检索结果-南通市图书馆

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

Plant Phenomics 2023年第2期5卷 139-148页

作者： Lei Zhou Qinlin Xiao Mohanmed Farag taha Chengjia Xu Chu Zhang College of Mechanical and electronic engineering Nanjing Forestry UniversityNanjingChina College of Biosystems engineering and Food Science Zhejiang UniversityZhejiangChina Department of Soil and Water Sciences Faculty of Environmental Agricultural SciencesArish UniversityNorth Sinai45516Egypt School of Information engineering Huzhou UniversityHuzhouChina

Deep learning and computer vision have become emerging tools for diseased plant *** previous studies focused on image-level disease *** this paper,pixel-level phenotypic feature(the distribution of spot)was analyzed by deep ***,a diseased leaf dataset was collected and the corresponding pixel-level annotation was contributed.A dataset of apple leaves samples was used for training and *** set of grape and strawberry leaf samples was used as an extra testing ***,supervised convolutional neural networks were adopted for semantic ***,the possibility of weakly supervised models for disease spot segmentation was also ***-CAM combined with ResNet-50(ResNet-CAM),and that combined with a few-shot pretrained U-Net classifier for weakly supervised leaf spot segmentation(WSLSS),was *** were trained using image-level annotations(healthy versus diseased)to reduce the cost of annotation *** showed that the supervised DeepLab achieved the best performance(IoU=0.829)on the apple leaf *** weakly supervised WSLSS achieved an IoU of *** processing the extra testing dataset,WSLSS realized the best IoU of 0.511,which was even higher than fully supervised DeepLab(IoU=0.458).Although there was a certain gap in IoU between the supervised models and weakly supervised ones,WSLSS showed stronger generalization ability than supervised models when processing the disease types not involved in the training ***,the contributed dataset in this paper could help researchers get a quick start on designing their new segmentation methods in future studies.

关键词： Deep computer weakly

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

effect of Diabetes Self-Management education on Glycaemic Control in Sudanese Adults with Type 2 Diabetes

引用

Journal of Biosciences and Medicines 2024年第3期12卷 316-327页

作者： Sahar Moawia Balla elnour Tayseer Abdelmotalib Ahmed taha Haiam Abdalla Wadatalla Ziryab Zainelabdin Mohamed elmahdi Marwah Isam Abdulmajeed Mohammedahmed Rowa Abdelmonem Sidig Hamadto Nahla Yousif Osman Mohammed Saeed Omnia Mubarak Saad Abdallah Sulafa Abdelbagi Mustafa Ahmed Hanady Abdelhameed Ahmed Mohamed Sarah Khalil Fathi Khalil Family Medicine Health Gates Primary Care Riyadh SAU Family Medicine Dhaman Health Assurance Hospitals Company Kuwait KWT Family Medicine First Health Cluster Riyadh SAU emergency Department Sheikh Khalifa Medical City Abudahbi ARE Family Medicine University of Medical Sciences and Technology Khartoum SDN Family Medicine Sudan Medical Specialization Board-Sudan Khartoum SDN Family Medicine Ultra Care Home Care Company Riyadh SAU Medicine Department Health Gates Primary Care Riyadh SAU Family Medicine Mouwasat Hospital Madinah SAU

Research Background: The high prevalence of diabetes in Sudan, estimated at 16%, highlights the importance of effective health education in diabetes management. Diabetes self-management education has been identified as a crucial tool in enhancing the knowledge, attitudes, and abilities necessary for self-management among individuals with diabetes. Aim: To assess the impact of diabetes self-management education on medication adherence and glycemic control in Sudanese adults with type 2 diabetes before and 3 months after the DSMe intervention. Method: The study was conducted in Sudan between September 2022 and March 2023, it was an interventional, one-group, pre- and post-test study that aimed to assess the impact of diabetes self-management education (DSMe) on medication adherence and diabetes control in Sudanese adults with type 2 diabetes. The research was conducted in primary health care centers in six cities in Sudan and involved 244 participants. The data entry and statistical analysis were conducted using the Statistical Package for Social Sciences version 27.0. A paired t test was used for analysis. Results: The study included 244 participants, 67% of whom were males. The age mean ± SD was 48.6 ± 9.3 years, and 85.3% of participants were married. Age at onset of diabetes mean ± SD was 40.60 ± 7.81 years;44.6% had diabetes for less than 5 years;and 84.1% had a positive family history of diabetes mellitus. The levels of poor, low, and partial adherence to medication decreased by 8.2%, 4%, and 20.6%, respectively, after the intervention. The levels of good and high medication regime adherence increased by 13% and 19.8%, respectively;BMI decreased by 1.1 ± 0.73 kg/m2 (p = 0.005). The fasting blood sugar decreased by 69 ± 32.9 mg/dl (p = 0.049), and the glycated hemoglobin decreased by 1.21 ± 0.28% (p = 0.001). Conclusions: The findings of this study reinforce the importance of patient education in improving glycemic control and enhancing self-management

关键词： Sudan Adherence Intervention education Self-Management Diabetes

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

Conditional Probability Approach for Fault Detection in Photovoltaic energy Farms

引用

Computer Systems Science & engineering 2022年第9期42卷 1109-1120页

作者： Nagy I.elkalashy Ibrahim B.M.taha electrical engineering Department Faculty of EngineeringMenoufia University32511Egypt electrical engineering Department College of EngineeringTaif University21944Saudi Arabia

Detection of electric faults in photovoltaic (PV) farms enhances a sustainable service continuity of farm energy generation. In this paper, a probabilisticfunction is introduced to detect the faults in the PV farms. The conditional probability functions are adopted to detect different fault conditions such as internalstring faults, string-to-string faults, and string-to-negative terminal faults. As thediodes are important to make the PV farms in-service safely during the faults,the distribution currents of these faults are evaluated with different concepts ofdiode consideration as well as without considering any diode installation. Thispart of the study enhances the diode utilization in the PV farms concerning theprotection point of view. The PV string currents are used as inputs to the conditional probability detection algorithms. However, the setting of the fault detectiontechnique is not portable for the other PV systems due to broad ranges of PV system ratings. To accordingly generalize the proposed fault detection algorithm, thePV string currents are first normalized to the total array current for universallyapplying the detection function at different PV string ratings. The limiting faultresistances are evaluated to show the sensitivity of the proposed fault *** results ensure the application of the proposed probabilistic detection functionfor PV farms.

关键词： Photovoltaic farm fault detection conditional probability diodes

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

Real and Altered Fingerprint Classification Based on Various Features and Classifiers

引用

Computers, Materials & Continua 2023年第1期74卷 327-340页

作者： Saif Saad Hameed Ismail taha Ahmed Omar Munthir Al Okashi College of Computer Sciences and Information Technology University of AnbarAnbarIraq

Biometric recognition refers to the identification of individuals through their unique behavioral features(e.g.,fingerprint,face,and iris).We need distinguishing characteristics to identify people,such as fingerprints,which are world-renowned as the most reliablemethod to identify *** recognition of fingerprints has become a standard procedure in forensics,and different techniques are available for this *** current techniques lack interest in image enhancement and rely on high-dimensional features to generate classification ***,we proposed an effective fingerprint classification method for classifying the fingerprint image as authentic or altered since criminals and hackers routinely change their fingerprints to generate fake *** order to improve fingerprint classification accuracy,our proposed method used the most effective texture features and *** Analysis(DCA)and Gaussian Discriminant Analysis(GDA)are employed as classifiers,along with Histogram of Oriented Gradient(HOG)and Segmentation-based Feature Texture Analysis(SFTA)feature vectors as *** performance of the classifiers is determined by assessing a range of feature sets,and the most accurate results are *** proposed method is tested using a Sokoto Coventry Fingerprint Dataset(SOCOFing).The SOCOFing project includes 6,000 fingerprint images collected from 600 African people whose fingerprints were taken ten *** distinct degrees of obliteration,central rotation,and z-cut have been performed to obtain synthetically altered replicas of the genuine *** proposal achieved massive success with a classification accuracy reaching 99%.The experimental results indicate that the proposed method for fingerprint classification is feasible and *** experiments also showed that the proposed SFTA-based GDA method outperformed state-of-art approaches in feature dimension and classification accuracy.

关键词： Fingerprint classification HOG SFTA discriminant analysis(DCA)classifier gaussian discriminant analysis(GDA)classifier SOCOFing

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

Upregulation of ReL and WSB1 in Patients With Psoriasis and Metabolic Syndrome

引用

International Journal of Dermatology and Venereology 2023年第4期6卷 189-194页

作者： Manahel Mahmood Alsabbagh Moiz Bakhiet Safa taha Princess Al-Jawhara Center for Molecular Medicine and Inherited Disorders Department of Molecular MedicineArabian Gulf UniversityManama 329Kingdom of Bahrain.

Objective:A strong association exists between metabolic syndrome and *** current study was performed to explore the gene regulation of metabolic syndrome in patients with ***:Patients were assessed for psoriasis and metabolic syndrome clinically (Psoriasis Area and Severity Index,height,weight,waist circumference,and blood pressure) and biochemically (lipid profile and fasting blood sugar concentration).Systemic gene regulation was first explored by microarray and analyzed using Transcriptome Analysis Console Software,after which two selected upregulated genes were further validated using polymerase chain reaction and enzyme-linked immunosorbent assay and analyzed using independent samplet ***:The analysis showed 7,269 upregulated and 3 downregulated genes at a fold change of 2 andP value of enes were upregulated and none were downregulated at a fold change of 8 andP value of eviously reported potential biomarkers of metabolic syndrome in patients with psoriasis showed that the levels of 16 biomarkers aligned with the gene regulation observed in the current *** particular,theReL transcript was upregulated 12-fold (P = 8.16 × 10-17),while theWSB1 transcript was upregulated 9-fold (P = 9.87 × 10-13).Validation showed thatReL was also upregulated 2-fold in the polymerase chain reaction,and its protein was expressed at 7.140 ng/*** levels in the cases (P = 0.048).However,WSB1 was upregulated 2-fold in the polymerase chain reaction compared with controls,and unexpectedly,its protein was undetectable in cases but detectable in controls (P = 0.018).Conclusion:The upregulation ofReL andWSB1 was observed in patients with psoriasis and metabolic syndrome,the clinical application ofReL andWSB1 as biomarkers needs further validation for potential future implications in clinical practice.

关键词： psoriasis diabetes mellitus hypertension inflammation metabolic syndrome obesity ReL WSB1

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

Fusion of Region extraction and Cross-entropy SVM Models for Wheat Rust Diseases Classification

引用

Computers, Materials & Continua 2023年第11期77卷 2097-2121页

作者： Deepak Kumar Vinay Kukreja Ayush Dogra Bhawna Goyal Talal taha Ali Department of Computer Science&engineering Chitkara University Institute of Engineering and TechnologyChitkara UniversityPunjab140401India Department of electronics&Communication engineering Chandigarh UniversityPunjab140413India Department of Dental Industry Techniques Al-Noor University CollegeNineveh41018Iraq

Wheat rust diseases are one of the major types of fungal diseases that cause substantial yield quality losses of 15%–20%every *** wheat rust diseases are identified either through experienced evaluators or computerassisted *** experienced evaluators take time to identify the disease which is highly laborious and too *** wheat rust diseases are predicted at the development stages,then fungicides are sprayed earlier which helps to increase wheat yield *** solve the experienced evaluator issues,a combined region extraction and cross-entropy support vector machine(Ce-SVM)model is proposed for wheat rust disease *** the proposed system,a total of 2300 secondary source images were augmented through flipping,cropping,and rotation *** augmented images are preprocessed by histogram *** a result,preprocessed images have been applied to region extraction convolutional neural networks(RCNN);Fast-RCNN,Faster-RCNN,and Mask-RCNN models for wheat plant patch *** layers of region extraction models construct a feature vector that is later passed to the Ce-SVM *** a result,the Gaussian kernel function in Ce-SVM achieves high F1-score(88.43%)and accuracy(93.60%)for wheat stripe rust disease classification.

关键词： Wheat rust diseases agricultural region extraction models intercropping image processing feature extraction precision agriculture

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

Adults with Congenital Heart Disease during the COVID-19 era:One-Year Tertiary Center experience

引用

Congenital Heart Disease 2022年第4期17卷 399-419页

作者： Fatma A.taha Osama Amoudi Fareed Alnozha Reda Abuelatta Adult Cardiology Department Madinah Cardiac CenterMadinahSaudi Arabia Cardiology Department Faculty of MedicineTanta UniversityTantaEgypt

Background:Adult patients with congenital heart disease(ACHD)might be at high risk of Coronavirus disease-2019(COVID-19).This study aimed to report on a one-year tertiary center experience regards COVID-19 infection in ACHD ***:This is a one-year(March-2020 to March-2021)tertiary-center retrospective study that enrolled all ACHD patients;COVID-19 positive patients’medical records,and management were ***:We recorded 542 patients,205(37.8%)COVID-19-positive,and 337(62.2%)COVID-19-negative *** single ventricle and eisenmenger syndrome patients were more vulnerable to COVID-19 infection(Pere arrhythmias in 47(22.9%)patients,heart failure in 39(19.0%)patients,cyanosis in 12(5.9%)patients,stroke/TIA in 5(2.4%)patients,hypertension and infective endocarditis in 2(1.0%)patients for each,pulmonary hypertension and pulmonary embolism in 1(0.5%)patient for each.11(5.4%)patients were managed with home isolation,147(71.7%)patients required antibiotics,32(15.6%)patients required intensive care unit(ICU),8(3.9%)patients required inotropes,7(3.4%)patients required mechanical ventilation,and 2(1.0%)patients required extracorporeal membrane oxygenation(eCMO).Thromboprophylaxis was given to all 46(22.4%)hospitalized *** College of Cardiology/American Heart Association classification revealed that complex lesions,and FC-C/D categories were more likely to develop severe/critical symptoms,that required mechanical ventilation and eCMO(Peported in 3(0.6%)patients with no difference between groups(P=0.872).193(35.6%)patients were ***:COVID-19 infection in ACHD patients require individualized risk stratification and *** syndrome,single ventricle palliation,complex lesions,and FC-C/D patients were more vulnerable to severe/critical symptoms that required ICU admission,mechanical ventilation,and *** vaccine was mostly tolerable.

关键词： Adult congenital heart disease COVID-19 era COVID-19 pandemic COVID-19 positive congenital heart disease patients COVID-19 infected adults with congenital heart disease

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 Hybrid Particle Swarm Optimization to Forecast Implied Volatility Risk

引用

Computers, Materials & Continua 2022年第11期73卷 4291-4309页

作者： Kais Tissaoui Sahbi Boubaker Waleed Saud Alghassab taha Zaghdoudi Jamel Azibi University of Ha’il Applied CollegeHail CitySaudi Arabia University of Tunis el Manar Faculty of Economic Sciences and Management of Tunisthe International Finance GroupTunisTunisia Department of Computer and Network engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21959Saudi Arabia Research Unit on Study of Systems and Renewable energy National College of Engineering of MonastirUniversity of MonastirMonastirTunisia LAReQUAD&FSeGT University of Tunis El ManarTunisTunisia University of Jendouba Law FacultyManagement and Economic Sciences of JendoubaTunisia

The application of optimization methods to prediction issues is a continually exploring *** line with this,this paper investigates the connectedness between the infected cases of COVID-19 and US fear index from a forecasting *** complex characteristics of implied volatility risk index such as non-linearity structure,time-varying and nonstationarity motivate us to apply a nonlinear polynomial Hammerstein model with known structure and unknown *** use the Hybrid Particle Swarm Optimization(HPSO)tool to identify the model parameters of nonlinear polynomial Hammerstein *** indicate that,following a nonlinear polynomial behaviour cascaded to an autoregressive with exogenous input(ARX)behaviour,the fear index in US financial market is significantly affected by COVID-19-infected cases in the US,COVID-19-infected cases in the world and COVID-19-infected cases in China,*** performance indicators provided by the developed models show that COVID-19-infected cases in the US are particularly powerful in predicting the Cboe volatility index compared to COVID-19-infected cases in the world and China(MAPe(2.1013%);R2(91.78%)and RMSe(0.6363 percentage points)).The proposed approaches have also shown good convergence characteristics and accurate fits of the data.

关键词： Forecasting Cboe’s volatility index COVID-19 pandemic nonlinear polynomial hammerstein model hybrid particle swarm optimization

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

Text-Independent Algorithm for Source Printer Identification Based on ensemble Learning

引用

Computers, Materials & Continua 2022年第10期73卷 1417-1436页

作者： Naglaa F.el Abady Mohamed taha Hala H.Zayed Department of Computer Science Faculty of Computers and Artificial IntelligenceBenha University13518Egypt School of Information Technology and Computer Science(ITCS) Nile University12677Egypt

Because of the widespread availability of low-cost printers and scanners,document forgery has become extremely *** or signatures are used to protect important papers such as certificates,passports,and identification *** the origins of printed documents is helpful for criminal investigations and also for authenticating digital versions of a document in today’s *** printer identification(SPI)has become increasingly popular for identifying frauds in printed *** paper provides a proposed algorithm for identifying the source printer and categorizing the questioned document into one of the printer classes.A dataset of 1200 papers from 20 distinct(13)laser and(7)inkjet printers achieved significant identification results.A proposed algorithm based on global features such as the Histogram of Oriented Gradient(HOG)and local features such as Local Binary Pattern(LBP)descriptors has been proposed for printer *** classification,Decision Trees(DT),k-Nearest Neighbors(k-NN),Random Forests,Aggregate bootstrapping(bagging),Adaptive-boosting(boosting),Support Vector Machine(SVM),and mixtures of these classifiers have been *** proposed algorithm can accurately classify the questioned documents into their appropriate printer *** adaptive boosting classifier attained a 96%*** proposed algorithm is compared to four recently published algorithms that used the same dataset and gives better classification accuracy.

关键词： Document forensics source printer identification(SPI) HOG LBP principal component analysis(PCA) bagging AdaBoost

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

effect of Fibre Size on Mechanical Properties and Surface Roughness of PLA Composites by Using Fused Deposition Modelling (FDM)

引用

Journal of Renewable Materials 2023年第8期11卷 3261-3276页

作者： Aida Haryati Jamadi Nadlene Razali Sivakumar Dhar Malingam Mastura Mohammad taha Fakulti Kejuruteraan Mekanikal Universiti Teknikal Malaysia MelakaHang Tuah JayaDurian TunggalMelaka76100Malaysia Fakulti Teknologi Kejuruteraan Mekanikal dan Pembuatan Universiti Teknikal Malaysia MelakaHang Tuah JayaDurian TunggalMelaka76100Malaysia Centre for Advanced Research on energy Universiti Teknikal Malaysia MelakaHang Tuah JayaDurian TunggalMelaka76100Malaysia

Naturalﬁbre as a reinforcing agent has been widely used in many industrial ***,several factors need to be considered,such as the size and weight percentage of theﬁbre used in *** fused deposition modelling(FDM),this factor was investigated by varying the size of naturalﬁbre as the responding variable with aﬁxed weight percentage of kenafﬁ*** process of modifying the naturalﬁbre in terms of size might increase the dispersion of kenafﬁbre in the polymer matrix and increase the adhesion bonding between theﬁbre and matrix of composites,subsequently improving the interfacial bonding between these two *** this paper,the effect ofﬁbre size was evaluated by performing the mechanical test,Scanning electron Micrograph(SeM)to observe the morphology of the composites,and also by surface *** surface roughness was visualised using a 3D proﬁlometer and theﬁgure was illustrated as colour shading in the *** composite withﬁbre size≤100μm displayed better tensile andﬂexural strength,compared to other *** conclusion,by reducing the size of theﬁbre,the composites could develop high strength performance for industrial applications.

关键词： Fibre size mechanical properties fused deposition modelling(FDM) surface analysis

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：