检索结果-南通市图书馆

Cyberbullying Sexism Harassment Identification by Metaheurustics-Tuned eXtreme Gradient Boosting

Computers, Materials & Continua 2024年第9期80卷 4997-5027页

作者： Milos Dobrojevic Luka Jovanovic Lepa Babic Miroslav Cajic Tamara Zivkovic Miodrag Zivkovic Suresh Muthusamy Milos Antonijevic Nebojsa Bacanin Technical faculty Singidunum UniversityBelgrade11000Serbia informatics and Computing Singidunum UniversityBelgrade11000Serbia business Economics Singidunum UniversityBelgrade11000Serbia Computing and informatics Sinergija UniversityBijeljina76300Bosnia and Herzegovina Department for Information Systems and Technologies University“Union Nikola Tesla”Cara DusanaBelgrade11080Serbia Department for Computer Science and informatics School of Electrical EngineeringUniversity of BelgradeBelgrade11000Serbia Department of Electrical and Electronics Engineering Kongu Engineering College(Autonomous)PerunduraiErode638060India Department of Mathematics Saveetha School of Engineering(Deemed to be University)SIMATS ThandalamChennai602105India MEU Research Unit Middle East UniversityAmman11831Jordan

Cyberbullying is a form of harassment or bullying that takes place online or through digital devices like smartphones,computers,or *** can occur through various channels,such as social media,text messages,online forums,or gaming *** involves using technology to intentionally harm,harass,or intimidate others and may take different forms,including exclusion,doxing,impersonation,harassment,and ***,due to the rapid growth of malicious internet users,this social phenomenon is becoming more frequent,and there is a huge need to address this ***,the main goal of the research proposed in this manuscript is to tackle this emerging challenge.A dataset of sexist harassment on Twitter,containing tweets about the harassment of people on a sexual basis,for natural language processing(NLP),is used for this *** algorithms are used to transform the text into a meaningful representation of numbers for machine learning(ML)input:Term frequency inverse document frequency(TF-IDF)and Bidirectional encoder representations from transformers(BERT).The well-known eXtreme gradient boosting(XGBoost)ML model is employed to classify whether certain tweets fall into the category of sexual-based harassment or ***,with the goal of reaching better performance,several XGBoost models were devised conducting hyperparameter tuning by *** this purpose,the recently emerging Coyote optimization algorithm(COA)was modified and adjusted to optimize the XGBoost ***,other cutting-edge metaheuristics approach for this challenge were also implemented,and rigid comparative analysis of the captured classification metrics(accuracy,Cohen kappa score,precision,recall,and F1-score)was ***,the best-generated model was interpreted by Shapley additive explanations(SHAP),and useful insights were gained about the behavioral patterns of people who perform social harassment.

关键词： Coyote optimization algorithm NLP TF-IDF BERT XGBoost online harassment and cyberbullying metaheuristics

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

Financial inclusion and carbon emissions in Asia:Implications for environmental sustainability

引用

Economic and Political Studies 2024年第1期12卷 88-104页

作者： Shahzad Hussain Tanveer Ahmad Sabeeh Ullah Ajid Ur Rehmand Syed Jawad Hussain Shahzad Department of business Administration Rawalpindi Women UniversityRawalpindiPakistan Institute of business Studies Kohat University of Science and TechnologyKohatPakistan Institute of business and Management Sciences Faculty of Management and Computer SciencesThe University of AgriculturePeshawarPakistan NUST business School National University of Sciences and TechnologyIslamabadPakistan Finance Control and Law DepartmentMontpellier Business SchoolMontpellierFrance

This study explores how carbon emissions are affected by financial *** a balanced panel data set of 26 Asian countries,we compute a composite index,through the principal component analysis(PCA)technique,of financial inclusion based on a set of attributes related to financial *** main analysis also delineates the subsamples of developed and developing Asian *** results reveal a long(short)-run positive(negative)impact of financial inclusion on carbon emissions across the Asian *** finding is also true for the developed country subsample,implying nonlinearity in shortand long-run *** the developing countries,a more pronounced long-run positive impact compared to developed countries is ***,the pairwise causality test results indicate the existence of bi-directional causality between financial inclusion and carbon *** findings have important policy implications,especially in the context of the strategic integration of financial inclusion and climate change strategies.

关键词： Financial inclusion CO2 emissions climate change sustainable development Asian countries

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

Economic Growth Performance and Economic Activities in Kosovo During the Covid-19 Pandemic in Kosovo

引用

Management Studies 2024年第3期12卷 172-181页

作者： Agim Berisha business College Faculty of EconomicsPristinaKosovo

The paper addresses economic growth and developments of economic activities during the Covid-19 crisis in *** the last war,Kosovo continues to remain among the countries with a low level of development and a high rate of *** low level of economic growth and the high rate of unemployment remain among the main economic challenges for *** importance of the paper consists in addressing economic issues and processes including developments in economic activities during the Covid-19 crisis in *** was affected by Pandemia Covid-19 starting from March ***,the Covid-19 crisis has had effects on economic processes,affecting the activity of various sectors of the *** main purpose of this paper is to analyze the performance of economic growth and economic activities during the Covid-19 crisis in *** order to achieve the objectives,the analysis method is mainly used,tabular and graphic separately,comparative method,analyzing in dynamics the issue related to economic activities in the Republic of *** this study,the results and recommendations given are considered to be considered by policy makers in the Republic of Kosovo.

关键词： economic growth economic activities economic processes Covid-19

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

SwinVid:Enhancing Video Object Detection Using Swin Transformer

引用

Computer Systems Science & Engineering 2024年第2期48卷 305-320页

作者： Abdelrahman Maharek Amr Abozeid Rasha Orban Kamal ElDahshan Computer Science Department Faculty of Artificial Intelligence and InformaticsBenhaEgypt Mathematics Department Faculty of SciencesAl-Azhar UniversityCairoEgypt Department of Computer Science College of Science and Arts in QurayyatJouf UniversitySakakaSaudi Arabia

What causes object detection in video to be less accurate than it is in still images?Because some video frames have degraded in appearance from fast movement,out-of-focus camera shots,and changes in *** reasons have made video object detection(VID)a growing area of research in recent *** object detection can be used for various healthcare applications,such as detecting and tracking tumors in medical imaging,monitoring the movement of patients in hospitals and long-term care facilities,and analyzing videos of surgeries to improve technique and ***,it can be used in telemedicine to help diagnose and monitor patients *** VID techniques are based on recurrent neural networks or optical flow for feature aggregation to produce reliable features which can be used for *** of those methods aggregate features on the full-sequence level or from nearby *** create feature maps,existing VID techniques frequently use Convolutional Neural Networks(CNNs)as the backbone *** the other hand,Vision Transformers have outperformed CNNs in various vision tasks,including object detection in still images and image *** propose in this research to use Swin-Transformer,a state-of-the-art Vision Transformer,as an alternative to CNN-based backbone networks for object detection in *** proposed architecture enhances the accuracy of existing VID *** ImageNet VID and EPIC KITCHENS datasets are used to evaluate the suggested *** have demonstrated that our proposed method is efficient by achieving 84.3%mean average precision(mAP)on ImageNet VID using less memory in comparison to other leading VID *** source code is available on the website https://***/amaharek/SwinVid.

关键词： Video object detection vision transformers convolutional neural networks 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

No more free lunch:The increasing popularity of machine learning and financial market efficiency

引用

Economic and Political Studies 2024年第1期12卷 34-57页

作者： Jian Feng Xin Liu faculty of business and Economics The University of Hong KongHong Kong SARChina School of Finance Renmin University of ChinaBeijingChina

In this paper,we show that the increasing popularity of machine learning improves market *** analysing the performance of a set of popular machine learning-based investment strategies,we find that profits from these strategies experience significant declines since the wide adoption of machine learning techniques,especially for profits based on the more preferred method of neural *** declines mainly come from long *** the‘machine learning’Google search index as a proxy for machine learning-based trading intensity,we find that returns from the neural networks-based long–short and long-only strategies are weaker following high levels of machine learning intensity,while no relation is found between machine learning intensity and the short-only neural networks-based strategy.

关键词： Machine learning market efficiency mispricing neural networks arbitraging activities

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

Response of Indonesian mineral supply to global renewable energy generation:Analysis based on gravity model approach

引用

Geoscience Frontiers 2024年第4期15卷 383-396页

作者： Md.Monirul Islam Kazi Sohag Suleiman O.Mamman Heyvon Herdhayinta Graduate School of Economics and Management Ural Federal UniversityYekaterinburgRussia Bangladesh Institute of Governance and Management(BIGM) University of DhakaBangladesh Department of Accounting Faculty of Economics and BusinessUniversitas Gadjah MadaIndonesia

The captivating surge of energy transitions in the major industrialized nations has elevated the global demand for critical *** demand pattern has enabled mineral-abundant emerging economies like Indonesia to enter the international market by exporting mineral ***,we investigate the Indonesian mineral export supply's response to the renewable energy production of the 18 clean energy-generating countries,considering crude oil and mineral prices,exchange rates,and economic growth of the resource and importer countries from 1990 to *** doing so,we apply the Poisson Pseudo-maximum Likelihood(PPML)approach to measuring the panel gravity model for mineral exports in *** a result,we observe a significant response of Indonesia's mineral export supply to the renewable energy generation of the 18 mineral importing ***,mineral and crude oil prices are insignificant,whereas the importer countries'exchange rates and income growth positively influence Indonesia's mineral export ***,Indonesia's income factor negatively affects its mineral export ***,we validate our results using an alternative estimator,the Driscoll-Kraay robust standard error estimation ***,our findings suggest implementing Indonesia's existing mineral policy to produce finished mineral goods to materialize the worldwide vision of energy transitions toward a crossroad of net-zero emissions by the middle of the current century.

关键词： Mineral export supply Energy transformation Gravity model PPML approach Indonesia Renewable energy-producing countries

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

Does nuclear energy reduce carbon emissions despite using fuels and chemicals?Transition to clean energy and finance for green solutions

引用

Geoscience Frontiers 2024年第4期15卷 359-371页

作者： Muhammad Imran Khalid Zaman Abdelmohsen A.Nassani Gheorghița Dinca˘ Haroon ur Rashid Khan Mohamed Haffar Department of Economics The University of HaripurHaripur Khyber Pakhtunkhwa 22620Pakistan Department of Management College of Business AdministrationKing Saud UniversityP.O.Box 71115Riyadh 11587Saudi Arabia Finance and Accounting Department Transilvania University of BrașovRomania faculty of business The University of Wollongong in DubaiDubai 20183United Arab Emirates Department of Management Birmingham Business SchoolUniversity of BirminghamBirminghamUnited Kingdom

Green power conversion is the shift away from traditional fuels towards clean energy sources such as nuclear power plants,hydroelectric dams,wind farms,and solar *** research examines the impact of clean energy demand and green financing on reducing carbon emissions in 29 economies in Europe and Asia from 2007 to *** study used a two-step differenced GMM estimator for the available data set spanning 2007 to *** study found that rising demand for nuclear power helps to achieve a carbon-neutral agenda,but insufficient funding for renewable energy leads to higher carbon *** research suggests increasing investment in nuclear energy and green financing can improve regional environmental *** study found a causal link between fuel imports,nuclear power and regional *** also determined that fuel imports,chemical use,green financing and the need for nuclear energy will likely impact regional environmental *** research recommends allocating more resources toward innovation to boost energy efficiency and expanding investment in renewable and nuclear energy production industries via green *** study also highlights the need to encourage the development of renewable energy sources to cut carbon emissions and establish a sustainable society.

关键词： Nuclear energy Renewable energy Green financing Fuel imports Chemical use Differenced GMM estimator

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

Hydrodynamic function and spring constant calibration of FluidFM micropipette cantilevers

引用

Microsystems & Nanoengineering 2024年第1期10卷 277-286页

作者： Attila Bonyár Ágoston G.Nagy Hans Gunstheimer Gotthold Fläschner Robert Horvath Department of Electronics Technology Faculty of Electrical Engineering and InformaticsBudapest University of Technology and EconomicsBudapestHungary Nanobiosensorics Laboratory Institute of Technical Physics and Materials ScienceCentre for Energy ResearchHUN-RENBudapestHungary Nanosurf AG Gräubernstrasse 12CH-4410 LiestalSwitzerland

Fluidic force microscopy(FluidFM)fuses the force sensitivity of atomic force microscopy with the manipulation capabilities of microfluidics by using microfabricated cantilevers with embedded fluidic *** innovation initiated new research and development directions in biology,biophysics,and material *** acquire reliable and reproducible data,the calibration of the force sensor is ***,the hollow FluidFM cantilevers contain a row of parallel pillars inside a rectangular *** precise spring constant calibration of the internally structured cantilever is far from trivial,and existing methods generally assume simplifications that are not applicable to these special types of *** addition,the Sader method,which is currently implemented by the FluidFM community,relies on the precise measurement of the quality factor,which renders the calibration of the spring constant sensitive to *** this study,the hydrodynamic function of these special types of hollow cantilevers was experimentally determined with different *** on the hydrodynamic function,a novel spring constant calibration method was adapted,which relied only on the two resonance frequencies of the cantilever,measured in air and in a *** on these results,our proposed method can be successfully used for the reliable,noise-free calibration of hollow FluidFM cantilevers.

关键词： spring cantilever function

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

Data-Driven Decision-Making for Bank TargetMarketing Using Supervised Learning Classifiers on Imbalanced Big Data

引用

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

Do investments in green energy,energy efficiency,and nuclear energy R&D improve the load capacity factor?An augmented ARDL approach

引用

Geoscience Frontiers 2024年第4期15卷 372-382页

作者： Xin Jin Zahoor Ahmed Ugur Korkut Pata Mustafa Tevfik Kartal Sinan Erdogan School of business Guilin Tourism UniversityGuilin 541006PR China Department of business Administration Faculty of EconomicsAdministrative and Social SciencesBahçesehir Cyprus UniversityNicosiaTurkey Department of Economic&Data Sciences New Uzbekistan University54 Mustaqillik Ave.Tashkent100007Uzbekistan Osmaniye Korkut Ata University Faculty of Economics and Administrative SciencesDepartment of Economics80000 MerkezOsmaniyeTurkey Department of Banking and Finance European University of LefkeLefkeNorthern CyprusTR-10 MersinTürkiye Adnan Kassar School of business Lebanese American UniversityBeirutLebanon Department of Economics and Management Khazar UniversityBakuAzerbaijan Hatay Mustafa Kemal University Faculty of Economics and Administrative SciencesHatayTurkey

Renewable energy,energy efficiency,and nuclear energy research and development(RER,EER,and NER)budgets are immensely important to fulfill sustainable development goals 7,9,and 13,by accelerating energy innovation,energy transition,and climate *** literature on the drivers of the load capacity factor(LCF),a recently developed ecological quality measure,is mounting;however,the roles of energy investments in the LCF are largely ***,this study assesses the impacts of RER,EER,NER,and financial globalization(FIG)on the LCF using data from 1974 to 2018 for *** and reliable time series tests(Augmented ARDL,DOLS,and Fourier causality)are adopted to analyze cointegration,long-run impacts,and causal *** outcomes unveil that both green energy and energy efficiency R&D promote the LCF by enhancing ecological ***,the positive impact of NER on the LCF is found to be weaker than the impacts of RER and *** curbs ecological degradation by expanding the ***,the U-shaped connection between economic growth(ECG)and the LCF confirms the load capacity ***,policymakers should focus on RER and EER to preserve the environment and promote sustainable growth.

关键词： Green Energy R&D Energy Efficiency R&D Nuclear Energy R&D Financial Globalization LCF

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：