检索结果-内蒙古大学图书馆

7th international conference on Intelligent computing and Control Systems, ICICCS 2023

作者： Alam, Ashraf Indian Institute of Technology Kharagpur Rekhi Centre of Excellence for the Science of Happiness West Bengal India

ISBN: (纸本)9798350397253

Educational data Mining (EDM) is a promising area of research that leverages computational methods to improve educational outcomes by extracting valuable insights from vast educational datasets. The purpose of this study is to explore the relationship between EDM and various educational theories, including Learning Analytics Theory (LAT), Educational Psychology Theory, Cognitive Load Theory, Self-Regulated Learning (SRL) Theory, Bloom's Taxonomy Theory, Multiple Intelligences Theory, Schema Theory, Situated Learning Theory, Zone of Proximal Development Theory, and Connectivism Theory. This scientific research provides a comprehensive overview of each theory, and discusses how EDM can be used to enhance the understanding and application of these theories in educational settings. Through various teaching-learning classroom examples, the study illustrates how EDM can help identify students' learning styles, strengths, and weaknesses, develop algorithms that adapt to students' learning needs in real-time, predict students' future academic performance, identify challenging areas of a course, and provide tailored instruction and support to individual students. The study further demonstrates how EDM can inform the design of effective teaching strategies, and contribute to the development of personalized and adaptive learning environments. © 2023 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

A Study on the Effect of Antenna Array Parameters in Optimizing the Radiation Pattern 7

A Study on the Effect of Antenna Array Parameters in Optimiz...

引用

2023 7th international conference On computing, Communication, Control And Automation, ICCUBEA 2023

作者： Banerjee, Archisman Pradhan, Sankarshan Dutta, Ayan Misra, Bitan School of Electronics Engineering KIIT-Deemed University Bhubaneswar India Hcl Technologies Kolkata India Techno International New Town Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350304268

In this work, aconcentric elliptical array of antennas is optimized with the help of three relatively new and efficient meta-heuristic algorithms;namely, Teaching Learning Based Optimization (TLBO), Multi-Verse Optimization (MVO), and Grey Wolf Optimization(GWO). This work demonstrates a detailed study of the effect of various antenna array contro lvariables for the improvemen to normalized power patterns generated by elliptical array *** objective of this study is to reduce Side Lobe Level (SLL) value to the possible amount and simultaneously reach the desired First Null BeamWidth (FNBW) value. A number of cases are studied and the outcomes are exhibited in a desegregated way with the best optimal values of eccentricities, semi-major axis, and inter-element spacing. An investigation is performed to explore theperformance of the algorithms based on the common antenna parameters such as the number of elements, obtained SLL, and obtained FNBW. Additionally, the statistical specifications of all the algorithms are examined in terms of mean, standard deviation, best objective function, and time complexity. T-test iscarried out at the end of this study, separately on each acquired data set to authenticate the result. © 2023 IEEE.

关键词： Concentric Elliptical Array Antenna (CEAA) First Null Beam Width (FNBW) Meta-heuristic algorithm Optimization Side Lobe Level (SLL)

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Cancer data Sets Utilizing data Mining 2

An Analysis of Cancer Data Sets Utilizing Data Mining

引用

2nd IEEE international conference on Advances in computing, Communication and Applied Informatics, ACCAI 2023

作者： Singh, Bhaludra R Nadh Keerthi, Sripuram Sai Nikitha, Vantari Sai Sradha, Sama Sai Rithika, Neelagiri Shiva Dornala, Shivani Bhoj Reddy Engineering College for Women Department of Computer Science and Engineering Telangana Hyderabad59 India Bhoj Reddy Engineering College for Women Telangana Hyderabad59 India

ISBN: (纸本)9798350315905

This research aims to ensure precision in medical outcomes by comparing and contrasting classification approaches using various (Lucamia) cancer knowledge sets using data processing technologies. Many researchers have investigated this question, and their findings have lent credence to using specialised knowledge bases and classifiers. They have compared and contrasted various knowledge sets, including those found online. Here, we compare the results of a neural network classification with those obtained without one. © 2023 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Numerical P Systems with Thresholds and Petri Nets 18th

Numerical P Systems with Thresholds and Petri Nets

引用

18th international conference on Bio-Inspired computing: Theories and Applications (BIC-TA)

作者： Zhang, Luping Zhang, Zhimeng East China Univ Technol Jiangxi Engn Technol Res Ctr Nucl Geosci Data Sci Sch Informat Engn Jiangxi Engn Lab Radioact Geosci & Big Data Techn Nanchang 330013 Jiangxi Peoples R China

ISBN: (纸本)9789819722716;9789819722723

Membrane computing provides efficient computing devices for broad applications due to its distributed storage and the parallel processing. As computing devices in membrane computing, numerical P systems with thresholds (NPT systems) are proven to be Turing universal, and their computational and operational semantics need to be further investigated. In this work, the intrinsic relationship between NPT systems and Petri nets is concerned. The ingredients of Petri nets are associated with the elements of numerical variables in NPT systems, and the operations of Petri nets are associated with the evolutions of NPT systems. The results on the boundedness and reachability of NPT systems are obtained by using the relationship between NPT systems and Petri nets.

关键词： Membrane computing Numerical P systems Threshold Petri net

来源：评论

学校读者我要写书评

暂无评论

HipBone: A performance-portable graphics processing unit-accelerated C plus plus version of the NekBone benchmark

引用

international JOURNAL OF HIGH PERFORMANCE computing APPLICATIONS 2023年第5期37卷 560-577页

作者： Chalmers, Noel Mishra, Abhishek Mcdougall, Damon Warburton, Tim Adv Micro Devices Inc Data Ctr GPU & Accelerated Proc Austin TX USA SUNY Buffalo Inst Computat & Data Sci Buffalo NY USA Virginia Tech Dept Math McBryde Hall Blacksburg VA USA Adv Micro Devices Inc Austin Data Ctr GPU & Accelerated Proc 7171 Southwest Pkwy Austin TX 78735 USA

We present hipBone, an open-source performance-portable proxy application for the Nek5000 (and NekRS) computational fluid dynamics applications. HipBone is a fully GPU-accelerated C++ implementation of the original NekBone CPU proxy application with several novel algorithmic and implementation improvements which optimize its performance on modern fine-grain parallel GPU accelerators. Our optimizations include a conversion to store the degrees of freedom of the problem in assembled form in order to reduce the amount of data moved during the main iteration and a portable implementation of the main Poisson operator kernel. We demonstrate near-roofline performance of the operator kernel on three different modern GPU accelerators from two different vendors. We present a novel algorithm for splitting the application of the Poisson operator on GPUs which aggressively hides MPI communication required for both halo exchange and assembly. Our implementation of nearest-neighbor MPI communication then leverages several different routing algorithms and GPU-Direct RDMA capabilities, when available, which improves scalability of the benchmark. We demonstrate the performance of hipBone on three different clusters housed at Oak Ridge National Laboratory, namely, the Summit supercomputer and the Frontier early-access clusters, Spock and Crusher. Our tests demonstrate both portability across different clusters and very good scaling efficiency, especially on large problems.

关键词： Nekbone/Nek5000/NekRS high-performance computing compute unified device architecture HIP GPU-Direct gather-scatter communication high order spectral element discretization

来源：评论

学校读者我要写书评

暂无评论

data Access Control in Cloud computing 2

Data Access Control in Cloud Computing

引用

2nd international conference on Advancements in Electrical, Electronics, Communication, computing and Automation, ICAECA 2023

作者： Rajeshwaran, K. Sathyakala, S. Sharmila, Alias Supriya J Savika, M. Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College Coimbatore India

ISBN: (纸本)9798350306811

This paper presents a research project focusing on enhancing security features in cloud access through the utilization of AES (Advanced Encryption Standard) algorithms. The primary objective of this project is to ensure the easy accessibility of data and applications exclusively for authorized users. To address the prevalent privacy concerns in cloud access systems, we propose a novel distributed data access control mechanism that aims to safeguard user privacy. The first component of our approach introduces a groundbreaking method for achieving user anonymity, specifically targeting collusion scenarios involving untrustworthy authorities. The second component features a state-of-the-art policy obfuscation mechanism that effectively protects the confidentiality of decision attributes (metadata) from conspiring parties. Furthermore, we introduce a third-party authority system as the third component of our privacy enhancements, allowing authorities to log in and out of the system without overriding each other's permissions. Additionally, we propose a new activation feature and conduct a comparative analysis against popular activation features such as VM Orchestrator, VMware Sphere, and Ovirt, with the objective of enhancing system performance and security. Through this project, we aim to contribute to the ongoing efforts in strengthening the security framework of cloud access systems while ensuring user privacy. © 2023 IEEE.

关键词： Activation analysis

来源：评论

学校读者我要写书评

暂无评论

Application of data fusion algorithm in detection of pesticide residues in food

Application of data fusion algorithm in detection of pestici...

引用

2023 international conference on Cloud computing, Performance computing, and Deep Learning, CCPCDL 2023

作者： Xu, Jiyuan Mai, Shaoyu Chen, Xiaoyue School of Traditional Chinese Medicine Southern Medical University Guangzhou510515 China Foshan Huayi Technology Co. Ltd Foshan528000 China Foshan Nanxu Technology Co. Ltd Foshan528000 China

ISBN: (纸本)9781510666474

In order to avoid the excessive pesticide content in the ecological environment caused by the use of a large number of pesticides, it will cause serious harm to people, livestock, water, atmosphere, soil and other environmental elements. Even if it is a small amount of residues, long-term contact will do harm to human health. In this paper, the application of data fusion algorithm in the detection of pesticide residues in food is proposed. A data fusion method suitable for repeated sampling of single sensor is applied to the processing of pesticide residue detection data. The data are grouped by statistical theory, while the support probability is fuzzy, and the support interval is determined by subsection discussion, which makes the fused data more stable than the previous results obtained by absolute support probability and support interval, and further ensures that the data fusion has better anti-interference. © 2023 SPIE.

关键词： Pesticides

来源：评论

学校读者我要写书评

暂无评论

Consolidating user data from social networks using Machine Learning and Serverless Cloud

Consolidating user data from social networks using Machine L...

引用

2023 international conference on Intelligent computing, Communication, Networking and Services, ICCNS 2023

作者： Kaplunovich, Alex Kaplunovich, Sophia University of Maryland Department of Computer Science BaltimoreMD21250 United States University of Delaware Psychological & Brain Sciences NewarkDE19716 United States

ISBN: (纸本)9798350339291

Social Networks are integral part of our lives. Each of them has application programming interface (API) to access its data. People willingly store their private information, photos, thoughts and locations in numerous forums. We decided to determine how much information we could obtain about a person using automatic cloud serverless architectures, social network's APIs and advanced data Science models and algorithms. The paper shows how vulnerable privacy is and how easy it is to consolidate users' information using modern cloud technologies. We were able to obtain geolocations, friends, similar profiles, predict influencers, and even predict missing friends using Machine Learning graph models. At the end of the day, people should always guard their private information and innovative social platform corporations should carefully think about what data could be given to third parties. © 2023 IEEE.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

RT DL Tasks Distribution for Sensitive data Protection and Resource Optimization 11

RT DL Tasks Distribution for Sensitive Data Protection and R...

引用

11th IEEE international conference on Intelligent computing and Information Systems, ICICIS 2023

作者： Zeidan, Farah Elhayani, Mostafa Soubra, Hassan German University in Cairo Computer Science and Engineering Cairo Egypt Informatics Technische Universität München Cairo Egypt

ISBN: (纸本)9798350322101

With the rapid growth of data-intensive applications and the proliferation of the Internet of Things (IoT) devices, traditional cloud architectures face significant challenges in enabling real-time decision-making. Centralized cloud infrastructures have limitations in handling the increasing volume of data generated at network ends. In response, edge computing has emerged as a promising paradigm that brings computation closer to the data source, offering advantages over traditional cloud architectures. This paper presents an edge computing system that incorporates a load balancer to determine whether real-time tasks should be offloaded to the edge or to the cloud. To enhance security, a data retention measure is introduced to ensure sensitive data remains within the edge device, irrespective of other load-balancing conditions. This approach minimizes the risk of attacks and unauthorized access by containing sensitive data within the edge device. Furthermore, the impact on system performance is evaluated by monitoring CPU utilization before and after task execution. This research contributes secure and efficient task offloading strategies in edge computing, with implications for real-time processing and data privacy sensitive applications. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

VisionHD: Towards Efficient and Privacy-Preserved Hyperdimensional computing for Image data 24

VisionHD: Towards Efficient and Privacy-Preserved Hyperdimen...

引用

29th ACM / IEEE international Symposium on Low Power Electronics and Design (ISLPED)

作者： Asgarinejad, Fatemeh Morris, Justin Rosing, Tajana Aksanli, Baris Univ Calif San Diego Dept Comp Sci & Engn La Jolla CA 92093 USA Dept Comp Sci & Informat Syst San Marcos CA 92096 USA Dept Elect & Comp Engn San Diego CA 92182 USA

ISBN: (纸本)9798400706882

Hyperdimensional computing (HDC) represents an emerging paradigm within the domain of cognitive computing, inspired by the information processing mechanisms observed in the human brain. Despite the research efforts devoted to improving and extending HDC algorithms and hardware, the efficacy and privacy of HDC remains challenging in handling image data. In this study, we highlight the accuracy, efficiency and privacy concerns of existing HDC-based methods on image data. We propose a novel vector-free encoding that shrinks the energy consumption and obviates the need for vector storage. We repurpose the released resources to augment the proposed encoding with a well crafted and privacy-aware feature extractor. Experimental results indicate that our proposed design, designated as VisionHD, gains a significant accuracy improvement (> 22%) while its energy consumption remains within the confines of the baseline HDC. To evaluate the privacy of VisionHD, we introduce a more effective and generic reversing technique, which reveals that VisionHD successfully obfuscates the information and improves the privacy metric by 16.9x.

关键词： Hyperdimensional computing Image Classification Energy Efficiency Privacy

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：