检索结果-南通市图书馆

Challenge-Response Emotion Authentication Algorithm Using Modified Horizontal Deep Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent Automation & Soft Computing 2023年第3期35卷 3659-3675页

作者： mohamed Ezz ayman mohamed mostafa ayman Elshenawy College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Systems and Computers Engineering DEPT Faculty of EngineeringAl-Azhar UniversityCairo11651Egypt Software Engineering&Information Technology Faculty of Engineering&TechnologyEgyptian Chinese UniversityEgypt

Face authentication is an important biometric authentication method commonly used in security *** is vulnerable to different types of attacks that use authorized users’facial images and videos captured from social media to perform spooﬁng attacks and dynamic movements for penetrating secur-ity *** paper presents an innovative challenge-response emotions authentication model based on the horizontal ensemble *** proposed model provides high accurate face authentication process by challenging the authorized user using a random sequence of emotions to provide a speciﬁc response for every authentication trial with a different sequence of *** proposed model is applied to the KDEF dataset using 10-fold *** improvements are made to the proposed ***,the VGG16 model is applied to the seven common ***,the system usability is enhanced by analyzing and selecting only the four common and easy-to-use ***,the horizontal ensemble technique is applied to enhance the emotion recognition accuracy and minimize the error during authen-tication ***,the Horizontal Ensemble Best N-Losses(HEBNL)is applied using challenge-response emotion to improve the authentication efﬁ-ciency and minimize the computational *** successive improvements implemented on the proposed model led to an improvement in the accuracy from 92.1%to 99.27%.

关键词： Face authentication challenge-response authentication transfer learning and horizontal ensemble technique

Advanced Authentication Mechanisms for Identity and Access Management inCloud Computing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2022年第12期43卷 967-984页

作者： Amjad Alsirhani mohamed Ezz ayman mohamed mostafa College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia

Identity management is based on the creation and management of useridentities for granting access to the cloud resources based on the user *** cloud identity and access management (IAM) grants the authorization tothe end-users to perform different actions on the specified cloud resources. Theauthorizations in the IAM are grouped into roles instead of granting them directlyto the end-users. Due to the multiplicity of cloud locations where data resides anddue to the lack of a centralized user authority for granting or denying cloud userrequests, there must be several security strategies and models to overcome theseissues. Another major concern in IAM services is the excessive or the lack ofaccess level to different users with previously granted authorizations. This paperproposes a comprehensive review of security services and threats. Based on thepresented services and threats, advanced frameworks for IAM that provideauthentication mechanisms in public and private cloud platforms. A threat modelhas been applied to validate the proposed authentication frameworks with different security threats. The proposed models proved high efficiency in protectingcloud platforms from insider attacks, single sign-on failure, brute force attacks,denial of service, user privacy threats, and data privacy threats.

关键词： Identity management cloud computing security threats and authentication mechanisms

A Multi-Factor Authentication-Based Framework for Identity Management in Cloud Applications

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5期71卷 3193-3209页

作者： Wael Said Elsayed mostafa M.M.Hassan ayman mohamed mostafa Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia

User’s data is considered as a vital asset of several *** data to the cloud computing is not an easy decision for any organization due to the privacy and security *** providers must ensure that both data and applications that will be stored on the cloud should be protected in a secure *** data stored on the public cloud will be vulnerable to outside and inside *** paper provides interactive multi-layer authentication frameworks for securing user identities on the *** access control policies are applied for verifying users on the cloud.A security mechanism is applied to the cloud application that includes user registration,granting user privileges,and generating user authentication *** intrusion detection system is embedded to the security mechanism to detect malicious *** multi factor authentication,intrusion detection,and access control techniques can be used for ensuring the identity of the ***,encryption techniques are used for protecting the data from being *** results are carried out to verify the accuracy and efficiency of the proposed frameworks and *** results recorded high detection rate with low false positive alarms.

关键词： Cloud computing service providers multi-layer authentication frameworks and access control

Prediction of COVID-19 Transmission in the United States Using Google Search Trends

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4期71卷 1751-1768页

作者： Meshrif Alruily mohamed Ezz ayman mohamed mostafa Nacim Yanes mostafa Abbas Yasser El-Manzalawy College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Faculty of Engineering Al-Azhar UniversityCairo11651Egypt Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt RIADI Laboratory La Manouba UniversityManouba2010Tunisia Department of Translational Data Science and Informatics GeisingerDanvillePA17822USA

Accurate forecasting of emerging infectious diseases can guide public health officials in making appropriate decisions related to the allocation of public health *** to the exponential spread of the COVID-19 infection worldwide,several computational models for forecasting the transmission and mortality rates of COVID-19 have been proposed in the *** accelerate scientific and public health insights into the spread and impact of COVID-19,Google released the Google COVID-19 search trends symptoms open-access *** objective is to develop 7 and 14-day-ahead forecasting models of COVID-19 transmission and mortality in the US using the Google search trends for COVID-19 related ***,we propose a stacked long short-term memory(SLSTM)architecture for predicting COVID-19 confirmed and death cases using historical time series data combined with auxiliary time series data from the Google COVID-19 search trends symptoms *** the SLSTM networks trained using historical data only as the base models,our base models for 7 and 14-day-ahead forecasting of COVID cases had the mean absolute percentage error(MAPE)values of 6.6%and 8.8%,*** the other side,our proposed models had improved MAPE values of 3.2%and 5.6%,*** 7 and 14-day-ahead forecasting of COVID-19 deaths,the MAPE values of the base models were 4.8%and 11.4%,while the improved MAPE values of our proposed models were 4.7%and 7.8%,*** found that the Google search trends for“pneumonia,”“shortness of breath,”and“fever”are the most informative search trends for predicting COVID-19 *** also found that the search trends for“hypoxia”and“fever”were the most informative trends for forecasting COVID-19 mortality.

关键词： Forecasting COVID-19 transmission and mortality in the US stacked LSTM SARS-COV-2 and google COVID-19 search trends

An E-Business Event Stream Mechanism for Improving User Tracing Processes

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 2021年第10期69卷 767-784页

作者： ayman mohamed mostafa Saleh N.Almuayqil Wael Said College of Computers and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt College of Computer Science and Engineering Taibah UniversityMedina42353Saudi Arabia

With the rapid development in business transactions,especially in recent years,it has become necessary to develop different mechanisms to trace business user records in web server log in an efficient *** business transactions have increased,especially when the user or customer cannot obtain the required *** example,with the spread of the epidemic Coronavirus(COVID-19)throughout the world,there is a dire need to rely more on online business *** order to improve the efficiency and performance of E-business structure,a web server log must be well utilized to have the ability to trace and record infinite user *** paper proposes an event stream mechanism based on formula patterns to enhance business processes and record all user activities in a structured log *** user activity is recorded with a set of tracing parameters that can predict the behavior of the user in business *** experimental results are conducted by applying clustering-based classification algorithms on two different datasets;namely,Online Shoppers Purchasing Intention and Instacart Market Basket *** clustering process is used to group related objects into the same cluster,then the classification process measures the predicted classes of clustered *** experimental results record provable accuracy in predicting user preferences on both datasets.

关键词： Business transactions event stream log file tracing parameters clustering-based classification

Digital Watermarking Scheme for Securing Textual Database Using Histogram Shifting Model

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6期71卷 5253-5270页

作者： Khalid A.El Drandaly Walid Khedr Islam S.mohamed ayman mohamed mostafa Faculty of Computers and Informatics Zagazig UniversityZagazig44519Egypt College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia

Information security is one of the most important methods of protecting the confidentiality and privacy of internet *** greater the volume of data,the more the need to increase the security methods for protecting data from *** task can be challenging for researchers in terms of managing enormous data and maintaining their safety and *** of digital content is a major issue in maintaining the privacy and secrecy of *** this end,digital watermarking is based on the concept of information security through the insertion and detection of an embedded watermark in an efficient *** methodologies in the research on digital watermarking result in data distortion after embedding the *** scenario can reduce the efficiency of detecting watermarks as well as violate data *** study adapts a robust reversible histogram shifting(HS)technique for textual data in relational ***,the study presents a digital watermarking scheme intended for document copyright protection and proof of *** major advantage of the proposed watermarking scheme is that it can protect digital data and preserve data *** the best of our knowledge,this research methodology is promising for use in the HS expansion model for watermarking data on nonnumeric *** addition,the results showed that despite exposing the database to an insertion attacks at 50%and 75%of the watermark,the proposed algorithm can recovermore than half of the embedded watermark in all addition and alteration attacks *** a result,the watermark information can be retained and restored completely.

关键词： Information security digital watermarking information hiding histogram shifting technique

Innovative Hetero-Associative Memory Encoder(HAMTE)for Palmprint Template Protection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第7期46卷 619-636页

作者： Eslam Hamouda mohamed Ezz ayman mohamed mostafa Murtada K.Elbashir Meshrif Alruily Mayada Tarek College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia College of Computers and Informatics Mansoura University35516Egypt

Many types of research focus on utilizing Palmprint recognition in user identification and *** Palmprint is one of biometric authentication(something you are)invariable during a person’s life and needs careful protection during enrollment into different biometric authentication *** and irreversibility are critical requirements for securing the Palmprint template during enrollment and *** paper proposes an innovative HAMTE neural network model that contains Hetero-Associative Memory for Palmprint template translation and projection using matrix multiplication and dot product multiplication.A HAMTE-Siamese network is constructed,which accepts two Palmprint templates and predicts whether these two templates belong to the same user or different *** HAMTE is generated for each user during the enrollment phase,which is responsible for generating a secure template for the enrolled *** proposed network secures the person’s Palmprint template by translating it into an irreversible template(different features space).It can be stored safely in a trusted/untrusted third-party authentication system that protects the original person’s template from being *** results are conducted on the CASIA database,where the proposed network achieved accuracy close to the original accuracy for the unprotected Palmprint *** recognition accuracy deviated by around 3%,and the equal error rate(EER)by approximately 0.02 compared to the original data,with appropriate performance(approximately 13 ms)while preserving the irreversibility property of the secure ***,the brute-force attack has been analyzed under the new Palmprint protection scheme.

关键词： Palmprint recognition hetero-associative memory neural network and Siamese network

Improved Siamese Palmprint Authentication Using Pre-Trained VGG16-Palmprint and Element-Wise Absolute Difference

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第8期46卷 2299-2317页

作者： mohamed Ezz Waad Alanazi ayman mohamed mostafa Eslam Hamouda Murtada K.Elbashir Meshrif Alruily College of Computers and Information Sciences Jouf UniversitySakaka72314Saudi Arabia

Palmprint identification has been conducted over the last two decades in many biometric ***-dimensional data with many uncorrelated and duplicated features remains difficult due to several computational complexity *** paper presents an interactive authentication approach based on deep learning and feature selection that supports Palmprint *** proposed model has two stages of learning;the first stage is to transfer pre-trained VGG-16 of ImageNet to specific features based on the extraction *** second stage involves the VGG-16 Palmprint feature extraction in the Siamese network to learn Palmprint *** proposed model achieves robust and reliable end-to-end Palmprint authentication by extracting the convolutional features using VGG-16 Palmprint and the similarity of two input Palmprint using the Siamese *** second stage uses the CASIA dataset to train and test the Siamese *** suggested model outperforms comparable studies based on the deep learning approach achieving accuracy and EER of 91.8%and 0.082%,respectively,on the CASIA left-hand images and accuracy and EER of 91.7%and 0.084,respectively,on the CASIA right-hand images.

关键词： Palmprint authentication transfer learning feature extraction classification VGG-16 and Siamese network

A Transfer Learning Approach Based on Ultrasound Images for Liver Cancer Detection

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 2023年第6期75卷 5105-5121页

作者： Murtada K.Elbashir Alshimaa Mahmoud ayman mohamed mostafa Eslam Hamouda Meshrif Alruily Sadeem M.Alotaibi Hosameldeen Shabana mohamed Ezz College of Computer and Information Sciences Jouf UniversitySakaka72314Saudi Arabia Department of Information Systems MCI AcademyCairoEgypt College of Medicine Shaqra UniversityShaqraKSA Faculty of Medicine Al Azhar UniversityCairoEgypt

The convolutional neural network(CNN)is one of the main algorithms that is applied to deep transfer learning for classifying two essential types of liver lesions;Hemangioma and hepatocellular carcinoma(HCC).Ultrasound images,which are commonly available and have low cost and low risk compared to computerized tomography(CT)scan images,will be used as input for the model.A total of 350 ultrasound images belonging to 59 patients are *** number of images with HCC is 202 and 148,*** images were collected from ultrasound ***(28 Hemangiomas patients and 11 HCC patients),the department of radiology,the University of Washington(7 HCC patients),the Atlas of ultrasound Germany(3 HCC patients),and Radiopedia and others(10 HCC patients).The ultrasound images are divided into 225,52,and 73 for training,validation,and testing.A data augmentation technique is used to enhance the validation *** proposed an approach based on ensembles of the best-selected deep transfer models from the on-the-shelf models:VGG16,VGG19,DenseNet,Inception,InceptionResNet,ResNet,and *** tuning both the feature extraction and the classification layers,the best models are *** accuracy is used for model tuning and *** accuracy,sensitivity,specificity and AUROC are used to evaluate the *** experiments are concluded in five *** first stage aims to evaluate the base model performance by training the on-the-shelf *** best accu-racy obtained in the first stage is 83.5%.In the second stage,we augmented the data and retrained the on-the-shelf models with the augmented *** best accuracy we obtained in the second stage was 86.3%.In the third stage,we tuned the feature extraction layers of the on-the-shelf *** best accuracy obtained in the third stage is 89%.In the fourth stage,we fine-tuned the classification layer and obtained an accuracy of 93%as the best *** the fifth stage,we applied the en

关键词： Transfer learning liver lesions ultrasound images and convolutional neural network