检索结果-南通市图书馆

Sports Prediction Model through Cloud Computing and Big Data Based on Artificial Intelligence Method

在线全文

学校读者我要写书评

暂无评论

Journal of Intelligent Learning Systems and Applications 2024年第2期16卷 53-79页

作者： Aws I. Abu Eid Achraf Ben Miled Ahlem Fatnassi Majid A. Nawaz Ashraf F. A. Mahmoud Faroug A. Abdalla Chams Jabnoun Aida Dhibi Firas M. Allan Mohammed Ahmed Elhossiny Salem Belhaj imen Ben Mohamed Faculty of Computing Studies Arab Open University Amman Jordan Computer Science Department Science College Northern Border University Arar Kingdom of Saudi Arabia Artificial Intelligence and Data Engineering Laboratory LR21ES23 Faculty of Sciences of Bizerte University of Carthage Tunis Tunisia Applied College Northern Border University Arar Kingdom of Saudi Arabia Faculty of Specific Education Mansoura University Mansoura Egypt

This article delves into the intricate relationship between big data, cloud computing, and artificial intelligence, shedding light on their fundamental attributes and interdependence. It explores the seamless amalgamation of AI methodologies within cloud computing and big data analytics, encompassing the development of a cloud computing framework built on the robust foundation of the Hadoop platform, enriched by AI learning algorithms. Additionally, it examines the creation of a predictive model empowered by tailored artificial intelligence techniques. Rigorous simulations are conducted to extract valuable insights, facilitating method evaluation and performance assessment, all within the dynamic Hadoop environment, thereby reaffirming the precision of the proposed approach. The results and analysis section reveals compelling findings derived from comprehensive simulations within the Hadoop environment. These outcomes demonstrate the efficacy of the Sport AI Model (SAIM) framework in enhancing the accuracy of sports-related outcome predictions. Through meticulous mathematical analyses and performance assessments, integrating AI with big data emerges as a powerful tool for optimizing decision-making in sports. The discussion section extends the implications of these results, highlighting the potential for SAIM to revolutionize sports forecasting, strategic planning, and performance optimization for players and coaches. The combination of big data, cloud computing, and AI offers a promising avenue for future advancements in sports analytics. This research underscores the synergy between these technologies and paves the way for innovative approaches to sports-related decision-making and performance enhancement.

关键词： Artificial Intelligence Machine Learning Spark Apache Big Data SAIM

An AOP-Based Security Verification Environment for KECCAK Hash Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第11期73卷 4051-4066页

作者： Hassen Mestiri imen Barraj Mohsen Machhout Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj 11942Saudi Arabia Higher Institute of Applied Sciences and Technology of Sousse University of SousseTunisia Electronics and Micro-Electronics Laboratory Faculty of Sciences of MonastirUniversity of MonastirTunisia Electrical Engineering Department Systems Integration&Emerging Energies(SI2E)National Engineers School of SfaxUniversity of SfaxTunisia Higher Institute of Computer Science and Multimedia of Gabes University of GabesTunisia

Robustness of the electronic cryptographic devices against fault injection attacks is a great concern to ensure *** to significant resource constraints,these devices are limited in their *** increasing complexity of cryptographic devices necessitates the development of a fast simulation environment capable of performing security tests against fault injection *** is a good choice for Electronic System Level(ESL)modeling since it enables models to run at a faster *** enable fault injection and detection inside a SystemC cryptographic model,however,the model’s source code must be *** altering the source code,Aspect-Oriented Programming(AOP)may be used to evaluate the robustness of cryptographic *** might replace conventional cryptanalysis methods in the real *** the ESL,we discuss a unique technique for simulating security fault attacks on cryptographic *** current study presents a fault injection/detection environment for assessing the KECCAK SystemC model’s resistance against fault injection *** approach of injecting faults into KECCAK SystemC model is accomplished via the use of weaving faults in AspectC++based on AOP programming *** confirm our technique by applying it to two scenarios using a SystemC KECCAK hash algorithm case study:The first concerns discuss the effect of the AOP on fault detection capabilities,while the second concerns discuss the effect of the AOP on simulation time and executable file *** simulation results demonstrate that this technique is fully capable of evaluating the fault injection resistance of a KECCAK *** demonstrate that AOP has a negligible effect on simulation time and executable file size.

关键词： Aspect-Oriented Programming SystemC AspectC++ cryptographic circuits KECCAK fault detection fault attacks

Global Exponential Convergence of Neutral Type Competitive Neural Networks with D Operator and Mixed Delay

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2020年第6期33卷 1785-1803页

作者： AOUITI Chaouki ASSALI El Abed BEN GHARBIA imen University of Carthage Faculty of Sciences of BizertaDepartment of MathematicsResearch Units of Mathematics and Applications UR13ES477021 ZarzounaBizertaTunisia

The models of competitive neural network(CNN)was in recent past proposed to describe the dynamics of cortical cognitive maps with unsupervised synaptic modifications,where there are two types of memories:Long-term memories(LTM)and short-term memories(STM),LTM presents unsupervised and slow synaptic modifications and STM characterize the fast neural *** paper is concerned with a class of neutral type CNN’s with mixed delay and D *** employing the appropriate differential inequality theory,some sufficient conditions are given to ensure that all solutions of the model converge exponentially to zero ***,an illustrative example is also given at the end of this paper to show the effectiveness of the proposed results.

关键词： Competitive neural networks D operator exponential convergence neutral type delay

A Genetic Algorithm to Minimize the Makespan in a Two-Machine Cross-Docking Flow Shop Problem

在线全文

学校读者我要写书评

暂无评论

Journal of the Operations Research Society of China 2020年第3期8卷 457-476页

作者： imen Hamdi Mohamed Fadhel Tekaya High Institute of Transport and Logistics University of SousseSousseTunisia MODILS lab Faculty of Economics and ManagementUniversity of SfaxSfaxTunisia

We consider the problem of two-machine cross-docking flow shop scheduling where each job on the second machine cannot be processed unless a job or a set of jobs have been completed on the first *** aim is to find a feasible schedule that minimizes the *** the problem is shown to be strongly NP-hard,we propose a genetic algorithm to solve small and large size *** test different types for each genetic operator where new ideas are introduced,which leads to propose six versions of the genetic *** then evaluate their effectiveness through an extensive computational experiments by using many instances generated randomly and by determining the percentage deviation from a lower bound from the literature.

关键词： Cross-docking Flow shop Scheduling Makespan Genetic algorithm

Robust Neural Control of Discrete Time Uncertain Nonlinear Systems Using Sliding Mode Backpropagation Training Algorithm

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2019年第2期16卷 213-225页

作者： imen Zaidi Mohamed Chtourou Mohamed Djemel Control & Energy Management Laboratory National School of Sfax EngineersUniversity of Sfax

This work deals with robust inverse neural control strategy for a class of single-input single-output(SISO) discrete-time nonlinear system affected by parametric uncertainties. According to the control scheme, in the first step, a direct neural model(DNM)is used to learn the behavior of the system, then, an inverse neural model(INM) is synthesized using a specialized learning technique and cascaded to the uncertain system as a controller. In previous works, the neural models are trained classically by backpropagation(BP) algorithm. In this work, the sliding mode-backpropagation(SM-BP) algorithm, presenting some important properties such as robustness and speedy learning, is investigated. Moreover, four combinations using classical BP and SM-BP are tested to determine the best configuration for the robust control of uncertain nonlinear systems. Two simulation examples are treated to illustrate the effectiveness of the proposed control strategy.

关键词： Discrete time uncertain nonlinear systems neural modelling sliding mode backpropagation (BP) algorithm robust neural control

Global Stability Analysis of Switched Nonlinear Observers

在线全文

学校读者我要写书评

暂无评论

International Journal of Automation and computing 2015年第4期12卷 432-439页

作者： imen Manaa Nabil Barhoumi Faouzi Msahli The National Engineering School of Monastir Department of Electrical EngineeringStudy of Industrial Systems and Renewable Energy

This paper considers the problem of simultaneous estimation of the system states and the strategy of commutation for a larger class of nonlinear switched ***,a hybrid high gain observer is considered to get the exact estimation of the continuous states where the strategy of switching is previously ***,an extension to a larger class of nonlinear hybrid systems with arbitrary switching is *** analysis is widely discussed for the two cases to provide a finite-time convergence of the estimation *** effectiveness of the proposed hybrid high gain observer has been proved by applying it to a quadruple tank process.

关键词： Nonlinear hybrid system switching strategies Lyapunov function stability analysis

An Optimized SW/HW AVMF Design Based on High-Level Synthesis Flow for Color Images

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第9期68卷 2925-2943页

作者： Turki MAlanazi Ahmed Ben Atitallah imen Abid Department of Electrical Engineering Jouf UniversitySakakaAljoufSaudi Arabia LETI(E.N.I.S.) University of SfaxSfaxTunisia

In this paper,a software/hardware High-level Synthesis(HLS)design is proposed to compute the Adaptive Vector Median Filter(AVMF)in *** fact,this filter is known by its excellent impulsive noise suppression and chromaticity *** software(SW)study of this filter demonstrates that its implementation is too *** purpose of this work is to study the impact of using an HLS tool to design ideal floating-point and optimized fixed-point hardware(HW)architectures for the AVMF filter using square root function(ideal HW)and ROM memory(optimized HW),respectively,to select the best HLS architectures and to design an efficient HLS software/hardware(SW/HW)embedded AVMF design to achieve a trade-off between the processing time,power consumption and hardware *** that purpose,some approximations using ROM memory were proposed to perform the square root and develop a fixed-point AVMF *** that,the best solution generated for each HLS design was integrated in the SW/HW environment and evaluated under ZC702 FPGA *** experimental results showed a reduction of about 65%and 98%in both the power consumption and processing time for the ideal SW/HW implementation relative to the ideal SW implementation for an AVMF filter with the same image quality,***,the power consumption and processing time of the optimized SW/HW are 70%and 97%less than the optimized SW implementation,*** addition,the Look Up Table(LUTs)percentage,power consumption and processing time used by the optimized SW/HW design are improved by nearly 45%,18%and 61%compared the ideal SW/HW design,respectively,with slight decrease in the image quality.

关键词： AVMF filter SW/HW design HLS flow ZC702 FPGA platform

Bank efficiency in Middle East and North African countries:Does political connection type matter?

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Financial Innovation 2023年第1期9卷 2992-3025页

作者： Naima Lassoued imen Khanchel imen Fakhfakh Higher School of Business Manouba UniversityManoubaTunisia QUARG UR17ES26 ESCTManouba UniversityManoubaTunisia LARIME LR11ES02 ESSECTUniversity of TunisTunisTunisia Faculty of Economic Sciences and Management Sfax UniversitySfaxTunisia Probability and Statistics Laboratory LR/18/ES‑28 FSSSfax UniversitySfaxTunisia

This study examines the effects of the political connections of chief executive officers(CEOs)or directors on technical,allocative,and cost bank efficiencies examining a panel of 144 banks operating in 12 Middle Eastern and North African(MENA)countries observed over the 2008–2021 *** random effect tobit regressions,we find that the three types of political connections explored(aggregate,CEO,and board of directors)have negative effects on banks’technical and cost *** addition,CEO political connections exhibit superior explanatory *** findings remain robust when we consider the sample in terms of monarchist and republican *** evidence reveals that the effect of political connections is observed more strongly during the pandemic period(2020–2021)than during the 2008–2009 financial crisis *** results indicate that banks in MENA countries must strategically regulate bank political connections during crises and consistently *** findings have implications for regulators investors and authorities in MENA countries.

关键词： Middle political Eastern

Quality assessment of local Trichogramma species (Hymenoptera, Tri- chogrammatidae) to control the olive moth Prays oleae Bern. (Lepidop- tera, Yponomeutidae)

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

环境昆虫学报 2011年第4期33卷 429-435页

作者： imen Blibech Unity of Plant Protection and Environment Olive Tree Institute

Assessment of quality of biological control agents is an important step for the success of any biocontrol *** were carried out to select candidate Trichogramma species for use in biological control of the olive moth Prays oleae Bern(Lepidoptera,Yponomeutidae).Thirteen local strains were preselected on the basis of the geographical origin and the availability from mass production of the rearing host Ephestia kuehniella ZELL.(Lepidoptera,Pyralidae) under laboratory *** tests were focusing on acceptance and preference for *** *** the acceptance test,a single parasitoid female was offered *** eggs on "tricho-card" for 6 hours at 25°C,70% HR and L16:D9 and assessed for parasitism after 6 *** preference was determined by offering the choice and observing contacts with eggs of the target pest *** and eggs of the host *** was therefore assessed 6 days after the experiment under similar laboratory *** host acceptance test,most eggs of *** were parasited by strains belonging to the species ***,*** and *** strains also showed a high number of contacts with olive moth eggs in preference ***,a small number of *** observed ovipositions resulted in successful ***,*** and *** were selected as candidates for further experiments.

关键词： Biological control Trichogramma Prays oleae Ephestia kuehniella preference tests