检索结果-内蒙古大学图书馆

A Painting Style System using an Improved CNN Algorithm

IEIE Transactions on Smart Processing and Computing 2022年第5期11卷 332-342页

作者： Zhong, Yuan Huang, Xinyan Department of Architecture Sichuan College of Architectural Technology Chengdu615000 China School of Computer Science and Technology Shandong University of Finance and Economics Ji’nan250014 China

The rapid development of deep learning technology allows ordinary people to create artwork that imitates the style of paintings by famous masters through an algorithm. To create such works with artistic style, this research proposes an artificial neural network algorithm based on an improved convolutional neural network (CNN). First, a fast style-rendering model based on the improved CNN is constructed, and then, a server front end is built with the Bootstrap framework. The server-side back end of the system is built by combining a Python algorithm and a web framework, and finally, a complete model of the front-end and back-end network of the style rendering system is constructed. The model proposed in this paper is compared with two other models to verify its performance. The results show that information entropy of the model constructed is the highest at 5.58, which is higher than information entropy of the other two models. The average gradient value and the peak signal-to-noise ratio under the constructed model are 22.54 and 27.81, respectively, which are also higher than the other two models. Mutual information and the structural similarity index between rendered images and sample images under all three models were compared. Mutual information and structural similarity index of the model constructed by this research are 1.19 and 0.56, respectively, with much larger data sizes than the two comparison models. © 2022 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reliably locking system v shared memory for user level communication in linux

Reliably locking system v shared memory for user level commu...

引用

2001 IEEE International Conference on Cluster Computing, CLUSTER 2001

作者： Seifert, Friedrich Rehm, Wolfgang Chemnitz University of Technology Department of Computer Science Chair of Computer Architecture Strabe der Nationen 62 Chemnitz09111 Germany

ISBN: (纸本)0769511163

A major trend in recent cluster communication systems is to circumvent the operating system during the actual data transfers. That, on the one hand, reduces latency since there is no user-kernel transition needed and, on the other hand, increases bandwidth by avoiding additional intermediate copies. The data transfer is handled completely by the networking hardware and its DMA engine. For example, the Virtual Interface processes can access networking hardware directly in a protected manner. One of its characteristics is that it requires that all memory used for communication be locked down into physical memory. The same requirement holds true for the Infiniband ensures reliable locking of regular, i.e. private, virtual memory without altering the kernel. In this paper we present an extended solution that can handle System V shared memory as well. © 2001 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Linux

来源：评论

学校读者我要写书评

暂无评论

A comparative evaluation of parallel programming models for shared-memory architectures

A comparative evaluation of parallel programming models for ...

引用

2012 10th IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2012

作者： Sanchez, Luis Miguel Fernandez, Javier Sotomayor, Rafael Garcia, J. Daniel Computer Architecture and Technology Area Computer Science Department Universidad Carlos III De Madrid Madrid Colmenarejo 28270 Spain

ISBN: (纸本)9780769547015

Nowadays, most computers that are commercially available off-the-shelf (COTS) include hardware features that increase the performance of parallel general-purpose threads (hyper threading, multicore, ccNUMA architectures) or SIMD kernels (CPU vector instructions, GPUs). The purpose of this paper is to perform a compared evaluation of several parallel programming models where each one is fitted to exploit some of these features but also each one requires a different level of programming skills. Four parallel programming models (OpenMP, Intel TBB, Intel ArBB, and CUDA) have been selected. The idea is to cover a wide spectrum of programming models and most of the parallel hardware features included in modern computers. On one hand, OpenMP and TBB platforms, that exploit parallel threads running on multicore systems. On the other hand, ArBB, that combines muticore parallel threads and multicore SIMD features with a simpler programming model, and CUDA that exploits SIMD features of the GPU hardware. Our results obtained with the benchmarks used on this paper suggest that OpenMP and TBB have a lower performance compared to ArBB and CUDA. But also that ArBB performance tends to be comparable with CUDA performance in most cases (although it is normally lower). Thus, there are evidences that a careful designed top range multicore and multisocket architecture, can be comparable in terms of performance with top range GPU cards for many applications, with the advantage of a simpler programming model. © 2012 IEEE.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

Expert mutation operators for the evolution of radial basis function neural networks

引用

6th International Work-Conference on Artificial and Natural Neural Networks, IWANN 2001

作者： González Rojas, Jesús Rojas, I. Pomares, H. Department of Computer Architecture and Computer Technology University of Granada Campus Cle Fncn Temeva E. 18071 Granada Spain

ISBN: (纸本)3540422358

This paper compares some mntationoperators containing expert knowledge about the problem of optimizing the parameters of a Radial Basis Function Neural Network. It is shown that the expert kno wledge is not always able to improve the results obtained by a blind evolutionary algorithm, and that the final results depend strongly on how the expert knowledge is utilized. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

On comparing non-singleton type-1 and singleton type-2 fuzzy controllers for a nonlinear servo system

On comparing non-singleton type-1 and singleton type-2 fuzzy...

引用

IEEE/ACM Symposium on Advances in Type-2 Fuzzy Logic Systems

作者： Cara, Ana Belén Rojas, Ignacio Pomares, Héctor Wagner, Christian Hagras, Hani Department of Computer Architecture and Computer Technology University of Granada Spain Computational Intelligence Centre School of Computer Science and Electronic Engineering University of Essex United Kingdom

ISBN: (纸本)9781612840789

Uncertainty handling is a major issue for the control of real-world systems. Traditional singleton type-1 Fuzzy Logic Controllers (FLCs) with crisp inputs and precise fuzzy sets cannot fully cope with the high levels of uncertainties present in real world environments (e.g. sensor noise, environmental impacts, etc.). While non-singleton type-1 fuzzy systems can provide an additional degree of freedom through non-singleton fuzzification of the inputs, it is unclear how this capability relates to singleton type-1 and specifically interval type-2 FLCs in terms of control performance (also because the application of non-singleton type-1 FLCs is quite rare in the literature). In recent years interval type-2 FLCs employing type-2 fuzzy sets with a Footprint of Uncertainty (FOU) have become increasingly popular. This FOU provides an additional degree of freedom that can enable type-2 FLCs to handle the uncertainties associated with the inputs and the outputs of the FLCs. One of the main criticisms of singleton type-2 FLCs is that they outperform (the usually singleton-) type-1 FLCs because they - respectively their type-2 fuzzy sets, employ extra parameters, thus making improved performance an obvious result. In order to address this criticism, we have implemented a non-singleton type-1 FLC which allows a more direct comparison between the non-singleton type-1 FLC and singleton interval type-2 FLC as the number of parameters for both controllers is very similar. The paper details the implementation details of the FLCs for the application of a nonlinear servo system and provides the experimental simulation results which were performed to study the effect of increasing levels of uncertainty (in the form of input noise) and the capability of the individual FLCs to cope with them. We conclude by providing our interpretation of the results and highlighting the essential differences in the uncertainty handling between the (non-) singleton type-1 and singleton interval type-2 FLC

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Reducing Synchronization Cost for Single-Level Store in Mobile Systems

引用

Journal of computer Science & technology 2016年第4期31卷 836-848页

作者： Yuan-Chao Xu Hu Wan Ke-Ni Qiu Tao Li Wei-Gong Zhang College of Information Engineering Capital Normal University Beijing 100048 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Department of Electrical and Computer Engineering University of Florida Gainesville FL 32611 U.S.A.

Emerging byte-addressable non-volatile memory technologies, such as phase change memory （PCM） and spin- transfer torque RAM （STT-RAM）, offer both the byte-addressability of memory and the durability of storage, thus making it feasible to build single-level store systems. To ensure the consistency of persistent data structures in the presence of power failures or system crashes, it requires flushing cache lines to persistent memory frequently, thus incurring non-trivial synchronization overhead. To mitigate this issue, we propose two techniques. First, we use non-volatile STT-RAM as scratchpad memory on chip to store recovery information, thereby eliminating synchronization cost in the logging phase due to the avoidance of off-chip logging operations. Second, we present an adaptive synchronization policy based on caching modes in terms of data access patterns, thereby eliminating unnecessary synchronization cost in the checkpoint phase. Evaluation results indicate that the two techniques improve the overall performance from 2.15x to 2.39x compared with conventional transactional persistent memory.

关键词： crash consistency synchronization cost persistent memory power failure mobile system

来源：评论

学校读者我要写书评

暂无评论

Maneuvering Angle Rigid Formations With Global Convergence Guarantees

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1464-1475页

作者： Liangming Chen Zhiyun Lin Hector Garcia de Marina Zhiyong Sun Mir Feroskhan School of Mechanical and Aerospace Engineering Nanyang Technological UniversitySingapore 639798Singapore Department of Computer Architecture and Technology and also with CITICUniversity of Granada18014 GranadaSpain Department of Electrical Engineering Eindhoven University of Technology5600 MB Eindhoventhe Netherlands

Angle rigid multi-agent formations can simultaneously undergo translational,rotational,and scaling maneuvering,therefore combining the maneuvering capabilities of both distance and bearing rigid ***,maneuvering angle rigid formations in 2D or 3D with global convergence guarantees is shown to be a challenging problem in the existing literature even when relative position measurements are *** by angle-induced linear equations in 2D triangles and 3D tetrahedra,this paper aims to solve this challenging problem in both 2D and3D under a leader-follower *** the 2D case where the leaders have constant velocities,by using local relative position and velocity measurements,a formation maneuvering law is designed for the followers governed by double-integrator *** the leaders have time-varying velocities,a sliding mode formation maneuvering law is proposed by using the same *** the 3D case,to establish an angle-induced linear equation for each tetrahedron,we assume that all the followers'coordinate frames share a common Z ***,a formation maneuvering law is proposed for the followers to globally maneuver Z-weakly angle rigid formations in *** extension to Lagrangian agent dynamics and the construction of the desired rigid formations by using the minimum number of angle constraints are also *** examples are provided to validate the effectiveness of the proposed algorithms.

关键词： Index Terms—Angle rigid formations formation control formation maneuvering global convergence multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Retrieving texture images using coarseness fuzzy partitions

Retrieving texture images using coarseness fuzzy partitions

引用

13th International Conference on Information Processing and Management of Uncertainty, IPMU 2010

作者： Chamorro-Martínez, Jesús Martínez-Jiménez, Pedro Manuel Soto-Hidalgo, Jose Manuel Department of Computer Science and Artificial Intelligence University of Granada Spain Department of Computer Architecture Electronics and Electronic Technology University of Córdoba Argentina

ISBN: (纸本)9783642140570

In this paper, a Fuzzy Dominant Texture Descriptor is proposed for semantically describing an image. This fuzzy descriptor is defined over a set of fuzzy sets modelling the "coarseness" texture property. Concretely, fuzzy partitions on the domain of coarseness measures are proposed, where the number of linguistic labels and the parameters of the membership functions are calculated relating representative coarseness measures (our reference set) with the human perception of this texture property. Given a "texture fuzzy set", its dominance in an image is analyzed and the dominance degree is used to obtain the image texture descriptor. Fuzzy operators over these descriptors are proposed to define conditions in image retrieval queries. The proposed framework makes database systems able to answer queries using texture-based linguistic labels in natural language. © Springer-Verlag Berlin Heidelberg 2010.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

Accelerating Iterative Big Data Computing Through MPI

引用

Journal of computer Science & technology 2015年第2期30卷 283-294页

作者：梁帆鲁小亿 State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Department of Computer Science and Engineering The Ohio State University Columbus OH 43210-1277 U.S.A

Current popular systems, Hadoop and Spark, cannot achieve satisfied performance because of the inefficient overlapping of computation and communication when running iterative big data applications. The pipeline of computing, data movement, and data management plays a key role for current distributed data computing systems. In this paper, we first analyze the overhead of shuffle operation in Hadoop and Spark when running PageRank workload, and then propose an event-driven pipeline and in-memory shuffle design with better overlapping of computation and communication as DataMPI- Iteration, an MPI-based library, for iterative big data computing. Our performance evaluation shows DataMPI-Iteration can achieve 9X-21X speedup over Apache Hadoop, and 2X-3X speedup over Apache Spark for PageRank and K-means.

关键词： iterative computation DataMPI Spark Hadoop MapReduce

来源：评论

学校读者我要写书评

暂无评论

Fuzzy partitions for modelling texture properties: Coarseness, contrast and directionality

Fuzzy partitions for modelling texture properties: Coarsenes...

引用

IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2015

作者： Chamorro-Martinez, Jesus Martinez-Jimenez, Pedro Manuel Soto-Hidalgo, Jose Manuel Department of Computer Science and Artificial Intelligence University of Granada Spain Department of Computer Architecture Electronics and Electronic Technology University of Córdoba Spain

ISBN: (纸本)9781467374286

The analysis of the perceptual properties of texture plays a fundamental role in tasks like semantic description of images or content-based image retrieval using linguistic queries. In this paper, we propose to model these properties by means of fuzzy partitions defined on the domain of some representative measures. In particular, we have focused our study on the properties of coarseness, contrast and directionality, that play a fundamental role in the human perception of texture. In our approach, the number of fuzzy sets in the partitions, as well as the parameters of the membership functions, are calculated by taking into account the relationship between the computational values given by the measures and the human perception of the corresponding property. The performance of the proposed modelling has been analyzed by applying the obtained fuzzy partitions in several experiments. © 2015 IEEE.

关键词： Membership functions

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：