检索结果-内蒙古大学图书馆

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

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

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

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

Blockchain: Secured Solution for Signature Transfer in distributed Intrusion Detection System

引用

Computer Systems Science & Engineering 2022年第1期40卷 37-51页

作者： Shraddha R.Khonde Venugopal Ulagamuthalvi Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Engineering M.E.S.College of EngineeringS.P.Pune UniversityPune411001India

Exchange of data in networks necessitates provision of security and *** networks compromised by intruders are those where the exchange of data is at high *** main objective of this paper is to present a solution for secure exchange of attack signatures between the nodes of a distributed *** activities are monitored and detected by the Intrusion Detection System(IDS)that operates with nodes connected to a distributed *** IDS operates in two phases,where the first phase consists of detection of anomaly attacks using an ensemble of classifiers such as Random forest,Convolutional neural network,and XGBoost along with genetic algorithm to improve the performance of *** novel attacks detected in this phase are converted into signatures and exchanged further through the network using the blockchain framework in the second *** phase uses the cryptosystem as part of the blockchain to store data and secure it at a higher *** blockchain is implemented using the Hyperledger Fabric v1.0 and v2.0,to create a prototype for secure signature *** exchanges signatures in a much more secured manner using the blockchain architecture when implemented with version 2.0 of Hyperl-edger *** performance of the proposed blockchain system is evaluated on UNSW NB15 *** performance has been evaluated in terms of execution time,average latency,throughput and transaction processing *** evidence of the proposed IDS system demonstrates improved performance with accuracy,detection rate and false alarm rate(FAR)as key parameters *** and detection rate increase by 2%and 3%respectively whereas FAR reduces by 1.7%.

关键词： Blockchain intrusion detection system machine learning algorithms secured communication ensemble approach

来源：评论

学校读者我要写书评

暂无评论

Harnessing distributed GPU computing for generalizable graph convolutional networks in power grid reliability assessments

引用

ENERGY AND AI 2025年 19卷

作者： Dhulipala, Somayajulu L. N. Casaprima, Nicholas Olivier, Audrey Vaagensmith, Bjorn C. Mcjunkin, Timothy R. Hruska, Ryan C. Idaho Natl Lab Nucl Sci & Technol Idaho Falls ID 83415 USA Univ Southern Calif Sonny Astani Dept Civil & Environm Engn Los Angeles CA 90089 USA Idaho Natl Lab Natl & Homeland Secur Idaho Falls ID 83415 USA Idaho Natl Lab Energy & Environm Sci & Technol Idaho Falls ID 83415 USA Idaho State Univ Civil & Environm Engn Pocatello ID 83209 USA

Although machine learning (ML) has emerged as a powerful tool for rapidly assessing grid contingencies, prior studies have largely considered a static grid topology in their analyses. This limits their application, since they need to be re-trained for every new topology. This paper explores the development of generalizable graph convolutional network (GCN) models by pre-training them across a wide range of grid topologies and contingency types. We found that a GCN model with auto-regressive moving average (ARMA) layers with a line graph representation of the grid offered the best predictive performance in predicting voltage magnitudes (VM) and voltage angles (VA). We introduced the concept of phantom nodes to consider disparate grid topologies with a varying number of nodes and lines. For pre-training the GCN ARMA model across a variety of topologies, distributed graphics processing unit (GPU) computing afforded us significant training scalability. The predictive performance of this model on grid topologies that were part of the training data is substantially better than the direct current (DC) approximation. Although direct application of the pre-trained model to topologies that are not part of the grid is not particularly satisfactory, fine-tuning with small amounts of data from a specific topology of interest significantly improves predictive performance. In the context of foundational models in ML, this paper highlights the feasibility of training large-scale GNN models to assess the reliability of power grids by considering a wide variety of grid topologies and contingency types.

关键词： Complex systems Graph neural networks Power grids Grid reliability Generalizable models

来源：评论

学校读者我要写书评

暂无评论

Adaptive Splitting Algorithm for neural network Modelling in AMP 21

Adaptive Splitting Algorithm for Neural Network Modelling in...

引用

21st IEEE International Symposium on Parallel and distributed processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Zhang, Kaifei Ma, Yuxiang Wu, Yulei Chen, Tao Ma, Huijie Henan University School of Computer and Information Engineering Kaifeng475004 China University of Bristol School of Electrical Electronic and Mechanical Engineering BristolBS8 1UB United Kingdom

ISBN: (纸本)9798350329223

Artificial Intelligence algorithms usually consume a lot of energy and computing resources during training, so data is usually sent to high-performance devices to complete model training. However, such a computing mode cannot make good use of computing resources in the network and is not conducive to the privacy protection of user information. In recent years, some studies have used end devices to participate in model training, among which federated learning is a typical representative. Due to the heterogeneous computing resources of the end devices, how to split the neural network model to achieve an effective balance between training time and energy consumption is an important issue. In this paper, we propose a novel model splitting method that includes the steps of collecting data, correcting the data, and determining the splitting layers to complete the splitting learning. We consider four factors (training time, energy consumption, CPU utilisation, and memory utilisation) to jointly decide the splitting layer and propose a scheme for adaptively revising the model. We use the VGG16 model for evaluation. The results show that the efficiency of our method is improved by 64.5% compared to the recently proposed ARES scheme. At the same time, our proposed method does not affect the convergence and accuracy of the model. © 2023 IEEE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

Detection of Road Surface Anomaly Using distributed Fiber Optic Sensing

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第11期23卷 22127-22134页

作者： Zhao, Jingnan Wang, Hao Chen, Yuheng Huang, Ming-Fang Rutgers State Univ Sch Engn Dept Civil & Environm Engn Piscataway NJ 08854 USA NEC Labs Amer Inc Princeton NJ 08540 USA

Road surface condition can significantly impact the interaction between vehicles and pavement structure, which may even cause high fuel consumption and safety issues of drivers and vehicles. distributed fiber optic sensing (DFOS) technology is a useful tool to perform continuous and real-time monitoring of traffic and road surface condition. However, it is challenging to process the data for the purpose of road anomaly detection. The study proposed two approaches to detect the road anomaly using DFOS. In the first method, local binary pattern (LBP) histograms were used to extract the features of the images with and without road anomaly, and support vector machine (SVM) combined with principal component analysis (PCA) was adopted as the classifier. The convolutional neural network (CNN) was applied on the binary classification data to analyze the images in the second method. The accuracy and benefits of two methodologies were compared. The vehicle speed was estimated by detecting lines using Hough transform. The feasibility of road anomaly detection using DFOS is proved.

关键词： Roads Sensors Support vector machines Feature extraction Optical imaging Convolutional neural networks Transforms DFOS road surface anomaly Hough transform image processing LBP SVM CNN

来源：评论

学校读者我要写书评

暂无评论

Research on Building a Standardized Library for Auditing Heterogeneous Information Models in distributed Data 7

Research on Building a Standardized Library for Auditing Het...

引用

7th IEEE International Conference on Information Systems and Computer Aided Education, ICISCAE 2024

作者： Heping, Huang Zhonglu, Zou Zhicai, Huang Dongguan Power Supply Bureau Guangdong Power Grid Corporation Guangdong Dongguan523000 China

ISBN: (纸本)9798350350760

With the advancement of smart grid transformation, the configuration audit of distribution network communication networks faces challenges such as diversified network devices, numerous manufacturers, and multi-source data management. Traditional methods exhibit significant deficiencies in processing efficiency and data consistency, failing to meet the demands of large-scale data management. This paper proposes a standard library construction method for configuration audit of distribution network data networks. By integrating knowledge graph technology with convolutional neural networks, this method establishes dynamic and static audit libraries, achieving accurate, rapid, and comprehensive management of audit data. The specific process includes the collection and preprocessing of multi-source data, construction of the knowledge graph, application of the inference mechanism, and intelligent retrieval and updating of the standard library. This method significantly improves the accuracy and completeness of data security configuration and optimizes the configuration audit process of distribution network communication networks. ©2024 IEEE.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Coded distributed Computation for Resilient Prediction Serving Systems 30th

Asymmetric Coded Distributed Computation for Resilient Predi...

引用

30th European Conference on Parallel and distributed processing (Euro-Par)

作者： Wang, Lin Hu, Yuchong Liu, Yuxue Xiao, Renzhi Feng, Dan Huazhong Univ Sci & Technol Wuhan Peoples R China

ISBN: (纸本)9783031697654;9783031697661

With the surge of AI services, prediction serving systems (PSSes) have been widely deployed. PSSes are often run on many workers and thus are prone to stragglers (slowdowns or failures), so it is critical to design straggler-resilient PSSes for low latency of prediction. A traditional way is replication that assigns the same prediction job to multiple workers, while incurring significant resources overheads due to its replicated redundant jobs. Recently, coded distributed computation (CDC) has become a more resource-efficient way than replication, as it encodes the prediction job into parity units for prediction reconstruction via decoding. However, we find that state-of-the-art CDC methods either trade accuracy for low latency with the encoder and decoder both simple, or trade latency for high accuracy with the encoder and decoder both complicated, leading to unbalance between accuracy and latency due to the above symmetry between the encoder and decoder. Our insight is that the encoder is always used in CDC-based prediction, while the decoder is only used when stragglers occur. In this paper, we first propose a new asymmetric CDC framework based on the insight, called AsymCDC, composed of a simple encoder but a complicated decoder, such that the encoder's simplicity makes a low encoding time that reduces the latency largely, while the decoder's complexity can be helpful for accuracy. Further, we design the decoder's complexity in two steps: i) an exact decoding method that leverages an invertible neural network's (INN) invertibility to make the decoding have no accuracy loss, and ii) a decoder compacting method that reshapes INN outputs to utilize knowledge distillation effectively that compacts the decoder for low decoding time. We prototype AsymCDC atop Clipper and experiments show that the prediction accuracy of AsymCDC is approximately the same as state-of-the-arts with the encoder and decoder both complicated, while the latency of AsymCDC only exceeds that of

关键词： Forward error correction

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：