检索结果-内蒙古大学图书馆

Improved Dynamic Johnson Sequencing Algorithm(DJS)in Cloud computing Environment for Efficient Resource Scheduling for Distributed Overloading

引用

Journal of Systems Science and Systems engineering 2024年第4期33卷 391-424页

作者： Anurag Sinha Pallab Banerjee Sharmistha Roy Nitasha Rathore Narendra Pratap Singh Mueen Uddin Maha Abdelhaq Raed Alsaqour Department of Computer Science Engineering ICFAI Tech SchoolICFAI UniversityJharkhandRanchi834004India Department of Computer Science Engineering Amity UniversityJharkhandRanchi835303India Department of Computing and Information Technology Usha Martin UniversityRanchi835103India Department of Information Technology Bharti Vidyapeeth’s College of EngineeringPaschim ViharNew DelhiIndia Department of CSE Delhi UniversityNew DelhiIndia College of Computing and Information Technology University of Doha for Science and TechnologyDoha24449Qatar Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdurrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computing and InformaticsSaudi Electronic University93499RiyadhSaudi Arabia

This study introduces an innovative approach to optimize cloud computing job distribution using the Improved Dynamic Johnson Sequencing Algorithm(DJS).Emphasizing on-demand resource sharing,typical to Cloud Service Providers(CSPs),the research focuses on minimizing job completion delays through efficient task *** Johnson’s rule from operations research,the study addresses the challenge of resource availability post-task *** advocates for queuing models with multiple servers and finite capacity to improve job scheduling models,subsequently reducing wait times and queue *** Dynamic Johnson Sequencing Algorithm and the M/M/c/K queuing model are applied to optimize task sequences,showcasing their efficacy through comparative *** research evaluates the impact of makespan calculation on data file transfer times and assesses vital performance indicators,ultimately positioning the proposed technique as superior to existing approaches,offering a robust framework for enhanced task scheduling and resource allocation in cloud computing.

关键词： First come first served(FCFS)scheduling round robin task scheduling queuing model Johnson scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

PSO Based Multi-Objective Approach for Controlling PID Controller

引用

Computers, Materials & Continua 2022年第6期71卷 4409-4423页

作者： Harsh Goud Prakash Chandra Sharma Kashif Nisar Ag.Asri Ag.Ibrahim Muhammad Reazul Haque Narendra Singh Yadav Pankaj Swarnkar Manoj Gupta Laxmi Chand Indian Institute of Information Technology NagpurIndia School of Computing&Information Technology Manipal UniversityJaipur(Rajasthan)India Faculty of Computing and Informatics University Malaysia SabahJalan UMS88400Kota Kinabalu SabahMalaysia Faculty of Computing&Informatics Multimedia UniversityPersiaran Multimedia63100CyberjayaSelangorMalaysia Maulana Azad National Institute of Technology BhopalIndia Department of Electronics and Communication Engineering JECRC UniversityJaipur(Rajasthan)India

CSTR(Continuous stirred tank reactor)is employed in process control and chemical industries to improve response characteristics and system *** has a highly nonlinear characteristic that includes complexities in its control and *** performance is compassionate to change in system parameterswhich need more effort for planning a significant controller for *** reactor temperature changes in either direction from the defined reference *** is important to note that the intensity of chemical actions inside the CSTR is dependent on the various levels of temperature,and deviation from reference values may cause degradation of biomass *** and implementation of an appropriate adaptive controller for such a nonlinear system are *** this paper,a conventional Proportional Integral Derivative(PID)controller is *** conventional techniques to deal with constraints suffer severe limitations like it has fixed controller ***,A novel method is applied for computing the PID controller parameters using a swarm algorithm that overcomes the conventional controller’s *** the proposed technique,PID parameters are tuned by Particle Swarm Optimization(PSO).It is not easy to choose the suitable objective function to design a PID controller using PSO to get an optimal *** this article,a multi-objective function is proposed for PSO based controller design of CSTR.

关键词： Particle swarm optimization multi-objective PSO continuous stirred tank reactor proportional integral derivative controller

来源：评论

学校读者我要写书评

暂无评论

Research on railroad line spatial information management technology

Research on railroad line spatial information management tec...

引用

2023 International Conference on Remote Sensing, Mapping, and Geographic Systems, RSMG 2023

作者： Li, Congxu Xu, Xiaolei Feng, Boqing Zhang, Maolin Institute of Computing Technologies China Academy of Railway Sciences Corporation Limited China Beijing University of Civil Engineering and Architecture School of Geomatics and Urban Spatial Informatics Beijing100044 China

ISBN: (纸本)9781510668898

With the completion of railroad line resurvey work, the measurement data are scattered in various units and lack unified storage and management, which brings many challenges and problems to railroad operation and maintenance. To solve this problem, this study proposes a multi-version, multi-temporal spatial data storage technology, as well as a distributed fast storage technology and a spatial service engine by studying the data management work, aiming to realize unified and fast storage, management and sharing of railroad survey data to improve the reliability, consistency and validity of data. First, this study focuses on the multi-version and multi-temporal spatial data storage technology. By adopting this technology, a large amount of spatial data generated by railroad line resurvey can be effectively handled, and the storage and management of different versions and temporal phases of data can be realized. Meanwhile, distributed fast storage technology is introduced to provide high-speed data access and processing capability to cope with the storage and processing demand of massive data. In addition, using the spatial service engine, fast query and analysis of measurement data can be realized. Second, this study also conducts an in-depth research on the railroad line measurement data management system. First, the overall architecture of the system is designed to ensure the scalability and flexibility of the system. Then, the data structure of the system was optimized to accommodate the storage and query requirements of multi-version and multi-temporal data. In terms of technical architecture, distributed storage technology is adopted to realize fast storage and retrieval of remote sensing, 2D vector and 3D model data. In addition, the sharing and exchange of measurement data is realized through information sharing and information interface. The innovation of this study is to propose a multi-version and multi-temporal spatial data storage technology, and to reali

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

A Systematic Overview on Simulation of Connected Vehicles Infrastructure in Smart Cities 1

A Systematic Overview on Simulation of Connected Vehicles In...

引用

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Gupta, Manik Dhaou, Imed Ben Garg, Kamal Deep Sharma, Bhisham Chitkara University School of Engineering and Technology Chitkara University Himachal Pradesh India Dar Al-Hekma University Hekma School of Engineering Computing and Informatics Department of Computer Science Jeddah Saudi Arabia Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (纸本)9781665472753

The development and use of connected vehicles are becoming increasingly important areas of study in the wireless networking and transportation research communities. These networks can provide various services such as collision warning. Unlike other types of devices, such as hand-held devices, the vehicles' nodes are not limited by their energy consumption and storage capacity. Therefore, the development of connected networks can be carried out with minimal resources. It is necessary to run a simulation in order to determine whether they are feasible. The availability of multiple devices and protocols has led to the creation of new utilization scenarios. Due to the complexity of the task, many simulation tools were developed during the past few years. This paper systematically reviews the current state of these tools and discusses their capabilities to evaluate the various scenarios related to the development of connected vehicles network. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Light-Weight Pointcloud Representation with Sparse Gaussian Process

Light-Weight Pointcloud Representation with Sparse Gaussian ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mahmoud Ali Lantao Liu Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

This paper presents a framework to represent high-fidelity pointcloud sensor observations for efficient communication and storage. The proposed approach exploits Sparse Gaussian Process to encode pointcloud into a compact form. Our approach represents both the free space and the occupied space using only one model (one 2D Sparse Gaussian Process) instead of the existing two-model framework (two 3D Gaussian Mixture Models). We achieve this by proposing a variance-based sampling technique that effectively discriminates between the free and occupied space. The new representation requires less memory footprint and can be transmitted across limited-bandwidth communication channels. The framework is extensively evaluated in simulation and it is also demonstrated using a real mobile robot equipped with a 3D LiDAR. Our method results in a 70~100 times reduction in the communication rate compared to sending the raw pointcloud. We have provided a demonstration video 1 1 Video: https://***/BQZzXiCFGrM and open-sourced our code 2 2 Code: https://***/mahmoud-a-ali/vsgp_pcl.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling technology for fusion of massive strip 3D terrain and feature models

Modeling technology for fusion of massive strip 3D terrain a...

引用

2023 International Conference on Remote Sensing, Mapping, and Geographic Systems, RSMG 2023

作者： Li, Congxu Feng, Boqing Xu, Xiaolei Zhang, Miao Institute of Computing Technologies China Academy of Railway Sciences Corporation Limited China School of Geomatics and Urban Spatial Informatics Beijing University of Civil Engineering and Architecture Beijing100044 China

ISBN: (纸本)9781510668898

In order to solve the problem that traditional GIS methods are difficult to handle massive data, complex spatial relationships and accurate geographic phenomenon modeling. By fusing terrain and feature models, geographic phenomena can be efficiently and accurately represented and analyzed to provide a reliable basis for decision making. This paper proposes a fusion modeling technique for massive strip 3D terrain and feature models, aiming to solve the problem of effective fusion and modeling of 3D terrain and feature models for strip data in large-scale spatial data processing. Based on open-source geographic information technology, the traditional method is designed to unify and model 2D vector data, raster data, BIM data and 3D data from different sources, formats and scales to form a standardized spatial data set, in response to the problems of high computational complexity, large storage requirements and data redundancy in processing massive data. For the characteristics of strip data and 3D terrain and feature models, geometric matching and semantic matching methods are used to fuse and process vector data representing the same entity with different attribute information and spatial location information to solve the problem of data redundancy and duplication;it is used to describe the different levels and precision of spatial data, and the appropriate data precision can be flexibly selected in the fusion modeling process, so as to achieve a balance between data quality and calculation The purpose of balancing data quality and computational efficiency. Based on LOD hierarchical detail technology fusion processing of terrain-independent BIM models, terrain-dependent fusion of linear 3D feature models, to achieve the surface fitting of multi-source 3D model data in a specific scene, to improve the 3D scene display effect. In terms of data processing efficiency: traditional GIS methods may face bottlenecks in computation and storage when dealing with massive data.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

CKN: An Edge AI Distributed Framework

CKN: An Edge AI Distributed Framework

引用

IEEE International Conference on e-Science and Grid computing

作者： Sachith Withana Beth Plale Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

The edge-cloud-HPC continuum is transformative for AI processing at the edge. With greater availability of both edge and cloud resources, AI inference, training, and optimization can be distributed across the continuum. We target edge-cloud in particular where the workload at the Edge server can exhibit discrete changes, for instance, when motion is detected. We optimize for Quality of Experience (QoE) and utilize historical data from the Edge, graphs, and Deep Learning to infer the next action to take. Using a large synthetic workload and publicly profiled inference models, our results show that predictive guidance outperforms random choice or best guess in optimal QoE of the edge-cloud continuum.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized Speech Enhancement

The Potential of Neural Speech Synthesis-Based Data Augmenta...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Anastasia Kuznetsova Aswin Sivaraman Minje Kim Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

With the advances in deep learning, speech enhancement systems benefited from large neural network architectures and achieved state-of-the-art quality. However, speaker-agnostic methods are not always desirable, both in terms of quality and their complexity, when they are to be used in a resource-constrained environment. One promising way is personalized speech enhancement (PSE), which is a smaller and easier speech enhancement problem for small models to solve, because it focuses on a particular test-time user. To achieve the personalization goal, while dealing with the typical lack of personal data, we investigate the effect of data augmentation based on neural speech synthesis (NSS). In the proposed method, we show that the quality of the NSS system’s synthetic data matters, and if they are good enough the augmented dataset can be used to improve the PSE system that outperforms the speaker-agnostic baseline. The proposed PSE systems show significant complexity reduction while preserving the enhancement quality.

关键词： Measurement Deep learning Adaptation models Neural networks Speech enhancement Signal processing Data models

来源：评论

学校读者我要写书评

暂无评论

GP-Frontier for Local Mapless Navigation

GP-Frontier for Local Mapless Navigation

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mahmoud Ali Lantao Liu Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN USA

We propose a new frontier concept called the Gaussian Process Frontier (GP-Frontier) that can be used to locally navigate a robot towards a goal without building a map. The GP-Frontier is built on the uncertainty assessment of an efficient variant of sparse Gaussian Process. Based only on local ranging sensing measurement, the GP-Frontier can be used for navigation in both known and unknown environments. The proposed method is validated through intensive evaluations, and the results show that the GP-Frontier can navigate the robot in a safe and persistent way, i.e., the robot moves in the most open space (thus reducing the risk of collision) without relying on a map or a path planner. A supplementary video that demonstrates the robot navigation behavior is available at https://***/ndpqTNYqGfw.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variational Inference on the Final-Layer Output of Neural Networks

arXiv

引用

arXiv 2023年

作者： Wei, Yadi Khardon, Roni Luddy School of Informatics Computing and Engineering Indiana University United States

Traditional neural networks are simple to train but they typically produce overconfident predictions. In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large parameter space. This paper proposes to combine the advantages of both approaches by performing Variational Inference in the Final layer Output space (VIFO), because the output space is much smaller than the parameter space. We use neural networks to learn the mean and the variance of the probabilistic output. Using the Bayesian formulation we incorporate collapsed variational inference with VIFO which significantly improves the performance in practice. On the other hand, like standard, non-Bayesian models, VIFO enjoys simple training and one can use Rademacher complexity to provide risk bounds for the model. Experiments show that VIFO provides a good tradeoff in terms of run time and uncertainty quantification, especially for out of distribution data. Copyright © 2023, The Authors. All rights reserved.

关键词： Multilayer neural 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：