检索结果-内蒙古大学图书馆

24th international Middleware conference Demos, Posters and Doctoral Symposium, Middleware 2023

作者： Tanimura, Yusuke Nakada, Hidemoto Dong, Yunzhi National Institute of Advanced Industrial Science and Technology Japan University of Tsukuba Japan

ISBN: (纸本)9798400704291

In order to respond data growth from edge to cloud and efficiently use various real data for advanced digital services, we advocate edge-side common data processing services on the computing continuum. This poster presents our background motivation of the concept, summarizes requirements and assumptions, and introduces an overview design of our proposed depot service, which would be implemented as our future work to show a proof of the concept. © 2023 ACM.

关键词： data handling

来源：评论

学校读者我要写书评

暂无评论

Exascale programing models for extreme data processing 23

Exascale programing models for extreme data processing

引用

20th ACM international conference on computing Frontiers (CF)

作者： Garcia-Blas, Javier Carretero, Jesus Univ Carlos III Madrid Madrid Spain

ISBN: (纸本)9798400701405

Extreme data is an incarnation of Big data concept distinguished by the massive amounts of data that must be queried, communicated and analysed in (near) real-time by using a very large number of memory/storage elements and Exascale computing systems. Immediate examples are the scientific data produced at a rate of hundreds of gigabits-per-second that must be stored, filtered and analysed, the millions of images per day that must be mined/analyzed in parallel, the one billion of social data posts queried in real-time on an in-memory components database. Traditional disks or commercial storage cannot handle nowadays the extreme scale of such application data. Following the need of improvement of current concepts and technologies, ASPIDE's activities focus on data-intensive applications running on systems composed of up to millions of computing elements (Exascale systems). Practical results will include the methodology and software prototypes that will be designed and used to implement Exascale applications. The ASPIDE project contributed with the definition of a new programming paradigms, APIs, runtime tools and methodologies for expressing data-intensive tasks on Exascale systems, which can pave the way for the exploitation of massive parallelism over a simplified model of the system architecture, promoting high performance and efficiency, and offering powerful operations and mechanisms for processing extreme data sources at high speed and/or real-time. This work is continued now in the ADMIRE EuroHPC project.

关键词： High Performance data Analysis Programming models Monitoring Auto-tuning

来源：评论

学校读者我要写书评

暂无评论

data Acquisition and Monitoring Scheme for Satellite Network with Time-Varying Topology

Data Acquisition and Monitoring Scheme for Satellite Network...

引用

international conference on Satellite computing

作者： Zhang, Ying Wo, Tianyu Wang, Guangjian Ye, Tianyu Zhang, Jiwei Liu, Xinye Feng, Xiao Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp BDB Beijing Peoples R China China Elect Technol Taiji Grp Corp Ltd Beijing Peoples R China

ISBN: (纸本)9798350305883;9798350305890

As human beings further explore space, satellite systems have become an indispensable tool for human society. However, managing satellite networks, especially in edge cloud computing scenarios, presents unique challenges due to its time-varying nature. To address these challenges, we propose a novel data acquisition and monitoring scheme specifically designed for satellite network environments. Our scheme leverages eBPF (extended Berkeley Packet Filter) technology for real-time monitoring data collection and utilizes a spatial-temporal graph representation to capture the dynamic topology of the satellite network. The Max-Min Fair (MMF) algorithm is employed to compute efficient routing paths, while data preprocessing techniques are applied to alleviate data transmission pressure. The scheme is designed to support user-defined monitoring targets and enables active detection and monitoring of application processes based on specific requirements. To evaluate the effectiveness of our proposed scheme, we conduct a comparative analysis against the Shortest Path on the Spatial-Temporal graph (SPST) algorithm and the Energy-Aware Multipath (EAMP) algorithm. Experimental results demonstrate the superiority of the MMF algorithm, exhibiting a significant 32.6% and 21.5% improvement in data transmission volume compared to the SPST and EAMP algorithms, respectively. Moreover, the utilization of the MMF algorithm reduces the average satellite bandwidth utilization by 37.1% and 41.2% throughout the transmission cycle, surpassing the performance of the SPST and EAMP algorithms.

关键词： satellite network time-varying topology data acquisition monitoring scheme

来源：评论

学校读者我要写书评

暂无评论

Learning with supervised data for anomaly detection in smart manufacturing

引用

international JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2023年第9期36卷 1331-1344页

作者： He, Meiling Petering, Matthew LaCasse, Phillip Otieno, Wilkistar Maturana, Francisco Rockwell Automat Inc Dept AI IoT DA&I IT Milwaukee WI USA Univ Wisconsin Milwaukee WI USA Univ Wisconsin Dept Ind & Mfg Engn Milwaukee WI USA

The emergence of the Internet of Things (IoT), cloud computing, cyber-physical systems, system integration, big data, and data analytics for Industry 4.0 have transformed the world of traditional manufacturing into an era of smart manufacturing (SM). Smart manufacturing's central focus is to process real-time IoT data and leverage advanced analytical approaches to detect abnormal behaviors. Social smart manufacturing applies analytics tools to empower decision makers and minimize duplication by executing the repetitive data processing work more consistently and precisely than can be done by a human operator. In smart manufacturing, the majority of industrial data is imbalanced. However, most traditional machine learning algorithms tend to be biased toward the majority class and under-represent the minority class. This research proposes a model selection architecture to automate the procedure of preprocessing input data and selecting the best combination of algorithms for anomaly detection. This design will play an essential role in producing high-quality products and improving quality control and business processes in diverse applications including predictive maintenance and fault detection. The framework is transferrable to any smart manufacturing task in the supervised learning domain.

关键词： Advanced analytics smart manufacturing imbalanced data generic model selection big data anomaly detection

来源：评论

学校读者我要写书评

暂无评论

2023 8th international conference on Intelligent computing and Signal processing, ICSP 2023

2023 8th International Conference on Intelligent Computing a...

引用

8th international conference on Intelligent computing and Signal processing, ICSP 2023

ISBN: (纸本)9798350302455

The proceedings contain 432 papers. The topics discussed include: consistent sensing algorithm for distributed PV station area line loss anomaly fluctuation based on spectral clustering;video anomaly detection based on multiple instance 3D channel attention;transformer-based Siamese neural network face verification method;a network structure for rehabilitation training evaluation based on transformer;intelligent evaluation model of fetal health based on PCA and stacking algorithm;attention feature selection based on prior knowledge injection;analysis and prediction of heart disease based on machine learning algorithms;point cloud simplification method based on two-fold neighboring feature preservation;multi-strategy fusion improved Archimedes optimization algorithm;a video captioning method based on visual-text semantic association;and an Improved DVB-S2 phase coarse synchronization algorithm and Its FPGA implementation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bird Call Recognition using Acoustic based Feature Selection approach in Machine Learning 7

Bird Call Recognition using Acoustic based Feature Selection...

引用

2023 7th international conference On computing, Communication, Control And Automation, ICCUBEA 2023

作者： Mishra, Shivam Ghatak, Rumpa Singh, Vishal Kumar Singh, Shivam Kumar Mahato, Anisha Information Technology Techno International New Town Kolkata India

ISBN: (纸本)9798350304268

The recognition of bird calls has been a challenging task in the field of bioacoustics. With the advancement of machine learning algorithms, automatic bird call recognition has become an active research area. In this paper, acoustic feature selection is used which involves the extraction of relevant features from audio recordings of bird calls. Then different classification algorithms are explored for the recognition of the bird calls. Evaluation of the approach is done on a dataset consisting of recordings from multiple bird species and compared it with other state-of-the-art machine learning algorithms. This research has the potential to contribute to the conservation of bird species and their habitats by enabling the efficient monitoring of bird populations. The data is classified into four different classes (namely Astfly, Bulori, Warvir and Woothr). All of which is found in the depths of Amazon Rainforest. © 2023 IEEE.

关键词： acoustic features bird call recognition machine learning

来源：评论

学校读者我要写书评

暂无评论

Application of Big data Analysis and Video Identification Methods in Urban Transportation Control System

Application of Big Data Analysis and Video Identification Me...

引用

2023 international conference on Applied Physics and computing, ICAPC 2023

作者： Sun, Heyuan Peng, Wenzhe The University of Hong Kong Department of Mechanical Engineering Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

ISBN: (纸本)9798350359244

This project intends to construct a set of traffic signal management and control system for intelligent road network, using big data analysis and artificial intelligence video identification methods to carry out real-time analysis of large-scale traffic information, and transform it into an event-based process. In this way, the precise control of the road network is achieved. Then this paper establishes multi-level intersections such as urban road intersections, regional and urban integrated dispatch centers based on big data. The system has high overall and coordination ability. Through multistage signal processing, the traffic signal can be efficiently regulated and controlled, so that it can achieve better traffic control effect in many cases. The model is simulated. It is found that the model can monitor the vehicle in real time in practical application. This method can greatly reduce the cost of the whole system, and has the characteristics of low overhead and high efficiency. © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Design of Anomaly Detection Algorithm for Intelligent data Acquisition Terminal of Internet of Things Based on Deep Learning

Design of Anomaly Detection Algorithm for Intelligent Data A...

引用

2023 international conference on Internet of Things, Robotics and Distributed computing, ICIRDC 2023

作者： Fang, Liyou Wuxi Taihu University Jiangsu Wuxi214062 China

ISBN: (纸本)9798350375275

Anomaly detection is the identification of items, events, or observed values that do not meet the expected situation or other conditions in the data set. In this paper, an anomaly detection algorithm of loT (Internet of Things) intelligent data acquisition terminal based on deep learning is proposed. In the case design, the Text-CNN (Text-convolutional Neural Network) is adopted as the algorithm of supervised detection scheme. Split the collected loT data set to obtain network traffic data of a plurality of different devices, and label these data in categories;Input the data into the established Text-CNN algorithm model through NLP;In the sample category output module, train the model, save the trained model, test it, and output the sample category. The test results show that the algorithm proposed in this chapter is superior to other literature algorithms in anomaly detection, and it is suitable for anomaly detection of complex data, especially high-dimensional data. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Research on Acceleration Technologies and Recent Advances of data Center GPUs 8

Research on Acceleration Technologies and Recent Advances of...

引用

8th international conference on Intelligent computing and Signal processing, ICSP 2023

作者： Cui, Chen Wu, Di Du, Jiawei Guo, Jin Liu, Zhe Unit 63891 Luoyang China

ISBN: (纸本)9798350302455

Deep learning applications in data centers are significantly computation-intensive and storage-intensive, and require GPUs with high throughput and high energy efficiency. Major manufacturers have successively released a number of high-performance data center GPU accelerators, which comprehensively use a variety of software and hardware optimization technologies to obtain excellent performance. Understanding and using these optimization technologies is of great significance to deeply understand GPUs and fully release their powerful computing capabilities. This paper analyzes and reviews the acceleration technologies and their recent advances used in data center GPU accelerators to improve throughput and energy efficiency, including convolution acceleration, data quantization, tensor/matrix cores, sparsity, high bandwidth and density memory, software stack, and multi-GPU system interconnect. This article also compares and analyzes the computation and storage performance of the latest data center GPU accelerators released by representative vendors such as Nvidia, AMD, Intel and so on. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Location-Based Geographical-Spatial data Mining for Detection and Visualization of Reported Problems using Image processing Techniques 14

Location-Based Geographical-Spatial Data Mining for Detectio...

引用

14th international conference on Advances in computing, Control, and Telecommunication Technologies, ACT 2023

作者： Harsoor, Anita Soma, Bhavani P D A College of Engineering Department of Computer Science and Engineering Kalaburagi India

We face many possible problems/issues in our daily lives, such as potholes, garbage filling, uncomfortable parking, broken roads, etc. To report that kind of problem becomes a great hassle. To solve this problem we developed a Geographical-Spatial data Mining System (GDMS), an android mobile application named Civicawareness for retrieving and analyzing textual data with geographical locations and photos as proof. The model has four constituents: data collection, data pre-processing, data analysis, and data visualization. Here, we use the k-means algorithm for clustering and SVM for classification. This system will collect a large number of data that will be used by common people to post the problems they have found. © Grenze Scientific Society, 2023.

关键词： data mining

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：