检索结果-内蒙古大学图书馆

TechRxiv 2021年

作者： Zheng, Danyang Shen, Gangxiang Cao, Xiaojun Mukherjee, Biswanath Suzhou Key Laboratory of Advanced Optical Communication Network Technology The School of Electronic and Information Engineering Soochow University Suzhou215006 China The Department of Computer Science Georgia State University AtlantaGA30302 United States

Emerging 5G technologies can significantly reduce end-to-end service latency for applications requiring strict quality of service (QoS). With network function virtualization (NFV), to complete a client’s request from those applications, the client’s data can sequentially go through multiple service functions (SFs) for processing/analysis but introduce additional processing delay. To reduce the processing delay from the serially-running SFs, network function parallelism (NFP) that allows multiple SFs to run in parallel is introduced. In this work, we study how to apply NFP into the SF chaining and embedding process such that the latency, including processing and propagation delays, can be jointly minimized. We introduce a novel augmented graph to address the parallel relationship constraint among the required SFs. Considering parallel relationship constraints, we propose a novel problem called parallelism-aware service function chaining and embedding (PSFCE). For this problem, we propose a near-optimal maximum parallel block gain (MPBG) first optimization algorithm when computing resources at each physical node are enough to host the required SFs. When computing resources are limited, we propose a logarithm-approximate algorithm, called parallelism-aware SFs deployment (PSFD), to jointly optimize processing and propagation delays. We conduct extensive simulations on multiple network scenarios to evaluate the performances of our schemes. Accordingly, we find that (i) MPBG is near-optimal, (ii) the optimization of end-to-end service latency largely depends on the processing delay in small networks and is impacted more by the propagation delay in large networks, and (iii) PSFD outperforms the schemes directly extended from existing works regarding end-to-end latency. © 2021, CC BY-SA.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Survey on the Application of Deep Reinforcement Learning in Image processing

引用

Journal on Artificial Intelligence 2020年第1期2卷 39-58页

作者： Wei Fang Lin Pang Weinan Yi School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjingChina State Key Laboratory for Novel Software Technology Nanjing UniversityNanjingChina Jiangsu Key Laboratory of Computer Information Process Technology Soochow UniversitySuzhouChina

feature representations from a large amount of data,and use reinforcement learning to learn the best strategy to complete the *** the combination of deep learning and reinforcement learning,end-to-end input and output can be achieved,and substantial breakthroughs have been made in many planning and decision-making systems with infinite states,such as games,in particular,AlphaGo,robotics,natural language processing,dialogue systems,machine translation,and computer *** this paper we have summarized the main techniques of deep reinforcement learning and its applications in image processing.

关键词： Reinforcement learning image processing

来源：评论

学校读者我要写书评

暂无评论

Software/Hardware Co-Design Optimization for Sparse Convolutional Neural Networks

Software/Hardware Co-Design Optimization for Sparse Convolut...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Wei Hu Yong Dong Fang Liu Qiang Jiao College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China School of Computer Science Wuhan University Wuhan China Wuhan City College Wuhan China

ISBN: (纸本)9781665442084

Deep convolutional neural network (DNN) has been widely used in image recognition, target detection, and natural language processing. Unfortunately, the previous state-of-the-art convolutional neural network (CNN) increase model accuracy by increasing the number of layers of the network, which leads to the problem of large models and complex calculations. Previous work has demonstrated that network compression can be achieved by weight pruning approaches, and that specialized hardware can be used to speed up reasoning. However, the format of compressed sparse rows (CSR) or compressed sparse columns (CSC) is generally used in model pruning. The approach leads to coding operations before calculation and decoding operations during calculation by processing units on specialized hardware. And the approach degrades the performance of the *** this paper, we propose a combination of hardware and software to address above bottlenecks. Firstly, we propose a novel software-based structured pruning, called vector-pruning. Secondly, we design a novel dataflow for our pruning method, called Vector-Sparse, our method eliminates complex coding and decoding Then, we design the corresponding hardware architecture for vector-prune. Finally, we evaluate the performance of our pruning approach for AlexNet on Xilinx xcvu19p-fsva3824-2-e. Experiments show that compared with a state-of-the-art convolution network accelerator, we proposed a software/hardware co-design approach that is 1.01x and 1.3x better in performance, effectively improving the inference speed of the model on Field Programmable Gate Array (FPGA).

关键词： Computational modeling Object detection Throughput Hardware Software Encoding Decoding

来源：评论

学校读者我要写书评

暂无评论

Correlation-aware deep generative model for unsupervised anomaly detection

arXiv

引用

arXiv 2020年

作者： Fan, Haoyi Zhang, Fengbin Wang, Ruidong Xi, Liang Li, Zuoyong School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

Unsupervised anomaly detection aims to identify anomalous samples from highly complex and unstructured data, which is pervasive in both fundamental research and industrial applications. However, most existing methods neglect the complex correlation among data samples, which is important for capturing normal patterns from which the abnormal ones deviate. In this paper, we propose a method of Correlation aware unsupervised Anomaly detection via Deep Gaussian Mixture Model (CADGMM), which captures the complex correlation among data points for high-quality low-dimensional representation learning. More specifically, the relations among data samples are correlated firstly in forms of a graph structure, in which, the node denotes the sample and the edge denotes the correlation between two samples from the feature space. Then, a dual-encoder that consists of a graph encoder and a feature encoder, is employed to encode both the feature and correlation information of samples into the low-dimensional latent space jointly, followed by a decoder for data reconstruction. Finally, a separate estimation network as a Gaussian Mixture Model is utilized to estimate the density of the learned latent vector, and the anomalies can be detected by measuring the energy of the samples. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed *** Codes 68T30 Copyright © 2020, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

RISC-VTF: RISC-V Based Extended Instruction Set for Transformer

RISC-VTF: RISC-V Based Extended Instruction Set for Transfor...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Qiang Jiao Wei Hu Fang Liu Yong Dong College of Computer Science and Technology Wuhan University of Science and Technology Wuhan Hubei China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System China School of Computer Science Wuhan University Wuhan China Wuhan City College Wuhan China

ISBN: (纸本)9781665442084

Deep learning model Transformer has been widely used in natural language processing(NLP) filed, and its demand for computing resources is also growing. However, general-purpose processors(CPU and GPU) have invested excessive hardware resources in the design because they have to flexibly support a variety of tasks, they are not efficient for the implementation of Transformer. Consequently, various software optimizations that towards general-purpose processors have been proposed one after another. But, under the condition of ensuring sufficient accuracy, the degree of software optimization is limited. It is requisite to friendly-support Transformer at the hardware *** analysing the computational characteristics of the Transformer model, based on RISC-V, we designed a hardware friendly instruction set architecture for the Transformer model. In addition to the basic instruction, for the intensive and general computing part of the model, according to the expansion rules of RISC-V instruction, we design the matrix load/store instruction calculation instruction, softmax instruction, activation instruction and other user-defined instructions. They support any matrix scale, and deploy it on FPGA to realize a flexible and efficient custom processor RISC-VTF for Transformer. The design is integrated on the Xilinx toolkit zynq-7000 FPGA, and the resource consumption and performance are analyzed. Compared with the traditional common ISA(Instruction Set Architecture) such as x86, arm or MIPs, RISC-VTF provides higher code density and performance efficiency.

关键词： Analytical models Computational modeling Instruction sets computer architecture Transformers Hardware Software

来源：评论

学校读者我要写书评

暂无评论

Using quantum thinking to construct a musical appreciation system 2nd

Using quantum thinking to construct a musical appreciation s...

引用

2nd International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2018

作者： Peng, Mei Gangyi, Ding Qiankun, Jin Fuquan, Zhang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9783030045845

With the richness of material and cultural life, participating in music activities and enjoying music works has become an indispensable activity in people’s leisure time. The rich emotions in music have different performances according to individual differences. After the composers create the music, the performer’s deductive processing and then the emotion is sublimated by the viewers finally. This paper proposes a new emotional system for basic emotional joy, anger, sadness, joy, etc., and interprets the superposition state of emotional expression in detail. The paper believes that the generation of consciousness and the resonance of thinking are precisely the result of the quantum collapse of mutual entanglement. © Springer Nature Switzerland AG 2019.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Unified Framework for Oculomotor Nerve Reconstruction: Tractography-Based Anatomical Assessment

引用

Journal of neuroimaging : official journal of the American Society of Neuroimaging 2025年第3期35卷 e70052页

作者： Jiahao Huang Qingrun Zeng Ye Wu Jiawei Zhang Mengjun Li Lei Xie Mingchu Li Yuanjing Feng Institute of Information Processing and Automation College of Information Engineering Zhejiang University of Technology Hangzhou China. Zhejiang Provincial United Key Laboratory of Embedded Systems Hangzhou China. School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China. Department of Radiology Second Xiangya Hospital Central South University Changsha China. Department of Neurosurgery Capital Medical University Xuanwu Hospital Beijing China.

BACKGROUND AND PURPOSE:The oculomotor nerve (OCN) innervates the eye muscles and can be affected by inflammatory, compressive, and pathological conditions. Diffusion MRI (dMRI) tractography shows the potential ability to describe the trajectory of the OCN. However, reconstruction of the OCN in the cavernous sinus is still challenging due to the complex tissue environment at the skull base. METHODS:In this study, we integrated anatomical knowledge to propose a unified framework for OCN tractography, using 45 dMRI datasets from the Human Connectome Project subjects aged 22-36 years and data from four neurosurgical patients aged 41-53 years with visual behavior disorders. We first employed automatically labeled direct and indirect anatomical landmarks as reference locations for individualized tractography. Next, we compared five widely used cranial nerve reconstruction algorithms to assess the most suitable method for OCN reconstruction. Finally, we tested the combination of the unified framework and the optimized tractography method in tumor patients. RESULTS:We found that unscented Kalman filter (UKF)-2T and probabilistic tractography outperformed other methods in OCN fiber tractography, owing to their "step-by-step" fiber direction computation and multidirectional consideration, respectively. In neurosurgical patients, UKF-2T effectively reconstructed OCN fibers around lesions. CONCLUSION:Our study provides valuable insights for researchers and clinicians in the diagnosis and treatment of OCN-related diseases and neurosurgeries.

关键词： Human Connectome Project diffusion magnetic resonance imaging neurosurgery oculomotor nerve tractography

来源：评论

学校读者我要写书评

暂无评论

Augmented reality-based pre-visualization for film making 2nd

Augmented reality-based pre-visualization for film making

引用

2nd International Conference on Smart Vehicular technology, Transportation, Communication and Applications, VTCA 2018

作者： Xue, Tong Ding, Gangyi Zhang, Fuquan School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

ISBN: (纸本)9783030045845

With the development of the augmented reality technologies, wearing devices such as Microsoft Hololens and Google glass become highly popular recently. In this paper, we proposed a novel augmented reality application that helps the film directors to complete and facilitate their film rehearsal process. We simulated a design space to provide film directors with a high-fidelity visual-audio experience. The directors wearing the hololens are allowed to observe the synthesized virtual-reality space in which they can recognize the whole design space, prefabricated boxes, and modify the space by defined gestures. Feedbacks from directors indicate the proposed tool is effective and the preliminary experimental results agree with our observations. In general, our research offers the guidelines for novel film rehearsal tactics. © Springer Nature Switzerland AG 2019.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Application of R-FCN algorithm in machine visual solutions on tensorflow based 5th

Application of R-FCN algorithm in machine visual solutions o...

引用

5th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2018

作者： Zhang, Yumeng Ma, Yanchao Zhang, Fuquan Beijing Information Science Technology University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9783030037659

This paper presents a solution based on Tensorflow platform and R - FCN deep learning model about self-driving cars image processing. Through the Supervised learning of data sets, make them exercise the image segmentation and recognition of information, thus to self-driving cars driving decision-making support. © Springer Nature Switzerland AG 2019.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

The mean-variance-skewness cardinality constrained portfolio optimization problem using a customized multi-objective evolutionary algorithm 3

The mean-variance-skewness cardinality constrained portfolio...

引用

3rd IEEE International Conference on Electronic information technology and computer Engineering, EITCE 2019

作者： Li, Lan Huang, Wenlan Zhang, Yu Harbin University of Commerce School of Computer and Information Engineering Heilongjiang Provincial Key Laboratory of Electronic Commerce and Information Processing Harbin China Harbin University of Commerce School of Computer and Information Engineering Harbin China

ISBN: (纸本)9781728135847

MVSCCPO is a mean-variance-skewness portfolio optimization problem with cardinality constraint. It increases the skewness as the third objective, and introduces cardinality constraint to reduce the difficulty of asset management. A customized NSGA-III(c-NSGA-III) algorithm is proposed for the problem. It introduces an effective solution representation mechanism, customized crossover and mutation operators, a tournament selection based on membership is introduced in the mating selection phase instead of the original random selection method. Finally, an empirical analysis is carried out to verify the effectiveness of the proposed algorithm by comparing with NSGA-II and MOEA/D. The results show that c-NSGA-III performs better than other algorithms on solving MVSCCPO problem. © 2019 IEEE.

关键词： Clustering algorithms

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：