检索结果-南通市图书馆

Advancing Crowd Object Detection: A Review of YOLO, CNN and ViTs Hybrid Approach*

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 Intelligent Learning Systems and Applications 2024年第3期16卷 175-221页

作者： Mahmoud Atta mohammed Ali tarek Aly Atef Tayh Raslan Mervat Gheith Essam A. Amin Faculty of Graduate Studies for Statistical Research Software Engineering Department Cairo University Giza Egypt

One of the most basic and difficult areas of computer vision and image understanding applications is still object detection. Deep neural network models and enhanced object representation have led to significant progress in object detection. This research investigates in greater detail how object detection has changed in the recent years in the deep learning age. We provide an overview of the literature on a range of cutting-edge object identification algorithms and the theoretical underpinnings of these techniques. Deep learning technologies are contributing to substantial innovations in the field of object detection. While Convolutional Neural Networks (CNN) have laid a solid foundation, new models such as You Only Look Once (YOLO) and Vision Transformers (ViTs) have expanded the possibilities even further by providing high accuracy and fast detection in a variety of settings. Even with these developments, integrating CNN, YOLO and ViTs, into a coherent framework still poses challenges with juggling computing demand, speed, and accuracy especially in dynamic contexts. Real-time processing in applications like surveillance and autonomous driving necessitates improvements that take use of each model type’s advantages. The goal of this work is to provide an object detection system that maximizes detection speed and accuracy while decreasing processing requirements by integrating YOLO, CNN, and ViTs. Improving real-time detection performance in changing weather and light exposure circumstances, as well as detecting small or partially obscured objects in crowded cities, are among the goals. We provide a hybrid architecture which leverages CNN for robust feature extraction, YOLO for rapid detection, and ViTs for remarkable global context capture via self-attention techniques. Using an innovative training regimen that prioritizes flexible learning rates and data augmentation procedures, the model is trained on an extensive dataset of urban settings. Compared to solo YOLO,

关键词： Object Detection Deep Learning Computer Vision YOLO Convolutional Neural Networks (CNN) Vision Transformers Neural Networks Transfer Learning Autonomous Driving Self-Drive Vehicles

Enhancing Data Analysis and Automation: Integrating Python with Microsoft Excel for Non-Programmers

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 Software Engineering and Applications 2024年第6期17卷 530-540页

作者： Osama Magdy Ali mohamed Breik tarek Aly Atef Tayh Nour El-Din Raslan Mervat Gheith Software Engineering Department Faculty of Graduate Studies for Statistical Research Cairo University Giza Egypt

Microsoft Excel is essential for the End-User Approach (EUA), offering versatility in data organization, analysis, and visualization, as well as widespread accessibility. It fosters collaboration and informed decision-making across diverse domains. Conversely, Python is indispensable for professional programming due to its versatility, readability, extensive libraries, and robust community support. It enables efficient development, advanced data analysis, data mining, and automation, catering to diverse industries and applications. However, one primary issue when using Microsoft Excel with Python libraries is compatibility and interoperability. While Excel is a widely used tool for data storage and analysis, it may not seamlessly integrate with Python libraries, leading to challenges in reading and writing data, especially in complex or large datasets. Additionally, manipulating Excel files with Python may not always preserve formatting or formulas accurately, potentially affecting data integrity. moreover, dependency on Excel’s graphical user interface (GUI) for automation can limit scalability and reproducibility compared to Python’s scripting capabilities. This paper covers the integration solution of empowering non-programmers to leverage Python’s capabilities within the familiar Excel environment. This enables users to perform advanced data analysis and automation tasks without requiring extensive programming knowledge. Based on Soliciting feedback from non-programmers who have tested the integration solution, the case study shows how the solution evaluates the ease of implementation, performance, and compatibility of Python with Excel versions.

关键词： Python End-User Approach Microsoft Excel Data Analysis Integration Spreadsheet Programming Data Visualization

Building Custom Spreadsheet Functions with Python: End-User Software Engineering Approach

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 Software Engineering and Applications 2024年第5期17卷 246-258页

作者： Tamer Bahgat Elserwy Atef Tayh Nour El-Din Raslan tarek Ali Mervat H. Gheith Department of Software Engineering Faculty of Graduate Studies for Statistical Research (FGSSR) Cairo University Giza Egypt Department of Information Systems Higher Institute of Advanced Studies Giza Egypt

End-user computing empowers non-developers to manage data and applications, enhancing collaboration and efficiency. Spreadsheets, a prime example of end-user programming environments widely used in business for data analysis. However, Excel functionalities have limits compared to dedicated programming languages. This paper addresses this gap by proposing a prototype for integrating Python’s capabilities into Excel through on-premises desktop to build custom spreadsheet functions with Python. This approach overcomes potential latency issues associated with cloud-based solutions. This prototype utilizes Excel-DNA and IronPython. Excel-DNA allows creating custom Python functions that seamlessly integrate with Excel’s calculation engine. IronPython enables the execution of these Python (CSFs) directly within Excel. C# and VSTO add-ins form the core components, facilitating communication between Python and Excel. This approach empowers users with a potentially open-ended set of Python (CSFs) for tasks like mathematical calculations, statistical analysis, and even predictive modeling, all within the familiar Excel interface. This prototype demonstrates smooth integration, allowing users to call Python (CSFs) just like standard Excel functions. This research contributes to enhancing spreadsheet capabilities for end-user programmers by leveraging Python’s power within Excel. Future research could explore expanding data analysis capabilities by expanding the (CSFs) functions for complex calculations, statistical analysis, data manipulation, and even external library integration. The possibility of integrating machine learning models through the (CSFs) functions within the familiar Excel environment.

关键词： End-User Software Engineering Custom Spreadsheet Functions (CSFs)

An Improved Enterprise Resource Planning System Using Machine Learning Techniques

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 Software Engineering and Applications 2024年第5期17卷 203-213页

作者： Ahmed Youssri Zakaria Elsayed Abdelbadea Atef Raslan tarek Ali Mervat Gheith Al-Sayed Khater Essam A. Amin Department of Software Engineering Faculty of Graduate Studies for Statistical Research (FGSSR) Cairo University Giza Egypt

Traditional Enterprise Resource Planning (ERP) systems with relational databases take weeks to deliver predictable insights instantly. The most accurate information is provided to companies to make the best decisions through advanced analytics that examine the past and the future and capture information about the present. Integrating machine learning (ML) into financial ERP systems offers several benefits, including increased accuracy, efficiency, and cost savings. Also, ERP systems are crucial in overseeing different aspects of Human Capital Management (HCM) in organizations. The performance of the staff draws the interest of the management. In particular, to guarantee that the proper employees are assigned to the convenient task at the suitable moment, train and qualify them, and build evaluation systems to follow up their performance and an attempt to maintain the potential talents of workers. Also, predicting employee salaries correctly is necessary for the efficient distribution of resources, retaining talent, and ensuring the success of the organization as a whole. Conventional ERP system salary forecasting methods typically use static reports that only show the system’s current state, without analyzing employee data or providing recommendations. We designed and enforced a prototype to define to apply ML algorithms on Oracle EBS data to enhance employee evaluation using real-time data directly from the ERP system. Based on measurements of accuracy, the Random Forest algorithm enhanced the performance of this system. This model offers an accuracy of 90% on the balanced dataset.

关键词： ERP HCM Machine Learning Employee Performance Pythonista Pythoneer

Emerging applications of nanomaterials in chemical enhanced oil recovery:Progress and perspective

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2020年第8期28卷 1995-2009页

作者： Najeebullah Lashari tarek Ganat Department of Petroleum Engineering Universiti Teknologi PETRONAS32610 Seri IskandarPerak Darul RidzuanMalaysia Department of Petroleum and Gas Engineering Dawood University of Engineering&TechnologyM.A Jinnah RoadKarachi-74800Pakistan

In enhanced oil recovery,different chemicalmethods utilization improves hydrocarbon recovery due to their fascinating abilities to alter some critical parameters in porous media,such as mobility control,the interaction between fluid to fluid,and fluid to rock *** decades the use of surfactant and polymer flooding has been used as tertiary recovery *** the current research,the inclusion of nanomaterials in enhanced oil recovery injection fluids solely or in the presence of other chemicals has got colossal *** emphasis of this review is on the applicability of nanofluids in the chemical enhanced oil *** responsiblemechanisms are an increment in the viscosity of injection fluid,decrement in oil viscosity,reduction in interfacial and surface tension,and alteration of wettability in the rock *** this review,important parameters are presented,which may affect the desired behavior of nanoparticles,and the drawbacks of nanofluid and polymer flooding and the need for a combination of nanoparticles with the polymer are *** to the lack of literature in defining the mechanism of nanofluid in a reservoir,this paper covers majorly all the previous work done on the application of nanoparticles in chemical enhanced oil recovery at home ***,the problems associatedwith the nano-enhanced oil recovery are outlined,and the research gap is identified,which must be addressed to implement polymeric nanofluids in chemical enhanced oil recovery.

关键词： Chemical enhanced oil recovery Mechanisms Nanoparticles Polymeric Nanofluids

The Effect of Core Eccentricity on the Structural Behavior of Concrete Tall Buildings

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Civil Engineering and Architecture 2024年第3期18卷 112-117页

作者： tarek Anwar Taha Awida Civil and Architecture Engineering Department College of EngineeringInternational University of Kuwait(IUK)Ardiya Government AreaKuwait

The main purpose of this paper is to investigate the effect of core eccentricity on the structural behavior of concrete tall *** buildings of 55 floors with plan dimensions 48.0×48.0 m2 were *** cases of main core locations are studied:centric(A),eccentric by one sixth(B)and one third(C)of building *** three-dimensional finite element method has been used in conducting structural analysis through ETABS *** and lateral(wind and seismic)loadings are applied to all building *** has been concluded that the core location is the prime parameter governing the structural behavior of tall *** the first two cases(A,B)have acceptable and similar structural behaviors conforming to code limits,in the third case(C),the building behavior came beyond code *** author introduced remedial action by adding two secondary cores in the opposite direction of the main core(C-R)to restore the building behavior to the code *** results of this action were satisfactory.

关键词： Concrete tall buildings core eccentricity structural behavior gravity wind seismic loadings

Synthesized graphene oxide and fumed aerosil 380 dispersion stability and characterization with partially hydrolyzed polyacrylamide

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2021年第6期34卷 307-322页

Hydrolyzed polyacrylamide(HPAM)is a commonly used polymer for the chemicals,mining and refining processes of hydrocarbon but suffers from a persistent high-temperature instability *** contrast,the nanoparticle suspension remains a technical challenge because of the strong interactions of van der Waal forces within nanoparticles,which always encourage *** research sought to improve nanoparticles(NP)stability and polymer(HPAM)rheological properties to improved hydrocarbon recovery by utilizing synthesized graphene oxide(GO)nanosheets and fumed Aerosil 380 Silica oxide(SiO_(2)).The aqueous nanocomposites based on HPAM-GO and HPAM-SiO_(2) in aqueous polymeric solutions have been developed,and its viscoelastic and static behaviour is *** results imply that by adding fumed silica NP,the viscoelastic behaviour of HPAM is marginally improved,particularly in high temperatures and salinity,however,the inclusion of GO's significantly improves the viscosity and stability of the base polymer fluid at high *** Fourier data for the transformation of the infrared spectrum confirmed that the hydrogen bonding formed between HPAM carbonyl groups and silica NP surface silanol functionality and covalent interlinking of electrostatic h-bonding between HPAM and functional GO contributed to the improved stabilization and improved rheological performance that helps to recover high salinity and temperature hydrocarbons.

关键词： Aggregation Composites Chemical enhance oil recovery Hydrocarbons Nanoparticles Polymer

Face Templates Encryption Technique Based on Random Projection and Deep Learning

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第3期44卷 2049-2063页

作者： Mayada tarek Department of Computer Science Mansoura UniversityMansoura35516Egypt Department of Computer Science Jouf UniversityJouf2014KSA

Cancellable biometrics is the solution for the trade-off between two concepts:Biometrics for Security and Security for *** cancelable template is stored in the authentication system’s database rather than the original biometric *** case of the database is compromised,it is easy for the template to be canceled and regenerated from the same biometric *** of the cancelable template comes from the diversity of the cancelable transformation parameters(cancelable key).Therefore,the cancelable key must be secret to be used in the system authentication process as a second authentication factor in con-junction with the biometric *** main contribution of this paper is to tackle the risks of stolen/lost/shared cancelable keys by using biometric trait(in different feature domains)as the only authentication factor,in addition to achieving good performance with high *** standard Generative Adversarial Network(GAN)is proposed as an encryption tool that needs the cancelable key during the training phase,and the testing phase depends only on the biometric ***,random projection transformation is employed to increase the proposed system’s security and *** proposed transformation system is tested using the standard ORL face database,and the experiments are done by applying different features ***,a security analysis for the proposed transformation system is presented.

关键词： Cancelable biometrics(CBs) random projection ORL face database generative adversarial network(GAN)

METHOD OF CENTERS ALGORITHM FORMULTI-OBJECTIVE PROGRAMMING PROBLEMS

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2009年第5期29卷 1128-1142页

作者： tarek Emam Department of Mathematics Faculty of Science (Suez) Suez Canal University Suez Egypt

In this paper, we consider a method of centers for solving multi-objective programming problems, where the objective functions involved are concave functions and the set of feasible points is convex. The algorithm is defined so that the sub-problems that must be solved during its execution may be solved by finite-step procedures. Conditions are given under which the algorithm generates sequences of feasible points and constraint multiplier vectors that have accumulation points satisfying the KKT conditions. Finally, we establish convergence of the proposed method of centers algorithm for solving multiobjective programming problems.

关键词： method of centers multi-objective convergence approximated efficient solution