检索结果-内蒙古大学图书馆

Petri-net-based deep reinforcement learning for real-time scheduling of automated manufacturing systems

JOURNAL OF MANUFACTURING SYSTEMS 2024年 74卷 995-1008页

作者： Luo, Jiliang Yi, Sijia Lin, Zexuan Zhang, Hongbin Zhou, Jiazhong Huaqiao Univ Coll Informat Sci & Engn Xiamen 361021 Peoples R China Huaqiao Univ Coll Mech Engn & Automat Xiamen 361021 Peoples R China Fujian Engn Res Ctr Motor Control & Syst Optimal S Xiamen 361021 Peoples R China

This work focuses on real-time and joint optimizing issues to handle the routing of automated guided vehicles and allocating processing tasks for automated manufacturing systems. A real-time scheduling approach is proposed based on Petri nets and deep reinforcement learning. First, the considered system is modeled with a placed -timed Petri net, which plays the role of the environment for deep reinforcement learning. Second, a novel graph convolutional network (GCN), called Petri-net-GCN, is designed by using the topological structures of a Petri net model such that it can adapt to changes in Petri -net structures caused by abrupt events such as new orders and failures of devices. Third, a deep Q -network method is presented to train Petri-net-GCN to predict the minimal time to lead a Petri net to its goal if an action (transition) is taken at a present state. Consequently, Petri-net-GCN can replace scheduling rules to schedule an automated manufacturing system in real time. Finally, numerical experiments are carried out where there exist failures of devices and new orders. The results show that Petri-net-GCN can adapt to the Petri -net changes caused by abrupt events and performs much better than the first -in -first -out and longest -processing -time -first rules, which are applicable for real-time scheduling issues in practice.

关键词： deep reinforcement learning Petri net real-time scheduling Graph convolutional network Automated manufacturing system

来源：评论

学校读者我要写书评

暂无评论

Enhanced image processing for Automobile Accident Detection Using deep learning

Enhanced Image Processing for Automobile Accident Detection ...

引用

Smart Technologies and Systems for Next Generation Computing (ICSTSN), International Conference on

作者： S. Usharani J. Dhanushkumar P. Manju Bala A. Balachandar Department of Artificial Intelligence and Machine Learning IFET College of Engineering (An Autonomous Institution) Villupuram India Department of Computer Science and Engineering IFET College of Engineering (An Autonomous Institution) Villupuram India

ISBN: (数字)9798350391565

ISBN: (纸本)9798350391572

Road safety can be creatively increased by utilizing systems for reporting and detecting accidents use the YOLO algorithm. Yolo, which stands for "You Only Look Once," is a sophisticated object recognition system that can identify and pinpoint objects in live video streams. By identifying accidents and notifying emergency services, the system lowers the reaction times and increases the possibility of saving lives by utilizing the YOLO algorithm. The object detection and alarm systems are the two primary parts of the proposed system. The YOLO method is employed by the object recognition module to look for accidents in live video broadcasts. A module of accident photos was used to teach the system to accurately identify incidents. When an accident is discovered, an alert system is activated. The location of the accident and a brief account of what transpired are communicated to the emergency services by the alert system. This information is communicated to emergency services through a wireless communication network, which expedites response times and increases the likelihood of saving lives. Positive results were obtained by testing the system using the images and an accident module. It was shown that the warning system could react in a couple of seconds and that the YOLO algorithm could identify accidents having a precision of around 94. Highways, busy intersections, and other high-risk areas may have systems in place to increase traffic safety and lower the number of accidents. Developing crash detection and warning systems using deep learning using the YOLO technique is one way to potentially increase road safety. With the use of technology, problems may be precisely identified in real-time video feeds, alerting emergency services and potentially increasing survival rates and reaction times.

关键词： YOLO deep learning Accuracy Alarm systems Streaming media Emergency services Road safety

来源：评论

学校读者我要写书评

暂无评论

DREAM-PCD: deep Reconstruction and Enhancement of mmWave Radar Pointcloud

引用

IEEE TRANSACTIONS ON image processing 2024年 33卷 6774-6789页

作者： Geng, Ruixu Li, Yadong Zhang, Dongheng Wu, Jincheng Gao, Yating Hu, Yang Chen, Yan Univ Sci & Technol China Sch Cyber Sci & Technol Hefei 230026 Peoples R China Univ Washington Dept Elect & Comp Engn Seattle WA 98195 USA Univ Sci & Technol China Sch Informat Sci & Technol Hefei 230026 Peoples R China

Millimeter-wave (mmWave) radar pointcloud offers attractive potential for 3D sensing, thanks to its robustness in challenging conditions such as smoke and low illumination. However, existing methods failed to simultaneously address the three main challenges in mmWave radar pointcloud reconstruction: specular information lost, low angular resolution, and severe interference. In this paper, we propose DREAM-PCD, a novel framework specifically designed for real-time 3D environment sensing that combines signal processing and deep learning methods into three well-designed components to tackle all three challenges: Non-Coherent Accumulation for dense points, Synthetic Aperture Accumulation for improved angular resolution, and real-Denoise Multiframe network for interference removal. By leveraging causal multiple viewpoints accumulation and the "real-denoise" mechanism, DREAM-PCD significantly enhances the generalization performance and real-time capability. We also introduce RadarEyes, the largest mmWave indoor dataset with over 1,000,000 frames, featuring a unique design incorporating two orthogonal single-chip radars, Lidar, and camera, enriching dataset diversity and applications. Experimental results demonstrate that DREAM-PCD surpasses existing methods in reconstruction quality, and exhibits superior generalization and real-time capabilities, enabling high-quality real-time reconstruction of radar pointcloud under various parameters and scenarios. We believe that DREAM-PCD, along with the RadarEyes dataset, will significantly advance mmWave radar perception in future real-world applications.

关键词： Radar Millimeter wave communication Radar imaging Three-dimensional displays Laser radar Interference Estimation image reconstruction Synthetic aperture radar Sensors mmWave imaging super-resolution pointcloud

来源：评论

学校读者我要写书评

暂无评论

Diabetic retinopathy detection using convolutional neural network with residual blocks

引用

BIOMEDICAL SIGNAL processing AND CONTROL 2024年 87卷

作者： Kommaraju, Rajasekhar Anbarasi, M. S. Puducherry Technol Univ Dept Informat Technol Pondicherry India

Diabetic Retinopathy (DR) is a disease that happens in the patient eyes of long-term diabetics. It also affects the retina which causes eye blindness. Therefore, DR has to be detected at its early stage to decrease the risk of blindness. Several researchers suggested approaches to detect the blood abnormalities (hemorrhages, Hard and soft exudates, and micro-aneurysms) in the retina images using deep learning models. The limitation with these approaches is the performance degradation and required high training time. To solve this, we suggest a model for automated detection of DR severity using a convolutional neural network (CNN) and residual blocks (DRCNNRB). deep learning models work effectively when they have been trained on vast datasets. Data Augmentation helps to increase the training samples as a result avoids the data imbalance problem. In our model, basic data augmentation techniques such as zooming, shearing, rotation, flipping, and rescaling are applied in DRCNNRB to solve the data imbalance problem. Pre-processing techniques are used to enhance the quality of the image. Extensive experimental results on the Diabetic Retinopathy 2015 Data Colored Resized database conclude that DRCNNRB provides better performance compared to other state-of-the-art works. Thus, DRCNNRB achieves better efficiency for real-time diagnosis.

关键词： deep learning Diabetic retinopathy Convolutional neural network Residual network

来源：评论

学校读者我要写书评

暂无评论

Detection of Overhanging and Dead Branches from In-Vehicle Camera images Using deep learning and image processing

Detection of Overhanging and Dead Branches from In-Vehicle C...

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Tomoka OKACHI Yasutoshi NOMURA Graduate school of science and engineering Ritsumeikan University Kusatsu Japan Civil and environmental engineering Ritsumeikan University Kusatsu Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

In recent years, the construction industry has been promoting ICT (Information and Communication Technology) to address the decline in construction workers and improve working conditions. However, despite advancements in technology, the industry still relies on the visual inspections of skilled technicians, leading to enormous time and cost expenditures for the maintenance of social infrastructure and surrounding obstacles. In light of this situation, there is a growing demand for the development of inspection systems using deep learning. This study focuses on constructing an inspection system that targets dead branches on roadside trees in mountainous areas. In these areas, after typhoons, dead branches often get caught in roadside trees, posing a risk of falling. Therefore, it is necessary to check and remove them in advance. Since it is difficult to observe roadside trees while driving, the goal of this study is to improve the current situation by developing a system that can detect overhanging branches and dead branches caught in them.

关键词： YOLO deep learning Training Visualization Correlation Tropical cyclones Roads Inspection Cameras Information and communication technology

来源：评论

学校读者我要写书评

暂无评论

image super-resolution reconstruction based on deep dictionary learning and A

引用

SIGNAL image AND VIDEO processing 2024年第3期18卷 2629-2641页

作者： Huang, Yi Bian, Weixin Jie, Biao Zhu, Zhiqiang Li, Wenhu Anhui Normal Univ Sch Comp & Informat Wuhu 241002 Anhui Peoples R China Anhui Prov Key Lab Network & Informat Secur Wuhu 241002 Anhui Peoples R China

The method of image super-resolution reconstruction through the dictionary usually only uses a single-layer dictionary, which not only cannot extract the deep features of the image but also requires a large trained dictionary if the reconstruction effect is to be better. This paper proposes a new deep dictionary learning model. Firstly, after preprocessing the images of the training set, the dictionary is trained by the deep dictionary learning method, and the adjusted anchored neighborhood regression method is used for image super-resolution reconstruction. The proposed algorithm is compared with several classical algorithms on Set5 dataset and Set14 dataset. The visualization and quantification results show that the proposed method improves PSNR and SSIM, effectively reduces the dictionary size and saves reconstruction time compared with traditional super-resolution algorithms.

关键词： deep dictionary learning image super-resolution Anchored neighborhood regression Sparse representation

来源：评论

学校读者我要写书评

暂无评论

real-time Video Stabilization Algorithm Based on SuperPoint

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1页

作者： Liu, Tao Wan, Gang Bai, Hongyang Kong, Xiaofang Tang, Bo Wang, Fangyi Nanjing Univ Sci & Technol Natl Key Lab Transient Phys Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Energy & Power Engn Nanjing 210094 Peoples R China Nanjing Vocat Univ Ind Technol Sch Elect Engn Nanjing 210023 Peoples R China

With numerous applications in the field of intelligent unmanned systems for flight patrol, airborne cameras have become crucial tools for measuring and tracking targets. However, the video captured by these cameras is susceptible to external disturbances and jitter, and traditional stabilizers often fail to accurately extract image feature points. Although deep learning approaches can stabilize videos, they are constrained by limited datasets and weak model controllability, making it challenging to achieve real-time performance. We introduce a SuperPoint stabilization framework based on deep learning feature point detection. By combining traditional and deep learning methods, our approach aims to construct a controllable and real-time video stabilizer. First, we extract image feature points using SuperPoint neural network, which is better than traditional manual feature point detector. Second, the extracted image feature points are homogenized. Third, we adopt the pyramid Lucas-Kanade (LK) to improve feature points matching speed and the accuracy for motion estimation. Finally, we define the moving average filter and the Kalman filter, respectively, and combine them to smooth unstable camera trajectories and then output stable video sequences after motion compensation. Experimental results show that our proposed method produces competitive results with current representative methods, and more importantly, it only takes an average of 32 ms to stabilize a frame, which is faster than others.

关键词： Feature extraction Trajectory Cameras real-time systems Three-dimensional displays Streaming media deep learning Motion estimation real-time process trajectory smoothing video process video stabilization

来源：评论

学校读者我要写书评

暂无评论

Dual-GAN Complementary learning for real-World image Denoising

引用

IEEE SENSORS JOURNAL 2024年第1期24卷 355-366页

作者： Zhao, Shaobo Lin, Sheng Cheng, Xi Zhou, Kexue Zhang, Min Wang, Hai Xidian Univ Sch Aerosp Sci & Technol Xian 710071 Peoples R China

The imaging process of real-world images is inevitably polluted by noise, which affects the visual quality and subsequent processing of images. How to restore image details while removing noise has always been a challenging problem. The existing complementary learning strategies combine the advantages of both denoised image learning and noise learning and have good denoised effects. However, these methods that are based on a single generative adversarial network (GAN) suffer from complex network structure, difficulty in training, and further improvement. Therefore, we propose the dual-GAN complementary learning (DGCL) strategy based on modular complementary learning strategy. The method based on this strategy has been verified on the real-world image denoising datasets [PolyU and smartphone image denoising dataset (SIDD)]. The results show that this strategy has a better performance compared with similar denoising algorithm in terms of visual quality and quantitative measurement, and this strategy shows the potential to further improve the performance by improving a module in the strategy.

关键词： Complementary learning deep learning generative adversarial network (GAN) image denoising

来源：评论

学校读者我要写书评

暂无评论

deep practice of internet of things image recognition technology based on deep learning in intelligent financial supervision system

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 9511-9523页

作者： Gao, Yanbing Ma, Rui Department of Management Engineering Hebei Petroleum University of Technology Hebei Chengde China Health and Rehabilitation College Chengdu University of Traditional Chinese Medicine Sichuan Chengdu China

With the deepening development of the financial market, the role of regulatory systems in ensuring green and safe financial environment is becoming increasingly prominent. The traditional intelligent financial regulatory systems on the market lack precise and effective real-time monitoring and recognition capabilities, making it difficult to effectively process and analyze large-scale financial data. In order to improve the real-time recognition of abnormal situations or potential risks, achieve automation and intelligence of supervision, this article combines deep learning technology to study the deep practice of IoT image recognition technology in intelligent financial supervision systems. In response to the "data silos"and cross regional linkage issues faced by financial industry regulation, this article designs and implements an intelligent regulatory system based on IoT image recognition technology through deep learning. Using Convolutional Neural Network (CNN) algorithm to classify and analyze system images for regulatory and risk control purposes. The research results indicate that the intelligent financial regulatory system constructed in this article has high stability and responsiveness, which can effectively meet the real-time regulatory needs of finance and help promote the healthy development of the financial market. © 2024 - IOS Press. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

deep learning techniques to detect rail indications from ultrasonic data for automated rail monitoring and maintenance

引用

ULTRASONICS 2024年 140卷 107314页

作者： Islam, Md Ashraful Olm, Georg Tech Univ Berlin Chair Civil Syst Engn Gustav Meyer Allee 25 D-13355 Berlin Germany

The increasing number of passengers and services using railways and the corresponding increase in rail use has caused the acceleration of rail wear and surface defects which makes rail defect identification an important issue for rail maintenance and monitoring to ensure safe and efficient operation. Traditional visual inspection methods for identifying rail defects are time-consuming, less accurate, and associated with human errors. deep learning has been used to improve railway maintenance and monitoring tasks. This study aims to develop a structured model for detecting railway artifacts and defects by comparing different deep-learning models using ultrasonic image data. This research showed whether it is practical to identify rail indications using image classification and object detection techniques from ultrasonic data and which model performs better among the above-mentioned methods. The methodology includes data processing, labeling, and using different conventional neural networks to develop the model for both image classification and object detection. The results of CNNs for image classification, and YOLOv5 for object detection show 98%, and 99% accuracy respectively. These models can identify rail artifacts efficiently and accurately in real-life scenarios, which can improve automated railway infrastructure monitoring and maintenance.

关键词： Ultrasonic sensors CNNs Artifacts Rail defects image classification Object detection

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：