检索结果-内蒙古大学图书馆

Coupled Noise Reduction in distributed Acoustic Sensing Seismic Data Based on Convolutional neural network

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Zhao, Yuxing Li, Yue Wu, Ning Jilin Univ Coll Commun Engn Dept Informat Changchun 130012 Peoples R China

distributed acoustic sensing (DAS) is widely recognized as a new technology to replace conventional geophones for the acquisition of seismic data. However, the collected data often contain a lot of coupled noise due to cable slapping and ringing along the borehole casing, which brings great difficulties to the interpretation of seismic data. The existing conventional coupled noise reduction methods often need to estimate the parameters of each coupled noise (such as amplitude, noise period, attenuation coefficient, etc.), which takes a lot of time and cannot meet the requirements for large-data-volume DAS seismic data processing. In addition, some deep learning-based denoising methods lack detailed analysis on coupled noise and have problems in the construction of training sets, resulting in insufficient generalization ability of the denoising model. To solve these problems, we propose a coupled noise reduction method based on the convolutional neural network (CNN). The proposed method does not need to estimate the parameters of coupled noise, and the denoising process is more convenient and efficient. In addition, through the analysis of DAS seismic data, we also construct a training set for coupled noise reduction using real data and synthetic data. The denoising results of both synthetic data and field data show that the proposed method can effectively reduce the coupled noise in DAS seismic data, and the effective signal has almost no energy loss. After processing, the signal affected by coupled noise becomes clear and continuous, providing high-quality data support for subsequent interpretation.

关键词： Noise reduction Training Attenuation Convolutional neural networks Data processing Mathematical models Geoscience and remote sensing Convolutional neural network (CNN) coupled noise denoise distributed acoustic sensing (DAS) training set

来源：评论

学校读者我要写书评

暂无评论

Flyback PPC Converter with Artificial neural network for distributed MPPT Application 8

Flyback PPC Converter with Artificial Neural Network for Dis...

引用

8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022

作者： Sebin Davis, K. Jegathesan, V. Karunya University Department of Eee Coimbatore641114 India

ISBN: (纸本)9781665408165

This paper proposes a partial power processing (PPC) based configuration of DC-DC converter to overcome the issues due to partial shading in photovoltaic (PV) modules. Series connected partial power converter (S-PPC) with flyback topology is utilised for the implementation of distributed maximum power point tracking (DMPPT). In a conventional DC-DC converter, the total string power is processed by a single converter known as global maximum power point tracking (GMPPT) is utilised. Again, in the conventional DC-DC converters, the converter process complete power to achieve maximum power point tracking (MPPT). This paper proposes a Flyback S-PPC circuit which process only a part of total power flow, which is known as a partial power processing (PPP). The Flyback S-PPC is connected to each PV module and ANN-based MPPT is applied, higher efficiency with good steady-state and better transient responses are obtained. A comparative study is conducted to validate the performance of the proposed DC-DC converter configuration, and its results are discussed in this paper © 2022 IEEE.

关键词： DC-DC converters

来源：评论

学校读者我要写书评

暂无评论

distributed data processing and task scheduling based on GPU parallel computing

引用

neural Computing and Applications 2024年第4期37卷 1757-1769页

作者： Li, Jun Department of Electronic Information Engineering Nanchong Vocational and Technical College Sichuan Nanchong637131 China

distributed data parallel (DDP) computing ensures data parallelism, enabling execution across several computers. A separate distributed data parallel computing instance should be created for each process that uses distributed data parallel computing. Task scheduling in parallel processing employs various methods and strategies to minimize the number of delayed jobs. Reliability in terms of a system’s capacity to distribute work over several machines and computers is improved by workload sharing, task migration, and automatic task replication;data transmission and reception are facilitated via the internet. The graphics processing unit (GPU) is a highly specialized electrical circuit. Compared to a traditional computer, a GPU parallel structure allows faster computation and greater effectiveness. GPUs are employed in parallel processing in new methods for DDP-GPUs with more processors, allowing a more significant workload to be handled in portions. The execution time of a program can be reduced by distributing various task areas among many processors. This study employs various multitasking scenarios, from simulated to real-world cases and from graphically heavy applications to parallel-processing workloads. The research compares the efficacy of several allocation algorithms, illuminating how best to divide GPU resources among multiple processes. By sorting through a vast volume of data more slowly, parallel computing saves time and money. Parallel and distributed computing concern the use of numerous computing resources to improve the results of a distributed and computationally expensive application. A single computer or a group of computers connected via a network can be used for computation. Our experimental findings show that the DPP-GPU implements task scheduling 95.3% better than the conventional GPU. The proposed model improves system reliability with an average execution time of 25.7 s. The time needed to run a program divided by the machine’s cost is approx

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

distributed photovoltaic cluster output monitoring method based on time series data acquisition

引用

Energy Informatics 2025年第1期8卷 1-27页

作者： Ye, Hua Lu, Xuegang Zhang, Wei Cheng, Fei Zhao, Ying School of Electrical and Information Engineering Tianjin University Tianjin300072 China Yunnan Power Grid Co. Ltd Yunnan Kunming650200 China

The data processing efficiency of distributed photovoltaic cluster output monitoring needs to be improved, improving the prediction effect of distributed photovoltaic power station cluster can effectively improve the security of power system operation and reduce the difficulty of power grid management. In order to obtain a reliable distributed photovoltaic cluster output monitoring method, this paper analyzes the output relationship of cluster power stations, combining time series data analysis methods for distributed cluster processing and monitoring data processing, a combined model of ceemdan and Bayesian neural network is proposed, the representative power plant prediction values obtained by establishing a combination model are weighted to obtain the cluster output prediction values. Compared with the simple superposition of the predicted values of cluster power stations, the average absolute error of this method is reduced by 3.3%, and the root mean square error is reduced by 5.86%. It is concluded that this model can effectively predict the power stations in the cluster. According to the experimental analysis, the output monitoring method of distributed photovoltaic clusters based on time series data collection proposed in this paper has certain effects and can provide theoretical support for the further development of distributed photovoltaic clusters. © The Author(s) 2025.

关键词： Data acquisition distributed photovoltaics Monitoring Time series

来源：评论

学校读者我要写书评

暂无评论

HiHGNN: Accelerating HGNNs Through Parallelism and Data Reusability Exploitation

引用

IEEE TRANSACTIONS ON PARALLEL AND distributed SYSTEMS 2024年第7期35卷 1122-1138页

作者： Xue, Runzhen Han, Dengke Yan, Mingyu Zou, Mo Yang, Xiaocheng Wang, Duo Li, Wenming Tang, Zhimin Kim, John Ye, Xiaochun Fan, Dongrui Chinese Acad Sci Inst Comp Technol State Key Lab Processors Beijing 100045 Peoples R China Univ Chinese Acad Sci Beijing 101408 Peoples R China Shanghai Innovat Ctr Processor Technol Shanghai 201203 Peoples R China Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 305701 South Korea

Heterogeneous graph neural networks (HGNNs) have emerged as powerful algorithms for processing heterogeneous graphs (HetGs), widely used in many critical fields. To capture both structural and semantic information in HetGs, HGNNs first aggregate the neighboring feature vectors for each vertex in each semantic graph and then fuse the aggregated results across all semantic graphs for each vertex. Unfortunately, existing graph neural network accelerators are ill-suited to accelerate HGNNs. This is because they fail to efficiently tackle the specific execution patterns and exploit the high-degree parallelism as well as data reusability inside and across the processing of semantic graphs in HGNNs. In this work, we first quantitatively characterize a set of representative HGNN models on GPU to disclose the execution bound of each stage, inter-semantic-graph parallelism, and inter-semantic-graph data reusability in HGNNs. Guided by our findings, we propose a high-performance HGNN accelerator, HiHGNN, to alleviate the execution bound and exploit the newfound parallelism and data reusability in HGNNs. Specifically, we first propose a bound-aware stage-fusion methodology that tailors to HGNN acceleration, to fuse and pipeline the execution stages being aware of their execution bounds. Second, we design an independency-aware parallel execution design to exploit the inter-semantic-graph parallelism. Finally, we present a similarity-aware execution scheduling to exploit the inter-semantic-graph data reusability. Compared to the state-of-the-art software framework running on NVIDIA GPU T4 and GPU A100, HiHGNN respectively achieves an average 40.0x and 8.3x speedup as well as 99.59% and 99.74% energy reduction with quintile the memory bandwidth of GPU A100.

关键词： Semantics Parallel processing Graph neural networks Vectors Graphics processing units Fuses Hardware GNN GNN accelerator graph neural network HGNN HGNN accelerator heterogeneous graph neural network

来源：评论

学校读者我要写书评

暂无评论

Leveraging Cloud Resources for distributed Training of Residual CNNs in Aerial Image Classification

引用

IEEE ACCESS 2025年 13卷 31131-31139页

作者： Kumar, Shantanu Singh, Shruti Kumar Dewangan, Narendra Amazon Seattle WA 98109 USA Washington State Univ IREACH Seattle WA 98195 USA Univ Petr & Energy Studies Sch Comp Sci Dehra Dun 248007 Uttaranchal India

Aerial image classification is crucial across multiple sectors, including environmental monitoring, agriculture, and urban planning. However, processing large-scale aerial imagery efficiently poses challenges in model performance, computational efficiency, and scalability. This research introduces a novel convolutional neural network (CNN) architecture tailored for cactus identification from aerial photographs. The proposed cloud-based pipeline enhances training efficiency through scalable data storage, preprocessing, and distributed training across platforms such as Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure. This comparative analysis demonstrates the model's computational efficiency, shorter training durations, and cost-effectiveness. The model integrates residual connections and depthwise separable convolutions, achieving 96.7% accuracy on the aerial cactus identification dataset. The results highlight the model's high performance, cost-efficiency, and scalability, making it suitable for real-world aerial image classification tasks. Future work aims to further optimize the model using advanced techniques and extend its application to multi-class classification challenges.

关键词： Cloud computing Computational modeling Training Artificial intelligence Data models Image classification Computer architecture Computational efficiency Accuracy Scalability Aerial image classification convolutional neural network (CNN) cloud computing distributed model training

来源：评论

学校读者我要写书评

暂无评论

Parmesan: Efficient Partitioning and Mapping Flow for DNN Training on General Device Topology

引用

IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 2024年第8期43卷 2426-2439页

作者： Liu, Lixin Liu, Tianji Jiang, Bentian Young, Evangeline F. Y. Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Peoples R China

Recently, various pipeline parallelism strategies are proposed to tackle the scalability problem of training a large DNN model on a distributed system. However, most of the works focus on pipeline scheduling while lacking a general methodology to handle network partitioning and mapping to distributed systems with heterogeneous interconnection. In this work, we propose an efficient design flow, named Parmesan, to map the training of a large DNN onto a system with general device topology to maximize the throughput. Parmesan works in an end-to-end manner and solves the whole optimization problem in two phases. The first phase aims at producing well-balanced partitions, and the second phase works toward placing the DNN on devices connected by an arbitrary topology network, considering the heterogeneity of the interconnection bandwidth. We show that Parmesan speeds up the pipeline training throughput on systems with different GPU topologies and is able to handle the mapping problem for heterogeneously interconnected architectures. We believe our proposed general device topology mapping algorithm will provide valuable information for architecture designers and assist them in designing a more DNN-friendly architecture.

关键词： Training Pipelines Topology Parallel processing Throughput Artificial neural networks network topology Deep learning system mapping neural network (NN) acceleration optimization parallelism partitioning

来源：评论

学校读者我要写书评

暂无评论

distributed Model-Free Adaptive Predictive Control for MIMO Multi-Agent Systems With Deception Attack

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION processing OVER networkS 2024年 10卷 32-47页

作者： Pan, Zhenzhen Chi, Ronghu Hou, Zhongsheng Qingdao Univ Dept Automat Acad Syst Sci & Control Qingdao 266071 Peoples R China Qingdao Univ Sci & Technol Inst Artificial Intelligence & Control Sch Automat & Elect Engn Qingdao 266061 Peoples R China

This work explores the challenging problems of nonlinear dynamics, nonaffine structures, heterogeneous properties, and deception attack together and proposes a novel distributed model-free adaptive predictive control (DMFAPC) for multiple-input-multiple-output (MIMO) multi-agent systems (MASs). A dynamic linearization method is introduced to address the nonlinear heterogeneous dynamics which is transformed as the unknown parameters in the obtained linear data model. A radial basis function neural network is designed to detect the deception attack and to estimate the polluted output that is further used in the controller design to compensate for the effect. Then, the DMFAPC is designed by defining a new expanded distributed output with a stochastic factor introduced. The bounded convergence is proved by using the contraction mapping method and the effectiveness of the proposed DMFAPC is verified by simulation examples.

关键词： Deception attack distributed model-free adaptive predictive control (DMFAPC) multi-agent systems (MASs) neural networks (NNs)

来源：评论

学校读者我要写书评

暂无评论

A distributed photovoltaic short-term power forecasting model based on lightweight AI for edge computing in low-voltage distribution network

引用

IET RENEWABLE POWER GENERATION 2024年第16期18卷 3955-3966页

作者： Fan, Yuanliang Wu, Han Lin, Jianli Li, Zewen Li, Lingfei Huang, Xinghua Chen, Weiming Zhao, Jian Fujian Elect Power Co Ltd Elect Power Res Inst Distribut Technol Res Ctr Fuzhou Peoples R China Shanghai Univ Elect Power Coll Elect Engn Shanghai Peoples R China

Recent years, the tremendous number of distributed photovoltaic are integrated into low-voltage distribution network, generating a significant amount of operational data. The centralized cloud data centre is unable to process the massive data precisely and promptly. Therefore, the operational status of distributed photovoltaic systems in low-voltage distribution network becomes difficult to predict. However, edge computing in the distribution network enable local processing of data to improve the real-time and reliability of the forecasting service. In this regard, this paper proposes a distributed photovoltaic short-term power forecasting model based on lightweight AI algorithms. Firstly, based on the Pearson correlation coefficient method, an analysis is conducted on the historical operational data in the network to extract important meteorological features that are correlated with the photovoltaic power output. Secondly, a distributed photovoltaic power forecasting model for the distribution network is constructed based on the Xception and attention mechanism. Finally, the model is trained using pruning, which involves removing redundant parts of the model, resulting in a compact and efficient forecasting model. By conducting validation on real-world datasets, the results demonstrate that the model presented in this article possesses a smaller size and higher forecasting accuracy compared to other state-of-the-art forecasting models. This paper proposes a short-term distributed photovoltaic power forecasting model based on lightweight convolutional neural networks. Firstly, the important factors influencing the photovoltaic output in the network are selected based on the Pearson correlation coefficients. Then, a lightweight forecasting model is constructed using the Xception convolution and attention mechanism. The model is further trained through channel pruning to generate the final lightweight model. image

关键词： artificial intelligence distributed control distribution networks

来源：评论

学校读者我要写书评

暂无评论

Remote sensing data processing and analysis for the identification of geological entities

引用

ACTA GEOPHYSICA 2023年第3期71卷 1565-1577页

作者： Chi, Huanzhao Sun, Jing Zhang, Cheng Miao, Changsheng Changchun Inst Technol Sch Prospecting & Surveying Engn Changchun 130021 Jilin Peoples R China Jilin Prov Key Lab Changbai Hist Culture & VR Rec Changchun 130021 Jilin Peoples R China CGS Qingdao Inst Marine Geol Qingdao 266071 Shandong Peoples R China Qingdao Natl Lab Marine Sci & Technol Lab Marine Mineral Resources Qingdao 266071 Shandong Peoples R China

As Earth observation technology has advanced, the volume of remote sensing big data has grown rapidly, offering significant obstacles to efficient and effective processing and analysis. A convolutional neural network refers to a neural network that covers convolutional calculations. It is a form of deep learning, and convolutional neural networks have characterization learning characteristics, which can classify information into different data. Remote Sensing Data processing from various sensors has been attracting with more information in Remote Sensing. Remote sensing data is generally adjusted and refined through image processing. Image processing techniques, such as filtering and feature detection, are ideal for dealing with the high-dimensionality of geographically distributed systems. The geological entity is a term in geological work which refers to the product of geological processes that occupy a certain space in the Earth's crust and are different from other materials. They are of different sizes and are divided into different types according to their size. It mainly focuses on improving classification accuracy and accurately describing scattering types. For geological entity recognition, this paper proposed a Deep Convolutional neural network Polarized Synthetic Aperture Radar (DCNN-PSAR). It is expected to use deep convolutional neural network technology and polarized SAR technology to explore new methods of geological entities and improve geological recognition capabilities. With the help of Multimodal Remote Sensing Data processing, it is now possible to characterize and identify the composition of the Earth's surface from orbital and aerial platforms. This paper proposes a ground object classification algorithm for polarized SAR images based on a fully convolutional network, which realizes the geological classification function and overcomes the shortcomings of too long. The evaluation of DCNN-PSAR shows that the accuracy of the water area is showing

关键词： Deep convolutional neural network Synthetic aperture radar Geological body Entity recognition Remote sensing Multimodal Data processing

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：