检索结果-内蒙古大学图书馆

International conference on Knowledge-Based Engineering and Innovation (KBEI)

作者： Kousha Nikkar Mohammad Javad Parseh Mohammad Ebrahim Samie Department of Computer Engineering Jahrom University Jahrom Iran

Nowadays, while increasing variety of online social networks (OSNs), content management has become harder. The paper suggests social media pages' managers to publish their contents, including the composition of image, video or text, only once on a OSN and then contents will simply transfer to other OSNs with an add-on software without having to re-use the internet traffic. Suggested method has more high performance than similar ones on any OSN. Also, the proposed technique makes it possible to transmit content between OSNs belonged to different companies. In this study, due to the availability of suitable facilities in both OSNs of Telegram and Instagram, an intermediary software, was implemented under the Android operating system and this action was carried out for the transmission media from the Instagram OSN to the Telegram channels or groups. This study contains three innovations than related researches. The first one is transmission content with the least usage of Internet traffic between OSNs which are not supported by one company. The next innovation is a caching software system to reduce processes of extracting contents from source OSN's network. The third item is transmission delay time decreased sharply. As a result, the trial version has served users and managers of pages and channels, including the official Telegram channel of a TV program named "90" and a news feed named "CANNews" (the analytical aviation industry news feed). Overall, this method not only has 98.81% correct action, but also contents are fitted into the post format of the destination OSN.

关键词： Social networking (online) Bot (Internet) Software Companies Servers Delays

来源：评论

学校读者我要写书评

暂无评论

Optimizing FPGA-based Convolutional Neural Networks Accelerator for Image Super-Resolution 18

Optimizing FPGA-based Convolutional Neural Networks Accelera...

引用

23rd Asia and South Pacific Design Automation conference (ASP-DAC)

作者： Chang, Jung-Woo Kang, Suk-Ju Sogang Univ Dept Elect Engn Seoul South Korea

ISBN: (纸本)9781509006021

Convolutional neural networks (CNN) are widely used in various computer vision applications. Recently, there have been many studies on FPGA-based CNN accelerators to achieve high performance and power efficiency. Most of them have been on CNN-based object detection algorithms, but researches on image super-resolution have been rarely conducted. Fast super-resolution CNN (FSRCNN), well known for CNN-based super-resolution algorithm, are a combination of multiple convolutional layers and a single deconvolutional layer. Since the deconvolutional layer generates high-resolution (HR) output feature maps from low-resolution (LR) input feature maps, its execution cycles are larger than those of the convolutional layer. In this paper, we propose a novel architecture of the FPGA-based CNN accelerator with the efficient parallelization. We develop a method of transforming a deconvolutional layer into a convolutional layer (TDC), a new methodology for the deconvolutional neural networks (DCNN). There is a massive parallelization source in the deconvolutional layer where multiple outputs within the same output feature map are created with the same inputs. When this new parallelization technique is applied to the deconvolutional layer, it generates the LR output feature maps the same as the convolutional layer. Thus, the performance of the accelerator increases without any additional hardware resources because the kernel size required to generate the LR output feature maps is smaller. In addition, if there is a DSP underutilization problem in the deconvolutional layer that some of the processors are in an idle state, the proposed method solves this problem by allowing more output feature maps to be processed in parallel. Experimental results show that the proposed TDC method achieves up to 81 times higher throughput than the state-of-the-art DCNN accelerator with the same hardware resources. We also improve the speed by 7.8 times by having all layers in the hourglass-type FSRCNN

关键词： Kernel Image resolution Parallel processing Convolutional codes Hardware Convolutional neural networks program processors

来源：评论

学校读者我要写书评

暂无评论

high-Fidelity, high-performance Computational Algorithms for Intrasystem Electromagnetic Interference Analysis of IC and Electronics

引用

IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY 2017年第5期7卷 653-668页

作者： Peng, Zhen Shao, Yang Gao, Hong-Wei Wang, Shu Lin, Shen Univ New Mexico Dept Elect & Comp Engn Appl Electromagnet Grp Albuquerque NM 87131 USA

Ever-increasing complexity in high-speed electronic devices and systems presents significant computational challenges in the numerical analysis in terms of desired accuracy, efficiency, and scalable parallelism. The objective of this paper is to investigate high-resolution, high-performance full-wave field solvers for scalable electromagnetic simulations of product-level integrated circuits (ICs) and electronics. The emphasis is placed on advancing parallel algorithms that are provably scalable facilitating a design-through-analysis paradigm, and enabling concurrent multiscale modeling and computation. The capability and the benefits of the algorithms are validated and illustrated through complex 3-D IC and electronics applications.

关键词： Domain decomposition (DD) method electromagnetic interference (EMI) integrated circuit (IC) signal integrity (SI)

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Based Automatic Severity Detector for Diabetic Retinopathy 1

引用

14th International conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2018

作者： AlSaad, Rawan Al-Maadeed, Somaya Al Mamun, Md. Abdullah Boughorbel, Sabri Systems Biology Department Sidra Medicine Doha Qatar Department of Computer Science and Engineering Qatar University Doha Qatar

ISBN: (数字)9783319961361

ISBN: (纸本)9783319961354

Automated Diabetic Retinopathy (DR) screening methods with high accuracy have the strong potential to assist doctors in evaluating more patients and quickly routing those who need help to a specialist. In this work, we used Deep Convolutional Neural Network architecture to diagnosing DR from digital fundus images and accurately classifying its severity. We train this network using a graphics processor unit (GPU) on the publicly available Kaggle dataset. We used Theano, Lasagne, and cuDNN libraries on two Amazon EC2 *** instances and demonstrated impressive results, particularly for a high-level classification task. On the dataset of 30,262 training images and 4864 testing images, our model achieves an accuracy of 72%. Our experimental results showed that increasing the batch size does not necessarily speed up the convergence of the gradient computations. Also, it demonstrated that the number and size of fully connected layers do not have a significant impact on the performance of the model. © 2018, Springer International Publishing AG, part of Springer Nature.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Scaling of Split-Gate Flash Memory with 1 .05V Select Transistor for 28 nm Embedded Flash Technology 10

Scaling of Split-Gate Flash Memory with 1 .05V Select Transi...

引用

10th IEEE International Memory Workshop (IMW)

作者： Do, N. Yang, J. W. Sheng, Y. J. Su, C. S. Wu, M. T. Ouyang, H. Liang, H. Hariharan, S. Tadayoni, M. Norman, J. Vu, T. Ly, A. Hong, S. Tran, H. Tiwari, V. Chen, C. H. Ou, T. F. Shih, C. C. Silicon Storage Technol Inc San Jose CA 95134 USA United Microelect Corp Hsinchu City Taiwan

ISBN: (纸本)9781538652473

This paper discusses the performance and reliability of the third generation split-gate flash memory cell (ESF3) successfully embedded in a high performance and low power 28 nm logic process technology. The scaling of the 1.05V select transistor is demonstrated with the excellent program and erase efficiency and the 1M program/erase (P/E) cycle endurance capability. The silicon result of a 4Mb test chip and a 32Mb design will be also be shown.

关键词： Nonvolatile memory computer architecture Split gate flash memory cells Logic gates Microprocessors Transistors Reliability

来源：评论

学校读者我要写书评

暂无评论

A Left-Looking Selected Inversion Algorithm and Task Parallelism on Shared Memory Systems 2018

A Left-Looking Selected Inversion Algorithm and Task Paralle...

引用

International conference on high performance Computing in Asia-Pacific Region (HPC Asia) / Workshop on Partitioned Global Address Space programming Models - Experiences and Implementations (PGAS-EI) / Intel-Xeon-Phi-User's-Group (IXPUG) Workshop Asia

作者： Jacquelin, Mathias Lin, Lin Jia, Weile Zhao, Yonghua Yang, Chao Lawrence Berkeley Natl Lab Berkeley CA 94720 USA Univ Calif Berkeley Berkeley CA 94720 USA Chinese Acad Sci Supercomp Ctr Beijing Peoples R China

ISBN: (纸本)9781450353724

Given a sparse matrix A, the selected inversion algorithm is an efficient method for computing certain selected elements of A-1. These selected elements correspond to all or some nonzero elements of the LU factors of A. In many ways, the types of matrix updates performed in the selected inversion algorithm are similar to those performed in the LU factorization, although the sequence of operations is different. In the context of LU factorization, it is known that the leftlooking and right-looking algorithms exhibit different memory access and data communication patterns, and hence different behavior on shared memory and distributed memory parallel machines. Corresponding to right-looking and left-looking LU factorization, the selected inversion algorithm can be organized as a left-looking or a right-looking algorithm. The parallel right-looking version of the algorithm has been developed in [9]. The sequence of operations performed in this version of the selected inversion algorithm is similar to those performed in a left-looking LU factorization algorithm. In this paper, we describe the left-looking variant of the selected inversion algorithm, and present an efficient implementation of the algorithm for shared memory machines using a task parallel method. We demonstrate that with the task scheduling features provided by OpenMP 4.0, the left-looking selected inversion algorithm can scale well both on the Intel Haswell multicore architecture and on the Intel Knights Landing (KNL) manycore architecture up to 16 and 64 cores, respectively. On the KNL architecture, we observe that the maximum parallel efficiency achieved by the left-looking selected inversion algorithm can be as high as 62% even when all 64 cores are used, despite the inherent asynchronous nature of the computation and communication patterns in sparse matrix operations. Compared to the right-looking selected inversion algorithm, the left-looking formulation facilitates efficient pipelining of operations

关键词： selected inversion shared memory parallel algorithm openmp multicore manycore task scheduling high performance computation

来源：评论

学校读者我要写书评

暂无评论

Assessing the performance of Quantitative Image Features on Early Stage Prediction of Treatment Effectiveness for Ovary Cancer Patients: A Preliminary Investigation 13

Assessing the Performance of Quantitative Image Features on ...

引用

conference on Biophotonics and Immune Responses XIII

作者： Zargari, Abolfazi Du, Yue Thai, Theresa C. Gunderson, Camille C. Moore, Kathleen Mannel, Robert S. Liu, Hong Zheng, Bin Qiu, Yuchen Univ Oklahoma Sch Elect & Comp Engn Norman OK 73019 USA Univ Oklahoma Hlth Sci Ctr Dept Radiol Oklahoma City OK 73104 USA Univ Oklahoma Hlth Sci Ctr Dept Obstet & Gynecol Oklahoma City OK 73104 USA

ISBN: (纸本)9781510614765

The objective of this study is to investigate the performance of global and local features to better estimat the characteristics of highly heterogeneous metastatic tumours, for accurately predicting the treatment effectiveness of the advanced stage ovarian cancer patients. In order to achieve this , a quantitative image analysis scheme was developed to estimate a total of 103 features from three different groups including shape & density, Wavelet, and Gray Level Difference Method (GLDM) features. Shape & density features are global features, which are directly applied on the entire target image;wavelet and GLDM features are local features, which are applied on the divided blocks of the target image. To assess the performance, the new scheme was applied on a retrospective dataset containing 120 recurrent and high grade ovary cancer patients. The results indicate that the three best performed features are skewness, root-mean-square (rms) and mean of local GLDM texture, indicating the importance of integrating local features. In addition, the averaged predicting performance are comparable among the three different categories. This investigation concluded that the local features contains at least as copious tumour heterogeneity information as the global features, which may be meaningful on improving the predicting performance of the quantitative image markers for the diagnosis and prognosis of ovary cancer patients.

关键词： Quantitative image features ovary cancer predicting performance computer aided diagnosis chemotherapy response

来源：评论

学校读者我要写书评

暂无评论

Efficient Small Object Detection with an Improved Region Proposal Networks

Efficient Small Object Detection with an Improved Region Pro...

引用

International conference on Electrical Engineering, Control and Robotics

作者： DongWen Ma XiaoJun Wu Honghong Yang Key Laboratory of Modern Teaching Technology Ministry of Education(Shaanxi Normal University) School of Computer Science(Shaanxi Normal University)

ISBN: (纸本)9781510887374

Although the state-of-the-art object detection methods, which depend on region proposal algorithms to hypothesize object locations, have achieved high detection accuracy, it still struggles in small-size object detection. In this paper, we present a novel method with a multi-scale and multi-tasking region proposal method to effectively detect small object. In the proposed method, multi-scale features and high-level features are employed to locate object position and identify object category, respectively. The main contributions of the proposed approach are two-fold:(1) A simpler way is used to improve the accuracy performance of small object detection, instead of the complex image pyramids and the complex combination framework, and make the object detection task more flexible.(2) Based on multi-scale and multi-tasking approaches, object location information in low layers and object semantic information in deep layers are made fully advantage respectively. The experimental results on the PASCAL VOC dataset show that the proposed method achieves the state-of-the art object detection accuracy.

关键词： Efficient Small Object Detection with an Improved Region Proposal Networks Object

来源：评论

学校读者我要写书评

暂无评论

A Service Annotation Quality Improvement Approach based on Efficient Human Intervention 25

A Service Annotation Quality Improvement Approach based on E...

引用

25th IEEE International conference on Web Services (IEEE ICWS) Part of the IEEE World Congress on Services

作者： Sun, Xuehao Chen, Shizhan Feng, Zhiyong Ge, Weimin Huang, Keman Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Tianjin Univ Sch Comp Sci & Technol Tianjin 300350 Peoples R China Tianjin Univ Sch Comp Software Tianjin 300350 Peoples R China MIT Sloan Sch Management Cambridge MA 02142 USA

ISBN: (纸本)9781538672471

Semantic Annotation plays an essential role in automatic service discovery and composition. However, existing approaches and tools cannot achieve high annotation quality to ensure the semantic service application. Meanwhile, the semiautomatic strategies for improving the annotation quality are time-consuming. To further improve the efficiency as well as the quality of the annotation, this paper presents an effective method involving human-computer interaction to further optimize the annotation procedure. Besides employing the feedback and propagation strategy to semi-automatically improve the annotation quality, the strategy to involve the manual annotation is developed when the efficiency of semi-automatically strategy is related low. To optimize the manual annotation procedure, a clustering based approach is presented to select the most impacted candidates to optimize the annotation improvement. In addition, to help the annotators to choose the correct annotation, the local ontology restriction based method is further designed to improve the recommendation performance. The experiments show that our approach effectively involving the human intervention can significantly improve the annotation quality, faster the quality improvement procedure and reduce the manual load by increasing the recommendation accuracy.

关键词： Annotation Quality for Web Services Human-computer Interaction Efficiency of Quality Improvement Effective Annotation Object Local Ontology Restriction

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Networks for Online Travel Mode Detection

Recurrent Neural Networks for Online Travel Mode Detection

引用

2019 IEEE Global Communications conference (GLOBECOM)

作者： Elton F. de S. Soares Hojjat Salehinejad Carlos Alberto V. Campos Shahrokh Valaee IBM Research Department of Electrical & Computer Engineering University of Toronto Toronto CA Postgraduate Program in Informatics Federal University of the State of Rio de Janeiro Rio de Janeiro RJ Brazil

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

Intelligent Transportation System's main objective is to provide sustainable and optimized means of transportation for citizens of urban centers. Identifying the travel modes used by citizens, in real- time, allows these systems to better adapt transportation infrastructure and services according to user needs and possibilities of interaction. Many works have explored the use of machine learning algorithms and ensemble methods, combined with general and domain specific feature extraction techniques, for this task. More recently, several works evaluated the use of deep learning algorithms while none of them has explored the use of Recurrent Neural Networks (RNNs) in conjunction with domain feature extraction to enable the development of flexible and lightweight travel mode detection solutions based on multiple smartphone sensor readings. In this paper, we propose a deep RNN architecture for building online travel mode detection models using Long-Short Term Memory (LSTM) cells and evaluate its performance using real mobility data collected with a wide variety of sensors. The experiments show that the proposed architecture allows the generation of models with high accuracy and lower memory consumption and computation cost than state-of-the-art supervised machine learning (ML) approaches.

关键词： Feature extraction Logic gates Machine learning Transportation Data models Global Positioning System Recurrent 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：