检索结果-内蒙古大学图书馆

CTIS spectral image reconstruction technology based on slit-scanning architecture

OPTICS EXPRESS 2024年第14期32卷 25276-25291页

作者： Zhou, Pengwei Lv, Yangfan Zheng, Yuqi Zhou, Jiamin Chen, Liang China Jiliang Univ Coll Opt & Elect Technol Hangzhou 310018 Peoples R China Minist Nat Resources Key Lab Marine Environm Survey Technol & Applicat Hangzhou Peoples R China

The computed tomography imaging spectrometer (CTIS) is a snapshot imaging spectrometer, excelling in dynamic detection tasks. It can capture two-dimensional spatial information and spectrally compressed information of a target within a single exposure time. However, traditional CTIS image reconstruction algorithms suffer from missing-cone problem, which reduces the accuracy of spectral reconstruction. In recent years, deep learning has been applied to CTIS spectral image reconstruction, significantly improving spectral reconstruction accuracy compared to traditional algorithms. However, due to the missing-cone problem, it is difficult to accurately recover the truth of spectral data cube in the real scene. Currently, most CTIS neural network reconstruction models are trained using simulated datasets of spectral data cubes and diffractive images. Because these data differ significantly from real data under actual application conditions, the established models may not be effectively applicable to real-world scenes. Therefore, we propose a new CTIS system based on slit-scanning architecture utilizing an adjustable slit aperture to obtain the real spectral data cube of the target while maintaining the simplicity of the CTIS structure. By limiting the field of view (FOV) through the slit, the area of diffraction overlap can be reduced, thereby enhancing the accuracy of CTIS spectral reconstruction using the expectation-maximization (EM) algorithm. This architecture allows us to obtain accurate spectral cubes that match the CTIS diffractive image of real-world scenes, providing a real dataset for training the reconstruction network. A prototype has been built to demonstrate the feasibility of our proposed solution. Furthermore, we also constructed a residual network based on multi-scale and attention mechanism. This network is trained using a combination of simulated and real spectral imaging data. Compared to the reconstruction performance of the EM algorithm and convolu

关键词： Computed tomography deep learning Diffractive optical elements Neural networks Optical transfer functions Spatial resolution

来源：评论

学校读者我要写书评

暂无评论

UtilityChain: Dynamic Resource Allocation for Mining and Servicing in Blockchain System

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2024年第5期17卷 2261-2272页

作者： Tapwal, Riya Misra, Sudip Pal, Surjya Kanta Indian Inst Technol Kharagpur Dept Comp Sci & Engn Kharagpur 721302 West Bengal India Indian Inst Technol Kharagpur Dept Mech Engn Kharagpur 721302 West Bengal India

In this research work, we propose - UtilityChain -, a method for efficient resource allocation of miners involved in both mining and service-related activities. The aim of this approach is to enhance the miner's utility (overall efficiency) in response to the increasing need for real-time data processing generated by IoT devices. The security of the data is a crucial matter of concern, and the integration of blockchain technology for secure data storage and edge computing for real-time processing is deemed a suitable approach. However, the utilization of edge computing devices adds an extra cost burden. Additionally, fluctuations in resource prices and mining rewards frequently result in miner departures and underutilized resources. To tackle these challenges, UtilityChain employs the resources of miners for mining and providing services to the end-users, without the use of edge computing devices. This is achieved through the utilization of advanced deep reinforcement learning technique to dynamically allocate miner resources for both mining and service tasks. The experimental results demonstrate the efficacy of UtilityChain, with a resource allocation accuracy of 99.2% and a miner allocation accuracy of 98.8%. Additionally, UtilityChain exhibits a resource utilization rate of 8.2% for CPU and 78.2% for memory.

关键词： Task analysis Resource management Industrial Internet of Things Data mining Blockchains Edge computing Security Blockchain edge computing deep reinforcement learning resource allocation mining servicing tasks

来源：评论

学校读者我要写书评

暂无评论

Multivariate time Series Forecasting: A Review 24

Multivariate Time Series Forecasting: A Review

引用

2nd Asia Conference on Computer Vision, image processing and Pattern Recognition (CVIPPR)

作者： Mendis, Kasun Wickramasinghe, Manjusri Marasinghe, Pasindu Univ Colombo Sch Comp Colombo 07 Sri Lanka

ISBN: (纸本)9798400716607

Multivariate time series forecasting is a critical task with applications across various domains, including finance, energy demand, and climate modeling. This review paper, provides a comprehensive overview of methodologies and advancements in multivariate time series forecasting, focusing on deep learning architectures, ensemble methods, and modeling techniques. Traditional approaches such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs) have paved the way for modeling sequential data, but challenges remain in capturing long-term dependencies. Recent advancements in transformer-based architectures and graph neural networks (GNNs) have addressed these challenges, offering enhanced accuracy and interpretability. Ensemble methods, leveraging the strengths of multiple models, have emerged as effective strategies for improving forecast robustness. The review discusses key methodologies, including hybrid models, attention mechanisms, and deep learning architectures, highlighting their strengths and limitations. Through interdisciplinary collaboration and methodological innovation, researchers can address complex forecasting problems, ultimately benefiting society across a wide range of applications.

关键词： time series forecasting multivariate machine learning deep learning

来源：评论

学校读者我要写书评

暂无评论

real time Sign Language Recognition using Knowledge Assisted Method 15

Real Time Sign Language Recognition using Knowledge Assisted...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Srivastava, Vivek Pratap, Jay Sinha, Shobhit Kumar, Sunil ABES Engineering College Uttar Pradesh Ghaziabad India

ISBN: (纸本)9798331300579

As we are aware that verbal communication can be hampered by speech impairment, and sign language is one of the best systems for resolving this problem. The goal of our paper is to create a system or application that can recognize sign language motions in order to reduce the gap between persons with disabilities and others, such as deaf and mute people. The suggested system uses machine learning and image processing to create a real-time system. Preprocessing photos and removing hand motions from the backdrop are both done via image processing. The 24 English alphabets are then included in a dataset created using these photos. Both a specially created dataset and live hand gestures produced by people of different ages are used to evaluate the Faster(R-CNN) that we proposed in our research. The accuracy comes near to 95%. © Grenze Scientific Society, 2024.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

A deep learning Approach for Landmines Detection Based on Airborne Magnetometry Imaging and Edge Computing

引用

Computer Modeling in Engineering & Sciences 2024年第5期139卷 2117-2137页

作者： Ahmed Barnawi Krishan Kumar Neeraj Kumar Bander Alzahrani Amal Almansour Faculty of Computing and Information Technology King Abdulaziz UniversityJeddahSaudi Arabia Department of Computer Science and Engineering Thapar Institute of Engineering and TechnologyDeemed to be UniversityPatialaIndia

Landmines continue to pose an ongoing threat in various regions around the world,with countless buried landmines affecting numerous human *** detonation of these landmines results in thousands of casualties reported worldwide ***,there is a pressing need to employ diverse landmine detection techniques for their *** effective approach for landmine detection is UAV(Unmanned Aerial Vehicle)based AirborneMagnetometry,which identifies magnetic anomalies in the local terrestrial magnetic *** can generate a contour plot or heat map that visually represents the magnetic field *** the effectiveness of this approach,landmine removal remains a challenging and resource-intensive task,fraughtwith *** computing,on the other hand,can play a crucial role in critical drone monitoring applications like landmine *** processing data locally on a nearby edge server,edge computing can reduce communication latency and bandwidth requirements,allowing real-time analysis of magnetic field *** enables faster decision-making and more efficient landmine detection,potentially saving lives and minimizing the risks involved in the ***,edge computing can provide enhanced security and privacy by keeping sensitive data close to the source,reducing the chances of data exposure during *** paper introduces the MAGnetometry Imaging based Classification System(MAGICS),a fully automated UAV-based system designed for landmine and buried object detection and *** have developed an efficient deep learning-based strategy for automatic image classification using magnetometry dataset *** simulating the proposal in various network scenarios,we have successfully detected landmine signatures present in themagnetometry *** trained models exhibit significant performance improvements,achieving a maximum mean average precision value of 97.8%.

关键词： CNN deep learning landmine detection magnetometer mean average precision UAV

来源：评论

学校读者我要写书评

暂无评论

Adaptive Weighted Damage Imaging of Lamb Waves Based on deep learning

引用

IEEE ACCESS 2024年 12卷 128860-128870页

作者： Shen, Ronghe Zhou, Zixing Xu, Guidong Zhang, Sai Xu, Chenguang Xu, Baiqiang Luo, Ying Jiangsu Univ Fac Civil Engn & Mech Zhenjiang 212013 Peoples R China Jiangsu Univ Sch Phys & Elect Engn Zhenjiang 212013 Peoples R China

The damage imaging method based on Lamb wave beamforming has been widely used in the field of SHM. The DAS method has a high imaging efficiency, but its ability to suppress interference signals is weak, resulting in low imaging resolution and signal-to-noise ratio. Drawing inspiration from the adaptive weighted MVDR damage imaging method, this paper constructs a neural network based on FCNN, with the images generated by the MVDR method as the target. By training the model, the mapping relationship between delayed channel input data and adaptive weighting factors is established, thereby improving the resolution and signal-to-noise ratio of Lamb wave damage imaging and achieving rapid imaging of damage. To verify the effectiveness and imaging performance of the FCNN method, imaging of two types of damage in aluminum plates is conducted through simulation and experiments, and the imaging results are compared and analyzed with DAS and MVDR. The results show that the imaging quality and the quantitative indicators of the FCNN method have not yet reached the performance level of the MVDR, but compared with DAS, FCNN has a significantly narrower main lobe width and lower sidelobe level. Furthermore, its quantitative indicators such as API, SNR, and FWHM are better than DAS. The proposed adaptive Lamb wave beamforming method based on FCNN combines high resolution and signal-to-noise ratio, as well as the advantage of rapid imaging, providing reference and support for real-time SHM based on Lamb waves.

关键词： Imaging Aluminum image resolution Covariance matrices Array signal processing Training Signal to noise ratio deep learning Adaptive weighting damage imaging deep learning lamb waves

来源：评论

学校读者我要写书评

暂无评论

Collaborative optimization of composite structure and fiber orientation through real-time correction of deep neural network (DNN) models with elite samples

引用

MECHANICS OF ADVANCED MATERIALS AND STRUCTURES 2024年第26期31卷 7944-7956页

作者： Li, Yuzhu Ge, Wenjie Liu, Bin Wang, Zhuo Wang, Chengmin Zhang, Yonghong Northwestern Polytech Univ Sch Mech Engn Xian Peoples R China

Gradient-free optimization methods can result in significant computational costs when solving complex structural design problems for composite materials. To this end, this article presents a machine learning-based co-optimization method for composite material structure and fiber orientation. In this approach, DNN are utilized as surrogate models for the optimization problem. Equilibrium optimizer is employed to find real-time optimal solution of the DNN. Subsequently, elite samples are generated based on this optimal solution and used to update the DNN until convergence is achieved. During the post-processing stage, B-spline functions are applied to smooth the density and fiber orientation of the optimized results.

关键词： Fiber reinforced composites topology optimization collaborative optimization fiber orientation composite structure deep neural network

来源：评论

学校读者我要写书评

暂无评论

Boosting with fine-tuning for deep image denoising

引用

SIGNAL processing 2024年 217卷

作者： Xie, Zhonghua Liu, Lingjun Wang, Cheng Chen, Zehong Huizhou Univ Sch Comp Sci & Engn Huizhou 516007 Peoples R China Huizhou Univ Sch Math & Stat Huizhou 516007 Peoples R China Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Peoples R China Shenzhen Key Lab Media Secur Shenzhen 518060 Peoples R China

While deep learning is ruling the image denoising domain in recent years, earlier works primarily focused on design of network architecture or training strategy. In this paper, we raise two questions: how to combine the advantages of traditional iterative methods and deep learning-based approaches, and how to avoid performance degradation caused by inaccurate modeling and estimation of noise. To answer the questions, we integrate recursive strategies and fine-tuning schemes to boost existing deep denoisers in a plug-and-play fashion. Specifically, based on the framework of plug-and-play priors, the image denoising problem is solved with the half quadratic splitting (HQS) algorithm to achieve iterative denoising. Different from the standard solving process, we develop a joint optimization scheme with regard to image restoration and network fine-tuning, realizing the matching between network and noise, thereby enabling better adaptation to the images contaminated by complex non-Gaussian noise. As such, two types of adaptive denoising boosters with convergence guarantee based on the fixed-point strategy and steepest-descent method are obtained. It is demonstrated in the experiments that the proposed schemes provide promising performance on additive white Gaussian noise (AWGN) and real-noise denoising for both supervised and self-supervised deep learning-based image denoising algorithms.

关键词： image denoising Boosting Plug-and-play priors deep neural network Fine-tuning

来源：评论

学校读者我要写书评

暂无评论

Dual-input anomaly detection method based on deep reinforcement learning

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2024年第3期23卷 1578-1591页

作者： Kang, Yuxiang Chen, Guo Wang, Hao Pan, Wenping Wei, Xunkai Nanjing Univ Aeronaut & Astronaut Coll Civil Aviat Nanjing Peoples R China Nanjing Univ Aeronaut & Astronaut Coll Gen Aviat & Flight Nanjing Peoples R China Beijing Aeronaut Engn Tech Res Ctr Beijing Peoples R China Nanjing Univ Aeronaut & Astronaut 29Jiangjun Ave Nanjing Jiangsu Peoples R China

Aiming at the problem of low accuracy of unsupervised learning anomaly detection algorithm, a dual-input anomaly detection method based on deep reinforcement learning was proposed. The proposed model mainly consists of a feature extractor and anomaly detector. Based on the deep reinforcement learning framework, the feature extractor uses a dual-input deep neural network to form the current value network and the target value network, which are used to extract the low-dimensional feature vectors. Based on the 3 & sigma;principle, the reward function of reinforcement learning is designed to reward and punish the output results of the model during training. The model was trained only with the normal data, and the extracted feature vector of the normal class was used as the input of the anomaly detector to complete the learning of the detector. During the test, the input anomaly detection was realized based on the dual-input convolutional neural network, and the anomaly detector was completed by learning. To illustrate the generality and generalization performance of the proposed method, four sets of image data and two sets of rolling bearing fault data in different fields were verified respectively. At the same time, the proposed method is applied to the fault detection of a real aero-engine rolling *** results show that the proposed model has high anomaly detection accuracy, which is superior to the current optimal method.

关键词： deep reinforcement learning anomaly detection dual-input deep neural network unsupervised learning rolling bearings

来源：评论

学校读者我要写书评

暂无评论

RT3C: real-time Crowd Counting in Multi-Scene Video Streams via Cloud-Edge-Device Collaboration

引用

IEEE TRANSACTIONS ON SERVICES COMPUTING 2024年第4期17卷 1739-1752页

作者： Wang, Rui Hao, Yixue Miao, Yiming Hu, Long Chen, Min Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China Pazhou Lab Guangzhou 510640 Peoples R China Chinese Univ Hong Kong Shenzhen Inst Artiffcial Intelligence & Robot Soc Sch Data Sci Shenzhen 518172 Guangdong Peoples R China South China Univ Technol Sch Comp Sci & Engn Guangzhou 510640 Peoples R China

Recently, the advancements in edge computing have boosted the deployment of video analysis systems based on deep learning, which breaks the limitation of the constrained communication and computing resources of local devices. However, processing multi-scene high-resolution video streams in crowd surveillance remains a significant challenge since it is difficult to formulate dynamic video content and communication environment to support offloading decisions. To bridge the gap between applications and modeling, this paper presents a real-time Cloud-edge-device Collaboration framework, which enables fast and accurate Crowd counting (RT3C) on the real dataset. RT3C comprises key frame detection, adaptive patch partition, patch encoder and decoder and computation offloading decision, designed to divide key frames into a minimum number of patches and determine the offloading location of patches. A real-time Multi-Agent Actor-Critic (RTMAAC) algorithm based on multi-agent reinforcement learning is proposed to decide whether to compute patches with a lightweight model on edge or a large model on cloud. Unlike traditional approaches ignoring the contents, RTMAAC is a dynamic online decision algorithm based on context of the network and video. Extensive experiments demonstrate that RT3C effectively discriminates the valid frames and optimizes offloading decisions in complex environments, outperforming other baseline algorithms on the two crowd counting datasets. In summary, RT3C provides a promising framework for multi-scene video streams, which can be extended to other applications to realize video computation based on deep models.

关键词： Cloud-edge-device collaboration crowd counting multi-agent deep reinforcement learning multi-scene video streams Cloud-edge-device collaboration crowd counting multi-agent deep reinforcement learning multi-scene video streams

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：