检索结果-南通市图书馆

Data-Driven Decision-making for Bank Targetmarketing Using Supervised Learning Classifiers on Imbalanced Big Data

Computers, materials and Continua 2024年第1期81卷 1703-1728页

作者： Nasir F. Ahmed A.A. SabirKiraz m. Yevseyeva I. Saif m. School of Computer Science and Informatics De Montfort University Leicester LE1 9BH United Kingdom Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor 86400 Malaysia

Integrating machine learning and data mining is crucial for processing big data and extracting valuable insights to enhance decision-making. However, imbalanced target variables within big data present technical challenges that hinder the performance of supervised learning classifiers on key evaluation metrics, limiting their overall effectiveness. This study presents a comprehensive review of both common and recently developed Supervised Learning Classifiers (SLCs) and evaluates their performance in data-driven decision-making. The evaluation uses various metrics, with a particular focus on the Harmonic mean Score (F-1 score) on an imbalanced real-world bank target marketing dataset. The findings indicate that grid-search random forest and random-search random forest excel in Precision and area under the curve, while extreme Gradient Boosting (XGBoost) outperforms other traditional classifiers in terms of F-1 score. employing oversampling methods to address the imbalanced data shows significant performance improvement in XGBoost, delivering superior results across all metrics, particularly when using the SmOTe variant known as the BorderlineSmOTe2 technique. The study concludes several key factors for effectively addressing the challenges of supervised learning with imbalanced datasets. These factors include the importance of selecting appropriate datasets for training and testing, choosing the right classifiers, employing effective techniques for processing and handling imbalanced datasets, and identifying suitable metrics for performance evaluation. Additionally, factors also entail the utilisation of effective exploratory data analysis in conjunction with visualisation techniques to yield insights conducive to data-driven decision-making. © 2024 The Authors. Published by Tech Science Press.

关键词： Big data data mining data visualization imbalanced dataset label encoding machine learning sampling techniques

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 new technique for fault diagnosis in transformer insulating oil based on infrared spectroscopy measurements

引用

High Voltage 2024年第2期9卷 319-335页

作者： mohamed m.F.Darwish mohamed H.A.Hassan Nagat m.K.Abdel-Gawad matti Lehtonen Diaa-eldin A.mansour Department of electrical engineering Faculty of Engineering at ShoubraBenha UniversityCairoEgypt Department of electrical engineering and Automation School of Electrical EngineeringAalto UniversityEspooFinland Department of electrical Power engineering Egypt-Japan University of Science and Technology(E-JUST)New Borg El-Arab CityEgypt Department of electrical Power and machines engineering Faculty of EngineeringTanta UniversityTantaEgypt

Condition monitoring of the insulating system within power transformers has a massive importance according to the electrical *** gas analysis(DGA)is frequently used for this ***,DGA lacks the necessary level of accuracy to identify all equipment faults,particularly in their initial stages of ***,it does not have the capability for real-time monitoring and relies on manual sampling and laboratory testing,causing potential delays in fault ***,the interpretation of DGA data necessitates specialised expertise,which may pose difficulties for smaller entities that have limited access to ***,the contribution of this research is to use infrared spectroscopy measurements as a new effective technique substituting the DGA method for fault diagnosis in insulating *** inception faults that were considered in this study were the electrical fault(discharges of high energy)and the thermal fault(300°Cemperatureegarding that,two test cells were crafted especially for serving the simulation processes inside the laboratory for both types of inception ***,six samples of pure paraffinic mineral oil were taken to be degraded in the *** that,all of them besides another sample that were not subjected to any kind of faults were taken to be examined by Fourier transform infrared(FTIR)spectroscopy to obtain an overview of the oil's behaviour in each fault *** that,the FTIR analysis was initially verified utilising the DGA ***,for further affirmation,the dielectric dissipation factor(DDF)for all samples was *** the final analysis,the verification tests provide experimental evidence about the outperformance of this new optical technique in detecting the transformer's inception faults in addition to proving its potential for being a superior alternative to the well-known traditional diagnostic techniques.

关键词： fault diagnosis spectroscopy

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

An explainable AI framework for robust and transparent data-driven wind turbine power curve models

引用

energy and AI 2024年第1期15卷 312-327页

作者： Simon Letzgus Klaus-Robert müller machine Learning Group Technische Universitβe BerlinStraβe des 17.Juni 135Berlin10623Germany Berlin Institute for the Foundations of Learning and Data Berlin10587Germany Department of Artificial Intelligence Korea UniversitySeoul136-713South Korea max Planck Institute for Informatics Saarbrücken66123Germany

In recent years,increasingly complex machine learning methods have become state-of-the-art in modelling wind turbine power curves based on operational *** these methods often exhibit superior performance on test sets,they face criticism due to a perceived lack of transparency and concerns about their robustness in dynamic,non-stationary environments encountered by wind *** this work,we address these issues and present a framework that leverages explainable artificial intelligence methods to gain systematic insights into data-driven power curve *** its core,we propose a metric to quantify how well a learned model strategy aligns with the underlying physical principles of the *** novel tool enables model validation beyond the conventional error metrics in an automated *** demonstrate,for instance,its capacity as an indicator for model generalization even when limited data is ***,it facilitates understanding how decisions made during the machine learning development process,such as data selection,pre-processing,or training parameters,affect learned *** a result,we obtain physically more reasonable models,a prerequisite not only for robustness but also for meaningful insights into turbine operation by domain *** latter,we illustrate in the context of wind turbine performance *** summary,the framework aims to guide researchers and practitioners alike toward a more informed selection and utilization of data-driven wind turbine power curve models.

关键词： explainable AI(XAI) machine learning Wind energy Wind turbine power curve SCADA Condition monitoring

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

Soil organic carbon stocks in native forest of Argentina:a useful surrogate for mitigation and conservation planning under climate variability

引用

ecological Processes 2024年第1期13卷 3-24页

作者： Pablo L.Peri Juan Gaitán matías mastrangelo marcelo Nosetto Pablo e.Villagra ezequiel Balducci martín Pinazo Roxana P.eclesia Alejandra Von Wallis Sebastián Villarino Francisco Alaggia marina González Polo Silvina manrique Pablo A.meglioli Julián Rodríguez-Souilla martín mónaco Jimena e.Chaves Ariel medina Ignacio Gasparri eugenio Alvarez Arnesi maría Paula Barral Axel von müller Norberto m.Pahr Josefina Uribe echevarria Pedro Fernández marina morsucci Dardo López Juan manuel Cellini Leandro Alvarez Ignacio Barberis Hernán Colomb Ludmila La manna Sebastián Barbaro Cecilia Blundo Ximena Sirimarco Laura Cavallero Gualberto Zalazar Guillermo martínez Pastur Instituto Nacional de Tecnología Agropecuaria (INTA) Universidad Nacional de la Patagonia Austral (UNPA) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Universidad Nacional de Luján Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Grupo de estudio de Agroecosistemas y Paisajes Rurales (GeAP) Universidad Nacional de Mar del Plata Consejo Nacional de Investigaciones Científicas y Técnicas(CONICET ) CCT San Luis Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Instituto Argentino de Nivología Glaciología y Ciencias Ambientales (IANIGLA) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Universidad Nacional de Cuyo Instituto de Investigaciones en Biodiversidad y medioambiente (INIBIOmA) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Instituto de Investigaciones en energía No Convencional CCT Salta-JujuyConsejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Laboratorio de Recursos Agroforestales Centro Austral de Investigaciones Científicas (CADIC) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Dirección Nacional de Bosques Ministerio de Ambiente y Desarrollo Sostenible de la Nación Instituto de ecología Regional Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET )Universidad Nacional de Tucumán Universidad Nacional de Rosario Instituto de Investigaciones en Ciencias Agrarias de Rosario Centro Científico Tecnológico CONICET Grupo de estudio de Agroecosistemas y Paisajes Rurales (GeAP) Universidad Nacional de Mar del Plata Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET ) Laboratorio de Investigaciones en maderas (LImAD) Universidad Nacional de La Plata (UNLP) Administración de Parques Nacionales (APN) Parque Nacional Los Alerces Centro de estudios Ambientales Integrados (CeAI) Universidad Nacional de la Patagonia San Juan Bosco (UNPASJB) Consejo Nacional de Investigaciones Científicas y Técnicas (CONICET )

Background The nationally determined contribution（NDC） presented by Argentina within the framework of the Paris Agreement is aligned with the decisions made in the context of the United Nations Framework Conven-tion on Climate Change（UNFCCC） on the reduction of emissions derived from deforestation and forest degradation, as well as forest carbon conservation（ReDD+）. In addition, climate change constitutes one of the greatest threats to forest biodiversity and ecosystem services. However, the soil organic carbon（SOC） stocks of native forests have not been incorporated into the Forest Reference emission Levels calculations and for conservation planning under cli-mate variability due to a lack of information. The objectives of this study were:（i） to model SOC stocks to 30 cm of native forests at a national scale using climatic, topographic and vegetation as predictor variables, and（ii） to relate SOC stocks with spatial–temporal remotely sensed indices to determine biodiversity conservation concerns due to threats from high inter-annual climate *** We used 1040 forest soil samples（0–30 cm） to generate spatially explicit estimates of SOC native forests in Argentina at a spatial resolution of approximately 200 m. We selected 52 potential predictive environmental covari-ates, which represent key factors for the spatial distribution of SOC. All covariate maps were uploaded to the Google earth engine cloud-based computing platform for subsequent modelling. To determine the biodiversity threats from high inter-annual climate variability, we employed the spatial–temporal satellite-derived indices based on enhanced Vegetation Index（eVI） and land surface temperature（LST） images from Landsat *** SOC model（0–30 cm depth） prediction accounted for 69% of the variation of this soil property across the whole native forest coverage in Argentina. Total mean SOC stock reached 2.81 Pg C（2.71–2.84 Pg C with a probability of 90%） for a total area of 460,790 km2,

关键词： Soil organic carbon Biodiversity Native forest Climate change mitigation modelling Resilience

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

Finding my way: The role of dirigent proteins in lignin assembly

引用

molecular Plant 2024年第2期17卷 230-232页

作者： Dyoni m.Oliveira Igor Cesarino Department of Plant Biotechnology and Bioinformatics Ghent University9052 GhentBelgium VIB Center for Plant Systems Biology 9052 GhentBelgium Departamento de Botanica Instituto de BiocienciasUniversidade de Sao PauloRua do Matao277Sao Paulo 05508-090Brazil Synthetic and Systems Biology Center InovaUSPAvenida Professor Lucio Martins Rodrigues370SaoPaulo 05508-020Brazil

Lignin emerged around 450 million years ago in early tracheophytes and played a pivotal role in the colonization of terrestrial ecosystems by *** aromatic biopolymer provides mechanical strength to supportive tissues and hydrophobicity to water-transporting vasculature and acts as a physical barrier against herbivores and pathogens(Renault et al.,2019).The deposition of lignin in cell walls for proper cellular functionalization involves several molecular steps,including the tight regulation of tissue-or cell-type-specific expression of lignin biosynthetic genes,the biosynthesis of distinct lignin monomers and their transportation to the apoplast,and the polymerization of monomer radicals to produce tissue-or cell-type-dependent polymers with distinct physico-chemical properties.

关键词： properties. lignin walls

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

Storylines of family medicine Ⅸ:people and places—diverse populations and locations of care

引用

Family medicine and Community Health 2024年第S3期12卷 79-88页

作者： William B Ventres Leslie A Stone emad R Abou-Arab Julio meza David S Buck Jerome W Crowder Jennifer Y C edgoose Alexander Brown ellen J Plumb Amber K Norris Jay J Allen Lauren e Giammar John e Wood Scott m Dickson G Austin Brown Family and Preventive medicine University of Arkansas for Medical Sciences College of MedicineLittle RockArkansasUSA Family medicine University of Michigan Medical SchoolAnn ArborMichiganUSA Family medicine University of California Los AngelesDavid Geffen School of MedicineLos AngelesCaliforniaUSA Community medicine University of HoustonTilman J Fertitta Family College of MedicineHoustonTexasUSA Social and Behavioral Sciences University of HoustonTilman J Fertitta Family College of MedicineHoustonTexasUSA Family medicine and Community Health University of Wisconsin-Madison School of Medicine and Public HealthMadisonWisconsinUSA NH Dartmouth Family medicine Residency ConcordNew HampshireUSA San Francisco VA medical Center San FranciscoCaliforniaUSA Duluth Family medicine Residency Program University of Minnesota Medical School Duluth CampusDuluthMinnesotaUSA UAmS Northeast Regional Campus Family medicine Residency Program JonesboroArkansasUSA Cascades east Family medicine Residency Program Oregon Health&Science University School of MedicineKlamath FallsOregonUSA

Storylines of Family medicine is a 12-part series of thematically linked mini-essays with accompanying illustrations that explore the many dimensions of family medicine as interpreted by individual family physicians and medical educators in the USA and elsewhere around the ***‘Ⅸ:people and places—diverse populations and locations of care’,authors address the following themes:‘LGBTQIA+health in family medicine’,‘A family medicine approach to substance use disorders’,‘Shameless medicine for people experiencing homelessness’,“Difficult”encounters—finding the person behind the patient’,‘Attending to patients with medically unexplained symptoms’,‘making house calls and home visits’,‘Family physicians in the procedure room’,‘Robust rural family medicine’and‘Full-spectrum family medicine’.may readers appreciate the breadth of family medicine in these essays.

关键词： illustration family dimensions

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

Overcoming geographical and socioeconomic limitations in colorectal cancer screening

引用

World Journal of Gastrointestinal Oncology 2024年第5期16卷 1683-1689页

作者： Sofia Rozani Panagis m Lykoudis School of medicine National and Kapodistrian University of AthensAthens 11527Greece Division of Surgery and Interventional Science University College LondonLondon WC1E 6BTUnited Kingdom

Despite colorectal cancer’s(CRC)high global incidence,residents of low-and middle-income countries,as well as low-income minorities in advanced economies have low screening *** studies demonstrate that in these groups higher incidence of CRC is observed,yet screening rates remain low for consistent *** income,low educational background,and lack of awareness in combination with inadequate social security of certain population groups impede access and compliance rates to CRC *** the other hand,despite the global availability of multiple screening approaches(colonoscopy,sigmoidoscopy,faecal occult blood test,faecal immunochemical test,computed tomography-colonography,etc.)with proven diagnostic validity,many low-income countries still lack established screening *** absence of screening guidelines in these countries along with the heterogeneity of guidelines in the rest of the world,demonstrate the need for global measures to tackle this issue *** essential step forward is to develop a global approach that will link specific elements of screening with the incidence and available resources in each country,to ensure the achievement of at least a minimum screening program in low-income *** cheaper,cost-effective techniques,which can be carried out by less specialized healthcare providers,might not be equivalent to endoscopy for CRC screening but seems more realistic for areas with fewer *** has been highlighted as the most pivotal element for the effective implementation of any screening program concerning ***,multiple studies have demonstrated that outreach strategies and community-based educational programs are associated with encouraging outcomes,yet a centrally coordinated expansion of these programs could provide more consistent ***,patient navigator programs,wherever implemented,have increased CRC screening and improved ***,global coordin

关键词： Colorectal cancer Screening Low-and middle-income countries Socioeconomic disparities Cancer

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

modulation of oxidative damage and genotoxicity of biosynthesized zinc oxide nanoparticles via supplementation with modified cinnamaldehyde-loaded chitosan nanoparticles in mice

引用

Food Science and Human Wellness 2024年

作者： mosaad A.Abdel-Wahhab Aziza A.el-Nekeety Asmaa S.Salman Zeinab K.Hamza engy m.Akl Soher e.Aly Wenyi Kang Department of Food Toxicology & Contaminants， National Research Centre Dokki， Cairo， Egypt Genetic and Cytology Department， National Research Centre Dokki， Cairo， Egypt Department of Fats and Oils， National Research Centre Dokki， Cairo， Egypt National R & D Center for edible Fungus Processing Technology， Henan University Joint International Research Laboratory of Food & medicine Resource Function Functional Food engineering Technology Research Center Henan

Synthesis of zinc oxide nanoparticles (Zn-NPs) via green method is an outstanding alternative to conventional/regular methods; however， the safety or toxicity of the biosynthesized ZnO-NPs in vivo is not fully explored. This study was conducted to evaluate the protective efficiency of cinnamaldehyde-loaded chitosan nanoparticles (Cin@CSNPs) against oxidative damage and genotoxicity of zinc oxide nanoparticles (ZnO-NPs) in mice. ZnO-NPs were biosynthesized using the extract of fresh leaves of mentha pulegium L. Cin was extracted from cinnamon essential oil， and was loaded into chitosan nanoparticle (Cin@CSNPs). Both ZnO-NPs， Cin@CSNPs and CSNPs were characterized. The in vitro release of Cin@CSNPs was determined. In the biological study， 6 groups of male Balb/c mice were treated by gavage for 3 weeks as follows， control group， the group received ZnO-NPs (25 mg/kg b.w)， the groups received Cin@CSNPs at low dose (50 mg/kg b.w) or high dose (100 mg/kg b.w)， and the groups received ZnO-NPs plus Cin@CSNPs at the two tested doses. Blood and tissue samples were collected for different biochemical， genetical and histological studies. The particle size of ZnO-NPs， CSNPs， and Cin@CSNPs were (20.78 ± 2.6)， (170.0 ± 3.7)， and (218.23 ± 2.9) nm， and ξ-potential were (32.7 ± 4.6)， (8.32 ± 0.27) and (4.8 ± 0.21)， respectively. ZnO-NPs disturbed the biochemical and oxidative stress indices， AFP， CeA， TNF-α， chromosomal aberrations in somatic and germ cells， and sperm abnormality along with severe pathological changes in the hepatic， renal， and testicular tissues. Cin@CSNPs improved significantly all the parameters tested and the histological picture in a dose-dependent. Therefore， the biosynthesized ZnO-NPs exhibit oxidative damage and genotoxicity， and Cin@CSNPs have potential protective effects against the risks of ZnO-NPs and may be a promising tool to overcome the challenges of using Cin in food and pharmaceuticals applications.

关键词：

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

Current remarks and future directions on the interactions between metabolic dysfunction-associated fatty liver disease and COVID-19

引用

World Journal of Gastroenterology 2024年第11期30卷 1480-1487页

作者： Leonidas Brilakis eirini Theofilogiannakou Panagis m Lykoudis School of medicine National&Kapodistrian University of AthensAthens 11527Greece Division of Surgery&Interventional Science University College LondonLondon WC1E 6BTUnited Kingdom

During the outbreak of the coronavirus disease 2019(COVID-19)pandemic,particular interest rose regarding the interaction between metabolic dysfunctionassociated fatty liver disease(mAFLD)and the COVID-19 *** studies highlighted the fact that individuals with mAFLD had higher probability of severe acute respiratory syndrome coronavirus 2 infection and more severe adverse clinical *** of the proposed mechanisms is the inflammatory response pathway,especially the one involving cytokines,such as interleukin 6,which appeared particularly elevated in those patients and was deemed responsible for additional insult to the already damaged *** should increase our vigilance in terms of early detection,close follow up and early treatment for individuals with mAFLD and COVID-19 *** the direction of early diagnosis,biomarkers such as cytokeratin-18 and scoring systems such as Fibrosis-4 index score are ***-19 is a newly described entity,expected to be of concern for the years to come,and mAFLD is a condition with an ever-increasing *** the interaction between these two entities should be brought into the focus of *** morbidity and mortality of patients with COVID-19 and mAFLD should be the ultimate objective,and the optimal way to achieve this is by designing evidence-based prevention and treatment policies.

关键词： metabolic dysfunction-associated fatty liver disease COVID-19 Liver fibrosis Cytokine storm Drug induced liver injury

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

Descriptors-based machine-learning prediction of cetane number using quantitative structure–property relationship

Energy and AI

引用

energy and AI 2024年第3期17卷 168-178页

作者： Rodolfo S.m.Freitas Xi Jiang School of engineering and materials Science Queen Mary University of LondonMile End RoadLondonE14NSUK

The physicochemical properties of liquid alternative fuels are important but difficult to measure/predict, especially when complex surrogate fuels are concerned. In the present work, machine learning is used to develop quantitative structure–property relationship models. The fuel chemical structure is represented by molecular descriptors, allowing the linking of important features of the fuel composition and key properties of fuel utilization. Feature selection is employed to select the most relevant features that describe the chemical structure of the fuel and several machine learning algorithms are tested to construct interpretable models. The effectiveness of the methodology is demonstrated through the development of accurate and interpretable predictive models for cetane numbers, with a focus on understanding the link between molecular structure and fuel properties. In this context, matrix-based descriptors and descriptors related to the number of atoms in the molecule are directly linked with the cetane number of hydrocarbons. Furthermore, the results showed that molecular connectivity indices play a role in the cetane number for aromatic molecules. Also, the methodology is extended to predict the cetane number of ester and ether molecules, leveraging the design of alternative fuels towards fully sustainable fuel utilization.

关键词： Chemical descriptors Quantitative structure-property relationship machine learning Cetane number Fuel design

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：