检索结果-内蒙古大学图书馆

3rd International conference on Cyberspace Data and Intelligence, Cyber DI 2019, and the International conference on Cyber-Living, Cyber-Syndrome, and Cyber-Health, CyberLife 2019

作者： Bo, Wen Yang, Hongju Xiao, Jiaojiao Li, Liangyan Zhang, Changyou School of Computer and Information Technology Shanxi University TaiyuanShanxi China Laboratory of Parallel Software and Computational Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789811519215

With the development of intelligent traffic system, high-definition cameras are spread along the urban roads. These devices transmit real-time captured images to data center for multi-purpose usability, but these bring higher requirements on network and storage capacity of the traffic images collection system. To address these problems, we proposed a compressed representation method for traffic images and collection system architecture. Firstly, the method proposed in this paper designed a distributed data collection system for traffic images based on edge computing mode. Secondly, we studied on the image feature representation methods for vehicle type/version retrieval, and formed a compressed representation method based on structural relationships selections. In this method, the retrieval precision reaches to 97.78% with the recall ratio of 90%, which proved the usability in this image collection system. Finally, we set up an analysis model based on Petri-net to observe the system requirements on storage, computing and transmission with different setting parameters. This model is powerful on finding bottlenecks of system in early stage and keeping balance in multi-aspects. The simulation experiments show that the data volume needs to be transported and preserved was compressed to 1/2250 comparing to the method of original images and the system transport delay was reduced more than 1/9 of original method. The experimental result showed that compared with the original collection method, the amount of data to be transmitted and stored was compressed by 1/2250, and the system transmission delay of the system was reduced to 1/9.15. This distributed data collection method and system proposed in this paper provided a novel referable revolution for traffic images processing system in intelligent traffics. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Relaxation Method of Convolutional Neural Networks for Natural Language processing 15th

Relaxation Method of Convolutional Neural Networks for Natur...

引用

15th International conference on distributed Computing and Artificial Intelligence (DCAI)

作者： Iwasaki, Ryo Hasegawa, Taku Mori, Naoki Matsumoto, Keinosuke Osaka Prefecture Univ Naka Ku 1-1 Gakuen Cho Sakai Osaka Japan

ISBN: (纸本)9783319946498;9783319946481

Deep learning has developed into one of the most powerful methods in the machine learning field. In particular, convolutional neural networks (CNNs) have been applied not only to image recognition tasks but also to natural language processing (NLP). To reuse older deep learning models, transfer learning techniques have been widely used in the image recognition field. However, there has been little research on transfer learning in NLP. In this paper, we propose a novel transfer learning model based on a relaxation method of CNNs for NLP. The effectiveness of the proposed method is verified using computer simulations, taking a film review score recognition task as an example.

关键词： Deep learning Convolutional neural network Relaxation Natural language processings

来源：评论

学校读者我要写书评

暂无评论

3rd EAI International conference on Advanced Hybrid Information processing, ADHIP 2019

3rd EAI International Conference on Advanced Hybrid Informat...

引用

3rd EAI International conference on Advanced Hybrid Information processing, ADHIP 2019

ISBN: (纸本)9783030364045

The proceedings contain 101 papers. The special focus in this conference is on Advanced Hybrid Information processing. The topics include: Research on Delay Control Method of Ultra-Wideband Wireless Communication Based on Artificial Intelligence;research on Anomaly Monitoring Algorithm of Uncertain Large Data Flow Based on Artificial Intelligence;Research on parallel Mining Method of Massive image Data Based on AI;Floating Small Target Detection in Sea Clutter Based on Jointed Features in FRFT Domain;research on Fatigue Life Prediction Method of Ballastless Track Based on Big Data;design of High Speed Railway Turnout Structural Damage Identification System Based on Machine Learning;research on Data Integrity Encryption Method of Cloud Storage Users Based on Big Data Analysis;intelligent Detection Method for Maximum Color Difference of image Based on Machine Learning;automatic Color Control Method of Low Contrast image Based on Big Data Analysis;construction Quality Inspection Method of Building Concrete Based on Big Data;research on Reduced Dimension Classification Algorithm of Complex Attribute Big Data in Cloud Computing;research on Hierarchical Mining Algorithm of Spatial Big Data Set Association Rules;uniform Acceleration Motion Target Location and Tracking Based on Time-Frequency Difference;Variable Scale Iterative SAR Imaging Algorithm Based on Sparse Representation;ioT Security Access Authentication Method Based on Blockchain;continuous Predictive Model for Quality of Experience in Wireless Video Streaming;Knowledge-Aided Group GLRT for Range distributed Target Detection in Partially Homogeneous Environment;Asynchronous distributed ADMM for Learning with Large-Scale and High-Dimensional Sparse Data Set;smart Phone Aided Intelligent Invoice Reimbursement System.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CNN-based Monocular Decentralized SLAM on embedded FPGA

CNN-based Monocular Decentralized SLAM on embedded FPGA

引用

IEEE International Symposium on parallel and distributed processing Workshops and Phd Forum (IPDPSW)

作者： Jincheng Yu Feng Gao Jianfei Cao Chao Yu Zhaoliang Zhang Zhengfeng Huang Yu Wang Huazhong Yang Electronic Engineering Department Tsinghua University Beijing China School of Microelectronics Hefei University of Technology Hefei China

ISBN: (数字)9781728174457

ISBN: (纸本)9781728174570

Decentralized visual simultaneous localization and mapping (DSLAM) can share locations and environmental information between robots, which is an essential task for many multi-robot applications. The visual odometry (VO) is a basic component to estimate the 6-DoF absolute pose for robot applications. Decentralized place recognition (DPR) is a fundamental element to produce candidate place matches for sharing information among different robots. The goal of this paper is to build a CNN-based real-time DSLAM system on embedded FPGA platforms. Because of the high precision requirement of VO, the existing quantization methods can not be directly applied. We improve the fixed-point fine-tune method for the CNN-based monocular VO, which enables VO can be deployed on the fixed-point FPGA accelerator. We also explore the influence of the DPR frequency on the DSLAM results, and find out a proper DPR frequency to balance the accuracy and speed. A cross-component pipeline scheduling method is proposed to improve DPR frequency and further improve the final accuracy of DSLAM under the same hardware resource constraints.

关键词： Robots Field programmable gate arrays Cameras image reconstruction Quantization (signal) Hardware Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Corporate-Level Communities at Ericsson: parallel Organizational Structure for Fostering Alignment for Autonomy 1

引用

20th International conference on Agile Software Development (XP)

作者： Smite, Darja Moe, Nils Brede Wigander, Jonas Esser, Hendrik Blekinge Inst Technol Karlskrona Sweden SINTEF Trondheim Norway Ericsson Stockholm Sweden

ISBN: (数字)9783030190347

ISBN: (纸本)9783030190347;9783030190330

Organizational management traditionally has taken care of all the important strategy, structure, and work-design decisions, as well as most of the ongoing decisions about work procedures. In large-scale corporations with many geographically distributed sites and high divisional detachment, such strategies are yet doomed to result in implementing irrelevant work methods and procedures that conflict with the local interests. As Tayloristic habits are disappearing, organizations willingly or unwillingly change their decision-making approaches to enable more participation and influence from the performers. These trends are associated with the rise of participation-based parallel structures, such as quality circles, task forces or communities of practice. In this paper, we present our findings from studying corporate-level communities by the means of a multi-case study at Ericsson. We found that the main hindrances are related to the limited decision-making authority of parallel structure, member selection and achieving representation across the organizational units. Our results suggest that parallel structures highly depend on the authority of the members within their local communities, and their ability to not only channel the dialog between the units they represent and the community, but also enable the active engagement of the unit in the community studies. As such, we believe that special attention shall be put on the ambassador role of the community members.

关键词： Large-scale agile Organizational agility Bottom-up governance Communities parallel structures Alignment for autonomy Empirical

来源：评论

学校读者我要写书评

暂无评论

Implementation of Temporal parallelization for Rapid Quasi-Static Time-Series (QSTS) Simulations 46

Implementation of Temporal Parallelization for Rapid Quasi-S...

引用

IEEE 46th Photovoltaic Specialists conference (PVSC)

作者： Azzolini, Joseph A. Reno, Matthew J. Montenegro, Davis Sandia Natl Labs Albuquerque NM 87185 USA Elect Power Res Inst Knoxville TN 37932 USA

ISBN: (纸本)9781728104942

Quasi-static time-series (QSTS) analysis of distribution systems can provide critical information about the potential impacts of high penetrations of distributed and renewable resources, like solar photovoltaic systems. However, running high-resolution yearlong QSTS simulations of large distribution feeders can be prohibitively burdensome due to long computation times. Temporal parallelization of QSTS simulations is one possible solution to overcome this obstacle. QSTS simulations can be divided into multiple sections, e.g. into four equal parts of the year, and solved simultaneously with parallel computing. The challenge is that each time the simulation is divided, error is introduced. This paper presents various initialization methods for reducing the error associated with temporal parallelization of QSTS simulations and characterizes performance across multiple distribution circuits and several different computers with varying architectures.

关键词： distribution system modeling quasi-static time-series PV grid integration parallel processing

来源：评论

学校读者我要写书评

暂无评论

Cloud-based difference algorithm using big GPR data for roadbed damage detection

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2020年第23期32卷

作者： Xu, Xianlei Gao, Wenru Zhang, Di Li, Taotao Qiao, Xu State Key Lab Water Resources Protect & Utilizat Beijing Peoples R China China Univ Min & Technol Beijing State Key Lab Coal Resources & Safe Min Beijing 100083 Peoples R China China Univ Min & Technol Beijing Sch Mech Elect & Informat Engn Beijing Peoples R China

Ground-penetrating radar (GPR) technology is being widely used for urban roadbed damage detection. In this paper, we present the development of a cloud-based difference detection method using big GPR data for roadbed damage detection. Unlike many processing methods relying on standalone servers, the proposed method can achieve high accuracy and processing efficiency by distributing the computation over a server cluster. The method includes a difference detection algorithm for GPR image enhancement and damage extraction, the Hadoop distributed File System, and MapReduce distributed parallel computing framework for big GPR data parallel processing and interpretation. Moreover, to automatize roadbed damage classification, a criterion with seven grades is established based on the wave group shape, amplitude, phase, and attenuation characteristics. We validate the proposed method through a detection experiment that was conducted on the Fourth Ring Road in Beijing, China. The detection revealed 187 damage from the efficient processing of big GPR data, thus suggesting the ability of the proposed method to provide timely support for road safety in cities.

关键词： cloud computing difference detection GPR parallel computation roadbed damage detection

来源：评论

学校读者我要写书评

暂无评论

A Critical Review of Object Detection using Convolution Neural Network 2

A Critical Review of Object Detection using Convolution Neur...

引用

2nd International conference on Communication, Computing and Digital Systems (C-CODE)

作者： Nisa, Sehar Un Imran, Muhammad Shaheed Zulfikar Ali Bhutto Inst Sci & Technol SZ Islamabad Pakistan

ISBN: (纸本)9781538696095

To recognize an object, for a human, is an easy task but for machines, to perform the same task with same efficiency is a complex task. For computer systems, images are sets of numeric values that have no meaning in itself. To make these numbers useful, diverse techniques have been proposed. Comparative to others, deep learning approaches achieved state-of-the-art performance in many computer vision applications, such as object detection, image classification, image retrieval, human pose estimation. To detect object of interest, Convolutional Neural Network (CNN) has been observed widely successful method. Few factors are there to get better accuracy and performance for instance efficient model, larger datasets and hardware support. This study aims to review CNN methods for object detection by highlighting the contribution and challenges from few recent research papers. Also how well to use these CNN techniques in combination to other methods for best suited results with other. Better performance such as increased accuracy, fast processing reduce error rates also introduced few new concerns and issues in parallel regarding the discussed methods such as time consumption, anonymous behavior of Neural Network. To address these issues a conceptual model is presented using CNN and Lease Square Support Vector Machine (LS-SVM).

关键词： computer vision Convolutional Neural Network detection image Lease Square Support Vector Machine object

来源：评论

学校读者我要写书评

暂无评论

LoCEC: Local Community-based Edge Classification in Large Online Social Networks

LoCEC: Local Community-based Edge Classification in Large On...

引用

International conference on Data Engineering

作者： Chonggang Song Qian Lin Guohui Ling Zongyi Zhang Hongzhao Chen Jun Liao Chuan Chen Tencent Inc National University of Singapore

ISBN: (数字)9781728129037

ISBN: (纸本)9781728129044

Relationships in online social networks often imply social connections in real life. An accurate understanding of relationship types benefits many applications, e.g. social advertising and recommendation. Some recent attempts have been proposed to classify user relationships into predefined types with the help of pre-labeled relationships or abundant interaction features on relationships. Unfortunately, both relationship feature data and label data are very sparse in real social platforms like WeChat, rendering existing methods inapplicable. In this paper, we present an in-depth analysis of WeChat relationships to identify the major challenges for the relationship classification task. To tackle the challenges, we propose a Local Community-based Edge Classification (LoCEC) framework that classifies user relationships in a social network into real-world social connection types. LoCEC enforces a three-phase processing, namely local community detection, community classification and relationship classification, to address the sparsity issue of relationship features and relationship labels. Moreover, LoCEC is designed to handle large-scale networks by allowing parallel and distributed processing. We conduct extensive experiments on the real-world WeChat network with hundreds of billions of edges to validate the effectiveness and efficiency of LoCEC.

关键词： Social network services image edge detection Games Task analysis Feature extraction Advertising Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Comparative Benchmarking Analysis of Next-Generation Space Processors

Comparative Benchmarking Analysis of Next-Generation Space P...

引用

IEEE Aerospace conference

作者： Gretok, Evan W. Kain, Evan T. George, Alan D. Univ Pittsburgh Dept Elect & Comp Engn NSF Ctr Space High Performance & Resilient Comp S 4420 Bayard StSuite 560 Pittsburgh PA 15213 USA

ISBN: (纸本)9781538668542

Researchers, corporations, and government entities are seeking to deploy increasingly compute-intensive workloads on space platforms. This need is driving the development of two new radiation-hardened, multi-core space processors, the BAE Systems RAD5545TM processor and the Boeing High-Performance Spaceflight Computing (HPSC) processor. As these systems remained in the development phase, the Freescale P5020DS and P5040DS systems, based on the same PowerPC e5500 architecture as the RAD5545 processor, and the Hardkernel ODROID-C2, sharing the same ARM Cortex-A53 core as the HPSC processor, were selected as facsimiles for evaluation. Several OpenMP-parallelized applications, including a color search, Sobel filter, Mandelbrot set generator, hyperspectral imaging target classifier, and image thumbnailer, were benchmarked on these processing platforms. Performance and energy consumption results on these facsimiles were scaled to forecasted frequencies of the radiation-hardened devices in development. In these studies, the RAD5545 achieved the highest and most consistent parallel efficiency, up to 99%. The HPSC processor achieved faster execution times, averaging about half that of the RAD5545 processor, with lower energy consumption. The evaluated applications reached up to 3.9 speedup across four cores. The frequency-scaling methods were validated by comparing the set of scaled measures with data points from an underclocked facsimile, which yielded an average accuracy of 97% between estimated and measured results. These performance outcomes help to establish the capabilities of both the RAD5545 and HPSC processors for on-board parallel processing of computationally-demanding applications for future space missions.

关键词： Program processors Performance evaluation Computer architecture Bandwidth parallel processing Space vehicles Benchmark testing

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：