检索结果-内蒙古大学图书馆

2008年国际电子商务、工程及科学领域的分布式计算和应用学术研讨会

作者： Norazaliza Mohd.Jamil Noraziah Ahmad Shaharuddin Salleh Faculty of Computer Systems & Software Engineering Universiti Malaysia PahangLocked Bag 1225000KuantanPahangMalaysia Department of Mathematics Faculty of ScienceUniversiti Teknologi Malaysia81310Johor BahruMalaysia

Single-row routing is fundamentally a routing technique for pairs of nodes arranged in a single-row *** contributes in the printed circuit hoard(PCB)design. The main objective in single-row routing is to achieve minimum congestion arising from the number of horizontal tracks in the *** results for a single layer network have been achieved through our previous model called ***,a single layer model suffers from non-tolerable lower bound values with high congestion depending on the network size. These results may further be improved by partitioning the network into two or more *** this paper,we propose a technique based on the graph partitioning concept for partitioning the nodes from a single-row network into several layers of planar *** experiment result shows that the proposed technique is able to decrease the network congestions.

关键词： Single-row routing ESSR graph partitioning maximum clique Kernighan-Lin algorithm

来源：评论

学校读者我要写书评

暂无评论

Training Differentially Private Models with Secure Multiparty Computation

arXiv

引用

arXiv 2022年

作者： Pentyala, Sikha Railsback, Davis Maia, Ricardo J.M. Melanson, David Dowsley, Rafael Nascimento, Anderson De Cock, Martine School of Engineering and Technology University of Washington Tacoma United States Department of Computer Science University of Brasilia Brazil Department of Software Systems and Cybersecurity Monash University Australia Department of Applied Mathematics Computer Science and Statistics Ghent University Belgium Mila - Quebec Ai Institute Canada

We address the problem of learning a machine learning model from training data that originates at multiple data owners, while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on Differential Privacy (DP) achieve this at the cost of a drop in accuracy. Solutions based on Secure Multiparty Computation (MPC) do not incur such accuracy loss but leak information when the trained model is made publicly available. We propose an MPC solution for training DP models. Our solution relies on an MPC protocol for model training, and an MPC protocol for perturbing the trained model coefficients with Laplace noise in a privacy-preserving manner. The resulting MPC+DP approach achieves higher accuracy than a pure DP approach, while providing the same formal privacy guarantees. Our work obtained first place in the iDASH2021 Track III competition on confidential computing for secure genome analysis. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing e-KYC Security and Privacy: Harnessing Quantum Computing and Blockchain in Web 3.0

引用

Distributed Ledger Technologies: Research and Practice 2024年第4期3卷 1-23页

作者： G. M. Faruk Ahmed Imran Hasan Md Soumike Hassan Rahul Khan Abu Jor Al Gefari Zain Buksh Joseph Liu A B M Shawkat Ali Cybersecurity Cell Rupali Bank Limited Dhaka Bangladesh Department of Computer Science and Engineering Islamic University Kushtia Bangladesh Department of Statistics Jahangirnagar University Dhaka Bangladesh Department of Pharmacy Bangladesh University Dhaka Bangladesh Rajshahi Science and Technology University Natore Bangladesh Department of Computer Science and Mathematics The University of Fiji Lautoka Fiji Department of Software Systems and Cybersecurity Monash University Melbourne Australia

By implementing a successful and effective Electronic-Know Your Customer (e-KYC) infrastructure, conventional defects and expenses may be greatly reduced. Strong authentication procedures are used by existing e-KYC solutions to guarantee safety and confidentiality. However, these technologies have shortcomings like as key administration expenses and dependency on encryption. We suggest a revolutionary strategy that integrates blockchain technology, Web 3.0, and quantum computing to get around these restrictions. In this research, we show how current e-KYC processes could possibly be improved, making them faster and more reliable, by integrating Web 3.0 with quantum computing. Our solution makes it simple to quickly verify several consumers, increasing productivity. We provide improved safety for online requests, transcending the weaknesses inherent in traditional encryption techniques by utilizing quantum computing technology and applying the concept of quantum encryption key methodology. We contribute to the development of safe and private solutions by addressing the shortcomings of the present e-KYC systems. The results of our research show how Web 3.0 and quantum computer technology have the power to completely alter the e-KYC environment.

关键词： e-KYC Quantum Computing Blockchain Web 3.0 Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Decentralized Authentication in Internet of Underwater Things Using Blockchain

Energy Efficient Decentralized Authentication in Internet of...

引用

IEEE Globecom Workshops

作者： Abbas Yazdinejad Reza M. Parizi Gautam Srivastava Ali Dehghantanha Kim-Kwang Raymond Choo Cyber Science Lab School of Computer Science University of Guelph Ontario Canada College of Computing and Software Engineering Kennesaw State University GA USA Department of Mathematics and Computer Science Brandon University Manitoba Canada Department of Information Systems and Cyber Security University of Texas at San Antonio TX USA

ISBN: (数字)9781728109602

ISBN: (纸本)9781728109619

In recent years, there has been rapid growth in developing smart cities. Nearly 70% of the Earthâ€™s surface is covered by water and a large proportion of underwater environments are still unknown and have not been explored. In this context, Internet of things (IoT) is one of the most important technologies used in smart cities. Due to the growth of IoT and its influence in all areas of human life, including the underwater environment, a new class of IoT, called Internet of underwater things (IoUT) has emerged. IoUT includes a network of underwater smart devices that are connected to each other and has applications in environmental monitoring, underwater exploration, disaster prevention and military. In autonomous interactions of underwater devices, objects must be authenticated and securely interconnected to avoid security risks by malicious nodes. Most authentication methods and security mechanisms are centralized and often require a trustful third party in communications, which may well increase the computation cost and energy consumption due to the subsequent overhead, especially for underwater communications. On the other hand, there are restrictions on devices in the underwater environment, the most important of which are energy constraints. In this paper, we propose a robust, transparent, and energy-efficient decentralized authentication mechanism for IoUT using blockchain technology. We show through results that the proposed method is suitable for underwater devices with limited memory, energy, and computational power. The proposed modelâ€™s decentralized authentication in a cluster network has a significant effect on reducing the energy consumption of the devices by 74.63% compared to classic authentication methods. Moreover, using the proposed method allows a savings of more than 41.9% in end-to-end delay and increases delivery rate by 21.6%.

关键词： Authentication Internet of Things Smart cities Energy consumption Cryptography

来源：评论

学校读者我要写书评

暂无评论

COVID-19 pneumonia level detection using deep learning algorithm

TechRxiv

引用

TechRxiv 2020年

作者： Ghafoor, Kayhan Zrar Ali, Abbas M. Mulahuwaish, Aos Maghdid, Halgurd S. Hussein, Safwan Mawlood Mohammed, Marwan A. Department of Software Engineering Salahaddin University-Erbil Iraq School of Mathematics and Computer Science University of Wolverhampton Wulfruna Street WolverhamptonWV1 1LY United Kingdom Department of Computer Science and Information Systems Saginaw Valley State University University Center 7400 Bay Rd Science East 174 MI48710 United States Department of Software Engineering Faculty of Engineering Koya University Kurdistan Iraq Computer Engineering Department Tishk International University Iraq

The first COVID-19 confirmed case is reported in Wuhan, China and spread across the globe with unprecedented impact on humanity. Since this pandemic requires pervasive diagnosis, it is significant to develop smart, fast and efficient detection technique. To this end, we developed an Artificial Intelligence (AI) engine to classify the lung inflammation level (mild, progressive, severe stage) of the COVID-19 confirmed patient. In particular, the developed model consists of two phases;in the first phase, we calculate the volume and density of lesions and opacities of the CT images of the confirmed COVID-19 patient using Morphological approaches. In the second phase, the second phase classifies the pneumonia level of the confirmed COVID-19 patient. To achieve precise classification of lung inflammation, we use modified Convolution Neural Network (CNN) and k-Nearest Neighbor (kNN). The result of the experiments show that the utilized models can provide the accuracy up to 95.65% and 91.304 % of CNN and kNN respectively. © 2020, CC BY.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Synchronization-based scalability of rings and chains of dense lumps

Synchronization-based scalability of rings and chains of den...

引用

作者： Lu, Jun-An Zhang, Yong Chen, Juan Lü, Jinhu Wu, Xiaoqun School of Mathematics and Statistics Wuhan University Wuhan 430072 China State Key Laboratory of Software Engineering Wuhan University Wuhan 430072 China Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China School of Electrical and Computer Engineering RMIT University Melbourne VIC 3001 Australia

ISBN: (纸本)9789881725592

This paper aims to investigate the scalability of synchronizability for the complex clustering networks of dense rings or chains with the network scale increasing. Our results reveal that the synchronizability of the above complex clustering networks decreases with the network scale increasing for any clustering structures. When the network size is increasing, the increase of the number of clusters decreases the synchronizability much faster than the increase of the size of individual cluster. Moreover, it is found that the ring or the chain structure has much greater influence on weakening the network synchronizability than that of the clustering property. © 2011 Chinese Assoc of Automati.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

software module clustering based on the fuzzy adaptive teaching learning based optimization algorithm

arXiv

引用

arXiv 2019年

作者： Zamli, Kamal Z. Din, Fakhrud Ramli, Nazirah Ahmed, Bestoun S. Faculty of Computer Systems and Software Engineering Universiti Malaysia Pahang Gambang Kuantan Pahang26300 Malaysia Department of Computer Science and IT Faculty of Information Technology University of Malakand KPK Pakistan Department of Mathematics and Statistics Faculty of Information Technology and Quantitative Science Universiti Teknologi MARA Pahang Malaysia Faculty of Electrical Engineering Department of Computer Science Czech Technical University Czech Republic

Although showing competitive performances in many real world optimization problems, Teaching Learning based Optimization Algorithm (TLBO) has been criticized for having poor control on exploration and exploitation. Addressing these issues, a new variant of TLBO called Adaptive Fuzzy Teaching Learning based Optimization (ATLBO) has been developed in the literature. This paper describes the adoption of Fuzzy Adaptive Fuzzy Teaching Learning based Optimization (ATLBO) for software module clustering problem. Comparative studies with the original Teaching Learning based Optimization (TLBO) and other Fuzzy TLBO variant demonstrate that ATLBO gives superior performance owing to its adaptive selection of search operators based on the need of the current search. Copyright © 2019, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Graph Transformations and Model-Driven engineering 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Gregor Engels Claus Lewerentz Wilhelm Schäfer Andy Schürr Bernhard Westfechtel

来源：评论

学校读者我要写书评

暂无评论

Price Estimation of Used Cars Using Machine Learning Algorithms 3rd

Price Estimation of Used Cars Using Machine Learning Algorit...

引用

3rd EAI International Conference on Cognitive Computing and Cyber Physical systems, IC4S 2022

作者： Valarmathi, B. Gupta, N. Srinivasa Santhi, K. Chellatamilan, T. Kavitha, A. Raahil, Armaan Padmavathy, N. Department of Software and Systems Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Manufacturing Engineering School of Mechanical Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Analytics School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Mathematics School of Advanced Sciences Vellore Institute of Technology Tamil Nadu Vellore India Department of Information Technology School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Electronics and Communication Engineering Vishnu Institute of Technology Andhra Pradesh Bhimavaram India

ISBN: (纸本)9783031289743

In this study, machine learning (ML) techniques are employed to predict used car prices. Several features are used to calculate the price of used cars, but in this paper, we find efficient ways to find the most precise car prices. Despite the fact that there are websites offering this service, they could not employ the most precise prediction system. It is also possible to predict a used car's true market value using a variety of models and techniques. It's important to understand their genuine market value before buying or selling. Both buyers and sellers will be benefitted from these accurate predictions. Support Vector regression, Random Forest regression, and CatBoost regression techniques are used in the proposed system. In the existing method [13], mean absolute error for decision tree regression was 0.6711, which was the least among other algorithms like Linear regression, Lasso regression, Ridge regression, Bayesian Ridge regression, and etc., they used. In the proposed system, mean absolute error (MAE) for Support Vector regression, CatBoost regression and Random Forest regression techniques are 0.1459, 0.1371 and 0.1284 respectively. The prices of second hand/used cars are predicted using the CatBoost regression, Support Vector regression, and Random Forest regression techniques. The accuracy of these algorithms are 86.28%, 85.40% and 87.16%. Among these three algorithms, Random Forest regression gives the least MAE of 0.1317 and the highest accuracy of 87.16%. © 2023, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-Unit Floor Plan Recognition and Reconstruction Using Improved Semantic Segmentation of Raster-Wise Floor Plans

arXiv

引用

arXiv 2024年

作者： Kratochvila, Lukas de Jong, Gijs Arkesteijn, Monique Bilík, Šimon Zemčík, Tomáš Horak, Karel Rellermeyer, Jan S. Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic Department of Software Technology Faculty of Electrical Engineering Mathematics and Computer Science TU Delft Delft Netherlands Department of Management in the Built Environment Faculty of Architecture and the Built Environment TU Delft Delft Netherlands Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Dependable and Scalable Software Systems Institute of Systems Engineering Faculty of Electrical Engineering and Computer Science Leibniz University Hannover Hannover Germany

Digital twins have a major potential to form a significant part of urban management in emergency planning, as they allow more efficient designing of the escape routes, better orientation in exceptional situations, and faster rescue intervention. Nevertheless, creating the twins still remains a largely manual effort, due to a lack of 3D-representations, which are available only in limited amounts for some new buildings. Thus, in this paper we aim to synthesize 3D information from commonly available 2D architectural floor plans. We propose two novel pixel-wise segmentation methods based on the MDA-Unet and MACU-Net architectures with improved skip connections, an attention mechanism, and a training objective together with a reconstruction part of the pipeline, which vectorizes the segmented plans to create a 3D model. The proposed methods are compared with two other state-of-the-art techniques and several benchmark datasets. On the commonly used CubiCasa benchmark dataset, our methods have achieved the mean F1 score of 0.86 over five examined classes, outperforming the other pixel-wise approaches tested. We have also made our code publicly available to support research in the field. © 2024, CC BY.

关键词： Semantic Segmentation

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：