检索结果-南通市图书馆

FAIR Machine Learning Model Pipeline Implementation of COVID-19 Data

Data Intelligence 2022年第4期4卷 971-990,1036页

作者： Sakinat Folorunso Ezekiel Ogundepo Mariam Basajja Joseph Awotunde abdullahi Kawu Francisca Oladipo abdullahi ibrahim Department of Mathematical Sciences Olabisi Onabanjo UniversityP.M.B 2002Ago-IwoyeOgun StateNigeria 120005Nigeria Data Science Nigeria Lagos 105102Nigeria Leiden University 1011NCAmsterdamthe Netherlands Department of Computer Science University of IlorinIlorinKwara State240103Nigeria Department of Computer Science Ibrahim Badamosi UniversityLapaiNiger State911101Nigeria Kampala International University 260101Uganda Federal University Lokoja Nigeria Virus Outbreak Data Network-Africa

Research and development are gradually becoming data-driven and the implementation of the FAIR Guidelines(that data should be Findable, Accessible, Interoperable, and Reusable) for scientific data administration and stewardship has the potential to remarkably enhance the framework for the reuse of research data. In this way, FAIR is aiding digital transformation. The ‘FAIRification’ of data increases the interoperability and(re)usability of data, so that new and robust analytical tools, such as machine learning(ML) models, can access the data to deduce meaningful insights, extract actionable information, and identify hidden patterns. This article aims to build a FAIR ML model pipeline using the generic FAIRification workflow to make the whole ML analytics process FAIR. Accordingly, FAIR input data was modelled using a FAIR ML model. The output data from the FAIR ML model was also made FAIR. For this, a hybrid hierarchical k-means (HHK) clustering ML algorithm was applied to group the data into homogeneous subgroups and ascertain the underlying structure of the data using a Nigerian-based FAIR dataset that contains data on economic factors, healthcare facilities, and coronavirus occurrences in all the 36 states of Nigeria. The model showed that research data and the ML pipeline can be FAIRified, shared, and reused by following the proposed FAIRification workflow and implementing technical architecture.

关键词： FAIRification Semantic data model Cluster analysis FAIR data Metadata Machine learning model

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

FAIR Guidelines and Data Regulatory Framework for Digital Health in Nigeria

引用

Data Intelligence 2022年第4期4卷 839-851,1042-1043页

作者： abdullahi Abubakar Kawu Joseph Elijah ibrahim abdullahi Jamilu Yahaya Maipanuku Sakinat Folorunso Mariam Basajja Francisca Oladipo Hauwa Limanko ibrahim Department of Computer Science Ibrahim Badamasi Babangida University911101 LapaiNigeria Department of Mathematical Sciences Olabisi Onabanjo UniversityAgo-Iwoye120005 Ogun StateNigeria Leiden Institute of Computer Science 1011NCAmsterdamthe Netherlands Federal University 260101 LokojaNigeria Kampala International University Uganda

Adopting the FAIR Guidelines—that data should be Findable, Accessible, Interoperable and Reusable(FAIR)—in the health data system in Nigeria will help protect data against use by unauthorised parties, while also making data more accessible to legitimate users. However, little is known about the FAIR Guidelines and their compatibility with data and health laws and policies in Nigeria. This study assesses the governance framework for digital and health/e Health policies in Nigeria and explores the possibility of a policy window opening for the FAIR Guidelines to be adopted and implemented in Nigeria’s e Health sector. Ten Nigerian policy documents were examined for mention of the FAIR Guidelines(or FAIR Equivalent terminology) and the 15 sub-criteria or facets. The analysis found that although the FAIR Guidelines are not explicitly mentioned, 70% of the documents contain FAIR Equivalent terminology. The Nigeria Data Protection Regulation contained the most FAIR Equivalent principles(73%) and some of the remaining nine documents also contained some FAIR Equivalent principles(between 0–60%). Accordingly, it can be concluded that a policy window is open for the FAIR Guidelines to be adopted and implemented in Nigeria’s e Health sector.

关键词： FAIR Health data policy FAIR Equivalent terminology

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

Computer-aided Detection of Tuberculosis from Microbiological and Radiographic Images

引用

Data Intelligence 2023年第4期5卷 1008-1032页

作者： abdullahi Umar ibrahim Ayse Gunnay Kibarer Fadi Al-Turjman Department of Biomedical Engineering Near East UniversityNicosiaMersin 10Turkey Research Center for Al and loT Faculty of EngineeringUniversity of KyreniaMersin 10Turkey Artificial Intelligence Engineering Dept. Al and Robotics InstituteNear East UniversityMersin 1Turkey

Tuberculosis caused by Mycobacterium tuberculosis have been a major challenge for medical and healthcare sectors in many underdeveloped countries with limited diagnosis *** can be detected from microscopic slides and chest X-ray but as a result of the high cases of tuberculosis,this method can be tedious for both Microbiologists and Radiologists and can lead to *** challenges can be solved by employing Computer-Aided Detection(CAD)via Al-driven models which learn features based on convolution and result in an output with high *** this paper,we described automated discrimination of X-ray and microscope slide images into tuberculosis and non-tuberculosis cases using pretrained AlexNet *** study employed Chest X-ray dataset made available on Kaggle repository and microscopic slide images from both Near East University Hospital and Kaggle *** classification of tuberculosis using microscopic slide images,the model achieved 90.56%accuracy,97.78%sensitivity and 83.33%specificity for 70:30 *** classification of tuberculosis using X-ray images,the model achieved 93.89%accuracy,96.67%sensitivity and 91.11%specificity for 70:30 *** result is in line with the notion that CNN models can be used for classifying medical images with higher accuracy and precision.

关键词： Tuberculosis Deep Learning Pretrained AlexNet Chest X-ray Microscopic slide

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

Coupled tripartite investigation of breaker fluid invasion and impact on hydrocarbon recovery in sandstone reservoirs

引用

Petroleum Research 2023年第3期8卷 338-349页

作者： Stella I.Eyitayo Kazeem A.Lawal Marshall C.Watson Oladoyin Kolawole ibrahim abdullahi Asekhame U.Yadua Oluchukwu M.Okoh Saka Matemilola Tunde Alabi Bob L.Herd Department of Petroleum Engineering Texas Tech University807 Boston AveLubbockTX79409USA FIRST Exploration and Petroleum Development Company(FIRST E&P) Nigeria John A.Reif Jr.Department of Civil and Environmental EngineeringNew Jersey Institute of TechnologyNewarkNJ07102USA Nigerian Petroleum Development Company(NPDC) Nigeria

Breaker fluids are designed to dissolve filter cakes by breaking their long-chain molecules,thereby removing solid deposits on the wellbore *** breaker fluids are not intended to infiltrate the hydrocarbon reservoir,they can invade and cause formation damage by altering sandstone reservoirs'wettability and relative *** can lead to a reduction in the overall reservoir *** study coupled tripartite methods to investigate the potential impact of breaker invasion and transport in hydrocarbon reservoirs and its multiscale effect on the performances of sandstone *** utilized experimental,analytical,and numerical methods to assess and predict the susceptibility of reservoirs to breaker fluid invasion and *** experimental and empirical investigations considered varying breaker fluid formulations to evaluate the effects of breaker fluid concentration,formation temperature,and solution gas-oil ratio(GOR)on residual-oil saturation(ROS)and oil-water relative *** adopting the ROS and relative permeability associated with the 50%v/v breaker fluid mixture,the performance of the hydrocarbon reservoir was numerically simulated under the limiting scenarios of no-invasion,moderate-invasion,and deep-invasion of breaker *** results indicate a positive correlation between breaker fluid concentration and ROS,highlighting the risks that breaker fluid invasion and deep infiltration pose to hydrocarbon ***,results show that both live-oil condition(LOC)and dead-oil condition(DOC)reservoirs are susceptible to the detrimental impacts of breaker fluid infiltration,while their invasion can reduce hydrocarbon recovery in both LOC(-6%)and DOC(-28%).The multi-scale effects on reservoir performance are more pronounced at near-wellbore and DOC than at far-field and *** from this work provide valuable insights into the complexity of breaker-fluid invasion in sandstone reservoirs and the mitigation of as

关键词： Breaker fluid Fluid invasion Formation damage Fluid transport Near-wellbore alteration

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 Steel Fiber on Concrete’s Compressive Strength

引用

Open Journal of Civil Engineering 2023年第1期13卷 192-197页

作者： Mohammed Saed Yusuf Abdirisak Bashir Isak Guled Ali Mohamud abdullahi Hashi Warsame Yahye ibrahim Osman abdullahi Husein ibrahim Liban Abdi Aziz Elmi Department of Civil Engineering Hormuud University Mogadishu Somalia

The general goal of this research is to investigate whether steel fiber has a significant “positive” or “negative” influence on concrete compressive strength, as well as the optimal steel fiber ratio that delivers best result. Manually, cement, fine aggregates, coarse aggregates, steel fibers, and water were mixed together properly. A slump test was carried on the mixed concrete. After determining the workability, the mixed concrete was poured into cubes dimension 150 mm × 150 mm × 150 mm and left for 24 hours. After 24 hours, the samples were removed from the mold and placed in a water tank to cure for 7 to 28 days. The cube was tested for compressive and flexural strength in a universal testing machine after the samples had cured for the required 7 - 28 days. This study focuses on how to obtain high strength concrete using with steel fiber in the Conventional mix ratio to enhance concrete strength. Concrete reinforcement using steel fibers alters the characteristics of the concrete, allowing it to withstand fracture and hence improve its mechanical qualities. This study reports on an experimental study that reveals the effect of steel fiber on concrete compressive strength and the optimal steel fiber ratio that produces the best results. Steel fiber reinforcing improved the compressive strength of concrete. The average compressive strength of normal M25 concrete with 0% steel fibers and curing ages of 7 and 28 days was determined to be 22.97 N/mm2 and 25.78 N/mm2, respectively. The steel fibers are then added in various concentrations, such as 1%, 2%, and 3%, with aspect ratios of 70. The compressive strength of concrete with 1%, 2%, and 3% steel fiber with an aspect ratio of 70 was examined at 7 days and found to be 23.96, 24.80, and 26.14 N/mm2 correspondingly.

关键词： Steel Fiber Reinforced Concrete Fiber Reinforcement Compression Strength of Concrete Improvement Compression Strength

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

Anthropometric Comparison of Three-Year-Old Nigerian Child and Crash Dummies

引用

Journal of Transportation Technologies 2016年第4期6卷 192-199页

作者： ibrahim abdullahi Rafukka Barkawi Bin Sahari Abdulaziz Nuraini Arumugam Manohar Department of Mechanical and Manufacturing Engineering Faculty of Engineering Universiti Putra Malaysia Serdang Malaysia Department of Mechanical Engineering Bayero University Kano Nigeria Department of Orthopaedic Surgery Faculty of Medicine and Health Sciences Universiti Putra Malaysia Serdang Malaysia

In this work, anthropometric data measured from three-year-old Nigerian child were compared with United States anthropometric database collected by Snyder, 1977 which formed the basis of US anthropometry used today. Further comparison was also carried out with the dimensions of crash dummies: Hybrid III three-year-old (HIII 3YO) and Q3s dummies in order to determine the validity of using such crash dummies for safety evaluation of cars and child restraint systems (CRS) used for Nigerian children. Anthropometric survey was performed on 30 Nigerian children aged 2.5 to 3.5 years old. Twenty three standard measurements were taken from each child including the weight, height and circumferences etc. Various percentiles mean and standard deviation values were obtained and compared with international database. As observed, the dimensions of three-year-old Nigerian child appeared to be about 25% lower than US data reported by Snyder. Significant difference was also found between the dimensions of three-year-old Nigerian child and crash dummies. This study provides the external dimensions of 3-year-old Nigerian child that could be used for crash dummy and CRS design.

关键词： Anthropometry Crash Dummies Child Restraint System Measurement Vehicle Safety

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

帕金森病患者不同程度抑郁发病率及其影响因素

帕金森病患者不同程度抑郁发病率及其影响因素

引用

作者：阿杜（abdullahi Abdi ibrahim）杭州师范大学

学位级别：硕士

目的:帕金森病(Parkinson's Disease,PD)是一类慢性进行性的运动障碍性疾病。近年来对PD患者抑郁症、焦虑障碍、睡眠障碍等非运动症状(Non Motor Symptoms,NMS)的研究越来越多,抑郁发病率占NMS比例较高,严重影响患者的生活质量。本项研... 详细信息

目的:帕金森病(Parkinson's Disease,PD)是一类慢性进行性的运动障碍性疾病。近年来对PD患者抑郁症、焦虑障碍、睡眠障碍等非运动症状(Non Motor Symptoms,NMS)的研究越来越多,抑郁发病率占NMS比例较高,严重影响患者的生活质量。本项研究目的在于了解PD患者不同程度抑郁的发病率及其相关联因素(如运动障碍、睡眠障碍、H-Y分期等),进一步寻找有效的干预因素来提高PD患者的生活质量。方法:收集某三甲医院确诊的符合入组标准的PD患者113例,采用24项汉密尔顿抑郁量表(HRSD)将入组人员分为非抑郁组、可能抑郁组及抑郁组,其中PD抑郁(Parkinson Disease with depression,PDD)再分为轻度、中度、重度三个亚组。使用相关量表评估患者焦虑状况、生活的质量、认知功能、运动状况等。同时收集患者病程、睡眠状况、性别年龄及多巴胺(Dopamine,DA)制剂等可能影响患者抑郁的因素,并用SPSS 23进行相关统计分析。结果:(1)PD患者中非抑郁患者19人,占16.8%,可能抑郁组60人,占53.1%。抑郁组34人,占入组总人数的30.1%,其中轻度抑郁人数占63.7%,中度抑郁者占32.7%,重度抑郁PD患者占3.6%。绝大多数PD患者患有抑郁或可能的抑郁,其中大部分PD患者为可能抑郁。(2)非抑郁组与抑郁组(包括可能抑郁组)PD患者之间的生活质量差异显著(P0.05)。(3)抑郁与PD患者的病程、性别、文化程度、是否使用DA制剂及睡眠障碍具有显著相关(P0.05)。(4)抑郁与PD患者的UPDRSⅠ、UPDRSⅡ、UPDRSⅢ、UPDRSⅣ、H-Y分级、焦虑指数、ADL、MMSE等因素均具有显著相关(P<0.05或<0.01)。结论:PD患者绝大多数具有抑郁或抑郁倾向,仅极少数人不伴发抑郁,PDD对患者生活质量影响最为著。而性别、病程、是否使用DA制剂及睡眠障碍等为影响PDD的主要因素。其中是否使用DA制剂和睡眠障碍为可干预性因素,提示或可尽早对二者进行有效干预来改善患者的抑郁状况,进一步提高PD患者的生活质量。同时使用与PDD联系显著相关的ADL等操作简单的量表动态观察患者抑郁情况,对临床观察及早干预PDD具有参考价值。

关键词：帕金森病抑郁生活质量相关因素

来源：

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Climate Change Impact on Sub-Surface Hydrology of Kaduna River Catchment

引用

Open Journal of Modern Hydrology 2013年第3期3卷 115-121页

作者： Haruna Garba Abubakar Ismail Rabia Lawal Batagarawa Saminu Ahmed abdullahi ibrahim Faustinus Bayang Department of Civil Engineering Nigerian Defence Academy Kaduna Nigeria Department of Water Resources and Environmental Engineering Ahmadu Bello University Zaria Nigeria.

This paper applied the use of a stochastic weather generator at the site of a hydrological model to simulate the impact of climate change on the sub-surface hydrological response of Kaduna River as a basis for a sustainable ground water development plan. Average time series of rainfall, temperature and gauge height observed readings were downscaled to the watershed flow volume and applied as forcing to simulate the ground water response as spatially lumped, ignoring the heterogeneous nature of the ground water aquifer. Future simulations indicate increase in base flow, ground storage and decrease soil storage throughout the summer and autumn months for the catchment.

关键词： Climate Change Simulation Ground Storage Soil Storage Base Flow

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

Classifying rockburst with confidence:A novel conformal prediction approach

引用

International Journal of Mining Science and Technology 2024年第1期34卷 51-64页

作者： Bemah ibrahim Isaac Ahenkorah University of South Australia UniSA STEMSA 5000Australia

The scientific community recognizes the seriousness of rockbursts and the need for effective mitigation *** literature reports various successful applications of machine learning(ML)models for rockburst assessment;however,a significant question remains unanswered:How reliable are these models,and at what confidence level are classifications made?Typically,ML models output single rockburst grade even in the face of intricate and out-of-distribution samples,without any associated confidence *** the susceptibility of ML models to errors,it becomes imperative to quantify their uncertainty to prevent consequential *** address this issue,we propose a conformal prediction(CP)framework built on traditional ML models(extreme gradient boosting and random forest)to generate valid classifications of rockburst while producing a measure of confidence for its *** proposed framework guarantees marginal coverage and,in most cases,conditional coverage on the test *** CP was evaluated on a rockburst case in the Sanshandao Gold Mine in China,where it achieved high coverage and efficiency at applicable confidence ***,the CP identified several“confident”classifications from the traditional ML model as unreliable,necessitating expert verification for informed *** proposed framework improves the reliability and accuracy of rockburst assessments,with the potential to bolster user confidence.

关键词： Rockburst Machine learning Uncertainty quantification Conformal prediction

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

Prevalence of Rifampicin Resistance and Associated Risk Factors among Suspected Multidrug Resistant Tuberculosis Cases in TB Centers Mogadishu-Somalia: Descriptive Study

引用

Open Journal of Respiratory Diseases 2016年第2期6卷 15-24页

作者： Ahmed Y. Guled Ayub Hassan Elmi Bashir Mohamud Abdi Abdihamid Mohamed Ali Rage Fartun Mohamed Ali abdullahi Hassan Abdinur abdullahi Abdulle Ali Anab Adam Ahmed Khadra abdullahi ibrahim Salah Osman Mohamed Fos Ali Mire Omar Abdi Adem Ali Dirie Osman Guuleed Hospital Mogadishu Somalia Faculty of Medicine Benadir University Mogadishu Somalia Department of Internal Medicine Benadir University Mogadishu Somalia

Introduction and Background: Multidrug-resistant tuberculosis (MDR-TB) has emerged as a significant global health concern. Patients who had failed previous TB treatment, relapsed after treatment, contacted known MDRTB patients or defaulted during previous treatment, and HIV patients are considered to be suspected and at high risk for developing drug resistant TB specially MDR-TB. However, there is little data available on the prevalence and trends of MDR tuberculosis in national level but luck of it in Mogadishu is our main concern. Methodology: This was a crosssectional, descriptive study involving all suspected MDR TB patients attended at the Mogadishu three Tb centers. Results: A total of 138 cases of suspected MDRTB patients were included in the study. Of these, 70 patients (51%) had rifampicin resistant-TB. Of the 138 study participants, 94 (68.62%) were between 21 - 40 years old that indicates the dominance of productive age group (21 - 40 years). Previous Tuberculosis treatment has been noted to be a major risk factor for development of multidrug resistance tuberculosis. MDR-TB prevalence is significantly higher in male than female patients. Conclusion and Interpretation: The prevalence of Rifampicin resistance among these high risk groups was significant. The high association of previous TB treatment to MDR-TB might be explained due to inappropriate anti-tubercular regimens, sub-optimal drugs, inadequate or irregular drug supply, unsatisfactory patient or clinician compliance, lack of supervision of treatment and absence of infection control measures in healthcare facilities. As the prevalence of MDRTB is high and yet the cases remain un-isolated in the community we recommend the MOH/NTP and funding agencies to facilitate establishment of MDRTB management centers earlier in Mogadishu in order to treat the MDRTB case otherwise it might Amplify of the incidence of this Emerging Disease.

关键词： Prevalence Risk Factors Tuberculosis Mogadishu

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：