检索结果-内蒙古大学图书馆

A shapelet-based framework for large-scale word-level sign language database auto-construction

NEURAL computing & APPLICATIONS 2023年第1期35卷 253-274页

作者： Ma, Xiang Wang, Qiang Zheng, Tianyou Yuan, Lin Harbin Inst Technol Dept Control Sci & Engn Harbin 150001 Peoples R China

Sign language recognition is a challenging and often underestimated problem that includes the asynchronous integration of multimodal articulators. Learning powerful applied statistical models requires much training data. However, well-labelled sign language databases are a scarce resource due to the high cost of manual labelling and performing. On the other hand, there exist a lot of sign language-interpreted videos on the Internet. This work aims to propose a framework to automatically learn a large-scale sign language database from sign language-interpreted videos. We achieved this by exploring the correspondence between subtitles and motions by discovering shapelets which are the most discriminative subsequences within the data sequences. In this paper, two modified shapelet methods were used to identify the target signs for 1000 words from 89 (96 h, 8 naive signers) sign language-interpreted videos in terms of brute force search and parameter learning. Then, an augmented (3-5 times larger) large-scale word-level sign database was finally constructed using an adaptive sample augmentation strategy that collected all similar video clips of the target sign as valid samples. Experiments on a subset of 100 words revealed a considerable speedup and 14% improvement in recall rate. The evaluation of three state-of-the-art sign language classifiers demonstrates the good discrimination of the database, and the sample augmentation strategy can significantly increase the recognition accuracy of all classifiers by 10-33% by increasing the number, variety, and balance of the data.

关键词： Sign language Shapelet Self-learning big data computing

来源：评论

学校读者我要写书评

暂无评论

Intelligent computing for Cybersocial Space 12

Intelligent Computing for Cybersocial Space

引用

12th IEEE International Black Sea Conference on Communications and Networking (BlackSeaCom)

作者： Hahanov, Vladimir Litvinova, Eugenia Davitadze, Zaza Chumachenko, Svetlana Devadze, David Abashidze, Marina Kharkov Natl Univ Radioelect Design Automat Dept Kharkov Ukraine Batumi Shota Rustaveli State Univ Dept Comp Sci Batumi Georgia Batumi Maritime Acad Maritime Fac Batumi Georgia

ISBN: (纸本)9798350351866;9798350351859

Intelligent computing architectures are proposed for managing cyber social processes based on monitoring and analysis of big data. It is proposed to process big data as truth table addresses to solve problems of identification, clustering, and classification of patterns of social and production processes. A family of automata is proposed for analyzing big data such as addresses. The purpose of this investigation is to enhance the big data economy by analyzing data as truth table addresses to identify patterns of production functionality based on the similarity-difference metric. The truth table is considered as a smart form of explicit data structures that have a useful constant - the standard order of addresses. For processing big data, it is necessary to structure their using a truth table. The representation of data as addresses is associated with the unitary coding of patterns by binary vectors on the found universe of primitive data. The mechanism is focused on non-processor data processing based on read-write transactions using in-memory computing technology with significant savings in time and energy. The truth table metric for big data processing is parallelism, technological simplicity, and linear computational complexity. The tradeoff for these benefits is the exponential memory redundancy of storing explicit structured data.

关键词： Intelligent computing Cloud Fog and Edge computing big data computing In-Memory computing Cyber Social computing Hadoop Map-Reduce Technique big data as Addresses Truth Table Logical Vector Similarity-Differences data Equivalence Universe Of Primitives Patterns As Binary Vectors

来源：评论

学校读者我要写书评

暂无评论

In-Memory Distributed Mosaicking for Large-Scale Remote Sensing Applications with Geo-Gridded data Staging on Alluxio

引用

REMOTE SENSING 2022年第23期14卷 5987-5987页

作者： Ma, Yan Song, Jie Zhang, Zhixin Chinese Acad Sci Aerosp Informat Res Inst 9 Dengzhuang South Rd Beijing 100089 Peoples R China Univ Chinese Acad Sci 19 A Yuquan Rd Beijing 100089 Peoples R China

The unprecedented availability of petascale analysis-ready earth observation data has given rise to a remarkable surge in demand for regional to global environmental studies, which exploit tons of data for temporal-spatial analysis at a much larger scale than ever. Imagery mosaicking, which is critical for forming "One Map" with a continuous view for large-scale climate research, has drawn significant concern. However, despite employing distributed data processing engines such as Spark, large-scale data mosaicking still significantly suffers from a staggering number of remote sensing images which could inevitably lead to discouraging performance. The main ill-posed problem of traditional parallel mosaicking algorithms is inherent in the huge computation demand and incredible heavy data I/O burden resulting from intensively shifting tremendous RS data back and forth between limited local memory and bulk external storage throughout the multiple processing stages. To address these issues, we propose an in-memory Spark-enabled distributed data mosaicking at a large scale with geo-gridded data staging accelerated by Alluxio. It organizes enormous "messy" remote sensing datasets into geo-encoded gird groups and indexes them with multi-dimensional space-filling curves geo-encoding assisted by GeoTrellis. All the buckets of geo-grided remote sensing data groups could be loaded directly from Alluxio with data prefetching and expressed as RDDs implemented concurrently as grid tasks of mosaicking on top of the Spark-enabled cluster. It is worth noticing that an in-memory data orchestration is offered to facilitate in-memory big data staging among multiple mosaicking processing stages to eliminate the tremendous data transferring at a great extent while maintaining a better data locality. As a result, benefiting from parallel processing with distributed data prefetching and in-memory data staging, this is a much more effective approach to facilitate large-scale data mosaicking

关键词： remote sensing big data earth observation data big data computing distributed data computing data mosaicking data tiling in-memory processing Alluxio

来源：评论

学校读者我要写书评

暂无评论

Causal Effects of Air Pollution on Mortality Rate in Massachusetts

引用

AMERICAN JOURNAL OF EPIDEMIOLOGY 2020年第11期189卷 1316-1323页

作者： Wei, Yaguang Wang, Yan Wu, Xiao Di, Qian Shi, Liuhua Koutrakis, Petros Zanobetti, Antonella Dominici, Francesca Schwartz, Joel D. Harvard TH Chan Sch Publ Hlth Dept Environm Hlth Landmark Ctr 4th West401 Pk Dr Boston MA 02215 USA Harvard TH Chan Sch Publ Hlth Dept Biostat Boston MA USA Tsinghua Univ Res Ctr Publ Hlth Sch Med Beijing Peoples R China Emory Univ Rollins Sch Publ Hlth Gangarosa Dept Environm Hlth Atlanta GA 30322 USA

Air pollution epidemiology studies have primarily investigated long- and short-term exposures separately, have used multiplicative models, and have been associational studies. Implementing a generalized propensity score adjustment approach with 3.8 billion person-days of follow-up, we simultaneously assessed causal associations of long-term (1-year moving average) and short-term (2-day moving average) exposure to particulate matter with an aerodynamic diameter less than or equal to 2.5 mu m (PM2.5), ozone, and nitrogen dioxide with all-cause mortality on an additive scale among Medicare beneficiaries in Massachusetts (2000-2012). We found that long- and short-term PM2.5, ozone, and nitrogen dioxide exposures were all associated with increased mortality risk. Specifically, per 10 million person-days, each 1-mu g/m(3) increase in long- and short-term PM2.5 exposure was associated with 35.4 (95% confidence interval (CD: 33.4, 37.6) and 3.04 (95% CI: 2.17, 3.94) excess deaths, respectively;each 1-part per billion (ppb) increase in long- and short-term ozone exposure was associated with 2.35 (95% CI: 1.08, 3.61) and 2.41 (95% CI: 1.81, 2.91) excess deaths, respectively;and each 1-ppb increase in long- and short-term nitrogen dioxide exposure was associated with 3.24 (95% CI: 2.75, 3.77) and 5.60 (95% CI: 5.24, 5.98) excess deaths, respectively. Mortality associated with long-term PM2.5 and ozone exposure increased substantially at low levels. The findings suggested that air pollution was causally associated with mortality, even at levels below national standards.

关键词： air pollution big data computing causality generalized propensity score linear probability model

来源：评论

学校读者我要写书评

暂无评论

On Machine Learning-based Stage-aware Performance Prediction of Spark Applications 39

On Machine Learning-based Stage-aware Performance Prediction...

引用

39th IEEE International Performance computing and Communications Conference (IPCCC)

作者： Ye, Guangjun Liu, Wuji Wu, Chase Q. Shen, Wei Lyu, Xukang Zhejiang Sci Tech Univ Sch Informat Sci & Technol Hangzhou 310018 Zhejiang Peoples R China New Jersey Inst Technol Dept Comp Sci Newark NJ 07102 USA Tianjin Univ Coll Intelligence & Comp Sch Comp Software Tianjin 300354 Peoples R China

ISBN: (纸本)9781728198293

The data volume of large-scale applications in various science, engineering, and business domains has experienced an explosive growth over the past decade, and has gone far beyond the computing capability and storage capacity of any single server. As a viable solution, such data is oftentimes stored in distributed file systems and processed by parallel computing engines, as exemplified by Spark, which has gained increasing popularity over the traditional MapReduce framework due to its fast in-memory processing of streaming data. Spark engines are generally deployed in cloud environments such as Amazon EC2 and Alibaba Cloud. However, storage and computing resources in these cloud environments are typically provisioned on a pay-as-you-go basis and thus an accurate estimate of the execution time of Spark workloads is critical to making full utilization of cloud resources and meeting performance requirements of end users. Our insight is that the execution pattern of many Spark workloads is qualitatively similar, which makes it possible to leverage historical performance data to predict the execution time of a given Spark application. We use the execution information extracted from Spark History Server as training data and develop a stage-aware hierarchical neural network model for performance prediction. Experimental results show that the proposed hierarchical model achieves higher accuracy than a holistic prediction model at the end-to-end level, and also outperforms other existing regression-based prediction methods.

关键词： big data computing performance modeling Spark in-memory processing

来源：评论

学校读者我要写书评

暂无评论

A general architecture for a real-time monitoring system based on the internet of things

引用

INTERNET OF THINGS 2021年 14卷

作者： Paudel, Nilakantha Neupane, Ram C. Gran Sasso Sci Inst Viale Francesco Crispi 7 I-67100 Laquila AQ Italy Texas A&M Univ 7101 Univ Ave Texarkana TX 75503 USA

Recently there has been significant progress in the real-time monitoring system based on the Internet of Things (IoT). The use rate of IoT has been increasing exponentially because of its enormous application in different areas, and many of them are yet to be explored. This paper explains how to design an IoT system and describes its working mechanism. We present a general architecture of the real-time monitoring system using IoT and related services. We successfully implement our proposed architecture for a single domain. Then, we describe how to use the proposed architecture to monitor the different real-time contextual domains. Also, we present ideas on how to plug the data from a third-party application into the proposed architecture. (C) 2021 Elsevier B.V. All rights reserved.

关键词： IoT Real time monitoring system Intelligent control big data computing Cloud computing Security

来源：评论

学校读者我要写书评

暂无评论

A novel application recommendation method combining social relationship and trust relationship for future internet of things

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2019年第21期78卷 29867-29880页

作者： Ju, Chunhua Wang, Jie Xu, Chonghuan Zhejiang Gongshang Univ Grad Sch Hangzhou 310018 Zhejiang Peoples R China Zhejiang Gongshang Univ Business Adm Coll Hangzhou 310018 Zhejiang Peoples R China Zhejiang Tech Inst Econ Shangmao Coll Hangzhou 310018 Zhejiang Peoples R China

Traditional collaborative filtering methods always utilize Cosine and Pearson methods to calculate the similarity of users. When the nearest neighbor doesn't comment the predicted item, then the nearest neighbor has no influence on results, thus affecting the accuracy of collaborative filtering recommendation. And the traditional recommendation systems always have the problems of data sparsity, cold start and so on. In this paper, we consider social relationship and trust relationship, and put forward a novel application recommendation method that combines users' social relationship and trust relationship. Specifically, we combine social relationship and user preference towards applications to calculate similarity score, we fuse the trust relationship based on familiarity and user reputation to calculate trust score. The final prediction score is calculated by fusing similar relationship and trust relationship properly. And the proposed method can effectively improve accuracy of recommendations.

关键词： big data computing Future internet of things Application recommendation Social relationship Social similarity Trust relationship

来源：评论

学校读者我要写书评

暂无评论

Rethinking elastic online scheduling of big data streaming applications over high-velocity continuous data streams

引用

JOURNAL OF SUPERcomputing 2018年第2期74卷 615-636页

作者： Sun, Dawei Yan, Hongbin Gao, Shang Liu, Xunyun Buyya, Rajkumar China Univ Geosci Sch Informat Engn Beijing 100083 Peoples R China Univ Melbourne Sch Comp & Informat Syst Cloud Comp & Distributed Syst CLOUDS Lab Parkville Vic Australia Deakin Univ Sch Informat Technol Burwood Vic 3216 Australia

Online scheduling plays a key role for big data streaming applications in a big data stream computing environment, as the arrival rate of high-velocity continuous data stream might fluctuate over time. In this paper, an elastic online scheduling framework for big data streaming applications (E-Stream) is proposed, exhibiting the following features. (1) Profile mathematical relationships between system response time, multiple application fairness, and online features of high-velocity continuous stream. (2) Scale out or scale in a data stream graph by quantifying computation and communication cost, and the vertex semantics for arrival rate of data stream, and adjust the degree of parallelism of vertices in the graph. Subgraph is further constructed to minimize data dependencies among the subgraphs. (3) Elastically schedule a graph by a priority-based earliest finish time first online scheduling strategy, and schedule multiple graphs by a max-min fairness strategy. (4) Evaluate the low system response time and acceptable applications fairness objectives in a real-world big data stream computing environment. Experimental results conclusively demonstrate that the proposed E-Stream provides better system response time and applications fairness compared to the existing Storm framework.

关键词： Elastic scheduling data stream graph Streaming application High-velocity stream big data computing

来源：评论

学校读者我要写书评

暂无评论

Space-Time Effect Modelling with Machine Learning: A Scalable Approach for Assessing Efficiency of Coal Resources 5

Space-Time Effect Modelling with Machine Learning: A Scalabl...

引用

5th International Conference on big data computing and Communications (bigCOM)

作者： Xue, Liming Du, Yulin Li, Wei Zhao, Xinghui China Univ Min & Technol Sch Energy & Min Beijing Peoples R China Washington State Univ Sch Engn & Comp Sci Vancouver WA 98686 USA

ISBN: (纸本)9781728140247

Resource shortage and environmental degradation have long been the major problems that the current generation is facing, and these problems are even more severe in developing countries, such as China. To address these challenges, being able to utilize existing resources more efficiently is a key. The first step towards efficient use of resources is to design and develop an effective and scalable approach to measure and evaluate resource efficiency. This has been a challenging problem due to a lack of widely accepted standards, as well as the complexity of the data collected by different communities. In this paper, we address this problem using an improved data envelopment analysis (DEA) model of Bootstrap. We leverage machine learning techniques to enhance the scalability, and explore the potentials of predicting future efficiency trend using historical data. Using this approach, we measure the coal resource efficiency of 30 provinces in China from 2000 to 2015. Our results show that the proposed approach can significantly improve the accuracy of the measurement of a traditional data Envelopment Analysis(DEA) model. In addition, when applying machine learning techniques to the data, the proposed model demonstrates better potentials for scalable and accurate prediction on the coal resource efficiency. Our approach can be easily adopted by various organizations to evaluate the resource efficiency over time, and develop more efficient strategies for resource use based on the measurement data.

关键词： big data computing Machine Learning Scalability Coal Efficiency Spatial Effect

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning Framework for Multi-Objective Design Space Exploration and Optimization of Manycore Systems 1

A Machine Learning Framework for Multi-Objective Design Spac...

引用

ACM/IEEE 1st Workshop on Machine Learning for CAD (MLCAD)

作者： Joardar, Biresh Kumar Deshwal, Aryan Doppa, Janardhan Rao Pande, Partha Pratim Washington State Univ Sch EECS Pullman WA 99164 USA

ISBN: (纸本)9781728157580

The growing needs of emerging big data applications has posed significant challenges for the design of optimized manycore systems. Network-on-Chip (NoC) enables the integration of a large number of processing elements (PEs) in a single die. To design optimized manycore systems, we need to establish suitable trade-offs among multiple objectives including power, performance, and thermal. Therefore, we consider multi-objective design space exploration problems arising in the design of NoC-enabled manycore systems: placement of PEs and communication links to optimize two or more objectives (e.g., latency, energy, and throughput). Existing algorithms suffer from scalability and accuracy challenges as size of the design space and the number of objectives grow. In this paper, we propose a novel framework referred as Guided Design Space Exploration (Guided-DSE) that performs adaptive design space exploration using a data-driven model to improve the speed and accuracy of multi-objective design optimization process. We provide two concrete instantiations of guided-DSE and present results to show their efficacy for designing 3D heterogeneous manycore systems.

关键词： Machine learning Manycore systems Heterogeneity Network-on-chip big data computing

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：