检索结果-内蒙古大学图书馆

IEEE International Symposium on parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Brett Wiens Daniel C. Lee School of Engineering Science Simon Fraser University Burnaby Canada

This paper presents signal space constellations that minimize symbol-error probability in an uncoded communications system. We develop a modified projected gradient optimization method to solve for these constellations that scales efficiently, enabling the optimization of very large constellations. The optimized constellation shapes show significant improvements in symbol-error probability over a wide range of channel conditions compared with uniformly-spaced constellations. At high SNR, small deviations from uniform spacing can make substantial improvements in system performance. These results have promising applications to low-complexity systems with real-time data transmission requirements.

关键词： Gradient methods Limiting Shape Quadrature amplitude modulation System performance Symbols Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation Of image Recognition of Tea Based on Deep Learning

Research and Implementation Of Image Recognition of Tea Base...

引用

Software Engineering, Artificial Intelligence, Networking and parallel/distributed Computing (SNPD-Winter), ACIS International Winter conference on

作者： Mucong Gao Minyong Shi Chunfang Li School of Computer Science and Cybersecurity Communication University of China Beijing China

With the advent of the Internet era, deep learning technology is developing rapidly in a wide range of application scenarios. As one of the main research methods of deep learning, convolutional neural network is widely used in the field of image recognition [5]. This paper hopes to build a modern intelligent tea image recognition system by combining in-depth learning technology, so as to help inherit traditional Chinese culture. The main work of this paper is as follows:(1)Making a sample data set containing about 49000 pictures;(2)Constructing convolution neural network;(3)The correct rate of training image recognition model is 96%;(4)Realize tea picture recognition;(5)Build the web *** the framework of tensorflow, the program of this subject realizes the tea picture recognition function by training convolution neural network [5][6], and builds it in the beautiful web page, so that the tea culture can be presented and spread in a more modern form, which is conducive to the inheritance and development of Chinese traditional culture.

关键词： Training Deep learning image recognition Convolution Neural networks Web pages Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and management of image processing pipelines within CPS: 2 years of experience from the FitOptiVis ECSEL Project 23

Design and management of image processing pipelines within C...

引用

23rd Euromicro conference on Digital System Design (DSD)

作者： Pomante, Luigi Palumbo, Francesca Rinaldi, Claudia Valente, Giacomo Sau, Carlo Fanni, Tiziana van der Linden, Frank Basten, Twan Geilen, Marc Peeren, Geran Kadlec, Jiri Jaaskelainen, Pekka Martinez, Marcos Saarinen, Jukka Santti, Tero Zedda, Maria Katiuscia Sanchez, Victor Goswami, Dip Al-Ars, Zaid de Beer, Ad Univ Aquila Laquila Italy Univ Sassari Sassari Italy Univ Cagliari Cagliari Italy Philips Amsterdam Netherlands Eindhoven Univ Technol Eindhoven Netherlands Inst Informat Theory & Automat Prague Czech Republic Tampere Univ Tampere Finland Thales Alenia Space Espana Madrid Spain Nokia Espoo Finland Univ Turku Turku Finland Abinsula Sassari Italy Delft Univ Technol Delft Netherlands

ISBN: (纸本)9781728195353

Cyber-Physical Systems (CPS) are dynamic and reactive systems interacting with processes, environment and, sometimes, humans. They are often distributed with sensors and actuators, smart, adaptive, predictive and react in real-time. Indeed, as sight for human beings, image- and video-processing pipelines are a prime source for environmental information for systems allowing them to take better decisions according to what they see. Therefore, in FitOptiVis we are developing novel methods and tools to integrate complex image and video processing pipelines. FitOptiVis aims to deliver a reference architecture for describing and optimizing quality and resource management for imaging and video pipelines in CPS both at design- and run-time. The architecture is concretized in low-power, high-performance, smart components, and in methods and tools for combined design-time and run-time multi-objective optimization and adaptation within system and environment constraints.

关键词： image-video processing distributed systems heterogeneous system energy and performance optimization Cyber-Physical Systems

来源：评论

学校读者我要写书评

暂无评论

Hardware parallel Architecture proposed to accelerate the Orthogonal Matching Pursuit Compressive Sensing Reconstruction 5

Hardware Parallel Architecture proposed to accelerate the Or...

引用

conference on Computational Imaging V

作者： Osorio Quero, C. Durini, D. Ramos-Garcia, R. Rangel-Magdaleno, J. Martinez-Carranza, J. Opt & Elect INAOE Natl Inst Astrophys Luis Enrique Erro 1 Puebla 72840 Mexico

ISBN: (纸本)9781510635692

The compressive sensing (CS) technique is a novel tool used to reconstruct images using fewer samples, normally sparse in the transform domain, than those required by conventional imaging systems. However, the methods applied for signal reconstruction within the CS approach still present some problems in the implementation, mainly due to their intensive computational demand and high power consumption requirements. These drawbacks need addressing if this approach is followed in systems aimed at e.g. drone autonomous flying or other embedded applications that additionally require very short processing times. In this paper we evaluate the use of hardware based parallel processing architecture for the implementation of the Orthogonal Matching Pursuit (OMP) algorithm, one of the most efficient CS reconstruction algorithms developed so far. To improve the algorithm performance, we target different maximum allowed processing times to reach minimum image resolutions required by each system of interest using different sparse (16 and 64) amounts of single-pixel generated samples per image. We also target the final image resolution to be above 20 dB in terms of the peak signal-to-noise ratio (PSNR). To reduce the execution and processing times required to generate each image, we propose implementing parallel kernels in the hardware platform for each of the operations required by the algorithms under study. In the proposed implementation the reconstructed images are used to generate video streams that form the foundation on which decisions are to be made by the system in continuous time, whereby each single image (frame) reconstruction cannot overcome 30 ms in order to maintain the minimum amount of frames per second (fps) above 33 (minimum required for an acceptable video stream). The implementation of a variation of the OMP algorithm in a graphics processing unit (GPU) using parallel architecture approach allows obtaining processing times 4 or 5 times shorter than those obtai

关键词： 2D/3D Imaging CUDA GPU architecture Orthogonal Matching Pursuit (OMP) patterns parallel architecture Compressive Sensing (CS)

来源：评论

学校读者我要写书评

暂无评论

Offline Imitation Learning Using Reward-free Exploratory Data 22

Offline Imitation Learning Using Reward-free Exploratory Dat...

引用

Proceedings of the 2022 5th International conference on Algorithms, Computing and Artificial Intelligence

作者： Hao Wang Dawei Feng Bo Ding Wei Li College of Computer National University of Defense Technology China National Laboratory for Parallel and Distributed Processing National University of Defense Technology China Independent Researcher China

ISBN: (纸本)9781450398336

Offline imitative learning(OIL) is often used to solve complex continuous decision-making tasks. For these tasks such as robot control, automatic driving and etc., it is either difficult to design an effective reward for learning or very expensive and time-consuming for agents to collect data interactively with the environment. However, the data used in previous OIL methods are all gathered by reinforcement learning algorithms guided by task-specific rewards, which is not a true reward-free premise and still suffers from the problem of designing an effective reward function in real tasks. To this end, we propose the reward-free exploratory data driven offline imitation learning (ExDOIL) framework. ExDOIL first trains an unsupervised reinforcement learning agent by interacting with the environment, and collects enough unsupervised exploration data during training; Then, a task independent yet simple and efficient reward function is used to relabel the collected data; Finally, an agent is trained to imitate the expert to complete the task through a conventional RL algorithm such as TD3. Extensive experiments on continuous control tasks demonstrate that the proposed framework can achieve better imitation performance(28% higher episode returns on average) comparing with previous SOTA method(ORIL) without any task-specific rewards.

关键词： dataset

来源：评论

学校读者我要写书评

暂无评论

Maintenance Worker Scheduling for Charging Pile Fault: a Multi-Agent RL Approach

Maintenance Worker Scheduling for Charging Pile Fault: a Mul...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Wen Wang Junchao Fan Xiaofeng Peng Ye Yang Chun Xiao Shuai Yang Mingcai Wang Lingfei Wang Hongyue Kang Xiaolin Chang State Grid Electric Vehicle Service Company Ltd. Beijing China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing China State Grid Shanxi Marketing Service Center Shanxi China

This paper investigates a maintenance worker scheduling system for charging pile faults, where maintenance workers are scheduled to repair the faulty charging piles. The existing works mostly adopt traditional optimization methods for personnel scheduling, which cannot adapt to dynamic environments and suffers high computation complexity for large-scale problems. Our objective is to minimize the repairing time by reasonably scheduling maintenance workers. To this end, the optimization problem is first formulated as a partially observable Markov decision process (POMDP) under the constraints of workers’ repairing speed and their driving speed on the route. Then, different from existing research, we design a multi-agent proximal policy optimization (MAPPO)-based reinforcement learning algorithm to solve the optimization problem, which is more effective in complex and dynamic environments. By introducing the centralized training with decentralized execution framework, the workers acting as agents can determine the optimal maintenance route. In addition, action mask is also leveraged to improve training efficiency. Experiment results demonstrate that our proposed algorithm achieves better performance in terms of minimizing the maintenance time compared to other baselines.

关键词： Training Processor scheduling Heuristic algorithms Optimization methods Reinforcement learning Maintenance engineering Markov processes

来源：评论

学校读者我要写书评

暂无评论

Deployment of Scalable Cloud Based image processing Application Using Fuzzy Coupled Learning Technique

Deployment of Scalable Cloud Based Image Processing Applicat...

引用

International conference on Computational Science and Technology (ICCST)

作者： B. Mathivanan K.R. Nandhashree C. Radhakrishnan S. Ananthi P. Suganthi R. Asokan Department of CSE Sri Ramakrishna Engineering College Coimbatore Department of Cyber Security SRM Valliammai Engineering College Department of CSE Kongunadu College of Engineering and Technology Trichy Department of ECE Kongunadu College of Engineering and Technology Trichy

ISBN: (纸本)9781665476560

Because image processing typically uses a lot of memory and computational time, a sophisticated platform is needed. As a result, it's critical to adopt cost-effective solutions to replace outdated ones. We chose to use cloud computing to fulfill our needs for large-scale data processing as a result of these factors. In the meantime, this strategy offers quick access to on-demand services that are highly available and scalable. By outsourcing computations to a third party and utilizing cloud services rather than internal applications, healthcare organizations can reduce operating costs. However, robust data protection against both unauthorized users and unreliable clouds is required to avoid the disclosure of malicious data. Users can now assemble and execute their data using the cloud thanks to the development of numerous frameworks. distributed systems, cryptosystems, or a combination of the two are frequently used in their construction. Almost all current implementations use homomorphism cryptosystems, Service Oriented Architecture, secret share schemes, and secure multi-party computation as their primary security mechanisms. The main disadvantage of utilizing these techniques for large-scale data analysis on the cloud is the cost of computing image processing tasks. Keeping medical records & sensitive health-related information secure is a problem. We suggest a fresh method for protecting data processing in cloud environments that is based on machine learning methods. We typically employ Fuzzy C-means Clustering and Multi-Dense Convolution Neural Network to more accurately classify image pixels. To further reduce the danger of a possible leak of medical data, we add a third level, the CloudSaS-TPM module, to the conventional two-layered design. The results show some encouraging discoveries that provide new angles for creating cloud storage for the medical industry.

关键词： Training Cloud computing Costs Sensitivity Scientific computing Neural networks Service-oriented architecture

来源：评论

学校读者我要写书评

暂无评论

3DVSR: 3D EPI volume-based approach for angular and spatial light field image super-resolution

引用

SIGNAL processing 2022年 192卷 108373-108373页

作者： Trung-Hieu Tran Berberich, Jan Simon, Sven Univ Stuttgart Inst Parallel & Distributed Syst D-70569 Stuttgart Germany

Light field (LF) imaging, which captures both spatial and angular information of a scene, is undoubtedly beneficial to numerous applications. Although various techniques have been proposed for LF acquisition, achieving both angularly and spatially high-resolution LF remains a technology challenge. In this paper, a learning-based approach applied to 3D epipolar image (EPI) is proposed to reconstruct high-resolution LF. Through a 2-stage super-resolution framework, the proposed approach effectively addresses various LF super-resolution (SR) problems, i.e., spatial SR, angular SR, and angular-spatial SR. While the first stage provides flexible options to up-sample EPI volume to the desired resolution, the second stage, which consists of a novel EPI volume-based refinement network (EVRN), substantially enhances the quality of the high-resolution EPI volume. An extensive evaluation on 90 challenging synthetic and real-world light field scenes from 7 published datasets shows that the proposed approach outperforms state-of-the-art methods to a large extend for both spatial and angular super-resolution problem, i.e., an average peak signal to noise ratio improvement of more than 2.0 dB, 1.4 dB, and 3.14 dB in spatial SR x2, spatial SR x4, and angular SR respectively. The reconstructed 4D light field demonstrates a balanced performance distribution across all perspective images and presents superior visual quality compared to the previous works. (C) 2021 Elsevier B.V. All rights reserved.

关键词： 3D-EPI volume Angular super-resolution Deep learning Light field Spatial super-resolution

来源：评论

学校读者我要写书评

暂无评论

Analysis of Real-Time Hostile Activitiy Detection from Spatiotemporal Features Using Time distributed Deep CNNs, RNNs and Attention-Based Mechanisms

Analysis of Real-Time Hostile Activitiy Detection from Spati...

引用

International image processing, Applications and Systems conference (IPAS)

作者： Labib Ahmed Siddique Rabita Junhai Tanzim Reza Salman Sayeed Khan Tanvir Rahman Department of Computer Science and Engineering BRAC University Dhaka Bangladesh Department of Computer and Information Sciences College of Engineering University of Delaware

ISBN: (纸本)9781665462204

Real-time video surveillance, through CCTV camera systems has become essential for ensuring public safety which is a priority today. Although CCTV cameras help a lot in increasing security, these systems require constant human interaction and monitoring. To eradicate this issue, intelligent surveillance systems can be built using deep learning video classification techniques that can help us automate surveillance systems to detect violence as it happens. In this research, we explore deep learning video classification techniques to detect violence as they are happening. Traditional image classification techniques fall short when it comes to classifying videos as they attempt to classify each frame separately for which the predictions start to flicker. Therefore, many researchers are coming up with video classification techniques that consider spatiotemporal features while classifying. However, deploying these deep learning models with methods such as skeleton points obtained through pose estimation and optical flow obtained through depth sensors, are not always practical in an IoT environment. Although these techniques ensure a higher accuracy score, they are computationally heavier. Keeping these constraints in mind, we experimented with various video classification and action recognition techniques such as ConvLSTM, LRCN (with both custom CNN layers and VGG-16 as feature extractor) CNNTransformer and C3D. We achieved a test accuracy of 80% on ConvLSTM, 83.33% on CNN-BiLSTM, 70% on VGG16-BiLstm, 76.76% on CNN-Transformer and 80% on C3D.

关键词： Deep learning Streaming media Feature extraction Cameras Video surveillance Real-time systems Skeleton

来源：评论

学校读者我要写书评

暂无评论

Two-step Phase Synchronization Algorithm for distributed Collaborative Beamforming

Two-step Phase Synchronization Algorithm for Distributed Col...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Jianwen Xu Yi Yang Yang Yang Ling Zhang Jian Wang Jie Zhuang School of Information and Communication Engineering University of Electronic Science and Technology of China (UESTC) Chengdu China State Grid Xin Jiang Company Limited Electric Power Research Institute Precision Measurement Radar System Technology Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9781665446006

Beamforming technology is mainly applied to increase the energy utilization efficiency in wireless communication, and to enlarge signal transmission range via multiantenna technology. The beamforming technology presented in this paper is distributed collaborative beamforming (DCBF) technology, which is a branch of cooperative communication. In this paper, we propose a phase synchronization algorithm to achieve DCBF in a distributed array. The proposed algorithm consists of two steps. First, in order to improve the convergent speed of the phase alignment, we traverse all N possible initial phases of each node to determine a local optimum iteration point. Then we perform two-bit feedback iteration to ensure that the normalized received signal strength (NRSS) reaches the threshold of cooperative beamforming. Numerical results demonstrate that proposed algorithm offers better phase synchronization performance compared with the classical one-bit feedback method and two-bit feedback method.

关键词： Phased arrays Monte Carlo methods Array signal processing Perturbation methods image processing Cooperative communication conferences

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：