检索结果-南通市图书馆

An Improved Deep Learning Framework for Automated Optic Disc Localization and Glaucoma Detection

Computer Modeling in Engineering & Sciences 2024年第8期140卷 1429-1457页

作者： Hela Elmannai Monia Hamdi Souham Meshoul Amel Ali Alhussan Manel Ayadi Amel Ksibi Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information System College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia

Glaucoma disease causes irreversible damage to the optical nerve and it has the potential to cause permanent loss of *** ranks as the second most prevalent cause of permanent *** glaucoma diagnosis requires a highly experienced specialist,costly equipment,and a lengthy wait *** automatic glaucoma detection,state-of-the-art glaucoma detection methods include a segmentation-based method to calculate the cup-to-disc *** methods include multi-label segmentation networks and learning-based methods and rely on hand-crafted *** the optic disc(OD)is one of the key features in retinal images for detecting retinal diseases,especially for glaucoma disease *** approach presented in this study is based on deep classifiers for OD segmentation and glaucoma ***,the optic disc detection process is based on object detection using a Mask Region-Based Convolutional Neural Network(Mask-RCNN).The OD detection task was validated using the Dice score,intersection over union,and accuracy *** OD region is then fed into the second stage for glaucoma ***,considering only the OD area for glaucoma detection will reduce the number of classification artifacts by limiting the assessment to the optic disc *** this task,VGG-16(Visual Geometry Group),Resnet-18(Residual Network),and Inception-v3 were pre-trained and *** also used the Support Vector Machine *** feature-based method uses region content features obtained by Histogram of Oriented Gradients(HOG)and Gabor *** final decision is based on weighted fusion.A comparison of the obtained results from all classification approaches is *** metrics including accuracy and ROC curve are compared for each classification *** novelty of this research project is the integration of automatic OD detection and glaucoma diagnosis in a global ***,the fusion-based decision system uses the g

关键词： Optic disc glaucoma fundus image deep 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

Enhancing Healthcare Data Security and Disease Detection Using Crossover-Based Multilayer Perceptron in Smart Healthcare Systems

引用

Computer Modeling in Engineering & Sciences 2024年第4期139卷 977-997页

作者： Mustufa Haider Abidi Hisham Alkhalefah Mohamed K.Aboudaif Department of Industrial Engineering College of EngineeringKing Saud UniversityP.O.Box-800Riyadh11421Saudi Arabia

The healthcare data requires accurate disease detection analysis,real-timemonitoring,and advancements to ensure proper treatment for ***,Machine Learning methods are widely utilized in Smart Healthcare Systems(SHS)to extract valuable features fromheterogeneous and high-dimensional healthcare data for predicting various diseases and monitoring patient *** methods are employed across different domains that are susceptible to adversarial attacks,necessitating careful ***,this paper proposes a crossover-based Multilayer Perceptron(CMLP)*** collected samples are pre-processed and fed into the crossover-based multilayer perceptron neural network to detect adversarial attacks on themedical records of *** an attack is detected,healthcare professionals are promptly alerted to prevent data *** paper utilizes two datasets,namely the synthetic dataset and the University of Queensland Vital Signs(UQVS)dataset,from which numerous samples are *** results are conducted to evaluate the performance of the proposed CMLP model,utilizing various performancemeasures such as Recall,Precision,Accuracy,and F1-score to predict patient *** the proposed method with existing approaches,it achieves the highest accuracy,precision,recall,and ***,the proposedmethod achieves a precision of 93%,an accuracy of 97%,an F1-score of 92%,and a recall of 92%.

关键词： Smart healthcare systems multilayer perceptron cybersecurity adversarial attack detection Healthcare 4.0

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

Formation of Natural Melanin/TiO_(2) Nanostructure Hybrids with Enhanced Optical,Thermal and Magnetic Properties as a Soft Material

引用

Journal of Wuhan University of Technology(Materials Science) 2024年第3期39卷 613-620页

作者： Saja Algessair Nawal Madkhali Department of Physics College of ScienceImam Mohammad Ibn Saud Islamic University(IMSIU)P.O.Box 5701Riyadh 11432Saudi Arabia

The natural Melanin/TiO_(2) was synthesized by the use of ultrasonication under UV *** influence of natural melanin on the structural,optical and thermal properties of TiO_(2) nanoparticles was investigated by using Fourier transform infrared spectroscopy,thermogravimetric analysis and UV-Vis *** was observed that incorporating natural melanin on TiO_(2) nanoparticles(TiO_(2)-Mel)occurred at 2.01 eV with a low value of Urbach energy around 100 meV indicating improvement in the crystalline *** measurement at room temperature showed diamagnetic ***,thermal results showed that TiO_(2)-Mel is stable even at temperatures up to 400℃.According to the results obtained by the thermal stability of melanin with titanium dioxide,it can be a good candidate in many applications such as solar cells and optoelectronics.

关键词： natural melanin/TiO_(2) thermal stability optoelectronic nanostructure UV radiation

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

Disentangling the effects of management and climate change on habitat suitability for saproxylic species in boreal forests

引用

Journal of Forestry Research 2024年第2期35卷 121-133页

作者： Ellinoora Ekman María Triviño Clemens Blattert Adriano Mazziotta Maria Potterf Kyle Eyvindson Department of Biological and Environmental Science University of JyvaskylaP.O.Box 3540014 JyvaskylaFinland Institute for Atmospheric and Earth System Research(INAR)/Physics Faculty of ScienceUniversity of HelsinkiP.O.Box 6800014 HelsinkiFinland School of Resource Wisdom University of JyvaskylaP.O.Box 3540014 JyvaskylaFinland Natural Resources Institute Finland(LUKE) Latokartanonkaari 900790 HelsinkiFinland Ecosystem Dynamics and Forest Management Group Technical University of MunichHans‑Carl‑Von‑Carlowitz‑Platz 285354 FreisingGermany Faculty of Environmental Sciences and Natural Resource Management Norwegian University of Life SciencesP.O.Box 50031433ÅsNorway

Forest degradation induced by intensive forest management and temperature increase by climate change are resulting in biodiversity decline in boreal *** forest management and high-end climate emission scenarios can further reduce the amount and diversity of deadwood,the limiting factor for habitats for saproxylic species in European boreal *** magnitude of their combined effects and how changes in forest management can affect deadwood diversity under a range of climate change scenarios are poorly *** used forest growth simulations to evaluate how forest management and climate change will individually and jointly affect habitats of red-listed saproxylic species in *** simulated seven forest management regimes and three climate scenarios(reference,RCP4.5 and RCP8.5)over 100 *** regimes included set aside,continuous cover forestry,business-as-usual(BAU)and four modifications of *** suitability was assessed using a speciesspecific habitat suitability index,including 21 fungal and invertebrate species groups.“Winner”and“loser”species were identified based on the modelled impacts of forest management and climate change on their habitat *** found that forest management had a major impact on habitat suitability of saproxylic species compared to climate *** suitability index varied by over 250%among management regimes,while overall change in habitat suitability index caused by climate change was on average only 2%.More species groups were identified as winners than losers from impacts of climate change(52%–95%were winners,depending on the climate change scenario and management regime).The largest increase in habitat suitability index was achieved under set aside(254%)and the climate scenario RCP8.5(>2%),while continuous cover forestry was the most suitable regime to increase habitat suitability of saproxylic species(up to+11%)across all climate change *** results show that close-to-na

关键词： Biodiversity Simulations Finland Forest planning Habitat suitability Deadwood

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

Revealing Al-O/Al-F reaction dynamic effects on the combustion of aluminum nanoparticles in oxygen/fluorine containing environments:A reactive molecular dynamics study meshing together experimental validation

引用

Defence Technology（防务技术） 2024年第4期34卷 313-327页

作者： Gang Li Chuande Zhao Qian Yu Fang Yang Jie Chen Institute of Chemical Materials China Academy of Engineering Physics(CAEP)P.O.Box 919-311Mianyang 621900SichuanChina

Improving the energy conversion efficiency in metallic fuel(e.g.,Al)combustion is always desirable but challenging,which often involves redox reactions of aluminum(Al)with various mixed oxidizing *** instance,Al-O reaction is the most common pathway to release limited energy while Al-F reaction has received much attentions to enhance Al combustion ***,microscopic understanding of the Al-O/Al-F reaction dynamics remains unsolved,which is fundamentally necessary to further improve Al combustion *** this work,for the first time,Al-O/Al-F reaction dynamic effects on the combustion of aluminum nanoparticles(n-Al)in oxygen/fluorine containing environments have been revealed via reactive molecular dynamics(RMD)simulations meshing together combustion *** RMD simulation systems of Al core/O_(2)/HF,n-Al/O_(2)/HF,and n-Al/O_(2)/CF4 with oxygen percentage ranging from 0%to 100%have been *** n-Al combustion in mixed O_(2)/CF_4 environments have been conducted by constant volume combustion *** results show that Al-O reaction exhibits kinetic benefits while Al-F reaction owns thermodynamic benefits for n-Al *** n-Al/O_(2)/HF,Al-O reaction gives faster energy release rate than Al-F reaction(1.1 times).The optimal energy release efficiency can be achieved with suitable oxygen percentage of 10%and 50%for n-Al/O_(2)/HF and n-Al/O_(2)/CF_4,*** combustion experiments,90%of oxygen percentage can optimally enhance the peak pressure,pressurization rate and combustion ***,Al-O reaction prefers to occur on the surface regions while Al-F reaction prefers to proceed in the interior regions of n-Al,confirming the kinetic/thermodynamic benefits of Al-O/Al-F *** synergistic effect of Al-O/Al-F reaction for greatly enhancing n-Al combustion efficiency is demonstrated at atomicscale,which is beneficial for optimizing the combustion performance of metallic fuel.

关键词： Al-O/Al—F reaction Kinetic benefits Thermodynamic benefits Molecular dynamics Combustion

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

A new fractional order 6D chaotic model:Study of model dynamics,system structure graph,electronic circuit realization and fractional control

引用

Journal of Ocean Engineering and Science 2024年第2期9卷 112-125页

作者： M.Higazy Norah Almalki Shabbir Muhammad A.Al-Ghamdi Department of Mathematics and Statistics College of ScienceTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Physics and Engineering Mathematics Faculty of Electronic EngineeringMenoufia UniversityMenouf 32952Egypt Research Center for Advanced Materials Science(RCAMS) King Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Department of Chemistry College of ScienceKing Khalid UniversityP.O.Box 9004Abha 61413Saudi Arabia Department of Physics Faculty of ScienceKing Abdulaziz UniversityP.O.Box 80203Jeddah 21589Saudi Arabia

A new fractional 6D chaotic model is constructed in this *** new fractional 6D chaotic model has six positive parameters plus the fractional order with eight nonlinear *** complicated chaotic dy-namics of the new fractional 6D model is presented and *** basic properties of this model are studied and its chaotic attractors,dissipative feature,symmetry,equilibrium points,Lyapunov Exponents are *** new dynamics of the 6D fractional model is numerically simulated using Matlab *** addition,utilizing the graph theory tools certain structural characteristics are *** electrical circuit is built to implement the new 5.4 fractional order 6D ***,an active fractional order controller is proposed to control the new model at different fractional *** chaos of the new model is very useful and can be used to produce random keys for data encryption.

关键词： Chaotic systems Fractional calculus Lyapunov exponents Chaotic attractors Adjacency matrix Hermitian matrix Electronic circuit realization

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

Enhancing Cancer Classification through a Hybrid Bio-Inspired Evolutionary Algorithm for Biomarker Gene Selection

引用

Computers, Materials & Continua 2024年第4期79卷 675-694页

作者： Hala AlShamlan Halah AlMazrua Department of Information Technology College of Computer and Information SciencesKing Saud UniversityP.O.Box 145111Riyadh4545Saudi Arabia

In this study,our aim is to address the problem of gene selection by proposing a hybrid bio-inspired evolutionary algorithm that combines Grey Wolf Optimization(GWO)with Harris Hawks Optimization(HHO)for feature *** for utilizingGWOandHHOstems fromtheir bio-inspired nature and their demonstrated success in optimization *** aimto leverage the strengths of these algorithms to enhance the effectiveness of feature selection in microarray-based cancer *** selected leave-one-out cross-validation(LOOCV)to evaluate the performance of both two widely used classifiers,k-nearest neighbors(KNN)and support vector machine(SVM),on high-dimensional cancer microarray *** proposed method is extensively tested on six publicly available cancer microarray datasets,and a comprehensive comparison with recently published methods is *** hybrid algorithm demonstrates its effectiveness in improving classification performance,Surpassing alternative approaches in terms of *** outcomes confirm the capability of our method to substantially improve both the precision and efficiency of cancer classification,thereby advancing the development ofmore efficient treatment *** proposed hybridmethod offers a promising solution to the gene selection problem in microarray-based cancer *** improves the accuracy and efficiency of cancer diagnosis and treatment,and its superior performance compared to other methods highlights its potential applicability in realworld cancer classification *** harnessing the complementary search mechanisms of GWO and HHO,we leverage their bio-inspired behavior to identify informative genes relevant to cancer diagnosis and treatment.

关键词： Bio-inspired algorithms bioinformatics cancer classification evolutionary algorithm feature selection gene expression grey wolf optimizer harris hawks optimization k-nearest neighbor support vector machine

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

Intelligent Machine Learning Based Brain Tumor Segmentation through Multi-Layer Hybrid U-Net with CNN Feature Integration

引用

Computers, Materials & Continua 2024年第4期79卷 1301-1317页

作者： Sharaf J.Malebary Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz UniversityP.O.Box 344Rabigh21911Saudia Arabia

Brain tumors are a pressing public health concern, characterized by their high mortality and morbidity ***, the manual segmentation of brain tumors remains a laborious and error-prone task, necessitatingthe development of more precise and efficient methodologies. To address this formidable challenge, we proposean advanced approach for segmenting brain tumorMagnetic Resonance Imaging (MRI) images that harnesses theformidable capabilities of deep learning and convolutional neural networks (CNNs). While CNN-based methodshave displayed promise in the realm of brain tumor segmentation, the intricate nature of these tumors, markedby irregular shapes, varying sizes, uneven distribution, and limited available data, poses substantial obstacles toachieving accurate semantic segmentation. In our study, we introduce a pioneering Hybrid U-Net framework thatseamlessly integrates the U-Net and CNN architectures to surmount these challenges. Our proposed approachencompasses preprocessing steps that enhance image visualization, a customized layered U-Net model tailoredfor precise segmentation, and the inclusion of dropout layers to mitigate overfitting during the training ***, we leverage the CNN mechanism to exploit contextual information within brain tumorMRI images,resulting in a substantial enhancement in segmentation *** experimental results attest to the exceptionalperformance of our framework, with accuracy rates surpassing 97% across diverse datasets, showcasing therobustness and effectiveness of our approach. Furthermore, we conduct a comprehensive assessment of ourmethod’s capabilities by evaluating various performance measures, including the sensitivity, Jaccard-index, andspecificity. Our proposed model achieved 99% accuracy. The implications of our findings are profound. Theproposed Hybrid U-Net model emerges as a highly promising diagnostic tool, poised to revolutionize brain tumorimage segmentation for radiologists and clinician

关键词： Brain tumor Hybrid U-Net CLAHE transfer learning MRI images

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

DFT investigation of half-metallic ferromagnetic rare earth based spinels MgHo_(2)Z_(4)(Z=S,Se)

引用

Journal of Rare Earths 2024年第1期42卷 121-128,I0005页

作者： Maiza Zanib Mumtaz Manzoor N.A.Noor M.Waqas Iqbal Mazia Asghar H.H.Hegazy A.Laref Department of Physics Riphah International UniversityLahore CampusPakistan Research Centre for Advanced Materials Science King Khalid UniversityP.O.Box 9004AbhaSaudi Arabia Department of Physics Faculty of ScienceKing Khalid UniversityP.O.Box 9004AbhaSaudi Arabia Department of Physics and Astronomy College of ScienceKing Saud UniversityRiyadh11451Saudi Arabia

Half-metallic ferromagnetism,mechanical as well as thermoelectric properties for rare earth-based spinels MgHo_(2)Z_(4)(Z=S,Se)were investigated using density functional theory(DFT).Structural optimization was done with Perdew-Burke-Ehrenzorf(PBE)sol-generalized gradient approximation(GGA)to calculate the lattice constant of both spinels comparable to experimental *** addition,Born stability criteria and negative formation energy show that our studied spinels are also structurally and dynamically stable in the cubic *** ferromagnetic(FM)state stability,we also calculated the energy differences among FM,antiferromagnetic(AFM),and non-magnetic(NM)***,Curie temperatures of ferromagnetic phases were also *** used Trans-Blaha improved BeckeJohnson(TB-mBJ)potential functional for electronics as well as magnetic characteristics,which lead to the consistent explanation of half-metallic ferromagnetism,representing the whole band-occupancy in material with exact detail of density of states(DOS).The stable FM state was examined in spinels due to the exchange splitting of Ho cation consisting of p-d hybridizations compatible with the result achieved for electronics band structure and ***,spin magnetic moment was explained in terms of anion,cation,and sharing charge on studied *** addition,the calculated thermoelectric properties clearly show that operation range of these systems may be utilized by future experimental works for identifying the potential applications of these systems.

关键词： Ho-based spinels DFT simulations Mechanical parameters Electronic properties HM ferromagnetism Figure of merit

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

Assessment of compressive strength of jet grouting by machine learning

引用

Journal of Rock Mechanics and Geotechnical Engineering 2024年第1期16卷 102-111页

作者： Esteban Diaz Edgar Leonardo Salamanca-Medina Roberto Tomas Departamento de Ingeniería Civil Escuela Politécnica SuperiorUniversidad de AlicanteP.O.Box 99E-03080AlicanteSpain

Jet grouting is one of the most popular soil improvement techniques,but its design usually involves great uncertainties that can lead to economic cost overruns in construction *** high dispersion in the properties of the improved material leads to designers assuming a conservative,arbitrary and unjustified strength,which is even sometimes subjected to the results of the test *** present paper presents an approach for prediction of the uniaxial compressive strength(UCS)of jet grouting columns based on the analysis of several machine learning algorithms on a database of 854 results mainly collected from different research *** selected machine learning model(extremely randomized trees)relates the soil type and various parameters of the technique to the value of the compressive *** the complex mechanism that surrounds the jet grouting process,evidenced by the high dispersion and low correlation of the variables studied,the trained model allows to optimally predict the values of compressive strength with a significant improvement with respect to the existing ***,this work proposes for the first time a reliable and easily applicable approach for estimation of the compressive strength of jet grouting columns.

关键词： Jet grouting Ground improvement Compressive strength 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

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：