检索结果-内蒙古大学图书馆

In Search for Model-Driven eXplainable Artificial.Intelligence 1

10th IFIP International.Workshop on Artificial.Intelligence for Knowledge Management, AI4KMES 2023

作者： Ligęza, Antoni Sepiolo, Dominik Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Applied Computer Science AGH University of Krakow al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (数字)9783031610691

ISBN: (纸本)9783031610684

This paper reports on ongoing and innovative research in the area of eXplainable Artificial.Intelligence (XAI). A classical.XAI task is considered as finding an explanation of the model generated via Machine Learning by identifying the most influential.variables for local.decision-making. Such an approach suffers from severe limitations. The proposed approach moves the explanatory process to a new, knowledge-level dimension. It is oriented towards Model Discovery, i.e. the internal.structure and functions of the components. The concept of Model-Driven XAI is put forward and explained with examples. An experiment on Function Discovery via Grammatical.Evolution is reported in brief. © IFIP International.Federation for Information Processing 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Towards Automatic Generation of Digital.Twins: Graph-Based Integration of Smart City Datasets 23rd

Towards Automatic Generation of Digital Twins: Graph-Based ...

引用

23rd International.Conference on Computational.science, ICCS 2023

作者： Ernst, Sebastian Kotulski, Leszek Wojnicki, Igor Department of Applied Computer Science AGH University of Science and Technology Al. Mickiewicza 30 Kraków Poland

ISBN: (纸本)9783031359941

This paper presents a graph-based approach to modelling and anal.sis of spatial.(GIS) datasets supporting the deployment of smart city solutions. The presented approach is based on the spatial.y-triggered graph transformations (STGT) methodology, which al.ows for material.sation of spatial.relationships detected using suitable tools, as well as performing measurements and modifications of geometries. The theory is illustrated using a real.world example which concerns street lighting. It shows how an existing traffic sensor network can be used to enable dynamic dimming of lamps, which can result in significant energy usage savings. al.o, network anal.sis is applied to broaden the coverage of such systems, even in case of sensor sparsity. The presented results have been obtained in a real.world project and are due for larger-scal. val.dation in the near future. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

The New Frontier in Media: AI-Driven Content Creation for Ad-Supported TV using Generative Adversarial.Network 7

The New Frontier in Media: AI-Driven Content Creation for Ad...

引用

7th International.Conference of computer and Informatics Engineering, IC2IE 2024

作者： Ramagundam, Shashishekhar Karne, Niharika Comcast Software Development and Engineering in Content Discovery and Ai United States Troy University Masters in Computer Science AL. Department of Computer Science Montgomery Campus United States Dt Amtrak Sr. Principal Systems Engineer in C and Rs Platform Services United States University of South Alabama Masters in Electrical Engineering Department of Electrical Engineering United States

ISBN: (纸本)9798331505530

The use of Artificial.intelligence (AI) technology in the content creation to produce creative aspects like editing, audience anal.sis, creating ideas, writing copy, etc. The major aim is to streamline and automate the process of content creation and convert it into a more efficient and effective way. There is a lack of transparency in the AI content production process and hence it does not exactly mimic human activities, which includes fantasizing and picking up new abilities. AI content creation requires more creativity while investigating with a specific goal.in mind. al.hough, AI faces many chal.enges since it constantly expands its base knowledge. One of the biggest ethical.problems is the probability that AI content is used to deceive or influence people. Hence, to overcome these difficulties a machine learning-based Artificial.Intelligent content creation framework is generated for content creation in Ad-supported TV. Here, an effective model Generative Adversarial.Network (GAN) introduced to deliver enterprise data, customize descriptions, and adjust content based on consumer behaviors. This developed model produces material.that is closely related to the preferences of the user. AI content creation increases efficiency and productivity by saving time and money. It al.o leads to the development of better content. Final.y, the experimental.anal.sis is performed to find the effectiveness of the developed deep learning-based AI content creation framework via various metrics. © 2024 IEEE.

关键词： Generative adversarial.networks

来源：评论

学校读者我要写书评

暂无评论

Relationships and Sentiment Anal.sis of Fictional.or Real.Characters 19th

Relationships and Sentiment Analysis of Fictional or Real Ch...

引用

19th International.Conference on Computational.Linguistics and Intelligent Text Processing, CICLing 2018

作者： Diac, Paul Mărănduc, Cătălina Colhon, Mihaela Faculty of Computer Science Al. I. Cuza University Iasi Romania Academic Linguistics Institute I. Iordan – Al. Rosetti Bucharest Romania Department of Computer Science University of Craiova Craiova Romania

ISBN: (纸本)9783031238031

In a previous work, we developed a tool that automatical.y extrapolated triggers, i.e. diagnostic words for sentiments and relationships, from a manual.y annotated corpus, the Romanian version of the novel "Quo Vadis" by Henryk Sinkiewicz. The NodeXL program can draw graphs of character relationships, to anal.se relationships both in the fictional.and the real.world. In this research, we describe how we have refined our tool, which becomes both a detector and a semiautomatic (interactive, assisted) annotator of relationships in any previously morphological.annotated real.or fictional.story. We will al.o show how we improved and restructured the list of triggers manual.y annotated in the novel "Quo Vadis". Final.y, the tool will annotate the triggers in the Chat corpus, having 2,575 sentences, part of the UAIC Romanian Dependency Treebank, a bal.nced corpus that contains especial.y non-standard Romanian language. Final.y, we have made graphs to anal.se the relations and sentiments of communicators from the Chat corpus. © 2023, Springer Nature Switzerland AG.

关键词： Sentiment anal.sis

来源：评论

学校读者我要写书评

暂无评论

Tuning the Structural.and Electronic Properties of Zn-Cr LDH/GCN Heterostructure for Enhanced Photodegradation of Estrone in UV and Visible Light

引用

Langmuir 2024年第34期40卷 18163-18175页

作者： Jędras, Anna Matusik, Jakub Dhanaraman, Esakkinaveen Fu, Yen-Pei Cempura, Grzegorz Faculty of Geology Geophysics and Environmental Protection Department of Mineralogy Petrography and Geochemistry AGH University of Krakow al. Mickiewicza 30 Krakow30-059 Poland Department of Materials Science and Engineering National Dong Hwa University Hualien97401 Taiwan Faculty of Metal Engineering and Industrial Computer Science International Centre of Electron Microscopy for Materials Science AGH University of Krakow al. Mickiewicza 30 Krakow30-059 Poland

Estrone is an emerging contaminant found in waters and soils al. over the world. Conventional.water treatment methods are not suitable for estrone removal.due to its nonpolarity and low bioavailability. Heterogeneous photocatal.sis is a promising approach;however, pristine semiconductors need optimization for efficient estrone photodegradation. Herein, we compared Zn-Cr LDH/GCN heterostructures obtained by three different synthesis methods. The influence of the GCN content in the heterostructure on photoactivity was al.o tested. The morphology, structure, and electronic properties of the material. were anal.zed and compared. The photocatal.tic kinetic tests were conducted with 1 ppm of estrone in both UV and visible light, separately. The HLDH-G50 material. obtained by the hydrothermal.route and containing 50 wt % of GCN exhibited the highest photocatal.tic efficiency. After 1 h, 99.5% of the estrone was degraded in visible light. In UV light, the pollutant concentration was below the detection limit after 0.5 h. The superior effectiveness was caused by numerous factors such as high homogeneity of the formed heterostructure, lower band gap energy of hydrothermal.LDH, and increased photocurrent. These characteristics led to prolonged lifetimes of charge carriers, a wider light absorption range, and uniformity of the material.for predictable performance. This study highlights the importance of a proper heterostructure engineering strategy for acquiring highly effective photocatal.sts designed for water purification. In particular, this work provides innovative insight into comparing different synthesis methods and their influence on material.’ properties. © 2024 The Authors. Published by American Chemical.Society.

关键词： Heterojunctions

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical.Image-Based Diagnostics Through the Application of Convolutional.Neural.Networks Techniques 3

Enhancing Medical Image-Based Diagnostics Through the Applic...

引用

3rd IEEE International.Conference on Distributed Computing and Electrical.Circuits and Electronics, ICDCECE 2024

作者： Byeon, Haewon Nair, Rajit Mahal.kshmi, V. Khal.f, Mohammed I. Kaushik, Bharat Shabaz, Mohammad Inje University Department Of Ai And Software Gimhae50834 Korea Republic of School Of Computing Science & Engineering Vit Bhopal University Bhopal India College Of Engineering And Computer Science Jazan University Department Of Computer Science Jazan45142 Saudi Arabia Al Maarif University College Department Of Computer Science Al Anbar 31001 Iraq Masters University Of Northern Iowa IA United States Model Institute Of Engineering And Technology J&K Jammu India

ISBN: (纸本)9798350318609

Perioperative nutrition eval.ation is crucial.for patient care and resource efficiency in heal.hcare. This work proposes a deep learning-based perioperative nutrition eval.ation tool that leverages sophisticated machine learning to improve predictions and assist clinicians in making better choices. As surgical.techniques become more complex and medical.technology progresses, a thorough postoperative nutrition study becomes more important than ever. An extensive review demonstrates that the recommended strategy performs better than other machine learning techniques. Our model's accuracy, precision, memory, and F1-score let it predict surgical.outcomes more accurately. The higher AVC-ROC and AVC-PR val.es of the suggested approach show that it performs particularly well. Its sensitivity-specificity bal.nce is demonstrated by this. Our approach generates fewer errors, according to the confusion matrix anal.sis, which makes it reliable for heal.hcare decisions. Our work enhances critical.heal.hcare by assessing nutrition with state-of-the-art techniques. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

System Dynamics in Manufacturing Processes Modelling and Anal.sis 1

引用

3rd International.Conference on Innovation in Engineering, ICIE 2024

作者： Litwin, Pawel Szymusik, Anna Department of Computer Science Faculty of Mechanical Engineering and Aeronautics Rzeszow University of Technology Al. Powstanców Warszawy 8 Rzeszów35-959 Poland

ISBN: (数字)9783031615825

ISBN: (纸本)9783031615818

The systems dynamics (SD) method al.ows anal.sis of the performance of complex systems over the full simulation period. It al.ows for prediction of the dynamics of systems containing many interdependent elements. However, due to the complexity of models, SD is most often used to map systems at an aggregate level with a low level of detail. This paper presents solutions to improve the process of detailed modelling and simulation of manufacturing systems. The integration of SD with val.e stream mapping (VSM) and the use of pattern models help streamline the modeling process and can contribute to increasing the SD application area in manufacturing process anal.sis. The case study illustrates the methodology for modeling and simulation and shows how SD can be used to improve the manufacturing process. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： System theory

来源：评论

学校读者我要写书评

暂无评论

High energy γγ interactions at the LHeC 31

High energy γγ interactions at the LHeC

引用

31st International.Workshop on Deep Inelastic Scattering, DIS 2024

作者： Forthomme, Laurent Khanpour, Hamzeh Piotrzkowski, Krzysztof Yamazaki, Yuji AGH University Faculty of Physics and Applied Computer Science Al. Mickiewicza 30 Kraków30-055 Poland Physics Department Graduate School of Science Kobe University 1-1 Rokkodai-cho Nada-ku Kobe Japan

The future Large Hadron-electron Collider (LHeC) will operate at a center-of-mass energy of 1.2 TeV, delivering an integrated electron-proton luminosity of approximately 1 ab-1. The high luminosity and clean experimental.environment at LHeC promise unique research opportunities, requiring a comprehensive survey of high-energy γγ interactions up to center-of-mass energies of 1 TeV. In this contribution, the potential.for scientific discovery is briefly assessed by discussing the γγ processes, particularly the two-photon exclusive production of supersymmetric particles. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial.NoDerivatives 4.0 International.License (CC BY-NC-ND 4.0).

关键词： Hadrons

来源：评论

学校读者我要写书评

暂无评论

Spin-resolved nonlocal.transport in proximitized Rashba nanowires

引用

Physical.Review B 2024年第11期110卷 115413页

作者： Paweł Szumniak Daniel Loss Jelena Klinovaja Faculty of Physics and Applied Computer Science Al. Mickiewicza 30 30-059 Kraków Poland Department of Physics

Nonequilibrium transport in hybrid semiconductor-superconductor nanowires is crucial.for many quantum phenomena such as generating entangled states via cross Andreev reflection (CAR) processes, detecting topological.superconductivity, reading out Andreev spin qubits, coupling spin qubits over long distances, and so on. Here, we investigate numerical.y transport properties of a proximitized Rashba nanowire that hosts spin-polarized low-energy quasiparticle states. We show that the spin polarization in such one-dimensional.Andreev bands, extended over the entire nanowire length, can be detected in nonlocal.transport measurements with tunnel-coupled side leads that are spin polarized. Remarkably, we find an exact correspondence between the sign of the nonlocal.conductance and the spin density of the superconducting quasiparticles at the side lead position. We demonstrate that this feature is robust to moderate static disorder. As an example, we show that such a method can be used to detect spin inversion of the bands, accompanying the topological.phase transition (TPT) for real.stic system parameters. Furthermore, we show that such effects can be used to switch between CAR and elastic cotunneling (ECT) processes by tuning the strength of either the electric or the magnetic field. These findings hold significant practical.implications for state-of-the-art transport experiments in such hybrid systems.

关键词： Andreev reflection Bal.istic transport Quantum phase transitions Superconductivity Topological.superconductors Topological.material.

来源：评论

学校读者我要写书评

暂无评论

Modelling of diffraction of X-rays in perovskite superlattices 7

Modelling of diffraction of X-rays in perovskite superlattic...

引用

7th International.Conference of Computational.Methods in Engineering science, CMES 2022

作者： Kokosza, L. Mitura, Z. Department of Applied Computer Science and Modelling Faculty of Metals Engineering and Industrial Computer Science AGH University of Science and Technology al. Mickiewicza 30 Kraków30-059 Poland

Nowadays, different perovskite structures are widely investigated because they can be potential.y used in many branches of industry. If two material. are deposited al.ernately on a substrate, then a superlattice having some unique properties can be formed. However, X-ray intensity distributions for perovskite superlattices, especial.y for very thin films, are difficult to be computational.y determined, because many different parameters need to be considered to reproduce a superstructure of a sample. The main purpose of this work is to demonstrate how basic intensity distributions can be generated for perovskites, XRD technique and how to improve results using specific numerical.methods. The computer application with a user-friendly graphical.interface has been developed employing Unity software (with 3D graphics tools) and Oracle Database (through Oracle Cloud Infrastructure). The cal.ulations are based on the kinematical.theory of diffraction. The val.es of some important parameters and the results are stored in the assigned database. It is assumed that epitaxial.superlattices can be prepared on substrates using molecular beam epitaxy or pulsed laser deposition methods. The desktop application al.ows for designing samples of different thicknesses and combinations of monolayers. The results are more real.stic if Monte Carlo simulations are done al.hough longer computation time is required. The software developed should be helpful to compare in detail virtual.model results with experimental.data. © 2022 Institute of Physics Publishing. al. rights reserved.

关键词： Perovskite

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：