检索结果-内蒙古大学图书馆

Traffic-Aware Hierarchical Beam Selection for Cell-Free Massive MIMO

IEEE TRANSACTIONS ON COMMUNICATIONS 2024年第10期72卷 6490-6504页

作者： Wang, Chenyang Zhang, Cheng Meng, Fan Huang, Yongming Zhang, Wei Southeast Univ Sch Informat Sci & Engn Natl Mobile Commun Res Lab Nanjing 210096 Peoples R China Purple Mt Labs Nanjing 211111 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia

Beam selection for joint transmission in cell-free massive multi-input multi-output systems faces the problem of extremely high training overhead and computational complexity. The traffic-aware quality of service additionally complicates the beam selection problem. To address this issue, we propose a traffic-aware hierarchical beam selection scheme performed in a dual timescale. In the long-timescale, the central processing unit collects wide beam responses from base stations (BSs) to predict the power profile in the narrow beam space with a convolutional neural network, based on which the cascaded multiple-BS beam space is carefully pruned. In the short-timescale, we introduce a centralized reinforcement learning (RL) algorithm to maximize the satisfaction rate of delay w.r.t. beam selection within multiple consecutive time slots. Moreover, we put forward three scalable distributed algorithms including hierarchical distributed Lyapunov optimization, fully distributed RL, and centralized training with decentralized execution of RL to achieve better scalability and better tradeoff between the performance and the execution signal overhead. Numerical results demonstrate that the proposed schemes significantly reduce both model training cost and beam training overhead and are easier to meet the user-specific delay requirement, compared to existing methods.

关键词： Delays Training Array signal processing Quality of service Optimization Radio frequency Predictive models Cell-free beam selection traffic delay satisfaction rate distributed

来源：评论

学校读者我要写书评

暂无评论

distributed Search Engine Query Optimization Using Artificial neural network

Distributed Search Engine Query Optimization Using Artificia...

引用

Cyber Resilience (ICCR), International Conference on

作者： Liaqat Ali Mahmoud M. Al-Sakhnini Deepak Kalra Farheen Afzaal Madiha Pervaiz Muhammad Farrukh Khan College of Engineering and Technology University of Science and Technology of Fujairah Fujairah UAE School of Business Skyline University College University City Sharjah Sharjah UAE Faculty of Computer and Information Technology Al-Madinah International University Kuala Lumpur Malaysia School of Information Technology Skyline University College University City Sharjah Sharjah UAE National College of Business Administration and Economics Lahore Pakistan University of south Asia Lahore Pakistan Department of Computer Science Minhaj University Lahore Pakistan

ISBN: (数字)9781665461221

ISBN: (纸本)9781665461238

In this research, we propose a distributed Search Engine Query Optimization (DSEQO) based sensor network concept for instantaneous forest fire exposure. The sensor network may identify and predict forest fire more sharp than the outdated satellite-based prediction method. The research mainly defines the information gathering and managing in sensor networks for real-time forest fire detection. To predict the real-time fire identification, an ANN technique is utilized to in-network information processing. After simulation it was seen that the suggested approach gives better results with LM approach in terms of Accuracy and Miss Rate.

关键词： Query processing Forestry Artificial neural networks Prediction methods Information processing Search engines Data processing

来源：评论

学校读者我要写书评

暂无评论

distributed-Order Fractional Graph Operating network 38

Distributed-Order Fractional Graph Operating Network

引用

38th Conference on neural Information processing Systems, NeurIPS 2024

作者： Zhao, Kai Li, Xuhao Kang, Qiyu Ji, Feng Ding, Qinxu Zhao, Yanan Liang, Wenfei Tay, Wee Peng Nanyang Technological University Singapore Anhui University China Singapore University of Social Sciences Singapore

We introduce the distributed-order fRActional Graph Operating network (DRAGON), a novel continuous Graph neural network (GNN) framework that incorporates distributed-order fractional calculus. Unlike traditional continuous GNNs that utilize integer-order or single fractional-order differential equations, DRAGON uses a learnable probability distribution over a range of real numbers for the derivative orders. By allowing a flexible and learnable superposition of multiple derivative orders, our framework captures complex graph feature updating dynamics beyond the reach of conventional models. We provide a comprehensive interpretation of our framework's capability to capture intricate dynamics through the lens of a non-Markovian graph random walk with node feature updating driven by an anomalous diffusion process over the graph. Furthermore, to highlight the versatility of the DRAGON framework, we conduct empirical evaluations across a range of graph learning tasks. The results consistently demonstrate superior performance when compared to traditional continuous GNN models. The implementation code is available at https://***/zknus/NeurIPS-2024-DRAGON. © 2024 neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Open-Set Event Recognition Model Using 1-D RL-CNN With OpenMax Algorithm for distributed Optical Fiber Vibration Sensing System

引用

IEEE SENSORS JOURNAL 2023年第12期23卷 12817-12827页

作者： Zhou, Zhengxian Jiao, Wenyang Hu, Xing Zhang, Dawei Qu, Jun Zheng, Xianfeng Yang, Haima Zhuang, Songlin Anhui Normal Univ Anhui Prov Key Lab Optoelectr Mat Sci & Technol Wuhu 241002 Peoples R China Univ Shanghai Sci & Technol Sch Optic Elect & Comp Engn Shanghai 200093 Peoples R China

distributed optical fiber vibration sensing system (DVS) based on phase-sensitive optical time domain reflectometer (OTDR) is widely used for its simple structure and high sensitivity. Signal recognition is crucial for DVS because it can help to classify the different types of vibration events. Deep learning provides accurate event classification and can automatically extract features according to sample distribution. However, almost all current methods focus on closed-set recognition, which misclassifies unknown events into known categories, thus reducing the recognition accuracy of sensing system. In this article, we propose a novel open-set event recognition model based on 1-D residual learning convolution neural network (1-D RL-CNN) with OpenMax algorithm for DVS, which is capable of processing the signals of known and unknown categories. The experimental results show that the proposed recognition model improves the classification accuracy greatly compared with the conventional 1-D CNN signal classification method. The overall open-set classification accuracy of 1-D RL-CNN with OpenMax is 91.19%, which is improved by 18.47% and 7.57% compared with 1-D CNN with SoftMax and 1-D CNN with OpenMax.

关键词： Sensors Vibrations Optical fibers Optical fiber sensors Feature extraction Convolutional neural networks Voltage control Convolution neural network deep learning distributed optical fiber vibration sensing event recognition

来源：评论

学校读者我要写书评

暂无评论

Improved heavy-ion PID using scintillation light detector with neural network analysis: a Monte Carlo simulation study

引用

JOURNAL OF INSTRUMENTATION 2025年第4期20卷 P04025-P04025页

作者： Cortesi, M. Dziubinski, S. Harca, I. M. Di Carlo, S. Michigan State Univ Facil Rare Isotope Beam 640 S Shaw Ln E Lansing MI 48824 USA

The photon collection efficiency of gaseous scintillator detectors varies according to the position of the impinging charged particles in the medium that generates scintillation light. Thus, when impinging particles are distributed over a large area, the intrinsic photon-number resolution of the system is affected by a large variation. This work presents and discusses a method for adjusting the total number of detected photons to account for variation in the photon collection efficiency as a function of the position of the light source within the scintillating medium. The method was developed and validated by processing data from systematic simulation studies based on GEANT4 that model the response of the Energy Loss Optical Scintillation System (ELOSS) detector. The position of the charged particle is calculated using a deep neural network algorithm. This is accomplished by analyzing the distribution of scintillation light recorded by the array of photosensors. The estimated particle position is then used to calculate the correction factor and adjust the amount of captured light to account for variations in the photon collection efficiency. The neural network algorithm provides excellent tracking capabilities, achieving sub-millimeter position resolution and an angular resolution of 12 mrad, approaching the performance of traditional tracking detectors (e.g., drift chambers). The present method can be generalized to any optical scintillation system where the photon collection efficiency depends on the position of the impinging particle.

关键词： dE/dx detectors Heavy-ion detectors Instrumentation and methods for heavy-ion reactions and fission studies

来源：评论

学校读者我要写书评

暂无评论

Signal processing of distributed Optoacoustic Sensors by Means of neural networks in the Automotive Transport Monitoring Problem

引用

Mathematical Models and Computer Simulations 2024年第5期16卷 667-675页

作者： Nazarenko, P.A. Levashkin, S.P. Zakharova, O.I. Ivanov, K.N. Kushukov, S.V. Artificial Intelligence Research Lab (AIRL) Povolzhskiy State University of Telecommunications and Informatics (PSUTI) Samara Russian Federation

Artificial neural network (ANN) models are used as a tool for an automotive transport monitoring. The solution of the problem of recognition of distributed optoacoustic sensor signals generated by vehicles using ANNs is considered. Signals features and signals preliminary processing are described. The ANN architecture for the vehicles generated signals recognition is selected. The architecture of the ANN of vehicles signal recognition, including heavy tracks signals, has single layer with two hundred and one input and one or two outputs. The ANN is designed using the Python programming language, Scikit-Learn, Keras and NumPy libraries. The ANN training patterns, the training results and the trained ANN practical application are described. The recommendations for further research in the field of using ANNs of various architectures for recognizing vehicle signals using distributed optoacoustic sensors are given. The study results are important for road traffic monitoring, as well as other areas of the distributed optoacoustic sensor applications. © Pleiades Publishing, Ltd. 2024.

关键词： artificial neural networks backpropagation algorithm big data space dimensionality reduction Keras machine learning pattern recognition perceptron Python Tens-orFlow training patterns

来源：评论

学校读者我要写书评

暂无评论

Stochastic photonic spiking neuron for Bayesian inference with unsupervised learning

引用

OPTICS LETTERS 2023年第6期48卷 1411-1414页

作者： Ma, Bowen Zhang, Junfeng Li, Xing Zou, Weiwen Shanghai Jiao Tong Univ Intelligent Microwave Lightwave Integrat Innovat C Dept Elect Engn State Key Lab Adv Opt Commun Syst & Networks 800 Dongchuan Rd Shanghai 200240 Peoples R China

Stochasticity is an inherent feature of biological neural activities. We propose a noise-injection scheme to implement a GHz-rate stochastic photonic spiking neuron (S-PSN). The firing-probability encoding is experimentally demonstrated and exploited for Bayesian inference with unsupervised learning. In a breast diagnosis task, the stochastic photonic spiking neural network (S-PSNN) can not only achieve a classification accuracy of 96.6%, but can also evaluate the diagnosis uncertainty with prediction entropies. As a result, the misdiagnosis rate is reduced by 80% compared to that of a conventional deterministic photonic spiking neural network (D-PSNN) for the same task. The GHz-rate S-PSN endows the neuromorphic photonics with high-speed Bayesian inference for reliable information processing in error-critical scenarios.(c) 2023 Optica Publishing Group

关键词： distributed feedback lasers Erbium doped fiber amplifiers Injection locking neural networks Semiconductor lasers Spontaneous emission

来源：评论

学校读者我要写书评

暂无评论

supported by the National Natural Science Foundation of China(Nos.62172051,61772085,and 61877005)and Jiangsu Agriculture Science and Technology Innovation Fund(***(18)3054).

引用

Tsinghua Science and Technology 2023年第1期28卷 82-92页

作者： Jinghui Zhang Yuchen Wang Tianyu Huang Fang Dong Wei Zhao Dian Shen School of Computer Science and Engineering Southeast UniversityNanjing 211189China Hefei Comprehensive National Science Center Hefei 231299China School of Computer Science and Technology Anhui University of TechnologyHefei 230026China Department of Computer Science&Engineering The Chinese University of Hong KongHong Kong 999077China

Numerous neural network(NN)applications are now being deployed to mobile *** applications usually have large amounts of calculation and data while requiring low inference latency,which poses challenges to the computing ability of mobile ***,devices’life and performance depend on ***,in many scenarios,such as industrial production and automotive systems,where the environmental temperatures are usually high,it is important to control devices’temperatures to maintain steady *** this paper,we propose a thermal-aware channel-wise heterogeneous NN inference *** contains two parts,the thermal-aware dynamic frequency(TADF)algorithm and the heterogeneous-processor single-layer workload distribution(HSWD)*** on a mobile device’s architecture characteristics and environmental temperature,TADF can adjust the appropriate running speed of the central processing unit and graphics processing unit,and then the workload of each layer in the NN model is distributed by HSWD in line with each processor’s running speed and the characteristics of the layers as well as heterogeneous *** experimental results,where representative NNs and mobile devices were used,show that the proposed method can considerably improve the speed of the on-device inference by 21%–43%over the traditional inference method.

关键词： neural network inference mobile device temperature adjustment channel-wise parallelization

来源：评论

学校读者我要写书评

暂无评论

Edge-Cloud Remote Sensing Data-Based Plant Disease Detection Using Deep neural networks With Transfer Learning

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 11219-11229页

作者： Mohammed, Mazin Abed Lakhan, Abdullah Abdulkareem, Karrar Hameed Almujally, Nouf Abdullah Al-Attar, Bourair Bourair Sadiq Mohammed Taqi Memon, Sajida Marhoon, Haydar Abdulameer Martinek, Radek Univ Anbar Coll Comp Sci & Informat Technol Dept Artificial Intelligence Anbar 31001 Iraq VSB Tech Univ Ostrava Dept Telecommun Ostrava 70800 Czech Republic VSB Tech Univ Ostrava Dept Cybernet & Biomed Engn Ostrava 70800 Czech Republic Dawood Univ Engn & Technol Dept Comp Sci Sindh 74800 Pakistan Al Muthanna Univ Coll Agr Samawah 66001 Iraq Univ Warith Al Anbiyaa Coll Engn Karbala 56001 Iraq Princess Nourah bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst Riyadh 11671 Saudi Arabia Univ Al Ameed Coll Med Karbala 1238 Iraq Dawood Univ Engn & Technol Dept Comp Syst Engn Sindh 74800 Pakistan Al Ayen Univ Sci Res Ctr Informat & Commun Technol Res Grp Thi Qar 64001 Iraq Univ Kerbala Coll Comp Sci & Informat Technol Karbala 1238 Iraq VSB Tech Univ Ostrava Dept Cybernet & Biomed Engn Ostrava 70800 Czech Republic

These days, the disease among different plants has been increasing day by day. It is a very hard task for government institutions and farmers to collect data on plant diseases from different distributed lands among regions. Therefore, data collection, disease detection, and processing are the key issues for plants when they are suffering from healthy and unhealthy issues in different lands. This article presents edge-cloud remote sensing data-based plant disease detection by exploiting deep neural networks with transfer learning. The objective is to solve the aforementioned issues, such as data collection at a wide range, disease detection, and processing them with higher accuracy and time on different machines. We suggest transfer learning commutative fuzzy deep convolutional neural network (FCDCNN) schemes based on combinatorial optimization problems. The convex function optimizes the processing time and learning rate of data training on different edge and cloud nodes to collect more and more data from different plants from distributed lands. In the concave function, we predict the diseases among different plants, such as sugarcane, blueberry, cotton, and cherry with images, videos, and numeric values. The plant disease detection app uses edge nodes and remote satellite point cloud nodes to gather and train data using transfer learning and make predictions using fuzzy DCNN schemes that are more accurate and take less time to process. Simulation results show that FCDCNN obtained higher accuracy by 98% with less processing time 25% and trained with a higher ratio of data than existing schemes.

关键词： Edge point cloud fuzzy deep neural networks plant disease detection remote sensing data transfer learning

来源：评论

学校读者我要写书评

暂无评论

Low-bit CUTLASS GEMM Template Auto-tuning using neural network 22

Low-bit CUTLASS GEMM Template Auto-tuning using Neural Netwo...

引用

22nd IEEE International Symposium on Parallel and distributed processing with Applications, ISPA 2024

作者： Guo, Hong Guo, Nianhui Meinel, Christoph Yang, Haojin University of Potsdam Hasso Plattner Institute Potsdam Germany

ISBN: (纸本)9798331509712

Optimizing General Matrix Multiplication (GEMM) on GPU platforms has become increasingly important due to the scaling demands of modern deep neural network research. While substantial progress has been made in accelerating high-precision GEMM, optimizing lower-bit GEMM remains an open problem. The CUTLASS library offers highly optimized low-bit GEMM based on tensor cores, but performance varies significantly with tile and pipeline settings across different GPUs. We introduce a novel auto-tuning framework for low-bit CUTLASS GEMM that employs a neural network model to predict optimal GEMM template parameters for target GPUs. This model was trained on a synthetic dataset featuring various matrix sizes from different Ampere GPUs and evaluated on these GPUs. In the test dataset, our method achieved an accuracy of up to 92.9%. Real-time evaluations of low-bit data types on the A100 GPU demonstrated speedups of up to 2.03× for GEMM and 1.44× for the linear layer compared to the default templates. © 2024 IEEE.

关键词： Graphics processing unit

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：