检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Göllner, Sabrina Tropmann-Frick, Marina Brumen, Boštjan Department of Computer Science Hamburg University of Applied Sciences Germany Faculty of Electrical Engineering and Computer Science University of Maribor Slovenia

Our research endeavors to advance the concept of responsible artificial intelligence (AI), a topic of increasing importance within EU policy discussions. The EU has recently issued several publications emphasizing the necessity of trust in AI, underscoring the dual nature of AI as both a beneficial tool and a potential weapon. This dichotomy highlights the urgent need for international regulation. Concurrently, there’s a need for frameworks that guide companies in AI development, ensuring compliance with such regulations. Our research aims to assist lawmakers and machine learning practitioners in navigating the evolving landscape of AI regulation, identifying focal areas for future attention. This paper introduces a comprehensive and, to our knowledge, the first unified definition of responsible AI. Through a structured literature review, we elucidate the current understanding of responsible AI. Drawing from this analysis, we propose an approach for developing a future framework centered around this concept. Our findings advocate for a human-centric approach to Responsible AI. This approach encompasses the implementation of AI methods with a strong emphasis on ethics, model explainability, and the pillars of privacy, security, and trust. © 2024, CC BY.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

引用

Journal of Rock Mechanics and Geotechnical engineering 2024年第10期16卷 3982-4003页

作者： Libing Yang Trung Nguyen-Thoi Trung-Tin Tran College of Civil Engineering and Architecture Hunan Institute of Science and TechnologyYueyang414006China Laboratory for Applied and Industrial Mathematics Institute for Computational Science and Artificial IntelligenceVan Lang UniversityHo Chi Minh CityViet Nam Faculty of Mechanical-Electrical and Computer Engineering School of TechnologyVan Lang UniversityHo Chi Minh CityViet Nam Department of Information Technology Greenwich VietnamFPT UniversityDa Nang550000Viet Nam

The accurate prediction of the friction angle of clays is crucial for assessing slope stability in engineering *** study addresses the importance of estimating the friction angle and presents the development of four soft computing models:YJ-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and *** of all,the Yeo-Johnson(YJ)transformation technique was used to stabilize the variance of data and make it more suitable for parametric statistical models that assume normality and equal *** technique is expected to improve the accuracy of friction angle prediction *** friction angle prediction models then utilized multi-layer perceptron neural networks(MLPnet)and metaheuristic optimization algorithms to further enhance performance,including flower pollination algorithm(FPA),coral reefs optimization(CRO),ant colony optimization continuous(ACOC),and cuckoo search algorithm(CSA).The prediction models without the YJ technique,***-MLPnet,CRO-MLPnet,ACOC-MLPnet,and CSA-MLPnet,were then compared to those with the YJ technique,***-FPA-MLPnet,YJ-CRO-MLPnet,YJ-ACOC-MLPnet,and *** these,the YJ-CRO-MLPnet model demonstrated superior reliability,achieving an accuracy of up to 83%in predicting the friction angle of clay in practical engineering *** improvement is significant,as it represents an increase from 1.3%to approximately 20%compared to the models that did not utilize the YJ transformation technique.

关键词： Natural hazards Slope stability Friction angle Clay Soft computing models Geotechnical engineering

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Methods to Support People Management in Organizations

Artificial Intelligence Methods to Support People Management...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable Technology, ICRISST 2024

作者： Sonawane, Prashant Ashok Mishra, Krishna Nand Raman, P. Kumar, Kishor Jawarkar, Nilesh G. Kandavalli, Sunanda Ratna. Gondwana University Department of Commerce Gadchiroli442605 India Radha Govind University Department of Computer Science Jharkhand Ramgarh829122 India College Poonamallee Department of Management Studies Panimalar Engineering Tamil Nadu Chennai600123 India Delhi Technological University Department of Applied Mathematics Delhi India JSPM' Rajarshi Shahu College of Engineering Department of Mechanical Engineering Pune India Sri Padmavati Mahila Visva Vidyalayam Department of Electronics & Communication Engineering Andhra Pradesh Tirupati517502 India

ISBN: (纸本)9798350309140

The research paper showcases in-depth research on AI technology and its direct impact on organizations and people. Along with this research paper also discussed how AI technology can support organizations in streamlining their business processes, improving their decision-making skills, enhancing staff engagement, and raising the rate of production with the help of machine learning and natural language processing. Besides this, it is examined in this paper that AI technology can also be applied to automate the entire screening method, shorten the timetable, and manage the available resources needed for new staff recruitment. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

ENVIRONMENTALLY FRIENDLY SOLAR ENERGY: POTENTIAL OF UTILIZING FIELD MARGINS IN RURAL AREAS FOR PHOTOVOLTAIC SYSTEMS IN COMBINATION WITH WILDFLOWER STRIPS 22

ENVIRONMENTALLY FRIENDLY SOLAR ENERGY: POTENTIAL OF UTILIZIN...

引用

22nd Wind and Solar Integration Workshop, WIW 2023

作者： Wunder, Kerstin Foth, Hannes Rolink, Johannes Kayser, Manfred Department of Electrical Engineering and Computer Science University of Applied Sciences Emden/Leer Emden Germany Institute for Applied Photogrammetry and Geoinformatics Jade University of Applied Sciences Oldenburg Germany Geo-Lab University of Vechta Vechta Germany Department of Crop Sciences University of Göttingen Göttingen Germany

ISBN: (纸本)9781839539824

This study assesses the economic potential of using field margins and wildflower strips in rural northwest Lower Saxony, Germany, for eco-friendly solar energy generation. Field margins, located at the edges of farmland, serve as buffers between crops and surrounding ecosystems and can promote biodiversity by using as wildflower strips. By integrating photovoltaic (PV) systems within these field margins, the study aims to investigate clean electricity production while preserving ecological balance. To estimate the potential of grid-connected field margin PV (FMPV), the paper considers regulatory, technical, and economic factors. Using geographic data, suitable areas are identified. The study assesses regulatory influence on FMPV operations and evaluates grid connection points' availability for economic analysis. Results show that 19,378 km of field margins are potentially suitable for grid-connected FMPV, implying an electricity generation potential of 23.6 TWh/a. However, compatible margins constitute just 15.5 % of existing field margins. The combination of wildflower strips and grid-connected FMPV provides an innovative energy approach in rural areas, however, this study highlights high grid connection costs. Off-grid photovoltaic systems seem more practical. Prioritizing off-grid systems for on-site electricity utilization and exploring affordable alternatives are essential for enhancing the economic viability of FMPV systems in rural areas. © Energynautics GmbH.

关键词： Rural areas

来源：评论

学校读者我要写书评

暂无评论

Slotted ALOHA with Code Combining for IoT Networks 3

Slotted ALOHA with Code Combining for IoT Networks

引用

3rd IEEE International Mediterranean Conference on Communications and Networking, MeditCom 2023

作者： Tyrovolas, Dimitrios Chrysologou, Athanasios Chondrogiannis, Georgios Tegos, Sotiris Mekikis, Prodromos-Vasileios Diamantoulakis, Panagiotis Ioannidis, Sotiris Liaskos, Christos Chatzidiamantis, Nestor Karagiannidis, George Aristotle University of Thessaloniki Dept. of Electrical and Computer Engineering Thessaloniki Greece Technical University of Chania Dept. of Electrical and Computer Engineering Chania Greece University of Ioannina Computer Science Engineering Department Ioannina Greece Cyber Security Systems and Applied Ai Research Center Lebanon

ISBN: (纸本)9798350333732

Internet of Things (IoT) networks are expected to be a key enabler technology for smart cities, due to their ability to offer real-time monitoring. In this work, we propose a novel medium access control (MAC) protocol, inspired by the synergy of slotted ALOHA and hybrid automatic repeat request with code combining (HARQ-CC), termed as code combining slotted ALOHA (CCSA), to improve the performance of IoT networks with multiple randomly deployed sensors. Specifically, we provide analytical closed-form expressions for the network's outage probability as well as for its average throughput when CCSA is applied. Finally, we provide simulation results that reveal the authenticity of the derived expressions and reveal the capabilities of HARQ-CC to significantly improve the network's performance when the sensors' access is based on a random access scheme. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Bright, periodic, compacton and bell-shape soliton solutions of the extended QZK and (3+1)-dimensional ZK equations

引用

Communications in Theoretical Physics 2021年第10期73卷 23-35页

作者： M Ali Akbar Md Abdul Kayum M S Osman Department of Applied Mathematics University of RajshahiBangladesh Department of Computer Science&Engineering North Bengal International UniversityRajshahiBangladesh Department of Mathematics Faculty of ScienceCairo UniversityGiza 12613Egypt

The(3+1)-dimensional Zakharov–Kuznetsov(ZK) and the new extended quantum ZK equations are functional to decipher the dense quantum plasma, ion-acoustic waves, electron thermal energy,ion plasma, quantum acoustic waves, and quantum Langmuir waves. The enhanced modified simple equation(EMSE) method is a substantial approach to determine competent solutions and in this article, we have constructed standard, illustrative, rich structured and further comprehensive soliton solutions via this method. The solutions are ascertained as the integration of exponential, hyperbolic,trigonometric and rational functions and formulate the bright solitons, periodic, compacton, bellshape, parabolic shape, singular periodic, plane shape and some new type of solitons. It is worth noting that the wave profile varies as the physical and subsidiary parameters change. The standard and advanced soliton solutions may be useful to assist in describing the physical phenomena previously mentioned. To open out the inward structure of the tangible incidents, we have portrayed the three-dimensional, contour plot, and two-dimensional graphs for different parametric values. The attained results demonstrate the EMSE technique for extracting soliton solutions to nonlinear evolution equations is efficient, compatible and reliable in nonlinear science and engineering.

关键词： (3+1)-dimensional ZK the extended QZK equation enhanced modified simple equation method soliton solutions NLEEs

来源：评论

学校读者我要写书评

暂无评论

Quantum Computing for Learning Analytics: An Overview of Challenges and Integration Strategies 2

Quantum Computing for Learning Analytics: An Overview of Cha...

引用

2nd Workshop on Quantum Programming for Software engineering, QP4SE 2023, co-located with ESEC/FSE 2023

作者： Pagano, Alessandro Angelelli, Mario Calvano, Miriana Curci, Antonio Piccinno, Antonio Department of Economics University of Bari Aldo Moro Bari Italy Department of Innovation Engineering Campi - Centre of Applied Mathematics and Physics for Industry University of Salento Lecce Italy Department of Computer Science University of Bari Aldo Moro Bari Italy

ISBN: (纸本)9798400703768

Quantum computing has emerged as a promising technology with the potential to revolutionize various fields, including learning analytics. This research paper explores the applications of quantum computing in learning analytics and discusses the suitability of quantum techniques for addressing the challenges posed by large-scale educational datasets. It also investigates the integration of quantum computing with existing learning analytics pipelines, highlighting compatibility issues, data representation and transformation challenges, algorithmic complexity, and evaluation considerations. By understanding the potential benefits, limitations, and integration strategies, researchers can pave the way for the development of innovative tools and approaches to analyze educational data and provide personalized learning experiences. © 2023 ACM.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach

HPC Application Parameter Autotuning on Edge Devices: A Band...

引用

International Conference on High Performance Computing

作者： Abrar Hossain Abdel-Hameed A. Badawy Mohammad A. Islam Tapasya Patki Kishwar Ahmed Department of Electrical Engineering and Computer Science The University of Toledo Department of Electrical and Computer Engineering New Mexico State University Department of Computer Science and Engineering The University of Texas at Arlington Lawrence Livermore National Laboratory Center for Applied Scientific Computing

ISBN: (数字)9798331509095

ISBN: (纸本)9798331509101

The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices.

关键词： Performance evaluation Analytical models Navigation High performance computing Computational modeling Data models Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Impact of Architectural Modifications on Deep Learning Adversarial Robustness

arXiv

引用

arXiv 2024年

作者： Juraev, Firuz Abuhamad, Mohammed Woo, Simon S. Thiruvathukal, George K. Abuhmed, Tamer Department of Computer Science and Engineering Sungkyunkwan University Korea Republic of Department of Computer Science Loyola University Chicago United States Department of Applied Data Science Sungkyunkwan University Korea Republic of

Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying variations of sophisticated techniques that improve the performance of models. However, such models are not immune to adversarial manipulations, which can cause the system to misbehave and remain unnoticed by experts. The frequency of modifications to existing deep learning models necessitates thorough analysis to determine the impact on models’ robustness. In this work, we present an experimental evaluation of the effects of model modifications on deep learning model robustness using adversarial attacks. Our methodology involves examining the robustness of variations of models against various adversarial attacks. By conducting our experiments, we aim to shed light on the critical issue of maintaining the reliability and safety of deep learning models in safety- and security-critical applications. Our results indicate the pressing demand for an in-depth assessment of the effects of model changes on the robustness of models. © 2024, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Quantum Attacks on Public Cryptosystems 6

Quantum Attacks on Public Cryptosystems

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Singh, Puneet Hasabnis, Amey R. Rajpoot, Subhadra Singh, Pankaj College of Telecommunication Engineering Faculty of Communication Engineering Military MP Mhow India Amiuty University Department of Applied Sciences Uttar Pradesh Greater Noida India BITS Pilani Pilani India Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350304480

Quantum Key Distribution (QKD) networks have emerged as a revolutionary technology in ensuring secure communication in the digital age. By leveraging the principles of quantum mechanics, QKD allows two parties to establish a secret key securely, which can subsequently be used for encrypting and decrypting sensitive information. While QKD holds immense promise for enhancing cybersecurity, it also presents several challenges that necessitate further research to achieve its full potential. The research presented here examines the development of QKD networks, their real-world use, as well as the general QKD network architecture and the most recent advancements in QKD network deployments. © 2023 IEEE.

关键词： Quantum Key Distribution (QKD Networks

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：