检索结果-内蒙古大学图书馆

19th Scandinavian Symposium on Algorithm Theory, SWAT 2024

作者： Gärtner, Bernd Kalani, Vishwas Reddy, Meghana M. Meulemans, Wouter Speckmann, Bettina Stojaković, Miloš Department of Computer Science ETH Zürich Switzerland Department of Computer Science and Engineering I.I.T. Delhi India Department of Mathematics and Computer Science TU Eindhoven Netherlands Department of Mathematics and Informatics Faculty of Sciences University of Novi Sad Serbia

ISBN: (纸本)9783959773188

In information visualization, the position of symbols often encodes associated data values. When visualizing data elements with both a numerical and a categorical dimension, positioning in the categorical axis admits some flexibility. This flexibility can be exploited to reduce symbol overlap, and thereby increase legibility. In this paper we initialize the algorithmic study of optimizing symbol legibility via a limited displacement of the symbols. Specifically, we consider unit square symbols that need to be placed at specified y-coordinates. We optimize the drawing order of the symbols as well as their x-displacement, constrained within a rectangular container, to maximize the minimum visible perimeter over all squares. If the container has width and height at most 2, there is a point that stabs all squares. In this case, we prove that a staircase layout is arbitrarily close to optimality and can be computed in O(n log n) time. If the width is at most 2, there is a vertical line that stabs all squares, and in this case, we give a 2-approximation algorithm (assuming fixed container height) that runs in O(n log n) time. As a minimum visible perimeter of 2 is always trivially achievable, we measure this approximation with respect to the visible perimeter exceeding 2. We show that, despite its simplicity, the algorithm gives asymptotically optimal results for certain instances. © Bernd Gärtner, Vishwas Kalani, Meghana M. Reddy, Wouter Meulemans, Bettina Speckmann, and Miloš Stojaković;licensed under Creative Commons License CC-BY 4.0.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Knowledge‐based deep learning system for classifying Alzheimer's disease for multi‐task learning

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 805-820页

作者： Amol Dattatray Dhaygude Gaurav Kumar Ameta Ihtiram Raza Khan Pavitar Parkash Singh Renato R.Maaliw III Natrayan Lakshmaiya Mohammad Shabaz Muhammad Attique Khan Hany S.Hussein Hammam Alshazly Department of Data Science University of WashingtonSeattleWashingtonUSA Department of Computer Science&Engineering Parul Institute of TechnologyParul UniversityVadodaraGujaratIndia Department of Computer Science Jamia HamdardDelhiIndia Department of Management Lovely Professional UniversityPhagwaraIndia 5 College of Engineering Southern Luzon State UniversityLucbanQuezonPhilippines Department of Mechanical Engineering Saveetha School of EngineeringSIMATSChennaiTamil NaduIndia Model Institute of Engineering and Technology JammuJ&KIndia Department of Computer Science HITEC UniversityTaxilaPakistan Department of Computer Science and Mathematics Lebanese American UniversityBeirutLebanon Electrical Engineering Department College of EngineeringKing Khalid UniversityAbhaSaudi Arabia Electrical Engineering Department Aswan UniversityAswanEgypt Faculty of Computers and Information South Valley UniversityQenaEgypt

Deep learning has recently become a viable approach for classifying Alzheimer's disease(AD)in medical ***,existing models struggle to efficiently extract features from medical images and may squander additional information resources for illness *** address these issues,a deep three‐dimensional convolutional neural network incorporating multi‐task learning and attention mechanisms is *** upgraded primary C3D network is utilised to create rougher low‐level feature *** introduces a new convolution block that focuses on the structural aspects of the magnetORCID:ic resonance imaging image and another block that extracts attention weights unique to certain pixel positions in the feature map and multiplies them with the feature map ***,several fully connected layers are used to achieve multi‐task learning,generating three outputs,including the primary classification *** other two outputs employ backpropagation during training to improve the primary classification *** findings show that the authors’proposed method outperforms current approaches for classifying AD,achieving enhanced classification accuracy and other in-dicators on the Alzheimer's disease Neuroimaging Initiative *** authors demonstrate promise for future disease classification studies.

关键词： classification deep learning

来源：评论

学校读者我要写书评

暂无评论

An ellipsoid restrictive region-based regularization for regression analysis

引用

International Journal of Information Technology (Singapore) 2025年第3期17卷 1865-1871页

作者： Dutta, Anurag Lakshmanan, K. Karthik, R. Priya, S. Shanmuga Ramamoorthy, A. Department of Computer Science and Engineering Government College of Engineering & Textile Technology Calcutta Serampore India Department of Mathematics Kuwait American School of Education Hawalli Salmiya Kuwait Department of Mathematics Velammal Engineering College Tamil Nadu Chennai India Department of Computer Science SRM University Tamil Nadu Tiruchirappalli India Department of Mathematics St. Josephs Institute of Technology Tamil Nadu Chennai India

Regression, as a statistical learning process seeks to minimize estimation error by modelling the relationship between independent variables, but Overfitting can result in minimal training loss with significant testing error. Although existing literature offers solutions like Ridge (ℓ2 Norm) and Lasso (ℓ1 Norm) Regression, these methods lack adaptability and precision. In this research, a modified ℓ2 Norm-based regularization is proposed, with an ellipsoid restrictive region for the choice of parameters with the least residual error. The modified ℓ2 regularization has been proved to possess a more adaptable and precise geometry, a better balance in the bias-variance trade-off, and further leads to tighter generalization bounds, as per the Vapnik-Chervonenkis dimension. The efficacy of this modified ℓ2 Norm based regularization in addressing overfitting is compared with various norm-based regularizations including the ℓ1, ℓ2, and a few state-of-the-art paradigms following its applicability on a few real-time datasets with cross-domain applicability. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Overfitting Regression Regularization Vector Algebra

来源：评论

学校读者我要写书评

暂无评论

Toward quantum unmanned systems

引用

science China(Technological sciences) 2024年第7期67卷 2277-2280页

作者： CHENG ShuMing QI HongSheng SUN Yue LIU LiJun XIE ShaoRong REN XiaoQiang Department of Control Science and Engineering Tongji UniversityShanghai 200092China Academy of Mathematics and Systems Science Chinese Academy of SciencesBeijing 100190China Cipher Cloud Core Ltd. Beijing 100085China College of Mathematics and Computer Science Shanxi Normal UniversityLinfen 041081China School of Computer Engineering and Science Shanghai UniversityShanghai 200444China School of Mechatronic Engineering and Automation Shanghai UniversityShanghai 200444China

1 Quantum information technology Quantum information technology utilizes physical systems at the microscopic level, such as photon, atom, ion, and superconducting, to accomplish information-processing tasks that are impossible for the classical macroscopic world. During the past decade, significant process has been achieved in the pursuit of quantum technology into practical applications,generating great research interest from various domains, with the potential to radically change our information infrastructure [1–3].

关键词： quantum utilize generating

来源：评论

学校读者我要写书评

暂无评论

Ensemble Learning-Based Approach for Email Spam Detection 5

Ensemble Learning-Based Approach for Email Spam Detection

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： El Bitar, Ibrahim Abbas, Nadine Raad, Mohamad Shmouri, Farah El Khechen, Fatima Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon Lebanese International University Department of Computer and Communication Engineering Beirut Lebanon

ISBN: (纸本)9798331519957

Email spam remains a pervasive and escalating challenge that poses serious inconveniences, security vulnerabilities, and productivity obstacles for global users. Hence, it is crucially imperative to create more precise and efficient spam detection models for email platforms. Many studies in the literature leverage traditional machine learning techniques for email spam detection. However, despite their simplicity, these methods still face shortcomings in accuracy and generalization. This paper proposed an effective Ensemble Learning model for detecting email spam using Support Vector Classifier, Multilayer Perceptron, and Extra Tree Classifier. Diverse metrics are employed to evaluate the performance of the developed spam email detection system. Experimental results underscore the effectiveness of the proposed model in accurately detecting and classifying spam emails surpassing conventional classification methods. The deployed model exhibits elevated detection rates while sustaining a minimal false positive rate, thereby enhancing the overall user experience and fortifying security measures. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Kubernetes Distributions: Insights from Stress Testing Scenarios 17

Evaluating Kubernetes Distributions: Insights from Stress Te...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Ramadan, Ibrahim Mohamed Centofanti, Carlo Marotta, Andrea Graziosi, Fabio University of L'Aquila Department of Information Engineering Computer Science and Mathematics L'Aquila67100 Italy

ISBN: (纸本)9798331531195

In the modern era, Kubernetes has gained widespread adoption for its capability to manage containerized applications through automation. With a variety of Kubernetes distributions aimed at enhancing and extending core functionalities, there's a pressing need for a thorough evaluation to identify the most efficient solutions for orchestrating workloads. This study aims to assess a variety of Kubernetes distributions including k3s, k3d, Kind, MicroK8s, Minikube, and standard streamlined Kubernetes, focusing on pod orchestration efficiency under stress conditions. Utilizing the open-source tool kube-burner for stress testing, we propose a testing architecture and methodology to measure pod initiation, scheduling, and overall readiness times. The results show that streamlined Kubernetes and k3d outperform the others overall, with Minikube excelling in initiation time, while Kind's performance suggests it might not be suitable for production environments. This analysis highlights the trade-offs and performance impacts of different Kubernetes distributions, guiding users in selecting the most efficient option for their needs. © 2025 IEEE.

关键词： Kubernetes Microservices Orchestration Performance Evaluation Workload Optimization

来源：评论

学校读者我要写书评

暂无评论

Modeling of metaheuristic-based dual cluster head selection with routing protocol for energy-efficient wireless sensor networks

引用

Soft Computing 2025年第6期29卷 2999-3020页

作者： Reddy, Maddikera Krishna Veluswamy, Anusha Sowbarnika Selvanayaki, S. Harini, C. Kumar, Pavan Shameem, Syed Department of Electronics and Communication Engineering Rajeev Gandhi Memorial College of Engineering and Technology Andhra Pradesh Nandyal India Department of Mathematics and Computer Science Susquehanna University Pennsylvania SelinsgrovePA United States Department of Artificial Intelligence and Data Science Saveetha Engineering College Chennai India Maisamma Guda Secunderabad India Department of Computer Science and Engineering Raghu Engineering College Andhra Pradesh Dakamarri Vizayanagaram India Department of ECE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Wireless Sensor Networks (WSN) are decentralized networks of spatially distributed sensors that gather and monitor environmental information for various applications, including industrial automation and environmental monitoring. This enables real-time information gathering without relying upon wired connections. In WSN, clustering and routing are essential techniques for improving data transmission. Clustering comprises grouping sensor nodes (SN) into clusters to optimize energy efficacy and extend the network's lifetime. However, selecting suitable and efficient cluster head (CH) components is crucial to harness their benefits. Selecting appropriate CHs and finding optimum coefficients for all the parameters of applicable fitness function (FF) in CH selection is a non-deterministic polynomial-time (NP-hard) problem that needs additional processing. In contrast, routing focuses on defining the most effective path for data to traverse through the network, ensuring timely and reliable data delivery and reducing energy consumption. Therefore, this study proposes a new Metaheuristic-Based Dual Cluster Head Selection with Routing Protocol (MBDCHS-RP) method for energy-efficient WSNs. The MBDCHS-RP method aims to cluster the nodes and select optimum routes for transmitting information in the WSN. To achieve this, the MBDCHS-RP method follows a two-stage clustering process, including tentative CH (TCH) and final CH (FCH) selection. The MBDCHS-RP technique utilizes a cheetah optimization algorithm (COA) with FF comprising residual energy (RE) and average node distance as input parameters for the TCH selection process. In addition, the flower pollination algorithm (FPA) is used to select final CHs with multiple input parameters, namely average intra-cluster distance, RE, and average sink distance. A carnivorous plant algorithm (CPA) is employed for the optimal route selection process with two parameters, RE and distance to the base station, to enable an effective data transm

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Enhancement in Quality of Routing Service Using Metaheuristic PSO Algorithm in VANET Networks

引用

Soft Computing 2023年第5期27卷 2739-2750页

作者： Javadpour, Amir Rezaei, Samira Sangaiah, Arun Kumar Slowik, Adam Mahmoodi Khaniabadi, Shadi School of Computer Science and Technology Guangzhou University Guangzhou510006 China Bernoulli Institute for Mathematics and Computer Science University of Groningen Groningen Netherlands School of Computing Science and Engineering VIT University Vellore India Department of Industrial Engineering and Management National Yunlin University of Science and Technology Douliu Taiwan Department of Electronics and Computer Science Koszalin University of Technology Koszalin Poland Department of Computer Science and Engineering USM Engineering Campus Pulau Pinang George Town14300 Malaysia

Vehicular ad hoc Networks (VANETs) can be designed in a way to organize road protection with no specific need for any fixed infrastructure. Accordingly, the movement of all vehicles can be planned according to perceived information, and Quality of Services Routing (QoSR) algorithms can be pressured according to its available options, paths, and links, and according to the criteria and reliability of the QoSR. Ensure that QoSR is aware of the environment of the network of vehicles, including location of vehicles, direction, and speed. This study is to reduce the effects of unpredictable problems on the best pathway to replace the broken path/link. A QoSR with Particle Swarm Optimization (QoSR-PSO) is used in this article for improving QoSs in vehicular ad hoc networks. By modeling the behavior of a group of particles, particle swarm optimization algorithms find the best possible solution to the problem. In order to perform simulation experiments, NS2 simulator and VanetMobisim have been used. The comparison results with benchmark studies show the improvement in packet delivery rate (PDR), delay, Packet Drop, and overload. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks (GANs) for Artistic Style Transfer in Images

Generative Adversarial Networks (GANs) for Artistic Style Tr...

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Jamalpur, Bhavana Kiruthiga, S. Ranjitha, B. Lefty Joyson, J. Jayaram, K. Soundar, K. Ruba S R University Department of Computer Science and Artificial Intelligence India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science & Engineering Chennai India Mohan Babu University Department of Mathematics India Jp College of Engineering Department of Computer Science and Engineering Ayikudi India College of Engineering Adoor Department of Computer Science and Engineering Pathanamthitta India Department of Computer Science and Engineering Sivakasi India

ISBN: (纸本)9798350375442

Many in computer vision and computational imaging consider Generative Adversarial Networks (GANs) a big advance. Style transfer converts semantic visual content into creative styles. Recently, GANs for style transfer have gained popularity. Adversarial training of GANs to create realistic counterfeits has yielded encouraging results. High-quality style transfer results have been achieved using this method. Mode collapse is a common problem in classical GANs. This causes unsteady training and poor style transmission. Additionally, the GAN generator only supports one style. Therefore, numerous GANs must be trained to allow users to shift styles. This study examines artistic style transfer in photographs using depth extraction generative adversarial network (DE-GAN). This research aims to improve photo aesthetics by adding famous artworks' distinctive qualities. This study investigates DE-GANs' mechanics and how they modify text while keeping a style's creative qualities. By studying adversarial training, this work hopes to understand how DE-GAN achieves this dual goal. This research analyzes DE-GAN-based style transfer models to evaluate their effectiveness, identify their limits, and recommend areas for improvement. The experiments show that DE-GAN creates realistic and attractive stylized visuals. This study also discusses DE-GAN's practical applications, problems, and future possibilities in artistic style transfer. © 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

Healthcare Monitoring Using Ensemble Classifiers in Fog Computing Framework

引用

computer Systems science & engineering 2023年第5期45卷 2265-2280页

作者： P.M.Arunkumar Mehedi Masud Sultan Aljahdali Mohamed Abouhawwash Department of Computer Science and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

Nowadays,the cloud environment faces numerous issues like synchronizing information before the switch over the data *** requirement for a centralized internet of things(IoT)-based system has been restricted to some *** to low scalability on security considerations,the cloud seems *** healthcare networks demand computer operations on large amounts of data,the sensitivity of device latency evolved among health networks is a challenging *** comparison to cloud domains,the new paradigms of fog computing give fresh alternatives by bringing resources closer to users by providing low latency and energy-efficient data processing *** fog computing frameworks have various flaws,such as overvaluing response time or ignoring the accuracy of the result yet handling both at the same time compromises the network *** this proposed work,Health Fog is integrated with the Optimized Cascaded Convolution Neural Network framework for diagnosing heart ***,the data is collected,and then pre-processing is done by Linear Discriminant *** the features are extracted and optimized using Galactic Swarm *** optimized features are given into the Health Fog framework for diagnosing heart disease *** uses ensemble-based deep learning in edge computing devices,which automatically monitors real-life health networks such as heart disease ***,the classifiers such as bagging,boosting,XGBoost,Multi-Layer Perceptron(MLP),and Partitions(PART)are used for classifying the *** the majority voting classifier predicts the *** work uses FogBus architecture and evaluates the execution of power usage,bandwidth of the network,latency,execution time,and accuracy.

关键词： Healthfog FogBus cascaded convolution neural network cloud computing heart disease automatic health monitoring internet of things

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：