing and Network Slicing

Optimizing Resource Allocation in 5G Networks: An Integrated...

引用

Ubiquitous Networking (UNet), International Conference on

作者： Abdellah Amzil Taoufyq Elansari Mohamed Hanini Abdellah Zaaloul Computer Networks Mobility and Modelling Laboratory (IR2M)) Faculty of Sciences and Techniques Hassan First University of Settat Morocco Department of Computer Sciences Faculty of Sciences Moulay Ismail University B.P. Meknes Morocco Computer Networks Mobility and Modeling Laboratory Faculty of Sciences and Techniques Hassan First University of Settat Morocco Mathematical Modeling Laboratory and Economic Calculation (LM2CE) Faculty of Economic and Social Legal Sciences Hassan First University of Settat Morocco

ISBN: (数字)9798350356144

ISBN: (纸本)9798350356151

In contemporary smart factory systems, the customization of services through advanced technologies such as Mobile Edge Computing (MEC) and Network Slicing is essential for managing diverse applications. These technologies enable the efficient segmentation and allocation of heterogeneous resources on a shared physical infrastructure, focusing primarily on supporting low-energy services. This paper introduces the Factory Resource Optimization (FRO) framework, a novel approach that leverages MEC, Network Slicing, and a modified Non-Orthogonal Multiple Access (NOMA) strategy called Layered Multiple Access (LMA) to optimize resource allocation in 5G networks within smart factories. Unlike previous approaches that often focus on either energy efficiency or latency optimization, FRO tackles both simultaneously by formulating a non-convex combinatorial optimization problem. The solution involves an iterative algorithm based on a decomposition methodology, a significant departure from traditional optimization techniques. This approach allows for the efficient allocation of resources while minimizing the energy consumption of Equipment Monitoring Units (EMUs) and guaranteeing reliable and low-latency communication for Factory Safety Detectors (FSDs). Simulation results demonstrate substantial energy savings for EMUs and adherence to FSD latency requirements, highlighting FRO's potential to enhance smart factory operations compared to existing methods.

关键词： NOMA Multi-access edge computing 5G mobile communication Network slicing Simulation Production facilities Safety Resource management Optimization Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Resource and Energy-Efficient Configuration of IEEE 802.11ah networks under Rayleigh Channels 4

Resource and Energy-Efficient Configuration of IEEE 802.11ah...

引用

4th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2022

作者： Taramit, Hamid Orozco-Barbosa, Luis Haqiq, Abdelkrim Faculty of Sciences and Techniques Computer Networks Mobility and Modeling Laboratory: IR2M Hassan First University of Settat Settat26000 Morocco Universidad de Castilla-La Mancha Albacete Research Institute of Informatics Albacete Spain

ISBN: (纸本)9781665494113

The Restricted Access Window (RAW) mechanism included in the IEEE 802.11ah standard is one of the promising solutions to meet the requirements of Internet of Things (IoT) applications. It splits channel time into RAW slots and limits channel access to only a group of stations at a time. In this paper, we consider an IEEE 802.11ah network operating under Rayleigh fading channel with capture effect, and we develop efficient schemes to optimize the gain of the RAW mechanism. We propose an algorithm to identify the best cases for the RAW slot duration. Then, we deploy this result to develop a resource-efficient scheme to reconfigure a RAW consisting of several RAW slots. The new configuration eliminates the extra time wasted during the RAW period, resulting in higher throughput and energy efficiency. We present numerical results and simulations to validate our findings and analyze the impact of several parameters. The proposed RAW reconfiguration scheme significantly increases RAW performance by up to 21% for throughput and up to 8% for energy efficiency. It further optimizes the channel allocation resources, providing a channel gain ratio of up to 19%. © 2022 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A New Hybrid Artificial Intelligence Model for Diseases Identification 7th

A New Hybrid Artificial Intelligence Model for Diseases Ide...

引用

7th International Conference on Smart City Applications, SCA 2022

作者： Maiti, Abdallah Abarda, Abdallah Hanini, Mohamed Computer Networks Mobility and Modeling Laboratory FST Hassan First University of Settat Settat Morocco LM2CE Lab Faculty of Economics and Management Settat Hassan First University of Settat Settat Morocco

ISBN: (纸本)9783031268519

Artificial intelligence is increasingly applied in many fields, specially in medicine to assist patients and physicians. Growing datasets provide a sound basis to adapt machine learning methods to identify and detect some diseases. These later, are often very similar which make difficult their identification by chest X-ray images. In this paper, we introduce a diagnostic AI model that allow to separate, diagnose and classify three various diseases: tuberculosis, covid19 and Pneumonia. The proposed model is based on a combination of Deep Learning using the deep SqueezeNet model and Machine Learning: SVM, KNN, Logistic Regression, decision tree and Naive Bayes. The model is applied to a chest X-ray dataset containing images for each type of disease. To train and test our model, we split the image dataset into two training and test subsets in order to differentiate between different disease types. The accuracy show clearly that our model provides better results of diagnosis and identification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision trees

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：