检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC)

作者： Xiao, Randong Yu, Haitao Du, Yong Beijing Transportat Informat Ctr Beijing 100161 Peoples R China

ISBN: (纸本)9781479949557

As the car number of Beijing break through five million, the mode share of public transportation sector is not large enough to ease congestion. To attract more people, the public transit should provide high quality service to the public. One way to achieve this is by developing intelligent transportation systems application to provide accurate bus arrival time prediction. Bus arrival time prediction has been a topic of research at home and abroad for years. However, little studies focus on the primary heterogeneous data processing which was the basic component of engineering practice. This study presents the method of primary data processing under heterogeneous conditions for bus arrival time prediction. The research also intends to test the proposed method using real-world bus data in Beijing, China, which performed effectively in terms of both prediction accuracy and computing time.

关键词： Bus-arrival time prediction bus line serialization heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

Zephyr: A High-Performance Framework for Graph Attention Networks on heterogeneous data 23

Zephyr: A High-Performance Framework for Graph Attention Net...

引用

23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2024

作者： Ding, Wenxiu Liu, Muzhi Cai, Yuxuan Chen, Mingxin Yan, Zheng Wang, Mingjun School of Cyber Engineering Xidian University Xi'an China Xidian University School of Computer Science and Technology Xi'an China Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai China

The Graph Attention Network (GAT), based on the foundational principles of Graph Neural Network (GNN), represents a significant advancement in the accurate representation and in-depth understanding of complex data structures. However, GAT can't proficiently handle heterogeneous data, which negatively affects model performance. Existing solutions incur substantial computational overhead when addressing these challenges, compromising efficiency and impeding practical deployment. In this paper, we propose Zephyr to enable GAT to efficiently process heterogeneous data with high performance. In Zephyr, we introduce Dynamic Multi-matrix Design and Spatial Multi-activation Design to eliminate the effects of finiteness of matrix representation capability and difference in heterogeneous spaces. Remarkably, Zephyr shows superior capability in processing heterogeneous data while requiring minimal storage space. Through comprehensive simulations and comparisons with existing schemes, Zephyr demonstrates a substantial performance improvement, increasing accuracy by over 8% on heterogeneous datasets and enhancing fitting speed by approximately 20%. Moreover, with heterogeneous data, it maintains memory overhead below 1.05x and curtails time overhead to 70%. © 2024 IEEE.

关键词： Fitting Enhancement Mechanism Graph Attention Networks heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

Power-Optimized Process Management in heterogeneous Computing Environments 2

Power-Optimized Process Management in Heterogeneous Computin...

引用

2nd International Conference on Sustainable Computing and Smart Systems (ICSCSS)

作者： Krishnan, R. Santhana Rajkumar, G. Vinoth Kokila, M. L. Sworna Raj, J. Relin Francis Jegadeesan, S. Gopikumar, S. Scad Coll Engn & Technol Dept Elect & Commun Engn Cheranmahadevi India JP Coll Engn Dept Elect & Commun Engn Thenkasi India SRM Inst Sci & Technol Sch Comp Coll Engn & Technol Dept Comp Technol Chennai Tamil Nadu India Saveetha Inst Med & Tech Sci Saveetha Sch Engn Dept Elect & Commun Chennai Tamil Nadu India Velammal Coll Engn & Technol Dept Informat Technol Madurai Tamil Nadu India Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & Dept Civil Engn Chennai Tamil Nadu India

ISBN: (纸本)9798350391558;9798350379990

Optimizing energy consumption while ensuring efficient process management is critical for eco-friendly and economic operations in contemporary computing environments. This research addresses the challenge of power-optimized process management in heterogeneous data processing environments, where diverse resources with varying capabilities and energy profiles coexist. Energy-efficient process management in such environments is essential for optimizing resource utilization and reducing operational costs. This study introduces a novel algorithm, Dynamic IoT-Boosted Neural Scheduling (DIBNS), which combines IoT data insights and neural network models to dynamically allocate tasks across diverse data processing resources, thereby reducing energy consumption. The proposed DIBNS algorithm adapts process management strategies based on real-time IoT data feedback, optimizing energy usage in heterogeneous data processing environments. Extensive simulations are conducted to evaluate the effectiveness of DIBNS, comparing it with existing algorithms using metrics such as energy consumption, makespan, and task completion time. The results demonstrate that DIBNS outperforms traditional scheduling algorithms by efficiently balancing computational loads across heterogeneous resources while minimizing energy consumption. Additionally, the adaptive nature of DIBNS allows it to respond to varying workload conditions, making it highly suitable for dynamic data processing environments.

关键词： Adaptive Scheduling Energy Efficiency heterogeneous data processing Machine Learning Neural Networks Task Allocation Process Management

来源：评论

学校读者我要写书评

暂无评论

Explanation of Deep Learning Models via Logic Rules Enhanced by Embeddings Analysis, and Probabilistic Models 6th

Explanation of Deep Learning Models via Logic Rules Enhanced...

引用

6th International Workshop on Explainable and Transparent AI and Multi-Agent Systems (EXTRAAMAS)

作者： Contreras, Victor Schumacher, Michael Calvaresi, Davide Univ Appl Sci Western Switzerland HES SO Delemont Switzerland

ISBN: (纸本)9783031700736;9783031700743

Deep Learning (DL) models are increasingly dealing with heterogeneous data (i.e., a mix of structured and unstructured data), calling for adequate eXplainable Artificial Intelligence (XAI) methods. Nevertheless, only some of the existing techniques consider the uncertainty inherent to the data. To this end, this study proposes a pipeline to explain heterogeneous data-based DL models by combining embedding analysis, rule extraction methods, and probabilistic models. The proposed pipeline has been tested using synthetic data (multi-individual food items tracking). This study has achieved (i) inference enhancement through probabilistic and evidential reasoning, (ii) generation of logical explanations based on extracted rules and predictions, and (iii) integration of textual data into the explanation pipeline through embedding analysis.

关键词： XAI Deep learning Uncertainty reasoning Rule extraction Preference modeling heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

Optimizing Multimodal Sarcasm Detection with a Dual Perceiving Network and Adaptive Fusion 12

Optimizing Multimodal Sarcasm Detection with a Dual Perceivi...

引用

12th International Conference on Information Systems and Computing Technology

作者： Zhai, Yi Liu, Jin Liu, Yuxin Jiang, Xiantao Shanghai Maritime Univ Coll Informat Engn Shanghai Peoples R China

ISBN: (纸本)9798350379860;9798350379877

Nowadays, posting sarcastic text or visual content on platforms like WhatsApp, Twitter, and Facebook has become a popular style, allowing individuals to avoid directly expressing pessimism, thereby indirectly conveying their thoughts or intentions. As more people express their opinions online, the need to develop effective models for accurate multimodal sarcasm detection is growing. However, most existing methods have deficiencies in extracting effective features from non-text modalities, which can result in the neglect of some sarcasm-related contextual information. Additionally, during the fusion phase of different modalities, simply using straightforward feature concatenation may introduce redundant information and noise. To address these challenges, a new model called Dual-Perceiving Network (DPN) was developed. It includes a dual-view perception module, which enables the text modality to fully perceive both the local and global features of the image modality, thereby obtaining context and background information conducive to constructing inconsistencies. Additionally, it employs an adaptive fusion method to effectively reduce the impact of redundant information. Extensive experiments comparing the proposed DPN with other multimodal sarcasm detection methods demonstrate its superior performance on public datasets.

关键词： Multimodal sarcasm detection Deep learning Large language models heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

Multi-Source data processing and Fusion Method for Power Distribution Internet of Things Based on Edge Intelligence

引用

FRONTIERS IN ENERGY RESEARCH 2022年 10卷

作者： Yuan, Quande Pi, Yuzhen Kou, Lei Zhang, Fangfang Li, Yang Zhang, Zhenming Changchun Inst Technol Changchun Peoples R China Changchun Inst Technol Natl Local Joint Engn Res Ctr Smart Distribut Gri Changchun Peoples R China Qilu Univ Technol Shandong Acad Sci Qingdao Peoples R China Northeast Elect Power Univ Jilin Jilin Peoples R China

With the rapid advancement of the Energy Internet strategy, the number of sensors within the Power Distribution Internet of Things (PD-IoT) has increased dramatically. In this study, an edge intelligence-based PD-IoT multi-source data processing and fusion method is proposed to solve the problems of confusing storage and insufficient fusion computing performance of multi-source heterogeneous distribution data. First, a PD-IoT multi-source data processing and fusion architecture based on edge smart terminals is designed. Second, the multi-source sensor data in the distribution network is unified in dimension and magnitude. By introducing the Box-Cox transform to improve the data offset problem in the Z-score normalization process, a multi-source heterogeneous data processing method for distribution networks based on the Box-Cox transform Z-score is proposed. Then, the conflicting phenomena of DS inference methods in data source fusion are optimally handled based on the PCA algorithm. A multi-source data fusion model based on DS inference with conflict optimization is constructed to ensure the effective fusion of distribution data sources from different domains. Finally, the effectiveness of the proposed method is verified by an experimental analysis of an IEEE39 node system in a regional distribution network in China.

关键词： energy internet edge intelligence power distribution internet of things heterogeneous data processing multi-source data fusion

来源：评论

学校读者我要写书评

暂无评论

data Management in EpiGraph COVID-19 Epidemic Simulator 27th

Data Management in EpiGraph COVID-19 Epidemic Simulator

引用

27th International European Conference on Parallel and Distributed Computing (Euro-Par)

作者： Guzman-Merino, Miguel Duran, Christian Marinescu, Maria-Cristina Delgado-Sanz, Concepcion Gomez-Barroso, Diana Carretero, Jesus Singh, David E. Univ Carlos III Madrid Dept Comp Sci Leganes Spain Barcelona Supercomp Ctr Barcelona Spain CIBER Epidemiol & Salud Publ CIBERESP Madrid Spain Carlos III Inst Hlth Natl Ctr Epidemiol Madrid Spain

ISBN: (纸本)9783031061561;9783031061554

The transmission of COVID-19 through a population depends on many factors which model, incorporate, and integrate many heterogeneous data sources. The work we describe in this paper focuses on the data management aspect of EpiGraph, a scalable agent-based virus-propagation simulator. We describe the data acquisition and pre-processing tasks that are necessary to map the data to the different models implemented in EpiGraph in a way that is efficient and comprehensible. We also report on post-processing, analysis, and visualization of the outputs, tasks that are fundamental to make the simulation results useful for the final users. Our simulator captures complex interactions between social processes, virus characteristics, travel patterns, climate, vaccination, and non-pharmaceutical interventions. We end by demonstrating the entire pipeline with one evaluation for Spain for the third COVID wave starting on December 27th of 2020.

关键词： Epidemiological simulation COVID-19 heterogeneous data processing Parallel tool

来源：评论

学校读者我要写书评

暂无评论

Design of smart factory network architecture based on non-uniform clustering 41

Design of smart factory network architecture based on non-un...

引用

第41届中国控制会议

作者： Lihui Wang Yonghui Zhang Haoyuan Zheng School of Information and Communication Engineering Hainan University Engineering Research Center of Embedded Intelligent System in Hainan Province

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

A smart factory network usually consists of multiple wireless sensor nodes and *** at the problem of the need to formulate unified multi-protocol conversion standards and network routing algorithms for heterogeneous network fusion in smart factories,this paper designs a smart factory network architecture based on non-uniform *** the acquisition layer,a non-uniform cluster routing algorithm is *** the analysis layer,a task-based knowledge model is proposed to abstract each production stage of intelligent *** the transmission layer,the hardware design scheme of the network node is *** simulation results show that the industrial production network finally forms a cluster *** the network upstream and downstream data of the gateway,HTTP response and other data,it can be seen that the network delay is relatively low,the data transmission is stable,and the network load is relatively balanced.

关键词： Smart factory Network architecture Cluster routing heterogeneous data processing

来源：评论

学校读者我要写书评

暂无评论

processing of Medical Different Types of data Using Hadoop and Java MapReduce 3

Processing of Medical Different Types of Data Using Hadoop a...

引用

3rd International Conference on Informatics and data-Driven Medicine (IDDM)

作者： Boyko, Nataliya Tkachuk, Nazar Lviv Polytech Natl Univ Profesorska St 1 UA-79013 Lvov Ukraine

This article shows the analysis of sample data of different types using Java MapReduce on the Hadoop platform. The Java programming language and the Java MapReduce API are used to work on large amounts of data ("Big data") that have different formats and structures. So, the task was to process the medical data and get a single source file. The result of the program was saved in the HDFS file system. These source data can then be saved to the NTFS file system using Sqoop or the files can be copied manually to the system for further processing.

关键词： data processing Hadoop Java Map/Reduce heterogeneous data processing MapReduce Big data data Analysis HDFS multiple input

来源：评论

学校读者我要写书评

暂无评论

Opinion mining on large scale data using sentiment analysis and k-means clustering

引用

CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS 2019年第3-Sup期22卷 S7149-S7164页

作者： Riaz, Sumbal Fatima, Mehvish Kamran, M. Nisar, M. Wasif COMSATS Inst Informat Technol Dept Comp Sci Wah Cantt Pakistan

With the rapid growth of web technology and easy access of internet, online shopping has been increased. Now people express their opinions and share their experiences that greatly influence new buyers for purchasing products, thereby generating large data sets. This large data is very helpful for analyzing customer preference, needs and its behavior toward a product. Companies face the challenge of analyzing this sheer amount of data to extract customer opinion. To address this challenge, in this paper, we performed sentiment analysis on the customer review real-world data at phrase level to find out customer preference by analyzing subjective expressions. Then we calculated the strength of sentiment word to find out the intensity of each expression and applied clustering for placing the words in various clusters based on their intensity. We also compared the results of our technique with star-ranking given on the same dataset and found the drastic change in our results. We also provide a visual representation of our results to provide a clear insight of customer preference and behavior to help decision makers for better decision making.

关键词： heterogeneous data processing Imbalanced learning Intelligent 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：