检索结果-内蒙古大学图书馆

An Initial Study of Machine Learning Underspecification Using Feature Attribution Explainable AI Algorithms: A COVID-19 Virus Transmission Case Study 18th

An Initial Study of Machine Learning Underspecification Usin...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Hinns, James Fan, Xiuyi Liu, Siyuan Raghava Reddy Kovvuri, Veera Yalcin, Mehmet Orcun Roggenbach, Markus Computer Science Department Swansea University Swansea United Kingdom Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands

ISBN: (纸本)9783030891879

From a dataset, one can construct different machine learning (ML) models with different parameters and/or inductive biases. Although these models give similar prediction performances when tested on data that are currently available, they may not generalise equally well on unseen data. The existence of multiple equally performing models exhibits underspecification of the ML pipeline used for producing such models. In this work, we propose identifying underspecification using feature attribution algorithms developed in Explainable AI. Our hypothesis is: by studying the range of explanations produced by ML models, one can identify underspecification. We validate this by computing explanations using the Shapley additive explainer and then measuring statistical correlations between them. We experiment our approach on multiple datasets drawn from the literature, and in a COVID-19 virus transmission case study. © 2021, Springer Nature Switzerland AG.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

A computational framework for Carreau nanomaterial induced by stretchy regime considering Brownian diffusion, viscous dissipation, ferromagnetism and thermophoresis

引用

Partial Differential Equations in Applied Mathematics 2025年 13卷

作者： Hussain, Iftikhar Khan, Waqar Azeem Tabrez, Muhammad Waqas, M. Ibrahim, Talib K. Saidani, Taoufik Kausar, M.S. Zamri, Nurnadiah Abdullaeva, Barno Garalleh, Hakim AL Department of Mathematics Mohi-ud-Din Islamic University Nerian Sharif Jammu and Kashmir Azad 12010 Pakistan School of Mathematics and Statistics Beijing Institute of Technology Beijing 100081 China NUTECH School of Applied Sciences and Humanities National University of Technology Islamabad 44000 Pakistan Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Besut Campus Terengganu Besut 22200 Malaysia Department of Computer Science and Mathematics Lebanese American University Beirut Lebanon Department of Petroleum Engineering College of Engineering Knowledge University Erbil 44001 Iraq Department of Petroleum Engineering Al-Kitab University Altun Kupri Iraq Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Faculty of Informatics and Computing Universiti Sultan Zainal Abidin (Kampus Gong Badak) Terengganu Kuala Terengganu 21300 Malaysia Department of Mathematics and Information Technologies Vice-Rector for Scientific Affairs Tashkent State Pedagogical University Tashkent Uzbekistan Department of Mathematical Science College of Engineering University of Business and Technology Jeddah 21361 Saudi Arabia

In recent decade, the research in nanotechnology brought the idea of nanofluids which are highly conducting materials. Some important applications of nanofluids are justified in pharmaceutical industry, coolants in vehicles engine, preparation process of various medicines for treatment of fatal diseases like cancer, aircraft industry, latest heat exchangers etc. The ferro particles are special class of nanomaterial which attract variety of interest from the researchers. The objective of current research is to perform the investigation for heat and mass transfer subject to Carreau nanofluid to observe the enhancement of heat transmission phenomena. The induction of magnetic dipole has been observed for thermal transport phenomenon. The flow is causing by stretched surface. A simplified system is obtained by utilizing the dimensionless variables. Physical interpretation of results have been presented. Result showed that temperature profile in presence of ferrofluid fluid boosts up with escalation in thermophoresis parameter, while opposite behavior is noted for power law index. The concentration of ferrofluid showing declining behavior for Schmidt numbers and rises for thermophoresis parameter. © 2024

关键词： Carreau ferrofluid Heat and mass transfer Magnetic dipole Numerical solution

来源：评论

学校读者我要写书评

暂无评论

New physical structures and patterns to the optical solutions of the nonlinear Schrödinger equation with a higher dimension

引用

Communications in Theoretical Physics 2023年第8期75卷 25-41页

作者： Karmina K Ali Abdullahi Yusuf Marwan Alquran Sibel Tarla Department of Mathematics Faculty of ScienceUniversity of ZakhoZakhoIraq Department of Computer Science College of ScienceKnowledge UniversityErbil 44001Iraq Department of Computer Engineering Biruni UniversityIstanbulTurkey Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Department of Mathematics Near East University TRNCMersin 10Nicosia 99138Turkey Department of Mathematics and Statistics Jordan University of Science&TechnologyIrbid 22110Jordan Department of Mathematics Faculty of ScienceFirat UniversityElazigTurkey

It is commonly recognized that,despite current analytical approaches,many physical aspects of nonlinear models remain *** is critical to build more efficient integration methods to design and construct numerous other unknown solutions and physical attributes for the nonlinear models,as well as for the benefit of the largest audience *** achieve this goal,we propose a new extended unified auxiliary equation technique,a brand-new analytical method for solving nonlinear partial differential *** proposed method is applied to the nonlinear Schrödinger equation with a higher dimension in the anomalous *** interesting solutions have been ***,to shed more light on the features of the obtained solutions,the figures for some obtained solutions are *** propagation characteristics of the generated solutions are *** results show that the proper physical quantities and nonlinear wave qualities are connected to the parameter *** is worth noting that the new method is very effective and efficient,and it may be applied in the realisation of novel solutions.

关键词： exact solutions nonlinear Schrodinger equation new extended unified auxiliary equation method Jacobi elliptic functions

来源：评论

学校读者我要写书评

暂无评论

Stream-dashboard: A framework for mining, tracking and validating clusters in a data stream

Stream-dashboard: A framework for mining, tracking and valid...

引用

1st International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications, BigMine-12 - Held in Conjunction with SIGKDD Conference

作者： Hawwash, Basheer Nasraoui, Olfa Department of Computer Engineering and Computer Science Knowledge Discovery and Web Mining Lab University of Louisville Louisville KY United States

ISBN: (纸本)9781450315470

Clustering data streams is a challenging problem that has received significant attention in the recent decade. In this paper, we address the hitherto inadequately addressed challenge of managing the output of stream clustering. This task comprises the continuous cluster model validation, monitoring, trend and change detection, and summarization of the cluster mining output. For this purpose, we propose a complete framework to mine, track and validate the clusters in a data stream. The proposed framework keeps track of each discovered cluster model of the stream through time, while quantifying, modeling and summarizing the cluster evolution trends, and storing a summary of the cluster models and the evolution trends only at milestones corresponding to the occurrence of significant changes. Our experiments demonstrate the accuracy of the proposed framework in tracking cluster evolution over time, while generating a concise summary of the evolution trends over the lifetime of the stream. Copyright © 2012 ACM.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Seed-Based Inter-Domain Supervised Framework to Cluster Mixed Data Types

A Seed-Based Inter-Domain Supervised Framework to Cluster Mi...

引用

4th International Joint Conference on knowledge Discovery, knowledge engineering and knowledge Management, IC3K 2012

作者： Abdullin, Artur Nasraoui, Olfa Knowledge Discovery and Web Mining Lab Department of Computer Engineering and Computer Science University of Louisville Louisville KY United States

ISBN: (纸本)9783642541049

We propose a Seed-based Inter-Domain Supervised (IDS) framework to handle possibly diverse data formats, mixed-type attributes and different sources of data. This approach can be used for combining diverse representations of the data, in particular where data comes from different sources, some of which may be unreliable or uncertain, or for exploiting optional external concept set labels to guide the clustering of the main data set in its original domain. Unlike semi-supervised clustering, our approach exploits the synergy between different domains instead of external labels. Also ensemble clustering and our proposed IDS clustering are different mechanisms with distinct goals: (i) the former aims to combine independent clustering results from many independent subsets sampled from the same data set or from different clustering algorithm results on the same data set, into one consensus, (ii) while the latter (IDS) aims to exploit a mutual synergy between different data domains or sources to guide the clustering in these different domains or sources. Our preliminary results in clustering data with mixed numerical and categorical attributes show that the proposed IDS framework gives better clustering results in the categorical domain. Thus the seeds or the constraints obtained from clustering the numerical domain give an additional knowledge to the categorical clustering algorithm. Additional results show that our approach outperforms clustering either domain on its own or clustering both domains converted to the same target domain. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Adding Semantics to Social Software engineering: (Re-)Using Ontologies in a Community-oriented Requirements engineering Environment

Adding Semantics to Social Software Engineering: (Re-)Using ...

引用

2010 Workshopband (inkl.Doktorandensymposium), Fachtagung des GI-Fachbereichs Softwaretechnik, Software engineering 2010 - 2010 Workshop (incl. Doctoral Symposium), Conference of the GI Division on Software engineering, Software engineering 2010

作者： Lohmann, Steffen Riechert, Thomas DEI Laboratory Computer Science Department Carlos III University of Madrid Spain Agile Knowledge Engineering and Semantic Web Department of Computer Science University of Leipzig Germany

ISBN: (纸本)9783885792543

Social Software is typically characterized by low formal semantics and weakly structured contents. Software engineering, in contrast, requires at least a certain degree of formality and structure. In order to face these opposing demands, we propose to ground Social Software engineering on concepts and technologies from the Semantic Web. In particular, we present a Semantic Wiki based approach in this paper that uses well-known ontologies to represent activities and artifacts that emerge in an online environment for community-oriented Requirements engineering. We illustrate the benefits of reusing these domain-independent ontologies and show how they can fruitfully be combined and interlinked in one common upper ontology. © 2010 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Developing active learning experiences for adaptive personalised elearning

引用

3rd International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, AH 2004

作者： Dagger, Declan Wade, Vincent P. Conlan, Owen Knowledge and Data Engineering Group Department of Computer Science Trinity College Dublin Ireland

ISBN: (纸本)3540228950

Developing adaptive, rich-media, eLearning courses tends to be a complex, highly-expensive and time-consuming task. A typical adaptive eLearning course will involve a multi-skilled development team of technologists, instructional developers, subject matter experts and integrators. Even where the adaptive course attempts to reuse existing digital resources, considerable effort is still required in the integration of the adaptive techniques and curriculum. This paper tackles the fundamental challenges of extending adaptivity across not only content (based on prior knowledge, goals, learning styles, connectivity etc.) but also across adaptive pedagogic approaches, communication tools and a range of e-activity types which are required for effective, deeper learning. This paper identifies key activities and requirements for adaptive course construction and presents the design of a tool to allow the rapid construction of such courses. The paper outlines the usage of this tool in the form of a case study and presents its research findings. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Modified VGG16 Learning Model for Classifying Skin Cancer Lesions

Evaluation of Modified VGG16 Learning Model for Classifying ...

引用

2023 IEEE International Conference on Network, Multimedia and Information Technology, NMITCON 2023

作者： Naser Alaubaidy, Mateen Ismail Abdullah, Abdulqadir Mousa Alwan, Fatimah College of Engineering and Computer Science Lebanese French University Department of Information Technology Kurdistan Region Erbil Iraq College of Engineering Knowledge University Department of Computer Engineering Kurdistan Region Erbil Iraq College of Engineering and Computer Science Bayan University Department of Computer Science Kurdistan Region Erbil Iraq

ISBN: (纸本)9798350300826

One of the most serious types of cancer that is prevalent around the world is skin cancer. It is widely known that skin cancer characterized by uncontrolled cell and tissue growth, presenting a challenge in detecting or diagnosis skin cancer in early stage. Accurate segmentation of skin lesions in dermatoscopic images holds great importance in diagnosis and assessment of skin cancer. Thus, Fast, precise, and real-time algorithms are essential in effectively detecting skin cancer to aid physicians in their treatment decision-making process. In this paper, we evaluated the performance of the modified VGG16 with using three common convolutional neural networks(CNN) in detecting the skin cancer with dermoscopic skin lesions images. In this study, the Kaggle dataset is used to classify skin cancer images. To classify skin lesions, the model modified VGG16 is compared to the most common models such as VGG16, mobileNetV2 and Inception ResNet v2. All models are trained on the same dataset and their performance is evaluated using metrics such as: accuracy, precision, F1-score, and recall. Finally, The comparative analysis revealed a promising performance of the modified VGG16 model in detecting multiclass skin cancer, which highlights its promising potential in classifying. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Strategies Supported by Blockchain Technology: Open Problems and Challenges

Supply Chain Strategies Supported by Blockchain Technology: ...

引用

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Rana, Sumit Kumar Rana, Arun Kumar Naz, Sardar M N Islam Singh, Ashutosh Kumar Bhushan, Bharat Panipat Institute of Engineering and Technology Department of Computer Science and Engineering Haryana Panipat India Galgotia College of Engineering Knowledge Park I Department of Computer Science Engineering Uttar Pradesh Greater Noida201310 India ISILC Victoria University Melbourne Australia Kurukshetra University NIT Department of Computer Applications Kurukshetra India Sharda Universi Knowledge Park III Department of Computer Science Engineering Greater Noida201310 India

ISBN: (纸本)9798350396485

The most prevalent issue in the supply chain ecosystem is introducing transparency to the system. Another issue is fostering trust among various stakeholders to support successful process execution. Depending on the domain and the stakeholders, the supply chain process may change. Thus, solving the issue is challenging. Blockchain technology, sometimes referred to as distributed ledger technology, is beneficial in many ways in a variety of industries, including finance and healthcare. Blockchain based model can resolve the issues of traditional supply chain ecosystem. It creates a decentralized and transparent system where every decision is taken with the help of consensus of the associated stakeholders. This supports an immutable ledger so unauthorized modification is not supported. In this article, we address the issues that the supply chain ecosystem faces as well as the benefits of blockchain technology in resolving these issues. As well as some of the remaining challenges and opportunities, other aspects of blockchain technology are explored that will enable it flourish in future supply chains. © 2023 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

A data science approach to flagging non-retention in engineering enrollment data

A data science approach to flagging non-retention in enginee...

引用

2020 ASEE Virtual Annual Conference, ASEE 2020

作者： Boujelbene, Mariem Damak, Khalil Sener, Asuman Cagla Acun Hieb, Jeffrey Lloyd Bego, Campbell R. Ralston, Patricia A. Nasraoui, Olfa Knowledge Discovery and Web Mining Lab Department of Computer Science and Computer Engineering University of Louisville United States Department of Engineering Fundamentals University of Louisville United States

This research paper discusses a new, data-driven metric for measuring retention. First and second year retention and retention rates are now well established as metrics in the engineering education research landscape, with many research studies exploring the impact of individual performance, noncognitive, and preparation characteristics on retention in engineering. Researchers at the University of Louisville, a large Research Institution in the Midwest, have compiled survey results and enrollment data for students in the engineering college since 2010, with the intention of conducting retrospective studies of engineering retention using this data. Using degree earned in six years or less to label students as retained makes over half the dataset unusable. First and second year retention are options, but these can have both false positives and false negatives. Using a data science pipeline, we analyzed the number of consecutive non-enrolled terms, referred to as enrollment gaps, and found that the best short-term criteria is three consecutive semesters not enrolled in engineering. With this criterion, we can reliably label a given student as not-retained. The proposed retention threshold approach has the following advantages: It does not rely on the requirement of earning a degree in engineering and could be applied across a variety of fields of study, it is not based on enrollment at a fixed point in time, and it can be used as the data set continues to grow. Most importantly, while other common heuristics use grades, success in certain consecutive courses, or even demographics;our method only uses enrollment (and hence enrollment gap) data. This is a significant advantage given that the enrollment data is always available;whereas other commonly used feature heuristics for retention determination are not always available or may only apply to subsets of students. © American Society for engineering Education 2020.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

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

请选择保存的检索档案：

请选择收藏分类：

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

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

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：