检索结果-内蒙古大学图书馆

Conference on Image Sensing Technologies - Materials, Devices, Systems, and Applications VII

作者： Goswami, Debabrata IIT Kanpur Dept Chem Kanpur 208016 Uttar Pradesh India

ISBN: (纸本)9781510635548

Many large image processing and data processing scenarios can soon develop into maze problems requiring, say, finding the longest possible path, which are unresponsive, intractable, and challenging to analyze! Such maze problems, of which the traveling salesman decision problem is a special case, are of the Non-determinate Polynomial (NP-complete) class of problems that are often impossible to solve with finite time and storage. We propose a novel methodology to approach this class of NP-complete problems. We convert a suitably formulated maze problem into a Quantum Search Problem (QSP), and the desired solutions are then sought using the iterative Grover's Search Algorithm. Thus, we reformulate the entire class of such NP-problems into QSPs. Our current solution deals with two-dimensional perfect mazes with no closed loops. We encode all possible individual paths from the starting point of the maze into a quantum register. A quantum fitness operator applied to the register encodes each qubit with its fitness value. We propose the design of an optical oracle that marks all entities above a certain fitness value and uses the Grover search algorithm to find the optimal marked state in an iterative manner.

关键词： Efficient image processing Effective Image processing parallelism Innovative image sensing system Effective processing of large image files Longest Path problem big data processing Traveling salesman Problem

来源：评论

学校读者我要写书评

暂无评论

Physics-based stitching of multi-FOV PIV measurements for urban wind fields

引用

BUILDING AND ENVIRONMENT 2021年 205卷 108306-108306页

作者： Li, Haiwei Zhao, Yongling Liu, Jianlin Carmeliet, Jan Swiss Fed Inst Technol Dept Mech & Proc Engn CH-8092 Zurich Switzerland Donghua Univ Coll Environm Sci & Engn Shanghai Peoples R China

Particle image velocimetry (PIV) is commonly used to measure multiple field-of-views (FOVs) of the flow in large urban domains, performed in wind tunnels using an array of cameras located at fixed positions or a single camera setup that traverses during the measurements. With respect to the large amount of data produced in this type of measurement, traditional stitching approaches are no longer adequate to efficiently merge the image data. A physics-based flow field stitching method is proposed for stitching flows in urban wind fields, named regionalflow stitching. It matches the flow characteristics within neighboring FOVs of flow using a vorticity-based reference window. The method is based on finding the optimal similarity between a reference window in one FOV and another possible matching window in the other FOV. The matching window rolls in both directions at the interval of two adjacent data points, which determines the stitching resolution. The matching in flow similarity is evaluated using the normalized root-mean-squared error (NRMSE) between reference and possible matching windows, which is evaluated by comparison to a traditional stitching method and further verified using planar and stereo wind tunnel PIV measurement results. A comparison of computational cost with 8 FOVs and approximate 7% surface overlap between FOVs shows that our method is faster, taking about 46% of processing time, than a traditional stitching method. 3D visualization of the merged FOVs is further demonstrated with ParaView. The proposed stitching method may serve as a powerful tool for experimental studies involving large domains of urban wind flow fields.

关键词： Urban wind field Wind tunnel measurement PIV data stitching big data processing

来源：评论

学校读者我要写书评

暂无评论

The new analysis framework at the ALICE experiment

The new analysis framework at the ALICE experiment

引用

Conference on Photonics Applications in Astronomy, Communications, Industry, and High Energy Physics Experiments

作者： Kabus, Maja Warsaw Univ Technol Fac Math & Informat Sci Warsaw Poland

ISBN: (数字)9781510639881

ISBN: (纸本)9781510639881

The ALICE experiment is one of the main detectors at the CERN Large Hadron Collider. Currently, the online/offline software of the experiment is being re-developed under the name O-2 as part of the ALICE upgrade aiming at an increased data-taking rate by a factor 100 compared to today. This includes the implementation of a new Analysis Framework for physics data analysis. The aim is to provide an efficient data processing with an object-like, user-friendly API, making it easier for the users to migrate from the old software framework and taking implicit advantage of vectorisation and parallelisation. The solution is based on Apache Arrow for data representation, allowing for integration with other tools like Python Pandas. Current progress and the advantages of the approach taken are presented.

关键词： ALICE Large Hadron Collider CERN O-2 Apache Arrow big data processing

来源：评论

学校读者我要写书评

暂无评论

Contact-Tracing based on Time-Varying Graphs Analysis 8

Contact-Tracing based on Time-Varying Graphs Analysis

引用

8th IEEE International Conference on big data (big data)

作者： Goglia, Lorenzo Zimeo, Eugenio Univ Sannio Dept Engn Benevento Italy Univ Sannio Dept Engn CINI Smart City Lab Benevento Italy

ISBN: (纸本)9781728162515

The widespread diffusion of the SARS-CoV2 virus in the last months has forced many organizations in different socio-economic fields to study new technologies to counteract its presence. One of these technologies is contact tracing based on the collection of device interactions by using specific apps and device capabilities. By tracing and storing device interactions, when a person is revealed as infected after a specific test, other people who entered in contact with the infected one are notified for an early screening aimed at stopping the infection spreading. Several solutions have been developed at regional, national or continental level, according to different architectures (centralized, decentralized and hybrid) depending on the degree of desired privacy. However, none of them exploits interaction tracing to build graphs for early detection of critical identities. y In this paper, we propose an architecture, a framework and an algorithm to identify, in quasi-real-time, critical spots in time-varying graphs inferred from device interactions captured by scanning Bluetooth advertisements. We show, by examples, how the approach could provide useful information for early detecting critical people in order to prioritize mass screening for improving the effectiveness and breaking infection chains. Finally, a prototype implementation is presented.

关键词： Bluetooth LE Graphs big data processing Microservices Betweeness centrality

来源：评论

学校读者我要写书评

暂无评论

Efficient processing of Recursive Joins on Large-Scale datasets in Spark 6th

Efficient Processing of Recursive Joins on Large-Scale Datas...

引用

6th International Conference on Computer Science, Applied Mathematics and Applications (ICCSAMA)

作者： Thuong-Cang Phan Anh-Cang Phan Thi-To-Quyen Tran Ngoan-Thanh Trieu Can Tho Univ Can Tho Vietnam Vinh Long Univ Technol Educ Vinh Long Vietnam Univ Rennes 1 Lannion France

ISBN: (纸本)9783030383640;9783030383633

MapReduce has become the dominant programming model for analyzing and processing large-scale data. However, the model has its own limitations. It does not completely support iterative computation, caching mechanism, and operations with multiple inputs. Besides, I/O and communication costs of the model are so expensive. One of the most notably complex operations extensively and expensively used in MapReduce is recursive joins. It requires processing characteristics that are the limitations of a MapReduce environment. Therefore, this research proposes efficient solutions for processing recursive joins in Spark, a next-generation data processing engine of MapReduce. Our proposal eliminates a large amount of redundant data generated in repeated join steps and takes advantages of in-memory computing means and cache mechanism. Through experiments, the present research shows that our solutions significantly improve the execution performance of recursive joins on large-scale datasets.

关键词： big data processing Recursive join MapReduce Spark

来源：评论

学校读者我要写书评

暂无评论

Computer Vision for Smart Farming and Sustainable Agriculture

Computer Vision for Smart Farming and Sustainable Agricultur...

引用

IST-Africa Conference (IST-Africa)

作者： Tombe, Ronald Kisii Univ Dept Comp Sci Kisii Kenya

ISBN: (纸本)9781905824656

Developments in satellite technology, remote sensors and drone technologies are mushrooming. These developments yield volumes of high quality scene images that require effective processing for intelligent farming applications. The recent deep learning technologies can leverage these opportunities to fuse computer vision and artificial intelligence in farming. This encompasses the big data phenomena and huge volumes of data that are captured, processed and applied for decision-making. This paper aims to give insights on the integration of computer vision for smart farming in-order to attain sustainable agriculture. Using a structured approach, this research proposes a computer vision technique for crop image feature characterization that applies in the determination of the crop's health status. To achieve this, a deep convolutional network is applied for image feature extraction and representation, and then these features are fed to the support vector-learning machine for training and subsequent image interpretation. From the experimental results, it is evident that the proposed technique generates superior visual interpretation results of scene images as compared to other methods in literature. It follows that the Global food security and agricultural sustainability can be attained through ICT enabled solutions that are integrates and works together a phenomenon referred to as smart farming.

关键词： remote sensing images drones computer vision deep learning machine learning big data processing

来源：评论

学校读者我要写书评

暂无评论

Smart Management for Smart Cities - Synchronized Solutions

引用

IFAC-PapersOnLine 2021年第13期54卷 732-737页

作者： Alexander F. Pashchenko Institute of Control Sciences of Russian Academy of Sciences Moscow Russia

The paper observes the most updated concepts of Smart Cities. Problem of sustainable development of the cities is presented. An overview of transformation from Smart Cities to Smart Countries is given. Intelligent management system is proposed in the paper enhancing efficiency in the application of intelligent e-Government and Smart City projects in all areas. Integrated Operation Center is introduced - a new concept of operational intelligence, being able to digitize, monitor, predict, act, make better and faster decisions and engage with their citizens. Proposed concept of smart city (smart region, smart country) management system would allow if implemented to make a breakthrough change, improve efficiency in the management and operation of a city or a region.

关键词： Smart City artificial intelligence internet of things big data processing smart management system sustainable development

来源：评论

学校读者我要写书评

暂无评论

Saksham: Resource Aware Block Rearrangement Algorithm for Load Balancing in Hadoop

Saksham: Resource Aware Block Rearrangement Algorithm for Lo...

引用

International Conference on Computational Intelligence and data Science (ICCIDS)

作者： Shah, Ankit Padole, Mamta Shankersinh Vaghela Bapu Inst Technol Gandhinagar 382650 India Maharaja Sayajirao Univ Baroda Vadodara 390002 India

big data Analytics demands huge processing power. Distributed computing seems to be a viable solution with the usage of commodity computers. But, processing big data optimally, on distributed systems poses the number of challenges, such as seamlessly integrating different resources of distributed systems. Hadoop provides this ease and hence is one of the most commonly used tools for the processing of big data. But, it is observed that the performance of Hadoop is compromised, when it comes to the heterogeneous environment. This paper proposes Saksham: The block rearrangement algorithm which optimizes the processing time by efficient file system management in the heterogeneous environment. Our proposed scheme successfully optimizes the big data processing over the homogeneous and heterogeneous environment. To achieve better performance for big data processing, we target two important aspects of heterogeneous distributed computing: file system management and process management. First, file system management basically controls the block placement and allows us to rearrange the blocks on specified nodes, considering the node's storage and processing capability. Second, we use the concept of node labeling and scheduling to achieve better process management. The results prove that the proposed approach has optimized job execution time along with reduced latency and data-skew substantially. (C) 2020 The Authors. Published by Elsevier B.V.

关键词： Hadoop load balancing Custom block placement Hadoop performance improvement big data processing Heterogeneous distributed computing

来源：评论

学校读者我要写书评

暂无评论

Framework for Error Detection & its Localization in Sensor data Stream for reliable big sensor data analytics using Apache Spark Streaming

引用

Procedia Computer Science 2020年 167卷 2337-2342页

作者： Govind P. Gupta Jahanvi Khedwal

Internet of Things (IoT) is one of the big sources of big Sensor data in which collected sensor readings often polluted due to corruption and losses of the sensor readings. In big Sensor data analytics, fast and efficient detection of error and its localization is a challenging research issue. Most of the existing solutions for the error detection and localization in sensor data use offline techniques for detecting errors. In this paper, we propose a novel framework for online error detection and its localization which uses an online scheme for detecting and localizing errors in sensor data using latest big data processing tools such as Apache Spark streaming. Performance evaluation of the proposed framework is done using two different datasets such as real-time air quality dataset of the Raipur city and Intel sensor dataset in terms of false positive.

关键词： Error detection Apache Spark Streaming big data processing localization Sensor data

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Parallelisation Model for Performance Prediction of Apache Spark on a Multinode Hadoop Cluster

引用

big data AND COGNITIVE COMPUTING 2021年第4期5卷 65页

作者： Ahmed, Nasim Barczak, Andre L. C. Rashid, Mohammad A. Susnjak, Teo Massey Univ Sch Nat & Computat Sci Auckland 0745 New Zealand Massey Univ Dept Mech & Elect Engn Auckland 0745 New Zealand

big data frameworks play a vital role in storing, processing, and analysing large datasets. Apache Spark has been established as one of the most popular big data engines for its efficiency and reliability. However, one of the significant problems of the Spark system is performance prediction. Spark has more than 150 configurable parameters, and configuration of so many parameters is challenging task when determining the suitable parameters for the system. In this paper, we proposed two distinct parallelisation models for performance prediction. Our insight is that each node in a Hadoop cluster can communicate with identical nodes, and a certain function of the non-parallelisable runtime can be estimated accordingly. Both models use simple equations that allows us to predict the runtime when the size of the job and the number of executables are known. The proposed models were evaluated based on five HiBench workloads, Kmeans, PageRank, Graph (NWeight), SVM, and WordCount. The workload's empirical data were fitted with one of the two models meeting the accuracy requirements. Finally, the experimental findings show that the model can be a handy and helpful tool for scheduling and planning system deployment.

关键词： big data processing Apache Spark execution time prediction performance prediction modelling

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：