检索结果-内蒙古大学图书馆

LEM: a Tool for Large-Scale Workflow Control in Edge-Based Industry 5.0 Applications 19

LEM: a Tool for Large-Scale Workflow Control in Edge-Based I...

19th Annual International Conference on Distributed computing in Smart systems and the Internet of Things, DCOSS-IoT 2023

作者： Reis, Rui Santos, Pedro M. Sousa, Mario J. Martins, Nuno Sousa, Joana Almeida, Luis Universidade Do Porto Faculdade de Engenharia Portugal Portugal Cister Research Center in Real-Time and Embedded Computing Systems Portugal

ISBN: (纸本)9798350346497

Edge computing is poised to greatly boost Industry 5.0 by providing a computing substrate that can run highly specialized applications with minimal latency, reducing the requirements on computational resources at the end-user and allowing the sharing of resources between multiple end-users. The intended services and workflows need to be designed, configured and deployed at target edge devices, and during operation their status needs to be monitored. There are several industrial frameworks that provide such functionalities, but often there is little support to execute them simultaneously over many target devices. In this paper we present the LEM tool, a tool that enables the management (monitor, configure, deploy) of workflows in a large number of edge devices. The tool connects to existing industrial frameworks to provide these functionalities, abstracting the low level configuration aspects of each framework and enabling simultaneous configuration of multiple devices, a feature that many frameworks do not support. The tool offers a web-based GUI that allows the infrastructure manager to conveniently check the status of all devices and flows running in each device, deploy new flows on selected devices, and start and stop flows. Experimental measurements show residual response time overhead as the number of devices increases. © 2023 IEEE.

关键词： edge Industry5.0 Node-RED workflow

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study on Genetic Algorithm for 2D Path Planning of Unmanned Aerial Vehicles with Obstacle Avoidance 23

An Empirical Study on Genetic Algorithm for 2D Path Planning...

引用

2023 International Conference on Computer, Vision and Intelligent Technology, ICCVIT 2023

作者： Zhao, Ya-Hong Lan, Yu-Lin Li, Shang-Lin Zhang, Wen-Fen School of Computer and Artificial Intelligence Xiangnan University China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Chenzhou China

ISBN: (纸本)9798400708701

Unmanned aerial vehicle (UAV), with high efficiency, low manpower costs, and flexible convenience, has attracted widespread attention in logistics. UAV trajectory planning is an essential component in this context. Genetic algorithm(GA) is an effective tool for solving complex route optimization problems. However, selecting the optimal combination of parameters for UAV path planning remains a challenging problem, especially in complex urban environments with numerous obstacles. This paper proposes a genetic algorithm-based UAV path planning approach(UAV_GA) that considers obstacle avoidance on a two-dimensional grid-based map. Furthermore, to investigate the general patterns in selecting parameters for GA in such problems, a comprehensive empirical study is conducted. The study analyzes the effects of population size, number of iterations, crossover, and mutation probabilities on algorithm performance. It aims to identify universal patterns for optimal parameter combinations and provide guidance for parameter selection in GA for UAV trajectory planning with obstacle avoidance. © 2023 ACM.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Comparing Performance of Machine Learning Tools Across computing Platforms 18

Comparing Performance of Machine Learning Tools Across Compu...

引用

18th Conference on Computer Science and Intelligence systems, FedCSIS 2023

作者： Vicente, Pedro Santos, Pedro M. Asulba, Barikisu Martins, Nuno Sousa, Joana Almeida, Luis Portugal Universidade Do Porto Faculdade de Engenharia Portugal Cister Research Center in Real-Time and Embedded Computing Systems Portugal Nos Inovacao Portugal

ISBN: (纸本)9788396744784

embedded systems (ES) are wide-spread in our world and responsible for many critical systems. More recently, machine learning (ML) tools have become a well-established solution for data-intensive tasks, but their application in embedded systems is still gaining traction and their real-time performance is often unclear. We provide a (non-extensive) review of the ML tools that may be suited for deployment in ES, from which we selected two representative tools - the well-established Python-based Scikit-Learn, and the interoperability-oriented ONNX Runtime - to compare their response time. Using archetypal datasets and four pre-trained ML models, we measure the prediction time for each sample, for each model, in Scikit-Learn and ONNX Runtime in a standard desktop (to compare performance of the tools in the same platform), and for ONNX Runtime in a representative ES, a Raspberry Pi v4 (to compare performance of the same tool across platforms). We report that ONNX considerably improves over Scikit-Learn, and experiences a negligible performance degradation when ported to the RPi. © 2023 Polish Information Processing Society.

关键词： embedded systems

来源：评论

学校读者我要写书评

暂无评论

IoT monitoring and control system of Distribution Transformers in Rwanda 23

IoT monitoring and control system of Distribution Transforme...

引用

12th International Conference on Software and Computer Applications, ICSCA 2023

作者： Bimenyimana, Emmanuel Nsengiyumva, Philibert Ngoga, Said R. University of Rwanda College of Science and Technology African center of Excellency in Internet of Things Embedded Computing Systems Rwanda University of Rwanda College of Science and Technology Rwanda

ISBN: (纸本)9781450398589

In developing countries, many customers do not get good quality of electricity power supply due to frequent and prolonged power fluctuations/cuts. Distribution transformer (DT) is a service transformer that provides the final voltage transformation in the electric power distribution system, stepping down the voltage to the level used by the customers. Monitoring and control of DT (as a crucial and expensive asset in the network) is a key enabler of power stability to consumers. A power utility is said to be a business oriented with good image representation if it delivers a reliable and affordable electricity. Modern technologies such as the Internet of Things (IoT) offer a wide range of applications in the energy sector to smoothly monitor, control and optimize processes. Currently, many energy companies in developing countries are not yet implementing the remote system to control and monitor the secondary side of DTs and timely get the notifications of fluctuations/abnormalities occurred on those DTs. That is why it is still challenging and time consuming to intervene urgently and do the necessary actions to prevent severe and prolonged power cuts/fluctuations and safeguard the damage of DTs themselves with customer’s appliances connected on those DTs. The secondary side of DT is the one connected directly and supply power to the customers. For this reason, we developed an affordable IoT system that automatically detects the abnormalities/fluctuations of three core technical parameters of DT (which are voltage, current and temperature) using current sensors, voltage sensors, and temperature sensor with ATmega 328P Microcontroller to collect and process data from sensors connected to DT system. Once one or all of those technical parameters become abnormal, the system cut off automatically the secondary side of DT in 2 seconds to isolate and protect the customers’ load with safeguarding DT itself using a power relay. At the same time, GSM/GPRS module uploads the sen

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Research into Curriculum Construction Platform of Computer Major Based on Intelligent Algorithm 12th

Research into Curriculum Construction Platform of Computer M...

引用

12th International Conference on Frontier computing, FC 2022

作者： Xie, Hui Wei, Li School of Computer and Artificial Intelligence Xiangnan University Hunan Chenzhou China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou China

ISBN: (纸本)9789819914272

Under the development background of educational curriculum reform, personalized curriculum design has become the key content of current reform of the computer major. In this context, this research carries out a design of a curriculum construction platform for the computer major based on intelligent algorithm. Through the user curriculum design module and personalized curriculum design optimization module design, the technological innovation of computer related discipline curriculum construction is realized. Based on the data collected of teachers and students’ subject behaviors and combined with data modeling, intelligent algorithms and other means, it is possible to realize the differentiated construction of subject curriculums and the purpose of personalized education. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Research on key technologies and application value of private cloud security cloud management platform 6

Research on key technologies and application value of privat...

引用

6th International Conference on Intelligent computing, Communication, and Devices, ICCD 2023

作者： Min, Xiao Mei, Guo School of Computer and Artificial Intelligence XiangNan University HuNan ChenZhou423000 China Advanced Embedded Computing and Intelligent Medical Systems Hunan Engineering Research Center HuNan ChenZhou423000 China

ISBN: (数字)9781510666269

ISBN: (纸本)9781510666252

Nowadays, with the rapid development and popularization of informatization and intelligence, "cloud computing service"is also born. Among them, "private cloud"is an important part of "cloud computing services". This is also known as the "internal cloud"or "corporate cloud"and plays an important role in the realization of information management within the enterprise. By studying the overall architecture of private cloud security management platform, this paper studies the key technologies of cloud security management platform and the application value of cloud security management platform. It can provide more flexible security solutions for governments and enterprises and provide better security for computer networks. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Research on Target Localization of Automatic Picking Robot for Rock Sugar Orange 23

Research on Target Localization of Automatic Picking Robot f...

引用

2023 International Conference on Computer, Vision and Intelligent Technology, ICCVIT 2023

作者： Guo, Yuchen Liu, Dong Li, Qingbo Jiang, Hang Peng, Taomo Zeng, Xiongjian Liu, Ailin School of Computer and Artificial Intelligence Xiangnan University Chenzhou423000 China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou423000 China

ISBN: (纸本)9798400708701

In the production process of rock sugar oranges, picking is the most labor-intensive step. Intelligent replacement of traditional manual labor, timely and rapid picking of rock sugar oranges, improving fruit picking quality, is of great significance for expanding the rock sugar orange market. How to effectively recognize and locate rock sugar oranges is a key technology in machine vision in the research of automatic picking robots. A rock sugar orange positioning method is proposed. Firstly, the rock sugar orange image is preprocessed, binarized using Otsu adaptive threshold segmentation, and the positioning parameters and radius of the rock sugar orange are obtained using Hough transform. The K-means clustering pattern classification method is used to classify different circles, and the clustering results are corrected using a circle parameter correction model. © 2023 ACM.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Flow Early Warning System Based on WiFi Probe

Pedestrian Flow Early Warning System Based on WiFi Probe

引用

International Conference on Internet of Things, Communication and Intelligent Technology, IoTCIT 2022

作者： Wang, Yichan Ouyang, Hongbo Duan, Yun Xiangnan University Hunan Chenzhou423000 China Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Chenzhou China China Post Group Co. Ltd Hunan Chenzhou423000 China

ISBN: (纸本)9789819904150

With the social development and the increasing population, the person flowrate increases year by year in various public places, such as stations、hospitals and shopping malls;in different periods of time, the person flowrate will appears different data values in such places. Therefore, the monitoring of person flowrate data is very important, as an important indicator of regional public health events. The unique MAC address of the customer's mobile phone could be collected by WiFi probe for the unique identification, through data analysis technology it can provide a certain degree of data decision-making basis for decision-makers. Data analysis based on the collected by WiFi probe, break the traditional mode, provide reliable person flowrate analysis, use the extended management ability to deeply understand and provide real flow information, provide effective support for hierarchical early warning of public health events. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Probes

来源：评论

学校读者我要写书评

暂无评论

Multi-food source differential salp swarm algorithm 23

Multi-food source differential salp swarm algorithm

引用

2023 International Conference on Computer, Vision and Intelligent Technology, ICCVIT 2023

作者： Lin, Anping Shi, Yaoting Zhang, Wenfen Liu, Dong Lan, Yulin School of Physics and Electronic Electrical Engineering Xiangnan University Chenzhou423000 China School of Computer and Artificial Intelligence Hunan Engineering Research Center of Advanced Embedded Computing and Intelligent Medical Systems Xiangnan University Chenzhou China

ISBN: (纸本)9798400708701

Salp swarm algorithm (SSA) divides the population into leaders and followers, and employs two different search methods to achieve steady convergence. However, the search methods adopted by SSA are relatively simple, hence SSA always trapped by local optima on complex multimodal problems. To improve the exploration of SSA, this paper proposes a multi-food source differential salp swarm algorithm (MFD-SSA) by transferring multi-leader mechanism and differential mutation strategy into SSA. MFD-SSA regards a portion of high fitness individuals as food sources and employ them for updating the position of leaders, the differential evolution mutation and the chaotic crossover are adopted to enhance swarm diversity. Then, the differential mutation and crossover operator are employed for enlarging search range. The MFD-SSA is tested on CEC2017 test suite and compared with five SSA variants and five other meta-heuristics. The test results indicate that MFD-SSA bears strong exploration, it outperforms five SSA variants and five meta-heuristics. On Planetary gear train design problem, MFD-SSA performs better than other five SSA variants too. © 2023 ACM.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Integrating digital twins and deep learning for medical image analysis in the era of COVID-19

引用

Virtual Reality & Intelligent Hardware 2022年第4期4卷 292-305页

作者： Imran AHMED Misbah AHMAD Gwanggil JEON School of Computing and Information Science Faculty of Science and EngineeringAnglia Ruskin UniversityEast RoadCambridgeEnglandUK Center of Excellence in IT Institute of Management SciencesHayatabadPeshawarPakistan Department of Embedded Systems Engineering Incheon National UniversityIncheonKorea

Background Digital twins are virtual representations of devices and processes that capture the physical properties of the environment and operational algorithms/techniques in the context of medical devices and *** twins may allow healthcare organizations to determine methods of improving medical processes,enhancing patient experience,lowering operating expenses,and extending the value of *** the present COVID-19 pandemic,various medical devices,such as X-rays and CT scan machines and processes,are constantly being used to collect and analyze medical *** collecting and processing an extensive volume of data in the form of images,machines and processes sometimes suffer from system failures,creating critical issues for hospitals and *** To address this,we introduce a digital-twin-based smart healthcare system in-tegrated with medical devices to collect information regarding the current health condition,configuration,and maintenance history of the device/machine/***,medical images,that is,X-rays,are analyzed by using a deep-learning model to detect the infection of *** designed system is based on the cascade recurrent convolution neural network(RCNN)*** this architecture,the detector stages are deeper and more sequentially selective against small and close false *** architecture is a multi-stage extension of the RCNN model and sequentially trained using the output of one stage for training the *** each stage,the bounding boxes are adjusted to locate a suitable value of the nearest false positives during the training of the different *** this manner,the arrangement of detectors is adjusted to increase the intersection over union,overcoming the problem of *** train the model by using X-ray images as the model was previously trained on another *** The developed system achieves good accuracy during the detection phase of *** experimental o

关键词： Digital twins Deep learning Healthcare COVID-19 Chest X-rays Artificial intelligence

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：