检索结果-内蒙古大学图书馆

28th International Joint conference on Artificial Intelligence, IJCAI 2019

作者： Huang, Ting Shen, Gehui Deng, Zhi-Hong School of Electronics Engineering and Computer Science Peking University China

ISBN: (纸本)9780999241141

Recurrent Neural Networks (RNNs) are widely used in the field of natural language processing (NLP), ranging from text categorization to question answering and machine translation. However, RNNs generally read the whole text from beginning to end or vice versa sometimes, which makes it inefficient to process long texts. When reading a long document for a categorization task, such as topic categorization, large quantities of words are irrelevant and can be skipped. To this end, we propose Leap-LSTM, an LSTM-enhanced model which dynamically leaps between words while reading texts. At each step, we utilize several feature encoders to extract messages from preceding texts, following texts and the current word, and then determine whether to skip the current word. We evaluate Leap-LSTM on several text categorization tasks: sentiment analysis, news categorization, ontology classification and topic classification, with five benchmark data sets. The experimental results show that our model reads faster and predicts better than standard LSTM. Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency. © 2019 International Joint conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forward to the special issue of the 9th International Symposium on Cyberspace Safety and Security (CSS 2017)

Forward to the special issue of the 9th International Sympos...

引用

作者： Wen, Sheng Castiglione, Aniello Wang, Tian Bhuiyan, Md Zakirul Alam School of Software and Electrical Engineering Swinburne University of Technology HawthornVIC Australia Department of Science and Technology University of Naples Parthenope Italy National Huaqiao University College of Computer Science and Technology Xiamen China Department of Computer and Information Sciences Fordham University New YorkNY United States

来源：评论

学校读者我要写书评

暂无评论

Iot-based 3D printing service framework for remote device monitoring 49

Iot-based 3D printing service framework for remote device mo...

引用

49th International conference on computers and Industrial Engineering, CIE 2019

作者： Maosen, Wang Fan, Zhang Yuanyuan, Zhao Yuegang, Tan Tao, E. Fang School of Mechanical and Electronic Engineering Wuhan University of Technology Wuhan China Hubei JOYE High-tech Co. Ltd China

3D printing has been regarded as one of remarkable manufacturing technologies, which has been applied in a wide range of applications. Nowadays, intelligent manufacturing has been developed by integrating mechanical techniques with information, computer and internet technologies on the basis of the internet access of machining devices and large amount of machining data. In this paper, in order to satisfy the requirement on internet access and remote monitoring of massive 3D printers under the operation mode, an IoT-based 3D printing service framework is developed including the design of network hardware module, device authentication protocol and service platform. The real-time printing data are collected from printer and then transmitted to the developed platform in a defined and unified form using the designed hardware module. Authentication protocol is worked out to ensure the secure access of printer. Service platform is constructed based on MQTT agreement and distributed storage to supply real-time remote monitoring, management and location of printer. Finally, the performance of the developed platform is measured by simulating the access of one thousand devices. It is shown that the platform is able to satisfy access and data processing of the required number of devices. © 2019, computers and Industrial Engineering. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A two-stage algorithm for engagement detection in online learning

A two-stage algorithm for engagement detection in online lea...

引用

2019 International conference on Sustainable Technologies for Industry 4.0, STI 2019

作者： Dash, Saswat Akber Dewan, M. Ali Murshed, Mahbub Lin, Fuhua Abdullah-Al-Wadud, M. Das, Animesh National Institute of Technology Department of Computer Science and Engineering Rourkela India School of Computing and Information Systems Athabasca University Edmonton Canada Software Development Bow Valley College Calgary Canada King Saud University Department of Software Engineering Riyadh Saudi Arabia

ISBN: (纸本)9781728160979

Online learning plays a key role in current education system. Engagement detection in online learning is crucial as the student's success in online courses heavily depends on his/her state of mind. In our previous work, we used facial expressions labeled as engaged and not-engaged for student's engagement detection. In this paper, we use student's behavioral (on-task and off-task) and emotional (satisfied, bored, and confused) information for engagement detection. Five different convolutional neural network models have been tested for the behavioral and the emotional dimensions detection to detect student's engagement in online learning. The models are All Convolutional Network, Network in Network, Very Deep Convolutional Network, Conv-Pool Convolutional Network, and a proposed model combing some special features from the above models. We used the dataset Dataset for the Affective States in E-Environments - for the performance evaluation. Experimental results show that the behavioral and emotional dimensions based engagement detection provides a high accuracy. © 2019 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Scalable data parallel approaches to anomaly detection in climate data using gaussian processes 18

Scalable data parallel approaches to anomaly detection in cl...

引用

18th IEEE International conference on Machine Learning and Applications, ICMLA 2019

作者： Gadiraju, Krishna Karthik Ramachandra, Bharathkumar Shashidharan, Ashwin Dutton, Benjamin Vatsavai, Ranga Raju Department of Computer Science North Carolina State University United States

ISBN: (纸本)9781728145495

Anomaly detection on large scale spatio-temporal data such as climate data is a challenging task depending on the spatial and temporal resolution and autocorrelation of the data. When considering global gridded daily temperature data, the number of locations and the length of time period considered makes anomaly detection a big data problem. Gaussian Process (GP) Learning is a method that is well-suited to identify the complex spatial and temporal autocorrelation properties of spatio-temporal data. One of the primary challenges with using GP is the computational complexity associated with inverting a covariance matrix. This is further compounded when considering data on a national/global scale and performing anomaly detection using such methods often requires dedicated high performance computing platforms. In this paper, we describe a purely temporal scalable anomaly detection technique for gridded temperature data based on GP Learning that ignore the spatial autocorrelation between neighboring grids and perform anomaly detection on each of the grids in parallel, thereby reducing the execution time. We introduce three methods: a standalone data parallel approach using a single GPU, a distributed memory version on multi-node clusters using MPI, and a mixed parallel approach using multiple GPUs. In comparison to a sequential approach, they are 17.2x, 47.1x, and 88.9x faster, respectively. © 2019 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Exascale Computing in the United States

引用

COMPUTING IN SCIENCE & ENGINEERING 2019年第1期21卷 17-29页

作者： Kothe, Douglas Lee, Stephen Qualters, Irene Oak Ridge Natl Lab Comp & Computat Sci Directorate Oak Ridge TN 37830 USA Los Alamos Natl Lab Comp & Computat Sci Div Los Alamos NM USA Natl Sci Fdn Comp & Informat Sci & Engn 4201 Wilson Blvd Arlington VA 22230 USA

The U.S. is a long-time international leader in HPC, rooted in a strong and innovative computing industry that is complemented by partnerships with and among federal agencies, academia, and industries whose success relies on HPC. The advent of exascale computing brings challenges in traditional simulation as well as in areas colloquially referred to as "BigData." Within this context, we describe the U.S. exascale computing strategy: 1) the National Strategic Computing Initiative, a multiple U.S. federal agency effort comprehensively addressing computing and computational science requirements in the U.S.;2) the Exascale Computing Initiative, a DOE effort to acquire, develop, and deploy exascale computing platforms within DOE laboratories on a given timeline;and, 3) the Exascale Computing Project (a component of the Exascale Computing Initiative), dedicated to the creation and enhancement of applications, software, and hardware technologies for exascale computers, focused on vital U.S. national security and science needs.

关键词： Parallel Processing Long Time International Leader HPC Exascale Computing Strategy National Strategic Computing Initiative United States DOE Laboratories high performance Computing Computational Modeling Exascale Computing Ecosystems Strategic Planning Hardware

来源：评论

学校读者我要写书评

暂无评论

Energy aware edge computing: a survey 2nd

Energy aware edge computing: a survey

引用

2nd International Workshop on high performance Computing for Advanced Modeling and Simulation in Nuclear Energy and Environmental Science, HPCMS 2018, and 1st International Workshop on HPC Supported Data Analytics for Edge Computing, HiDEC 2018 held at the 32nd ACM International conference on Supercomputing, ACM ICS 2018

作者： Fan, Tiantian Qiu, Yeliang Jiang, Congfeng Wan, Jian Key Laboratory of Complex Systems Modeling and Simulation Hangzhou Dianzi University Hangzhou310018 China School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou310023 China

ISBN: (纸本)9789813299863

Edge computing is an emerging paradigm to meet the ever-increasing computation demands from pervasive devices such as sensors, actuators, and smart things. Though the edge devices can execute complex applications, it is necessary for some applications to migrate to centralized servers. By offloading the computation from the edge nodes to the edge servers or cloud servers, the quality of computation experience could be greatly improved. However, it may cause delay and increase network overheads, and energy consumption eventually. Therefore, an optimal offloading strategy should take into account what task should be offloaded, when to offload and where to offload to avoid the overheads. Thus, it is important to tradeoff between energy consumption, computation delay and throughput when the system makes the computation offloading to achieve high energy efficiency. In this paper, we conduct a survey of energy aware edge computing, including the existing work on computation offloading frameworks and strategies in edge computing. Specifically, we describe the strategies from the perspective of energy aware offloading, energy optimization offloading and offloading algorithms. © Springer Nature Singapore Pte Ltd 2019.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

HPGA: A high-performance Graph Analytics Framework on the GPU

HPGA: A High-Performance Graph Analytics Framework on the GP...

引用

International conference on Information Systems and computer Aided Education (ICISCAE)

作者： Yang, Haoduo Su, Huayou Wen, Mei Zhang, Chunyuan Natl Univ Def Technol Dept Comp Changsha 410000 Hunan Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha 410000 Hunan Peoples R China

ISBN: (纸本)9781538657386

In recent years, the rapidly growing use of graphs has sparked parallel graph analytics frameworks for leveraging the massive hardware resources, specifically graphics processing units (GPUs). However, the issues of the unpredictable control flows, memory divergence, and the complexity of programming have restricted high-level GPU graph libraries. In this work, we present HPGA, a high performance parallel graph analytics framework targeting the GPU. HPGA implements an abstraction which maps vertex programs to generalized sparse matrix operations on GPUs for delivering high performance. HPGA incorporates high-performance GPU computing primitives and optimization strategies with a high-level programming model. We evaluate the performance of HPGA for three graph primitives (BFS, SSSP, PageRank) with large-scale datasets. The experimental results show that HPGA matches or even exceeds the performance of MapGraph and nvGRAPH, two state-of-the-art GPU graph libraries.

关键词： Graph Analytics high-performance Computing GPU

来源：评论

学校读者我要写书评

暂无评论

QoE-aware user association and resource allocation for mixed services in heterogeneous networks 2

QoE-aware user association and resource allocation for mixed...

引用

2nd International Symposium on Application of Materials Science and Energy Materials, SAMSE 2018

作者： Li, Shuxian Tang, Liangrui Yan, Jiangyu State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing102206 China School of Control and Computer Engineering North China Electric Power University Beijing102206 China

In heterogeneous networks (HetNets), user association and resource allocation (UARA) is a great challenge for radio resource management (RRM). In this paper, a novel QoE-aware UARA scheme is proposed. The delay factor is introduced to QoE metric to weight delays' effect on service transmitting. Then the UARA scheme based on QoE is formulated as an optimization problem which is a mixed integer nonlinear programming (MINLP) problem. To solve the problem, we adopt the genetic algorithm (GA) and associate the user association and the resource with population and fitness respectively. Through the evolutions of genetic algorithm, the optimal UARA scheme can be worked out. The simulation results indicate that the proposed scheme can reduce packet loss rate, and improve the system load balancing performance. © Published under licence by IOP Publishing Ltd.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Context-aware Deep Feature Compression for high-speed Visual Tracking 31

Context-aware Deep Feature Compression for High-speed Visual...

引用

31st IEEE/CVF conference on computer Vision and Pattern Recognition (CVPR)

作者： Choi, Jongwon Chang, Hyung Jin Fischer, Tobias Yun, Sangdoo Lee, Kyuewang Jeong, Jiyeoup Demiris, Yiannis Choi, Jin Young Seoul Natl Univ ECE ASRI Seoul South Korea Imperial Coll London Personal Robot Lab EEE London England Univ Birmingham Sch Comp Sci Birmingham W Midlands England NAVER Corp Clova AI Res Seoul South Korea

ISBN: (纸本)9781538664209

We propose a new context-aware correlation filter based tracking framework to achieve both high computational speed and state-of-the-art performance among real-time trackers. The major contribution to the high computational speed lies in the proposed deep feature compression that is achieved by a context-aware scheme utilizing multiple expert auto-encoders;a context in our framework refers to the coarse category of the tracking target according to appearance patterns. In the pre-training phase, one expert auto-encoder is trained per category. In the tracking phase, the best expert auto-encoder is selected for a given target, and only this auto-encoder is used. To achieve high tracking performance with the compressed feature map, we introduce extrinsic denoising processes and a new orthogonality loss term for pre-training and fine-tuning of the expert auto encoders. We validate the proposed context-aware framework through a number of experiments, where our method achieves a comparable performance to state-of-the-art trackers which cannot run in real-time, while running at a significantly fast speed of over 100 fps.

关键词： Target tracking Correlation Real-time systems Convolutional codes Training Noise reduction

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：