检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Big Data Analysis, ICBDA 2018

作者： Cartlidge, John Gong, Shuhui Bai, Ruibin Yue, Yang Li, Qingquan Qiu, Guoping Department of Computer Science University of Bristol BristolBS8-1UB United Kingdom International Doctoral Innovation Centre Department of Computer Science University of Nottingham Ningbo China Ningbo315100 China Shenzhen Key Laboratory of Spatial Smart Sensing and Services Research Institute for Smart Cities Department of Urban Informatics School of Architecture and Urban Planning Shenzhen University Shenzhen518060 China School of Computer Science University of Nottingham NottinghamNG8-1BB United Kingdom

ISBN: (纸本)9781538647936

Taxi trajectory data (GPS data collected for 15,000 taxis at intervals of 30 seconds across three million journeys over eight days) is used to generate a spatio-temporal prediction of shopping behaviours in the emerging metropolitan city of Shenzhen, China. Two approaches are compared: time-series forecasting using ARIMA;and a gravity model approach, using the Huff model calibrated with Geographical Weighted Regression. Results demonstrate that ARIMA performs with significantly higher accuracy than the more traditional Huff model method. Further, it is demonstrate that while the accuracy of the Huff model is constrained by model assumptions, applying time-series methods to the underlying data directly (i.e., the ARIMA method) has no such constraints, and is limited only by the amount of data available. This suggests that, as richer data sets become available, spatio-temporal modelling of this kind will become more accurate. © 2018 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Towards memory-efficient processing-in-memory architecture for convolutional neural networks

引用

ACM SIGPLAN Notices 2017年第5期52卷 81-90页

作者： Wang, Yi Zhang, Mingxu Yang, Jing College of Computer Science and Software Engineering Shenzhen University China Experimental and Innovation Practice Center Harbin Institute of Technology Shenzhen China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

Convolutional neural networks (CNNs) are widely adopted in artificial intelligent systems. In contrast to conventional computing centric applications, the computational and memory resources of CNN applications are mixed together in the network weights. This incurs a significant amount of data movement, especially for highdimensional convolutions. Although recent embedded 3D-stacked Processing-in-Memory (PIM) architecture alleviates this memory bottleneck to provide fast near-data processing, memory is still a limiting factor of the entire system. An unsolved key challenge is how to efficiently allocate convolutions to 3D-stacked PIM to combine the advantages of both neural and computational processing. This paper presents Memolution, a compiler-based memory efficient data allocation strategy for convolutional neural networks on PIM architecture. Memolution offers thread-level parallelism that can fully exploit the computational power of PIM architecture. The objective is to capture the characteristics of neural network applications and present a hardware-independent design to transparently allocate CNN applications onto the underlining hardware resources provided by PIM. We demonstrate the viability of the proposed technique using a variety of realistic convolutional neural network applications. Our extensive evaluations show that, Memolution significantly improves performance and the cache utilization compared to the baseline scheme. © 2017 ACM.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

The differential fault analysis on block cipher FeW

引用

Cybersecurity 2023年第2期6卷 62-74页

作者： Haiyan Xiao Lifang Wang Jinyong Chang School of Computer Science Northwestern Polytechnical UniversityXiAn 710055People's Republic of China Engineering University of PAP XiAn 710055People's Republic of China School of Information and Control Engineering XiAn University of Architecture and TechnologyXi'An 710055People's Republic of China State Key Laboratory of Information Security(SKLOIS) Institute of Information EngineeringChinese Academy of SciencesBeijing 100089People's Republic of China

Feather weight(FeW)cipher is a lightweight block cipher proposed by Kumar et *** 2019,which takes 64 bits plaintext as input and produces 64 bits *** Kumar et ***,FeW is a software oriented design with the aim of achieving high efficiency in software based *** seems that FeW is immune to many cryptographic attacks,like linear,impossible differential,differential and zero correlation ***,in recent work,Xie et *** the security of *** precisely,they proved that under the differential fault analysis(DFA)on the encryption states,an attacker can completely recover the master secret *** this paper,we revisit the block cipher FeW and consider the DFA on its key schedule algorithm,which is rather popular cryptanalysis for kinds of block *** particular,by respectively injected faults into the 30th and 29th round subkeys,one can recover about 55/80~69%bits of master *** the brute force searching remaining bits,one can obtain the full master secret *** simulations and experiment results show that our analysis is practical.

关键词： Differential fault analysis Block cipher FeW Side channel attack

来源：评论

学校读者我要写书评

暂无评论

I/O lower bounds for auto-tuning of convolutions in CNNs

arXiv

引用

arXiv 2020年

作者： Zhang, Xiaoyang Xiao, Junmin Tan, Guangming State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Science China

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement (i.e., memory access). This work provides comprehensive analysis and methodologies to minimize the communication for the convolution in CNNs. With an in-depth analysis of the recent I/O complexity theory under the red-blue game model, we develop a general I/O lower bound theory for a composite algorithm which consists of several different sub-computations. Based on the proposed theory, we establish the data movement lower bound results for two main convolution algorithms in CNNs, namely the direct convolution and Winograd algorithm, which represents the direct and indirect implementations of a convolution respectively. Next, derived from I/O lower bound results, we design the near I/O-optimal dataflow strategies for the two main convolution algorithms by fully exploiting the data reuse. Furthermore, in order to push the envelope of performance of the near I/O-optimal dataflow strategies further, an aggressive design of auto-tuning based on I/O lower bounds, is proposed to search an optimal parameter configuration for the direct convolution and Winograd algorithm on GPU, such as the number of threads and the size of shared memory used in each thread block. Finally, experiment evaluation results on the direct convolution and Winograd algorithm show that our dataflow strategies with the auto-tuning approach can achieve about 3.32× performance speedup on average over cuDNN. In addition, compared with TVM, which represents the state-of-the-art technique for auto-tuning, not only our auto-tuning method based on I/O lower bounds can find the optimal parameter configuration faster, but also our solution has higher performance than the optimal solution provided

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A computer-supported collaborative learning platform based on clouds

引用

Journal of Computational Information Systems 2011年第11期7卷 3811-3818页

作者： Li, Jiandun Peng, Junjie Zhang, Wu Han, Fangfang Yuan, Qin Joint Lab of Cloud Computing School of Computer Engineering and Science Shanghai University Shanghai 200072 China Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

computer-supported collaborative learning (CSCL) is an emerging branch of learning science concerned with studying how people can learn together with the help of computers. As an indispensable ingredient, computer mediation evolves through couples of phases, e.g. centralized server, peer-to-peer network, grid computing. Nevertheless, with daily rising trend on requirement's dynamic changes in service, existing models fall short to respond on demand. Thus, in this paper, by taking advantage of cloud computing, we propose a feasible CSCL platform and the experiments show that it can not only fulfill the basic requirement of CSCL, but also respond to learner's dynamic need on demand. Copyright © 2011 Binary Information Press.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Development of computer programme for the description of plastic deformation by slip 7

Development of computer programme for the description of pla...

引用

7th Korea-Russia International Symposium on science and Technology, KORUS 2003

作者： Semenov, M.E. Kolupaeva, S.N. Laboratory of Computer Aided Design of Advanced Materials Institute of Strength Physics and Materials Science Akademichesky pr. 2/1 Tomsk634021 Russia Department of Applied Mathematics Tomsk State University of Architecture and Building Solyanaya sq. 2 Tomsk634003 Russia

ISBN: (纸本)8978686184

The interface and structure of a package of applied programs for the description of plastic deformation by slip in f.c.c. materials are developed. The mathematical model used for calculations is based on the set of differential equations of balance of deformation defects in f.c.c. materials. The processes of generation and annihilation of deformation defects have essentially different rates, and the system of ODE (ordinary differential equations) is stiff. Application of implicit absolutely steady methods is necessary in this situation, because classical Runge-Kutta's methods can require much time for calculations. In this case the use of implicit multistep Gear's method of the variable order for decision the system of ODE is more effective. The applied programs for the description of plastic deformation are oriented for the users who have different qualification in programming and are not require an experience of decision of ODE. © 2003 7th Korea-Russia Intl Sym on science.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

UCC 2013: Message from the conference organization chairs

Proceedings - 2013 IEEE/ACM 6th International Conference on ...

引用

Proceedings - 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing, UCC 2013 2013年 xv-xvi页

作者： Buyya, Rajkumar Schill, Alexander Spillner, Josef Laboratory Department of Computer Science and Software Engineering University of Melbourne Australia Department of Computer Science Institute for Systems Architecture Technische Universität Dresden Germany Technische Universität Dresden Germany

来源：评论

学校读者我要写书评

暂无评论

Point cloud modelling based on the tunnel axis and block estimation for monitoring the Badaling Tunnel, China

Point cloud modelling based on the tunnel axis and block est...

引用

ISPRS Geospatial Week 2017

作者： Wang, J. Zheng, H.B. Huang, H. Ma, G.W. Beijing Key Laboratory of Traffic Engineering Beijing University of Technology China College of Civil Engineering and Architecture Beijing University of Technology China Institute for Applied Computer Science Bundeswehr University Munich Germany School of Civil Environmental and Mining Engineering University of Western Australia Australia

Recent years have witnessed a growing investigation of terrestrial laser scanning (TLS) for monitoring the deformation of tunnels. TLS provides the ability to obtain a more accurate and complete description of the tunnel surfaces, allowing the determination of the mechanism and magnitude of tunnel deformation, because the entire surface of the tunnel is more concretely modelled rather than being represented by a number of points. This paper models and analyses the point clouds from TLS to detect the possible deformation of a newly built tunnel. In the application of monitoring the Badaling Tunnel for the Winter Olympics 2020 in Beijing, China, the proposed method includes the following components: the tunnel axis is automatically estimated based on a 3D quadratic form estimation;all of the point clouds are segmented into axis-based blocks;and representative points, solved by a singular value decomposition (SVD) method, are estimated to describe the tunnel surface and establish the correspondence of data between days. The deformations are detected in the form of the distance discrepancies of representative points and verified by the measurements using total station. © Authors 2017. CC BY 4.0 License.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

A Fusion Neural Network Incorporating Attention for Sensor-Based Human Activity Recognition 3

A Fusion Neural Network Incorporating Attention for Sensor-B...

引用

3rd International Conference on computer Vision, Image and Deep Learning and International Conference on computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lu, Limeng Zhang, Chuanlin Cao, Kai Deng, Dao Institute of Chinese Ethnic Information Technology Northwest Minzu University Lanzhou China Key Laboratory of China's Ethnic Languages and Information Technology Ministry of Education Lanzhou China Northwest Minzu University School of Mathematics and Computer Science Lanzhou China Northwest Minzu University Key Laboratory of Streaming Data Computing Technologies and Application Lanzhou China

ISBN: (纸本)9781665459112

Even though the RNN, LSTM, and other networks are used to extract dependencies in time series, sensor-based human behavior recognition (HAR) still faces some difficulties, and the ability of deep learning (DL) networks to extract features still needs to be improved. We propose a fusion neural network in which an optimized small optimized Convolutional Block Attention Module (MP-CBAM) is suitable for HAR tasks to extract samples. The MP-CBAM is added to two branches Convolutional Neural Network (CNN) with different convolution kernel sizes, and the fused features are labeled with GRU for temporal dependence. Then the softmax function is used for classification. We validate on benchmark datasets UCI-HAR and WISDM and accuracies of 97.15% and 9S.9S% are obtained, respectively, demonstrating the adaptation of our framework to both single-sensor and multi-sensor devices. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Rule discovery and probabilistic modeling for onomastic data

引用

7th European Conference on Principles and Practice of Knowledge Discovery in Databases, PKDD 2003

作者： Leino, Antti Mannila, Heikki Pitkänen, Ritva Liisa Helsinki Institute for Information Technology Basic Research Unit Department of Computer Science University of Helsinki P.O. Box 26 FIN-00014 Finland Research Institute for the Languages of Finland Sörnäisten rantatie 25 HelsinkiFIN-00500 Finland Helsinki University of Technology Laboratory of Computer and Information Science P.O. Box 5400 HutFIN-02015 Finland University of Helsinki Department of Finnish University of Helsinki P.O. Box 3 FIN-00014 Finland

ISBN: (纸本)3540200851

The naming of natural features, such as hills, lakes, springs, meadows etc., provides a wealth of linguistic information;the study of the names and naming systems is called onomastics. We consider a data set containing all names and locations of about 58,000 lakes in Finland. Using computational techniques, we address two major onomastic themes. First, we address the existence of local dependencies or repulsion between occurrences of names. For this, we derive a simple form of spatial association rules. The results partially validate and partially contradict results obtained by traditional onomastic techniques. Second, we consider the existence of relatively homogeneous spatial regions with respect to the distributions of place names. Using mixture modeling, we conduct a global analysis of the data set. The clusterings of regions are spatially connected, and correspond quite well with the results obtained by other techniques;there are, however, interesting differences with previous hypotheses. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Lakes

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：