检索结果-南通市图书馆

Optimal Deep Transfer Learning Model for Histopathological Breast Cancer Classification

Computers, Materials & Continua 2022年第11期73卷 2849-2864页

作者： mahmoud Ragab Alaa F.Nahhas Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah 21589Saudi Arabia Center for Artificial Intelligence in Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Mathematics Department Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Biochemistry Department Faculty of ScienceKing Abdulaziz UniversityJeddah21589Saudi Arabia

Earlier recognition of breast cancer is crucial to decrease the severity and optimize the survival *** of the commonly utilized imaging modalities for breast cancer is histopathological *** manual inspection of histopathological images is a challenging task,automated tools using deep learning(DL)and artificial intelligence(AI)approaches need to be *** latest advances of DL models help in accomplishing maximum image classification performance in several application *** this view,this study develops a Deep Transfer Learning with Rider Optimization Algorithm for Histopathological Classification of Breast Cancer(DTLRO-HCBC)*** proposed DTLRO-HCBC technique aims to categorize the existence of breast cancer using histopathological *** accomplish this,the DTLRO-HCBC technique undergoes pre-processing and data augmentation to increase quantitative ***,optimal SqueezeNet model is employed for feature extractor and the hyperparameter tuning process is carried out using the Adadelta ***,rider optimization with deep feed forward neural network(RO-DFFNN)technique was utilized employed for breast cancer *** RO algorithm is applied for optimally adjusting the weight and bias values of the DFFNN *** demonstrating the greater performance of the DTLRO-HCBC approach,a sequence of simulations were carried out and the outcomes reported its promising performance over the current state of art approaches.

关键词： Breast cancer histopathological images machine learning biomedical analysis deep learning computer vision

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

尼日利亚Gwagwalada原发性开角型青光眼患者的社会人口学和临床特征

引用

国际眼科杂志 2024年第7期24卷 1005-1012页

作者： Abdulkabir Ayansiji Ayanniyi Abdulraheem Olarongbe mahmoud Yetunde Olamide JohnSam Rauf Ibrahim Rauf David Paul Ejeba Rosita Ujunwa Akasike-Enuh Emmanuel Oluwatosin Bisiriyu Margaret Uche Afam-Osemene Eunice Adamma Chijioke Pankyes Amos Damter Nkosi Linus Agwadu 阿布贾大学眼科尼日利亚阿布贾902101 阿布贾教学医院眼科尼日利亚Gwagwalada902101 伊洛林大学眼科尼日利亚伊洛林240003 阿布贾大学统计学教研室尼日利亚阿布贾902101

目的:探讨比较尼日利亚Gwagwalada原发性开角型青光眼(POAG)与非青光眼患者的临床社会人口学特征。方法:横断面对比研究。共调查235例成年患者,其中96例POAG及139例非青光眼。记录患者年龄、性别、教育程度、职业、种族、青光眼家族史... 详细信息

目的:探讨比较尼日利亚Gwagwalada原发性开角型青光眼(POAG)与非青光眼患者的临床社会人口学特征。方法:横断面对比研究。共调查235例成年患者,其中96例POAG及139例非青光眼。记录患者年龄、性别、教育程度、职业、种族、青光眼家族史、眼痒、糖尿病和高血压情况。眼部检查包括视力、中央视野、杯盘比、前房角评估和眼压。结果:平均年龄为49.88±13.75岁,其中男114例(48.5%)。POAG患者包括42个种族,其中伊博人(24/96,25.0%)和约鲁巴人(20/96,20.8%)最为常见。大多数POAG(74/96,77.1%)年龄在40-69岁之间。POAG(73/96,76.0%)有不同程度的视力障碍。POAG组与非青光眼组的对比如下:青光眼阳性家族史(34/96,35.4%)vs(25/139,18.0%;P=0.012);糖尿病史(8/96,8.3%)vs(6/139,4.3%);高血压病史(24/96,25.0%)vs(28/139,20.1%);糖尿病合并高血压病史(1/96,1.0%)vs(4/139,2.9%;P=0.268);使用抗糖尿病药物者(5/96,5.2%)vs(7/139,5.0%);使用降压药者(24/96,25.0%)vs(23/139,16.5%);联合使用抗糖尿病和抗高血压药物者(4/96,4.2%)vs(5/139,3.6%;P=0.328);有眼痒症状者(18/96,18.7%)vs(37/139,26.6%;P=0.328);视力障碍[右眼(RE):51/96,53.1%;左眼(LE):60/96,62.5%]vs(RE:40/139,28.7%;LE:37/139,26.6%;P=0.000);垂直杯盘比>0.4(RE:96/96,100%;LE:96/96,100%)vs(RE:131/139,94.2%;LE:124/139,89.2%)(RE:P=0.307;LE:P=0.006);眼压>22 mmHg(RE:17/96,17.7%;LE:22/96,22.9%)vs(RE:2/139,1.4%;LE:2/139,1.4%;P=0.006)。大多数POAG患者(60/96,62.5%)正在服用抗青光眼药物,(23/96,24.0%)尚未开始用药,P=0.000。许多POAG(32/96,33.3%)正在服用β受体阻滞剂、前列腺素抑制剂和碳酸酐酶抑制剂的联合抗青光眼药物。结论:青光眼具有与其他眼部疾病不同的临床社会人口学特征。许多参与者肯定了青光眼的家族史,大多数青光眼参与者正在接受抗青光眼治疗。包括失明在内的视力障碍与青光眼显著相关。该研究证实,开角型青光眼与高杯盘比和高眼内压有关。

关键词：原发性开角型青光眼尼日利亚青光眼社会人口学

来源：

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

An Intelligent Tree Extractive Text Summarization Deep Learning

引用

Computers, Materials & Continua 2022年第11期73卷 4231-4244页

作者： Abeer Abdulaziz AlArfaj Hanan Ahmed Hosni mahmoud Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

In recent research,deep learning algorithms have presented effective representation learning models for natural *** deep learningbased models create better data representation than classical *** are capable of automated extraction of distributed representation of *** this research,we introduce a new tree Extractive text summarization that is characterized by fitting the text structure representation in knowledge base training module,and also addresses memory issues that were not addresses *** proposed model employs a tree structured mechanism to generate the phrase and text *** proposed architecture mimics the tree configuration of the text-texts and provide better feature *** also incorporates an attention mechanism that offers an additional information source to conduct better summary *** novel model addresses text summarization as a classification process,where the model calculates the probabilities of phrase and text-summary *** model classification is divided into multiple features recognition such as information entropy,significance,redundancy and *** model was assessed on two datasets,on the Multi-Doc Composition Query(MCQ)and Dual Attention Composition dataset(DAC)*** experimental results prove that our proposed model has better summarization precision *** models by a considerable margin.

关键词： Neural network architecture text structure abstractive summarization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chaotic Metaheuristics with Multi-Spiking Neural Network Based Cloud Intrusion Detection

引用

Computers, Materials & Continua 2023年第3期74卷 6101-6118页

作者： Mohammad Yamin Saleh Bajaba Zenah mahmoud AlKubaisy Department of Management Information Systems Faculty of Economics and AdministrationKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Business Administration Faculty of Economics and AdministrationKing Abdulaziz UniversityJeddah21589Saudi Arabia

Cloud Computing(CC)provides data storage options as well as computing services to its users through the *** the other hand,cloud users are concerned about security and privacy issues due to the increased number of *** protection has become an important issue since the users’information gets exposed to third *** networks are exposed to different types of attacks which have extensively grown in addition to the novel intrusion methods and hacking *** Detection Systems(IDSs)can be used in a network to manage suspicious *** IDSs monitor the activities of the CC environment and decide whether an activity is legitimate(normal)or malicious(intrusive)based on the established system’s confidentiality,availability and integrity of the data *** the current study,a Chaotic Metaheuristics with Optimal Multi-Spiking Neural Network-based Intrusion Detection(CMOMSNN-ID)model is proposed to secure the cloud *** presented CMOMSNNID model involves the Chaotic Artificial Bee Colony Optimization-based Feature Selection(CABC-FS)technique to reduce the curse of *** addition,the Multi-Spiking Neural Network(MSNN)classifier is also used based on the simulation of brain *** is applied to resolve pattern classification *** order to fine-tune the parameters relevant to theMSNN model,theWhale Optimization Algorithm(WOA)is employed to boost the classification *** demonstrate the superiority of the proposed CMOMSNN-ID model,a useful set of simulations was *** simulation outcomes inferred that the proposed CMOMSNN-ID model accomplished a superior performance over other models with a maximum accuracy of 99.20%.

关键词： Cloud computing security intrusion detection feature selection multi-spiking neural network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Deep Learning Model for EEG-Based Lie Detection Test Using Spatial and Temporal Aspects

引用

Computers, Materials & Continua 2022年第12期73卷 5655-5669页

Lie detection test is highly significant task due to its impact on criminology and *** lie detection test model using electroencephalogram(EEG)signals is studied in *** this paper we studied deep learning framework in lie detection test ***,we apply a preprocessing technique to utilize only a small fragment of the EEG image instead of the whole *** model describes a temporal feature map of the EEG signals measured during the lie detection test.A deep learning attention model(V-TAM)extracts the temporal map vector during the learning *** technique reduces computational time and lessens the overfitting in Deep Learning *** propose a Cascading attention model with a deep learning convolutional neural network(CNN).V-TAM model extracts local features and global features in separate paths spatial and ***,to enhance the EEG segmentation precision,a novel Visual-Temporal AttentionModel(V-TAM)is *** accuracy was evaluated using data measured from a sensor from a public dataset of 9512 subjects during fifteen minutes lie detection *** compared our model with three recent published *** proposed model attained the highest performance of(98.5%)with(p<0.01).The visual-temporal model of the proposed platform shows an optimized balance between prediction accuracy and time *** investigationwere performed to prove the correctness and reliability of the proposed method through sizing of the input data,proving its effectiveness in attaining satisfactory performance by using only a smaller size input data.

关键词： Lie detection EEG image deep learning machine learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Video Identification Based on Watermarking Schemes and Visual Cryptography

引用

Computer Systems Science & Engineering 2022年第2期40卷 441-453页

作者： Maged Wafy Samr Gamal Zanaty mahmoud Elkhouly Department of Information Technology Computers and Artificial Intelligence Helwan UniversityCairoEgypt Department of Information Technology Computing Studies Arab Open UniversityCairoEgypt Department of Information Technology Information Technology and Computer Science Sinai UniversityIsmailiaEgypt

Related to the growth of data sharing on the Internet and the wide-spread use of digital media,multimedia security and copyright protection have become of broad *** cryptography(VC)is a method of sharing a secret image between a group of participants,where certain groups of participants are defined as qualified and may combine their share of the image to obtain the original,and certain other groups are defined as prohibited,and even if they combine knowledge of their parts,they can’t obtain any information on the secret *** visual cryptography is one of the techniques which used to transmit the secrete image under the cover *** vision systems are connected to visual *** black and white image was originally used as a hidden *** order to achieve the owner’s copy right security based on visual cryptography,a watermarking algorithm is *** suggest an approach in this paper to hide multiple images in video by meaningful shares using one binary *** a common share,which we refer to as a smart key,we can decrypt several images *** on a given share,the smart key decrypts several hidden *** smart key is printed on transparency and the shares are involved in video and decryption is performed by physically superimposing the transparency on the *** binary,grayscale,and color images,we test the proposed method.

关键词： Visual cryptography(VC) video watermarking PSNR

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Torsional Wave in a Dissipative Cylindrical Shell Under Initial Stresses

引用

Computers, Materials & Continua 2022年第2期70卷 3021-3030页

作者： mahmoud M.Selim Khaled A.Gepreel Department of Mathematics-College of Sciences&Humanities in Al Aflaj Prince Sattam bin Abdulaziz UniversityAl-Aflaj11912KSA Department of Mathematics Suez Faculty of ScienceSuez UniversityEgypt Department of Mathematics Faculty of ScienceTaif UniversityTaif21944Saudi Arabia

The dispersion relation of torsional wave in a dissipative,incompressible cylindrical shell of infinite length incorporating initial stresses effects is *** governing equation and closed form solutions are derived with the aid of Biot’s *** velocity and damping of torsional wave are obtained analytically and the influences of dissipation and initial stresses are studied in *** proposed a new method for obtaining the phase and damping velocities of torsional wave in a complex *** results analyzing the torsional wave propagation incorporating initial stress effects are analyzed and presented in *** analytical and numerical solutions reveal that,the dissipation as well as the initial stresses have notable impacts on the phase velocity of torsional wave in a pre-stressed dissipative cylindrical *** numerical results reveal that,the initial stresses and dissipation,considerably,effect the phase velocity of the torsional *** has been observed that,any change in dissipation parameter(δ)produces a substantial change in damping velocity of torsional *** addition,it can be seen that,the phase velocity increases as the initial stress parameter ***,the result of numerical simulation illustrated the influence of dissipation and initial stresses on damping and phase velocities of torsional wave *** conclusion made shown the consistency with the Biot’s incremental deformation theory,and the effective on model such as engineering mechanics and displacement of particles.

关键词： Propagation torsional wave dissipation cylindrical shell initial stress

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Arithmetic Optimization with Deep Learning Enabled Anomaly Detection in Smart City

引用

Computers, Materials & Continua 2022年第10期73卷 381-395页

作者： mahmoud Ragab Maha Farouk S.Sabir Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Centre of Artificial Intelligence for Precision Medicines King Abdulaziz UniversityJeddah21589Saudi Arabia Mathematics Department Faculty of ScienceAl-Azhar UniversityNaser City11884CairoEgypt Information Systems Department Faculty of Computing and Information Technology King Abdulaziz UniversityJeddah21589Saudi Arabia

In recent years,Smart City Infrastructures(SCI)have become familiar whereas intelligent models have been designed to improve the quality of living in smart ***,anomaly detection in SCI has become a hot research topic and is widely explored to enhance the safety of *** increasing popularity of video surveillance system and drastic increase in the amount of collected videos make the conventional physical investigation method to identify abnormal actions,a laborious *** this background,Deep Learning(DL)models can be used in the detection of anomalies found through video surveillance *** current research paper develops an Internet of Things Assisted Deep Learning Enabled Anomaly Detection Technique for Smart City Infrastructures,named(IoTAD-SCI)*** aim of the proposed IoTAD-SCI technique is to mainly identify the existence of anomalies in smart city ***,IoTAD-SCI technique involves Deep Consensus Network(DCN)model design to detect the anomalies in input video *** addition,Arithmetic Optimization Algorithm(AOA)is executed to tune the hyperparameters of the DCN ***,ID3 classifier is also utilized to classify the identified objects in different *** experimental analysis was conducted for the proposed IoTADSCI technique upon benchmark UCSD anomaly detection dataset and the results were inspected under different *** simulation results infer the superiority of the proposed IoTAD-SCI technique under different metrics.

关键词： Object detection anomaly detection smart city infrastructure deep learning parameter tuning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A Dual Attention Encoder-Decoder Text Summarization Model

引用

Computers, Materials & Continua 2023年第2期74卷 3697-3710页

作者： Nada Ali Hakami Hanan Ahmed Hosni mahmoud Jazan University Computer Science DepartmentCollege of Computer Science and Information TechnologyJazanSaudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

A worthy text summarization should represent the fundamental content of the *** studies on computerized text summarization tried to present solutions to this challenging *** models are employed extensively in text summarization *** attention techniques are utilized to acquire the context data in the decoding ***,without real and efficient feature extraction,the produced summary may diverge from the core *** this article,we present an encoder-decoder attention system employing dual attention *** the dual attention mechanism,the attention algorithm gathers main data from the encoder *** the dual attentionmodel,the system can capture and producemore rational main *** merging of the two attention phases produces precise and rational text *** enhanced attention mechanism gives high score to text repetition to increase phrase *** also captures the relationship between phrases and the title giving them higher *** assessed our proposed model with or without significance optimization using ablation *** model with significance optimization achieved the highest performance of 96.7%precision and the least CPU time among other models in both training and sentence extraction.

关键词： Text summarization attention model phrase significance

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Diagenetic signatures in the deltaic and fluvial-estuarine Messinian sandstone reservoirs in the Nile Delta as a tool for high-resolution stratigraphic correlations

引用

International Journal of Sediment Research 2023年第5期38卷 754-768页

作者： mahmoud Leila Andrea Moscariello Dustin Sweet Branimir ?egvi? Geology Department Faculty of Science Mansoura University Department of Earth Sciences University of Geneva Department of Geosciences Texas Tech University

The current study utilizes a range of diagenetic fingerprints to differentiate between sandstone facies deposited in the Nile Delta before and during the Messinian salinity crisis(MSC), which is normally a challenging task considering the complex bio-and lithostratigraphic subdivisions of Messinian rock units. Subaerial exposure of the pre-MSC(Qawasim deltaic sandstone), during drawdown of the Mediterranean Sea at the time of the MSC, triggered pervasive dissolution of unstable rock fragments, kaolinization of feldspar, and meteoric dolomitization of carbonate. This was followed by mesogenetic calcite cementation and kaolinite transformation into dickite in deeply buried Qawasim sandstone. Comparatively, the Abu Madi estuarine facies, deposited during transgression after drawdown related to the MSC,is characterized by eogenetic iron(Fe)-calcite, glauconite, and pyrite(averages of 14.5%, 6%, and 2%,respectively). This facies transition is marked by abundance of mature glauconite(with potassium oxide(K2O) at about 8%) whose content abates upward from the transgression surface. Moreover, the compositional variability of the Abu Madi sandstone gave rise to multiple diagenetic trajectories that resulted in chlorite formation presumably following smectite and kaolinite. Listed diagenetic variations in the studied Messinian sandstone resulted from a complex interplay between rocks’ compositional,depositional, and burial attributes, ultimately serving as a basis for high-resolution stratigraphic correlation in continental and marginal marine settings with poor biostratigraphic controls.

关键词： Messinian Nile Delta Diagenesis Deltaic sedimentation Fluvial-estuarine Stratigraphic correlation

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：