检索结果-内蒙古大学图书馆

Convergence of Edge Computing and Deep Learning: A Comprehensive Survey

ieee COMMUNICATIONS SURVEYS AND TUTORIALS 2020年第2期22卷 869-904页

作者： Wang, Xiaofei Han, Yiwen Leung, Victor C. M. Niyato, Dusit Yan, Xueqiang Chen, Xu Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Adv Networking Tianjin 300350 Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Univ British Columbia Dept Elect & Comp Engn Vancouver BC V6T 1Z4 Canada Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore Huawei Technol Lab 2012 Shenzhen 201206 Peoples R China Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Peoples R China

Ubiquitous sensors and smart devices from factories and communities are generating massive amounts of data, and ever-increasing computing power is driving the core of computation and services from the cloud to the edge of the network. As an important enabler broadly changing people's lives, from face recognition to ambitious smart factories and cities, developments of artificial intelligence (especially deep learning, DL) based applications and services are thriving. However, due to efficiency and latency issues, the current cloud computing service architecture hinders the vision of "providing artificial intelligence for every person and every organization at everywhere". Thus, unleashing DL services using resources at the network edge near the data sources has emerged as a desirable solution. Therefore, edge intelligence, aiming to facilitate the deployment of DL services by edge computing, has received significant attention. In addition, DL, as the representative technique of artificial intelligence, can be integrated into edge computing frameworks to build intelligent edge for dynamic, adaptive edge maintenance and management. With regard to mutually beneficial edge intelligence and intelligent edge, this paper introduces and discusses: 1) the application scenarios of both;2) the practical implementation methods and enabling technologies, namely DL training and inference in the customized edge computing framework;3) challenges and future trends of more pervasive and fine-grained intelligence. We believe that by consolidating information scattered across the communication, networking, and DL areas, this survey can help readers to understand the connections between enabling technologies while promoting further discussions on the fusion of edge intelligence and intelligent edge, i.e., Edge DL.

关键词： Edge computing Cloud computing Training computational modeling Reliability Wireless communication Internet of Things Edge computing deep learning wireless communication computation offloading artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A Machine-Learning-Based Auction for Resource Trading in Fog Computing

引用

ieee COMMUNICATIONS MAGAZINE 2020年第3期58卷 82-88页

作者： Luong, Nguyen Cong Jiao, Yutao Wang, Ping Niyato, Dusit Kim, Dong In Han, Zhu PHENIKAA Univ Fac Informat Technol Hanoi Vietnam PRATI Hanoi Vietnam Nanyang Technol Univ Sch Comp Sci & Engn Singapore Singapore York Univ Dept Elect Engn & Comp Sci N York ON Canada Sungkyunkwan Univ Coll Informat & Commun Engn Suwon South Korea Univ Houston Elect & Comp Engn Dept Houston TX 77004 USA

Fog computing is considered to be a key enabling technology for future networks. By broadening the cloud computing services to the network edge, fog computing can support various emerging applications such as IoT, big data, and blockchain with low latency and low bandwidth consumption cost. To achieve the full potential of fog computing, it is essential to design an incentive mechanism for fog computing service providers. Auction is a promising solution for the incentive mechanism design. However, it is challenging to design an optimal auction that maximizes the revenue for the providers while holding important properties: IR and IC. Therefore, this article introduces the design of an optimal auction based on deep learning for the resource allocation in fog computing. The proposed optimal auction is developed specifically to support blockchain applications. In particular, we first discuss resource management issues in fog computing. Second, we review economic and pricing models for resource management in fog computing. Third, we introduce fog computing and blockchain. Fourth, we present how to design the optimal auction by using deep learning for the fog resource allocation in the blockchain network. Simulation results demonstrate that the proposed scheme outperforms the baseline scheme (i.e., the greedy algorithm) in terms of revenue, and IC and IR violations. Thus, the proposed scheme can be used as a useful tool for the optimal resource allocation in general fog networks.

关键词： Edge computing Blockchain Resource management Biological system modeling Integrated circuits Cloud computing computational modeling Machine learning

来源：评论

学校读者我要写书评

暂无评论

Special Issue on AI Enabled Cognitive Communication and Networking for IoT

引用

ieee INTERNET OF THINGS JOURNAL 2019年第2期6卷 1906-1910页

作者： Yang, Kai Liu, Sijia Cai, Lin Yilmaz, Yasin Chen, Pin-Yu Walid, Anwar Tongji Univ Dept Comp Sci Shanghai 201804 Peoples R China IBM Res MIT IBM Watson AI Lab Yorktown Hts NY 10598 USA Univ Victoria Dept Elect & Comp Engn Victoria BC V8W 2Y2 Canada Univ S Florida Elect Engn Dept Tampa FL 33620 USA IBM Thomas J Watson Res Ctr AI Fdn Learning Grp Yorktown Hts NY 10598 USA Nokia Bell Labs Murray Hill NJ 07974 USA

As we enter the Internet of Things (IoT) era in which the communication network is becoming increasingly dynamic, heterogeneous, and complex, it is desirable to have cognitive communication systems and networks that possess multiple interacting capabilities for situation assessment, resource management, online/distributed learning, big-data processing, and intelligent decision making. AI techniques, such as deep learning, probabilistic graph model, and reinforcement learning, aided with big data and IoT, provide a wide variety of tools and solutions to many new problems encountered in the design, operation, and optimization of cognitive communication systems and networking, including resource management, situation assessment, channel identification, anomaly detection, root cause analysis, and online/distributed learning.

关键词： Special issues and sections Internet of Things Resource management Dynamic scheduling Decision making Communication networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Dynamic Cooperative Coevolution for Large Scale Optimization

引用

ieee TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2019年第6期23卷 935-948页

作者： Zhang, Xin-Yuan Gong, Yue-Jiao Lin, Ying Zhang, Jie Kwong, Sam Zhang, Jun Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Guangdong Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China South China Univ Technol Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou 510006 Guangdong Peoples R China Sun Yat Sen Univ Dept Psychol Guangzhou 510006 Guangdong Peoples R China Beijing Univ Chem Technol Sch Informat Sci & Technol Beijing 100029 Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

The cooperative coevolution (CC) framework achieves a promising performance in solving large scale global optimization problems. The framework encounters difficulties on nonseparable problems, where variables interact with each other. Using the static grouping methods, variables will be theoretically grouped into one big subcomponent, whereas the random grouping strategy endures low efficiency. In this paper, a dynamic CC framework is proposed to tackle the challenge. The proposed framework works in a computationally efficient manner, in which the computational resources are allocated to a series of elitist subcomponents consisting of superior variables. First, a novel estimation method is proposed to evaluate the contribution of variables using the historical information of the best overall fitness. Based on the contribution and the interaction information, a dynamic grouping strategy is conducted to construct the dynamic subcomponent that evolves in the next evolutionary period. The constructed subcomponents are different from each other, and therefore the required parameters to control the optimization of each subcomponent vary a lot in each evolutionary period. A stage-by-stage parameter adaptation strategy is proposed to adapt the optimizer to the dynamic optimization environment. Experimental results indicate that the proposed framework achieves competitive results compared with the state-of-the-art CC frameworks.

关键词： Optimization Benchmark testing computational efficiency Estimation Dimensionality reduction Evolutionary computation Computer science Cooperative coevolution (CC) dynamic grouping (DyG) strategy large scale global optimization (LSGO) nonseparable problems

来源：评论

学校读者我要写书评

暂无评论

A preliminary study on Hybrid Spill-Tree Fuzzy k-Nearest Neighbors for big data classification

A preliminary study on Hybrid Spill-Tree Fuzzy k-Nearest Nei...

引用

ieee International Conference on Fuzzy Systems (FUZZ-ieee)

作者： Maillo, Jesus Luengo, Julian Garcia, Salvador Herrera, Francisco Triguero, Isaac Univ Granada Dept Comp Sci & Artificial Intelligence E-18071 Granada Spain Univ Nottingham Sch Comp Sci Jubilee Campus Nottingham NG8 1BB England

ISBN: (纸本)9781509060207

The Fuzzy k Nearest Neighbor (Fuzzy kNN) classifier is well known for its effectiveness in supervised learning problems. kNN classifies by comparing new incoming examples with a similarity function using the samples of the training set. The fuzzy version of the kNN accounts for the underlying uncertainty in the class labels, and it is composed of two different stages. The first one is responsible for calculating the fuzzy membership degree for each sample of the problem in order to obtain smoother boundaries between classes. The second stage classifies similarly to the standard kNN algorithm but uses the previously calculated class membership degree. To deal with very large datasets, distributed versions of the Fuzzy kNN algorithm have been proposed. However, existing approaches remain not fully scalable as they aim to replicate the exact behavior of the Fuzzy kNN. In this work, we present an approximate and distributed Fuzzy kNN approach based on Hybrid Spill-Tree implemented under Apache Spark. The aim of this model is to alleviate the scalability problems and to deal with big datasets maintaining high accuracy. In our experiments, we compare in precision and runtime with the Fuzzy kNN for big data problems existing in the literature, running with datasets of up to 11 million instances. The results show an improvement in the runtime and accuracy with respect to the previous exact model.

关键词： Training Approximation algorithms big data Runtime Proposals Sparks computational modeling

来源：评论

学校读者我要写书评

暂无评论

Euler Clustering on Large-scale dataset

引用

ieee TRANSACTIONS ON big data 2018年第4期4卷 502-515页

作者： Wu, Jian-Sheng Zheng, Wei-Shi Lai, Jian-Huang Suen, Ching Y. Sun Yat Sen Univ Sch Informat Sci & Technol Guangzhou 510006 Guangdong Peoples R China Nanchang Univ Sch Informat Engn Nanchang 330031 Jiangxi Peoples R China Sun Yat Sen Univ Sch Data & Comp Sci Guangzhou 510006 Guangdong Peoples R China Natl Univ Def Technol Collaborat Innovat Ctr High Performance Comp Changsha 410073 Hunan Peoples R China Guangdong Prov Key Lab Informat Secur Guangzhou 510275 Guangdong Peoples R China Concordia Univ Ctr Pattern Recognit & Machine Intelligence CENPA Suite EV3-4031445 Maisonneuve Blvd West Montreal PQ H3G 1M8 Canada

Our concern is nonlinear clustering on large-scale dataset. While existing popular kernels (RBF, Polynomials, Spatial Pyramid, etc.) are popularly used for implicitly mapping data into a high-dimensional or infinite dimensional space in order to generalise linear clustering methods, using these kernels cannot make kernel clustering approaches directly applicable for large scale dataset, since large scale kernel matrix or similarity matrix consumes a lot of memory (e.g., 7,450 GB memory over 1 million samples of data). To solve this problem, we introduce an Euler clustering approach. Euler clustering employs Euler kernels in order to intrinsically map the input data onto a complex space of the same dimension as the input or twice, so that Euler clustering can get rid of kernel trick and does not need to rely on any approximation or random sampling on kernel function/matrix, whilst performing a more robust nonlinear clustering against noise and outliers. Moreover, since the original Euler kernel cannot generate a non-negative similarity matrix and thus is inapplicable to spectral clustering, we introduce a positive Euler kernel, and more importantly we have proved when it can generate a non-negative similarity matrix. We apply Euler kernel and the proposed positive Euler kernel to kernel k-means and spectral clustering so as to develop Euler k-means and Euler spectral clustering, respectively. An efficient Stiefel-manifold-based gradient method and an equivalent weighted positive Euler k-means are derived for fast computation of Euler spectral clustering and further alleviating the impact of discretization of the cluster membership indicators in Euler spectral clustering. The results show that the proposed Euler clustering approach achieves overall better clustering performance compared to using popular Mercer kernels and approximation models, whilst keeping the computational complexity of the same magnitude as the most popular linear clustering method k-means.

关键词： Large-scale clustering kernel k-means spectral clustering Euler kernel

来源：评论

学校读者我要写书评

暂无评论

Competitive Swarm Optimizer with Dynamic Grouping for Large Scale Optimization

Competitive Swarm Optimizer with Dynamic Grouping for Large ...

引用

ieee Congress on Evolutionary Computation (ieee CEC) as part of the ieee World Congress on computational intelligence (ieee WCCI)

作者： Ling, Tao Zhan, Zhi-Hui Wang, Yong -Xing Wang, Zi-Jia Yu, Wei-Jie Zhang, Jun Heilongjiang Univ Elect Engn Coll Harbin 150080 Heilongjiang Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Guangdong Peoples R China Guangdong Prov Key Lab Computat Intelligence & Cy Guangzhou Guangdong Peoples R China

ISBN: (纸本)9781509060177

The arrival of the era of "big data" has witnessed an urgent need of finding a proper algorithm for large scale optimization. Hence, this paper proposes a competitive swarm optimizer with dynamic grouping (CSO-DG) for large scale optimization. In CSO-DG, particles are separated into many groups to search for different regions of the large landscape. Moreover, the size of the group (the number of particles in each group) changes dynamically to control the swarm competitive strength, so as to balance the convergence and diversity. We also investigate the influences of different group sizes on different problems, and then propose a size range for the dynamic change bounds. By using multiple groups, only the worst particle in each group will be updated by learning from the best particle in the same group and the mean position of the whole swarm. This is helpful to save fitness evaluations. This way, the algorithm is able to work well in high-dimensional optimization. The experimental results show that CSO-DG exhibits a competitive performance than other state-of-the-art algorithms on 20 benchmark functions (CEC'2010) for large scale optimization.

关键词： Competitive swarm optimizer Dynamic grouping Large-scale optimization

来源：评论

学校读者我要写书评

暂无评论

Deep Gaussian processes for geophysical parameter retrieval 38

Deep Gaussian processes for geophysical parameter retrieval

引用

38th Annual ieee International Geoscience and Remote Sensing symposium, IGARSS 2018

作者： Svendsen, Daniel Heestermans Morales-Álvarez, Pablo Molina, Rafael Camps-Valls, Gustau Universitat de València Spain Computer Science and Artificial Intelligence Department Universidad de Granada Spain

ISBN: (纸本)9781538671504

This paper introduces deep Gaussian processes (DGPs) for geo-physical parameter retrieval. Unlike the standard full GP model, the DGP accounts for complicated (modular, hierarchical) processes, provides a efficient solution that scales well to large datasets, and improves prediction accuracy over standard full and sparse GP models. We give empirical evidence of performance for estimation of surface dew point temperature from infrared sounding data. © 2018 ieee

关键词： Global Positioning System Kernel Training Gaussian processes Standards Atmospheric modeling computational modeling

来源：评论

学校读者我要写书评

暂无评论

Structuring data for Intelligent Predictive Maintenance in Asset Management

Structuring Data for Intelligent Predictive Maintenance in A...

引用

16th IFAC symposium on Information Control Problems in Manufacturing (INCOM)

作者： Aremu, Oluseun Omotola Palau, Adria Salvador Parlikad, Ajith Kumar Hyland-Wood, David McAree, Peter Ross Univ Queensland Sch Mech & Min Engn Brisbane Qld 4072 Australia Univ Cambridge Inst Mfg Cambridge CB2 1PZ England Univ Queensland Sch Informat Technol & Elect Engn Brisbane Qld 4072 Australia

Predictive maintenance (PdM) within asset management improves savings in operational cost, productivity, and safety management capabilities. While PdM can be administered using various methods, growing interest in Artificial intelligence (AI) has lead to current state of the art PdM relying on machine learning (ML) technology. Like other tools used in PdM for asset management, standards for applying ML technology for PdM are required. This work introduces a standard of practice in regards to usage of asset data to develop ML analytic tools for PdM. It provides a standard method for ensuring asset data is in a form conducive to ML algorithms, and ensuring retention of asset information necessary for optimum PdM during the data transform. In the ML domain, it has been proven through research initiatives that the data structure used to train and test ML algorithms has a great impact on their performance and accuracy. Using poorly trained models for estimation due to improper data usage, can leave some AI-based PdM tools vulnerable to high rates of inaccurate estimations. Thus, leading to value loss during an asset's life cycle. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Asset management predictive maintenance artificial intelligence information sharing big data

来源：评论

学校读者我要写书评

暂无评论

Nearest Neighbor Classification for High-Speed big data Streams Using Spark

引用

ieee TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 2017年第10期47卷 2727-2739页

作者： Ramirez-Gallego, Sergio Krawczyk, Bartosz Garcia, Salvador Wozniak, Michal Manuel Benitez, Jose Herrera, Francisco Univ Granada Dept Comp Sci & Artificial Intelligence E-18071 Granada Spain Virginia Commonwealth Univ Dept Comp Sci Richmond VA 23284 USA Wroclaw Univ Technol Dept Comp Sci PL-50370 Wroclaw Poland

Mining massive and high-speed data streams among the main contemporary challenges in machine learning. This calls for methods displaying a high computational efficacy, with ability to continuously update their structure and handle ever-arriving big number of instances. In this paper, we present a new incremental and distributed classifier based on the popular nearest neighbor algorithm, adapted to such a demanding scenario. This method, implemented in Apache Spark, includes a distributed metric-space ordering to perform faster searches. Additionally, we propose an efficient incremental instance selection method for massive data streams that continuously update and remove outdated examples from the case-base. This alleviates the high computational requirements of the original classifier, thus making it suitable for the considered problem. Experimental study conducted on a set of real-life massive data streams proves the usefulness of the proposed solution and shows that we are able to provide the first efficient nearest neighbor solution for high-speed big and streaming data.

关键词： Apache Spark big data data streams distributed computing instance reduction machine learning nearest neighbor

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：