检索结果-内蒙古大学图书馆

distributed Brillouin frequency shift extraction via a convolutional neural network

Photonics Research 2020年第5期8卷 690-697页

作者： YIQING CHANG HAO WU CAN ZHAO LI SHEN SONGNIAN FU MING TANG Wuhan National Laboratory for Optoelectronics(WNLO)&National Engineering Laboratory for Next Generation Internet Access System School of Optical and Electronic InformationHuazhong University of Science and TechnologyWuhan 430074China

distributed optical fiber Brillouin sensors detect the temperature and strain along a fiber according to the local Brillouin frequency shift(BFS),which is usually calculated by the measured Brillouin spectrum using Lorentzian curve *** addition,cross-correlation,principal component analysis,and machine learning methods have been proposed for the more efficient extraction of ***,existing methods only process the Brillouin spectrum individually,ignoring the correlation in the time domain,indicating that there is still room for ***,we propose and experimentally demonstrate a BFS extraction convolutional neural network(BFSCNN)to retrieve the distributed BFS directly from the measured two-dimensional *** ideal Brillouin spectra with various parameters are used to train the *** the simulation and experimental results show that the extraction accuracy of the BFSCNN is better than that of the traditional curve fitting algorithm with a much shorter processing *** BFSCNN has good universality and robustness and can effectively improve the performances of existing Brillouin sensors.

关键词： neural network individual

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction in a distributed Environment Using a Tensor processing Unit A Comparison With a CPU-Based Model

引用

IEEE SYSTEMS MAN AND CYBERNETICS MAGAZINE 2022年第2期8卷 39-43页

作者： Khan, Mohd Hammad Sharma, Devdutt Prasanth, N. Narayanan Raja, S. P. Vellore Inst Technol Sch Comp Sci & Engn Vellore 632014 Tamil Nadu India

Bitcoin is the world’s most traded cryptocurrency and highly popular among cryptocurrency investors and miners. However, its volatility makes it a risky investment, which leads to the need for accurate and fast price-prediction models. This article proposes a Bitcoin price-prediction model using a long short-term memory (LSTM) network in a distributed environment. A tensor processing unit (TPU) has been used to provide the distributed environment for the model. The results show that the TPU-based model performed significantly better than a conventional CPU-based model.

关键词： Training data Tensors Program processors Machine learning algorithms neural networks Bitcoins Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approach to network Security 5

Intelligent DoS and DDoS Detection: A Hybrid GRU-NTM Approac...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Panggabean, Caroline Venkatachalam, Chandrasekar Shah, Priyanka John, Sincy Renuka Devi, P. Venkatachalam, Shanmugavalli Karnataka Bangalore India Karnataka Bangalore India Ksr College of Engineering Department of Cse Tamil Nadu Namakkal India

ISBN: (纸本)9798331504403

Detecting Denial of Service (DoS) and distributed Denial of Service (DDoS) attacks remains a critical challenge in cybersecurity. This research introduces a hybrid deep learning model combining Gated Recurrent Units (GRUs) and a neural Turing Machine (NTM) for enhanced intrusion detection. Trained on UNSW-NB15 and BoT-IoT datasets, the model employs GRU layers for sequential data processing and an NTM for long-term pattern recognition. The model achieves 99% accuracy in distinguishing between normal, DoS, and DDoS traffic. This approach offers promising advancements in realtime threat detection, potentially improving network security across various domains. © 2024 IEEE.

关键词： Turing machines

来源：评论

学校读者我要写书评

暂无评论

Cooperative Trajectory Design of Multiple UAV Base Stations With Heterogeneous Graph neural networks

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2023年第3期22卷 1495-1509页

作者： Zhang, Xiaochen Zhao, Haitao Wei, Jibo Yan, Chao Xiong, Jun Liu, Xiaoran Natl Univ Def Technol Coll Elect Sci & Engn Changsha 410073 Hunan Peoples R China Natl Univ Def Technol Coll Intelligence Sci & Technol Changsha 410073 Hunan Peoples R China

Unmanned aerial vehicles as base stations (UAV-BSs) are recognized as effective means for tackling eruptive communication service requirements especially when terrestrial infrastructures are unavailable. Quality of service (QoS) received by ground terminals (GTs) highly depends on the spatial movement of UAV-BSs. In this paper, we investigate the cooperative trajectory design problem of multiple UAV-BSs towards fair throughput maximization of GTs. Considering the restriction of coverage and sensing, we first propose a heterogeneous-graph-based formulation of relations between GTs and UAV-BSs. Subsequently, we design a framework named graph vision and communication (GVis&Comm) to 1) let each UAV-BS efficiently manage time-varying local observations;2) facilitate cooperation between UAV-BSs through explicit information exchange. To further reduce the overhead of over-the-air cooperation, we realize discretization of the message passing process among UAV-BSs while still enabling end-to-end training. By leveraging multi-agent reinforcement learning (MARL), UAV-BSs as agents learn a distributed trajectory design policy. Extensive numerical simulation shows that our framework on the one hand achieves remarkable efficiency in processing local observations of each UAV-BS, and on the other improves the overall network performance via close cooperation among UAV-BSs.

关键词： Unmanned aerial vehicle (UAV) multi-agent reinforcement learning (MARL) heterogeneous graph neural networks (HGNNs) trajectory design wireless coverage

来源：评论

学校读者我要写书评

暂无评论

Research on distributed Dynamic Spectrum Access Based on Deep Reinforcement Learning

Research on Distributed Dynamic Spectrum Access Based on Dee...

引用

International Conference on Communications, Signal processing, and Systems, CSPS 2023

作者： Liu, Yanchao Zhang, Xiaohua Wang, Shubin College of Electronic Information Engineering Inner Mongolia University Hohhot China Department of Foreign Languages Guizhou University of Commerce Guiyang China

ISBN: (纸本)9789819975396

Dynamic Spectrum Access (DSA) is a critical technology for Cognitive Wireless Sensor network (CWSN). The main challenge of DSA is how Secondary Users (SUs) can quickly and accurately identify vacant spectrum, while ensuring that the service of the Primary User (PU) is not interrupted. The current DSA solutions do not satisfy the requirements of high throughput, low interference and fast convergence simultaneously for large scale multiple users and multiple channels access scenarios. In this paper, we propose a distributed DSA algorithm based on Deep Reinforcement Learning (DRL). First, we construct a Cognitive Wireless Sensor network (CWSN) environment with multiple users and multiple channels. Next, based on the spectrum sensing results, each SU provides channel observations to our proposed Deep Q-network (DQN) model for training in order to learn the optimal spectrum access policy. Finally, using the output of the DQN model, each SU intelligently accesses the appropriate channel. In order to improve the training accuracy and address the performance degradation problem caused by the network depth in deep neural networks, we added the Residual network (ResNet) structure to the DQN. Simulation results show that the proposed algorithm achieves faster convergence speed, completely avoids collisions between SUs, greatly reduces the interference of SUs to PU, and significantly improves the success rate of channel access. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Exploiting Fine-Grained Structured Pruning for Efficient Inference on CNN Model 29

Exploiting Fine-Grained Structured Pruning for Efficient Inf...

引用

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Wu, Cheng-Hung Hong, Ding-Yong Liu, Pangfeng Wu, Jan-Jan National Taiwan University Department of Computer Science and Information Engineering Taiwan Institute of Information Science Academia Sinica Taiwan

ISBN: (纸本)9798350330717

Weight pruning is a technique to remove redundant or unimportant weights from the network. It can help reduce the size and computational cost of neural networks while preserving their accuracy. In this paper, we aim to design efficient CNN models with N:M pruning on the CPU. We propose a dynamic programming algorithm to find a good sparsity ratio for every layer under a total time budget based on the execution times and L1 norm of layers. After deciding the sparsity ratio of each layer, we leverage the auto-tuner of the TVM compiler to search for an optimization schedule of the pruned convolution to accelerate fine-grained pruned models. Experimental results show that our scheme can achieve 0.35% accuracy improvement and a 1.55× speedup on VGG-16 with ImageNet than the dense model. © 2023 IEEE.

关键词： deep neural network weight pruning

来源：评论

学校读者我要写书评

暂无评论

Novel distributed Beamforming Algorithms for Heterogeneous Space Terrestrial Integrated network

引用

IEEE INTERNET OF THINGS JOURNAL 2022年第13期9卷 11351-11364页

作者： Shi, Xiaoyan Liu, Rongke Thompson, John S. Univ Edinburgh Inst Digital Commun Edinburgh EH9 3FG Midlothian Scotland Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Univ Edinburgh Sch Engn Inst Digital Communciat Edinburgh EH9 3FG Midlothian Scotland

An integrated space-terrestrial network based on the ultradense low-earth-orbit (LEO) satellite constellations has been envisioned in both 5G and beyond 5G (B5G) networks. This approach is a powerful solution to some key challenges from Internet of Things (IoT) services, such as the lack of link capacity to deal with large data transfer or coverage in the remote areas. This article focuses on the beamforming design for the transmissions from multiple LEO satellites, equipped with massive phased array antenna, to a large number of heterogeneous terrestrial terminals. Superposition coding-based beamforming is efficient in dealing with the receiver heterogeneity, but at the cost of higher computational complexity. Based on the dual decomposition theory as well as deep neural networks (DNNs), this article proposes to combine the nonlinear approximation ability of DNNs with distributed algorithms. This combination not only supports advanced nonorthogonal beamforming algorithms for achieving superior throughput performance, but also keeps the overall computational complexity low and enables the beamforming process to be speed up dramatically through parallel computing.

关键词： Array signal processing Satellites Low earth orbit satellites Receivers NOMA Quality of service Phased arrays Beamforming distributed algorithms low-earth-orbit (LEO) satellites receiver heterogeneity

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Task Scheduling Based on Graph neural network and Federated Learning in Vehicle Edge Computing 29

Fine-grained Task Scheduling Based on Graph Neural Network a...

引用

29th IEEE International Conference on Parallel and distributed Systems, ICPADS 2023

作者： Zhang, Gaowei Song, Junping Hu, Yahui Fan, Pengfei Li, Chong Zhou, Xu Chinese Academy of Sciences Computer Network Information Center Beijing China University of Chinese Academy of Sciences Beijing China China University of Mining and Technology Beijing China

ISBN: (纸本)9798350330717

Vehicle Edge Computing (VEC) has emerged as an efficacious paradigm that supports real-time, computation-intensive vehicular applications. However, due to the highly dynamic nature of computing node topology, existing scheduling algorithms need to more effectively apprehend the characteristics of fine-grained task topologies and network topologies. Moreover, they require significant communication overhead and training costs, making them inadequate for fine-grained task scheduling in vehicular networks. In response, our research explores fine-grained task scheduling issues within VEC scenarios, proposing a scheduling algorithm based on Graph neural networks and Federated Learning (FL-GNN). This algorithm maintains a global scheduling model that periodically aggregates local scheduling models deployed on Roadside Units (RSUs) and high-performance vehicles. Furthermore, to enhance the model's ability to perceive topology and expedite the convergence rate, we incorporate a graph neural network layer in each local model to preprocess the raw state of the VEC environment. Lastly, we construct a simulation platform and implement multiple competitive solutions, demonstrating the superiority of the FL-GNN algorithm in aspects such as reducing the average task delay, balancing the load, and improving the task scheduling success rate. © 2023 IEEE.

关键词： deep reinforcement learning Federated learning fine-grained task scheduling graph neural networks vehicle edge computing

来源：评论

学校读者我要写书评

暂无评论

Decentralised Biomedical Signal Classification using Early Exits 21

Decentralised Biomedical Signal Classification using Early E...

引用

21st IEEE Interregional NEWCAS Conference (NEWCAS)

作者： Li Xiaolin Vandierendonck, Hans Nikolopoulos, Dimitrios S. Ji, Bo Cardiff, Barry John, Deepu Univ Coll Dublin Dublin Ireland Queens Univ Belfast Belfast Antrim North Ireland Virginia Tech Blacksburg VA USA

ISBN: (纸本)9798350300246

This paper presents a decentralised signal classification approach for data acquired using Internet of Things (IoT) wearable sensors. Traditionally, data from IoT sensors are processed in a centralised fashion, and in a single node. This approach has several limitations, such as high energy consumption on the edge sensor, longer response times, etc. We present a distributed processing approach for convolutional neural network (CNN) based classifiers where a single CNN model can be split into multiple sub-networks using early exits. To reduce the transfer of large feature maps between sub-networks, we introduced an encoder-decoder pair at the exit points. processing of inputs that can be classified with high confidence at an exit point will be terminated early, without needing to traverse the entire network. The initial sub-networks can be deployed on the edge to reduce sensor energy consumption and overall complexity. We also experimented with multiple exit point locations and show that the point of exit can be adjusted for trade-offs between complexity and performance. The proposed system can achieve a sensitivity of 98.45% and an accuracy of 97.55% for electrocardiogram (ECG) classification and save 60% of the data transmitted wirelessly while reducing 38.45% of the complexity.

关键词： ECG classification Arrhythmia Decentralised Inferencing distributed network Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Automatic detection, localization and quantification of structural cracks combining computer vision and crowd sensing technologies

引用

CONSTRUCTION AND BUILDING MATERIALS 2025年 476卷

作者： Jin, Tao Ye, Xiao-Wei Que, Wei-Ming Wang, Ming-Yang Zhejiang Univ Technol Coll Civil Engn Hangzhou 310023 Peoples R China Zhejiang Univ Dept Civil Engn Hangzhou 310058 Peoples R China Zhejiang Univ MOE Key Lab Soft Soils & Geoenvironm Engn Hangzhou 310058 Peoples R China

The emerging of computer vision based methods provides the capacity to detect and quantify the structural damages efficiently. Moreover, the integration of high-performance sensors in the mobile phone allows for the efficient acquisition of multi-source heterogeneous data of damages such as images, locations, etc. This study proposed a computer vision and crowd sensing based method to detect and quantify structural cracks for the distributed in-service bridges. A previously established crowd sensing system was employed to acquire bridge structural cracks and the corresponding locations, which is consisted of a mobile application (APP) and the cloud management platform. As many as 15 volunteers were mobilized to use the APP to collect the multi-source heterogeneous data of cracks from in-service bridges, which consists of 223 crack images, covering 5 typical bridge structural components, i.e., the guardrails, the road surfaces, the beam undersides, the abutments and the piers. Then, the classic U-Net model was trained to segment the crack regions from the image background. Finally, an image skeleton-based processing method was proposed to acquire the pixel size of the cracks for quantitative evaluation. Testing results show that for images with a resolution of 256 x 256 pixels, the crack width is within 10 pixels, while the crack length ranges from 200 to 500 pixels, the error compared to the actual value is within 5 %. Crack images from different scenarios were used to test the applicability of the proposed method. This study provides a novel method to alleviate the demand for professional inspection engineers and vehicles, and validates the feasibility of the proposed method in practical application.

关键词： Structural health assessment Crowd sensing Crack detection Deep neural network Smartphone Quantitative evaluation

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：