检索结果-内蒙古大学图书馆

neural network and distributed processing

This Volume 4555 of the conference proceedings contains 29 papers. Topics discussed include neural network and distributed processing, hardware parallel, character recognition, image segmentation and image classificat... 详细信息

关键词： neural networks

来源：评论

学校读者我要写书评

暂无评论

distributed Downlink Precoding for Cell-Free Massive MIMO: A Quasi-neural network Approach

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 2025年第2期73卷 1157-1168页

作者： Dai, Weijie Wang, Rui Liu, Junkai Jiang, Yi Fudan Univ Sch Informat Sci & Technol Dept Commun Sci & Engn Key Lab Informat Sci Electromagnet Waves MoE Shanghai 200438 Peoples R China

This paper proposes a novel downlink precoding method for a cell-free massive multiple-input multiple-output (CF-mMIMO) network, requiring no channel state information sharing between the access points via fronthaul links. By drawing analogies between a CF-mMIMO network and an artificial neural network, the proposed algorithm borrows the idea of backpropagation to train the precoders and the combiners through over-the-air ping-pong signaling between the access points and user equipments. It utilizes manifolds optimization to meet the per-AP power constraint and is named as distributed quasi-neural network precoding on manifold (DQNPM). The DQNPM algorithm can accommodate a large category of objective functions for fully distributed implementation. Numerical simulations show that our method outperforms the state-of-the-art approaches, and is robust against pilot contamination.

关键词： Precoding Downlink Manifolds Artificial neural networks Transmitting antennas Signal to noise ratio Signal processing algorithms Cell-free massive MIMO distributed precoding quasi-neural network Riemannian manifold

来源：评论

学校读者我要写书评

暂无评论

distributed Graph neural network Design for Sum Ergodic Spectral Efficiency Maximization in Cell-Free Massive MIMO

引用

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 2025年第3期74卷 5181-5186页

作者： Tung, Nguyen Xuan Chien, Trinh Van Ngo, Hien Quoc Hwang, Won Joo Pusan Natl Univ Dept Informat Convergence Engn Busan 46241 South Korea Hanoi Univ Sci & Technol HUST Sch Informat & Commun Technol SoICT Hanoi 100000 Vietnam Queens Univ Belfast Ctr Wireless Innovat CWI Belfast BT7 1NN North Ireland Pusan Natl Univ Ctr Artificial Intelligence Res Sch Comp Sci & Engn Busan 46241 South Korea

This paper proposes a distributed learning-based framework to tackle the sum ergodic rate maximization problem in cell-free massive multiple-input multiple-output (MIMO) systems by utilizing the graph neural network (GNN). Different from centralized schemes, which gather all the channel state information (CSI) at the central processing unit (CPU) for calculating the resource allocation, the local resource of access points (APs) is exploited in the proposed distributed GNN-based framework to allocate transmit powers. Specifically, APs can use a unique GNN model to allocate their power based on the local CSI. The GNN model is trained at the CPU using the local CSI of one AP, with partially exchanged information from other APs to calculate the loss function to reflect system characteristics, capturing comprehensive network information while avoiding computation burden. Numerical results show that the proposed distributed learning-based approach achieves a sum ergodic rate close to that of centralized learning while outperforming the model-based optimization.

关键词： Massive MIMO Training Graph neural networks Resource management Central processing Unit Downlink Optimization Computational modeling Wireless communication Uplink Cell-free massive MIMO distributed learning graph neural network

来源：评论

学校读者我要写书评

暂无评论

PSMNet: A neural network-Driven Approach for Pixel Similarity Measurement in distributed Scatterer Interferometry

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Zhao, Changjun Yu, Hanwen Jiang, Mi Tian, Xin Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Peoples R China Sun Yat Sen Univ Sch Geospatial Engn & Sci Guangzhou 510275 Peoples R China Southeast Univ Sch Transportat Nanjing 210096 Peoples R China

Pixel similarity measurement is a critical step in distributed scatterer (DS) interferometry, directly affecting DS phase estimation. Despite considerable efforts to improve its accuracy, existing methods still suffer from unsatisfactory performance, especially with small stack sizes. In recent years, deep neural networks have achieved remarkable breakthroughs in interferometric synthetic aperture radar (InSAR) processing. However, their potential for measuring pixel similarity in multitemporal InSAR remains unexplored. This article proposes a neural network-driven pixel similarity measurement approach, termed PSMNet. To address the challenge of accurately defining true data, a supervised learning strategy is designed. The proposed network consists of two main modules: 1) a feature extraction module that generates high-level feature images with enhanced representation and reduced noise and 2) a similarity measurement module that evaluates pixel similarity without relying on assumptions about data distribution. The network is trained on synthetic data, enabling it to generalize for different stack sizes and target characteristics. Extensive experiments on simulated and real TanDEM-X images demonstrate a significant accuracy improvement of the proposed approach, highlighting its robust performance for varying stack sizes and computational efficiency advantage compared to traditional methods. The proposed approach further enhances DS phase estimation and increases the number of measurement points, showing great promise for ground surface deformation monitoring.

关键词： Coherence Accuracy Phase estimation Phase measurement Noise Supervised learning Vectors Interferometry Feature extraction Training distributed scatterer (DS) interferometry interferometric synthetic aperture radar (InSAR) neural network pixel similarity measurement

来源：评论

学校读者我要写书评

暂无评论

Islanding Detection Using Empirical Mode Decomposition and Artificial neural network for Inverter Interfaced distributed Generation

引用

Journal of The Institution of Engineers (India): Series B 2025年第1期106卷 15-30页

作者： Farhan, M. A. Aneesa Soni, Kushal Thelegthoti, Maria K. Rana, Ankur Singh Department of Electrical and Electronics Engineering National Institute of Technology Tiruchirappalli Tamil Nadu Tiruchirappalli620015 India

The empirical mode decomposition (EMD) and artificial neural network (ANN) are used in this paper to solve an islanding detection problem. In light of this, the voltage signal parameter is obtained or measured at the inverter interfaced distributed generation (IIDG) point of common coupling (PCC) and EMD signal processing technique is used to obtain the attributes. Accordingly, various intrinsic mode functions (IMFs) are generated by breaking down the signal parameter. The neural network receives statistical attributes as input after being extracted from these IMFs. Using an Artificial neural network (ANN), islanding can be identified. Several islanding scenarios, such as mismatches in active power and reactive power, and various non-islanding scenarios, such as fault conditions, switching of capacitors, and switching of loads, are simulated. The suggested algorithm is tested to demarcate between an islanding scenario and a non-islanding scenario. © The Institution of Engineers (India) 2024.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Deep neural network Assisted distributed Strain and Temperature Fiber Sensor System for Natural Gas Pipeline Monitoring

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Lalam, Nageswara Bhatta, Hari Bukka, Sandeep Reddy Zhang, Pengdi Diemler, Nathan Shumski, Alexander Ohodnicki, Paul R. Buric, Michael P. Wright, Ruishu F. Natl Energy Technol Lab Pittsburgh PA 15236 USA Leidos Res Support Team Pittsburgh PA 15236 USA Univ Pittsburgh Dept Mech Engn & Mat Sci Pittsburgh PA 15213 USA

Natural gas pipeline integrity monitoring is crucial to detect potential leaks, find structural issues, and prevent environmental damage. This article presents a system of natural gas pipeline monitoring that uses a specialized double Brillouin peak sensing fiber along with the Brillouin optical time domain analysis (BOTDAs) technique. The calibrated sensing fiber coefficients for strain and temperature are 41.8 kHz/mu epsilon and 0.9 MHz/degrees C for peak 1;and 47.2 kHz/mu epsilon, and 1.11 MHz/degrees C for peak 2, respectively. Initially, lab tests were performed by installing a short section of double Brillouin peak fiber (DBPF) on a 1-in steel pipe under pressure up to 1000 per square inch (psi) at elevated temperatures. Simultaneous distributed measurements of temperature and pressure-induced hoop strain were successfully measured. Considering the long processing speed to extract Brillouin frequency shift (BFS), we employ a novel probabilistic deep neural network (PDNN) framework for rapid BFS prediction. Additionally, using the Finite Element Method, the effects of the pipeline pressure on hoop strain were modeled and compared to the experimental hoop strain under the same set of pipeline conditions. Finally, an actual 4-in outer diameter steel natural gas pipeline was used for pilot-scale tests, where hoop strain was measured at various pressure levels. Leaks were simulated to demonstrate accurate pipeline integrity monitoring. At an internal pipe pressure of 1000 psi, hoop strain of approximately 300 mu epsilon was observed, and the sensitivity was calculated as0.28 mu epsilon/psi. The results of this pilot-scale study demonstrated that the system is capable of performing distributed monitoring sufficient to detect pipeline pressure and the presence of leaks to ensure the safe operation of gas pipelines in the field.

关键词： Pipelines Temperature measurement Strain Optical fiber networks Monitoring Temperature sensors Optical fiber sensors Scattering Strain measurement Natural gas Deep neural network (DNN) distributed sensing pipeline monitoring strain and temperature sensing

来源：评论

学校读者我要写书评

暂无评论

Practical Near-Data-processing Architecture for Large-Scale distributed Graph neural network

引用

IEEE ACCESS 2022年 10卷 46796-46807页

作者： Huang, Linyong Zhang, Zhe Li, Shuangchen Niu, Dimin Guan, Yijin Zheng, Hongzhong Xie, Yuan Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310058 Peoples R China Alibaba Grp Hangzhou 311121 Peoples R China

Graph neural networks have drawn tremendous attention in the past few years due to their convincing performance and high interpretability in various graph-based tasks like link prediction and node classification. With the ever-growing graph size in the real world, especially for industrial graphs at a billion-level, the storage of graphs can easily consume Terabytes so that the process of GNNs has to be processed in a distributed manner. As a result, the execution could be inefficient due to the expensive cross-node communication and irregular memory access. Various GNN accelerators have been proposed for efficient GNN processing. They, however, mainly focused on small and medium-size graphs, which is not applicable to large-scale distributed graphs. In this paper, we present a practical Near-Data-processing architecture based on a memory-pool system for large-scale distributed GNNs. We propose a customized memory fabric interface to construct the memory pool for low-latency and high throughput cross-node communication, which can provide flexible memory allocation and strong scalability. A practical Near-Data-processing design is proposed for efficient work offloading and bandwidth utilization improvement. Moreover, we also introduce a partition and scheduling scheme to further improve performance and achieve workload balance. Comprehensive evaluations demonstrate that the proposed architecture can achieve up to 27 x and 8 x higher training speed compared to two state-of-the-art distributed GNN frameworks: Deep Graph Library and P-3, respectively.

关键词： Graph neural network large-scale graph processing memory pool near data processing

来源：评论

学校读者我要写书评

暂无评论

A distributed neural network Architecture for Dynamic Sensor Selection With Application to Bandwidth-Constrained Body-Sensor networks

引用

IEEE Journal of Biomedical and Health Informatics 2025年第5期29卷 3465-3477页

作者： Strypsteen, Thomas Bertrand, Alexander KU Leuven Department of Electrical Engineering STADIUS Center for Dynamical Systems Signal Processing and Data Analytics LeuvenB-3001 Belgium Leuven.AI KU Leuven Institute for AI LeuvenB-3001 Belgium

We propose a dynamic sensor selection approach for deep neural networks (DNNs), which is able to derive an optimal sensor subset selection for each specific input sample instead of a fixed selection for the entire dataset. This dynamic selection is jointly learned with the task model in an end-to-end way, using the Gumbel-Softmax trick to allow the discrete decisions to be learned through standard backpropagation. We then show how we can use this dynamic selection to increase the lifetime of a wireless sensor network (WSN) by imposing constraints on how often each node is allowed to transmit. We further improve performance by including a dynamic spatial filter that makes the task-DNN more robust against the fact that it now needs to be able to handle a multitude of possible node subsets. Finally, we explain how the selection of the optimal channels can be distributed across the different nodes in a WSN. We validate this method on a use case in the context of body-sensor networks, where we use real electroencephalography (EEG) sensor data to emulate an EEG sensor network for motor execution decoding. For this use case, we demonstrate that the distributed algorithm -with only a small amount of cooperation between the nodes- achieves a performance close to the upper bound defined by a fully centralized dynamic selection (maximum absolute decrease of 4% in accuracy). Furthermore, we observe that our dynamic sensor selection framework can achieve large reductions in transmission energy with a limited cost to the task accuracy, validating it as a practical tool for increasing the lifetime of body-sensor networks. © 2013 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Towards a real-time processing framework based on improved distributed recurrent neural network variants with fastText for social big data analytics

引用

INFORMATION processing & MANAGEMENT 2020年第1期57卷 102122-000页

作者： Hammou, Badr Ait Lahcen, Ayoub Ait Mouline, Salma Mohammed V Univ Rabat IT Ctr Associated Unit CNRST URAC 29 Fac SciLRIT Rabat Morocco Ibn Tofail Univ Natl Sch Appl Sci ENSA LGS Kenitra Morocco

Big data generated by social media stands for a valuable source of information, which offers an excellent opportunity to mine valuable insights. Particularly, User-generated contents such as reviews, recommendations, and users' behavior data are useful for supporting several marketing activities of many companies. Knowing what users are saying about the products they bought or the services they used through reviews in social media represents a key factor for making decisions. Sentiment analysis is one of the fundamental tasks in Natural Language processing. Although deep learning for sentiment analysis has achieved great success and allowed several firms to analyze and extract relevant information from their textual data, but as the volume of data grows, a model that runs in a traditional environment cannot be effective, which implies the importance of efficient distributed deep learning models for social Big Data analytics. Besides, it is known that social media analysis is a complex process, which involves a set of complex tasks. Therefore, it is important to address the challenges and issues of social big data analytics and enhance the performance of deep learning techniques in terms of classification accuracy to obtain better decisions. In this paper, we propose an approach for sentiment analysis, which is devoted to adopting fastText with Recurrent neural network variants to represent textual data efficiently. Then, it employs the new representations to perform the classification task. Its main objective is to enhance the performance of well-known Recurrent neural network (RNN) variants in terms of classification accuracy and handle large scale data. In addition, we propose a distributed intelligent system for real-time social big data analytics. It is designed to ingest, store, process, index, and visualize the huge amount of information in real-time. The proposed system adopts distributed machine learning with our proposed method for enhancing decision-making

关键词： Big data FastText Recurrent neural networks LSTM BiLSTM GRU Natural language processing Sentiment analysis Social big data analytics

来源：评论

学校读者我要写书评

暂无评论

GNN at the Edge: Cost-Efficient Graph neural network processing Over distributed Edge Servers

引用

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2023年第3期41卷 720-739页

作者： Zeng, Liekang Yang, Chongyu Huang, Peng Zhou, Zhi Yu, Shuai Chen, Xu Sun Yat sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China

Edge intelligence has arisen as a promising computing paradigm for supporting miscellaneous smart applications that rely on machine learning techniques. While the community has extensively investigated multi-tier edge deployment for traditional deep learning models (e.g. CNNs, RNNs), the emerging Graph neural networks (GNNs) are still under exploration, presenting a stark disparity to its broad edge adoptions such as traffic flow forecasting and location-based social recommendation. To bridge this gap, this paper formally studies the cost optimization for distributed GNN processing over a multi-tier heterogeneous edge network. We build a comprehensive modeling framework that can capture a variety of different cost factors, based on which we formulate a cost-efficient graph layout optimization problem that is proved to be NP-hard. Instead of trivially applying traditional data placement wisdom, we theoretically reveal the structural property of quadratic submodularity implicated in GNN's unique computing pattern, which motivates our design of an efficient iterative solution exploiting graph cuts. Rigorous analysis shows that it provides parameterized constant approximation ratio, guaranteed convergence, and exact feasibility. To tackle potential graph topological evolution in GNN processing, we further devise an incremental update strategy and an adaptive scheduling algorithm for lightweight dynamic layout optimization. Evaluations with real-world datasets and various GNN benchmarks demonstrate that our approach achieves superior performance over de facto baselines with more than 95.8% cost reduction in a fast convergence speed.

关键词： Edge intelligence graph neural networks cost optimization distributed edge 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：