检索结果-内蒙古大学图书馆

Data-driven roughness estimation of additively manufactured samples using build angles

MANUFACTURING LETTERS 2024年 41卷 1092-1099页

作者： Galarza, Jose Barron, Jorge, Jr. Ahmed, Farid Li, Jianzhi Univ Texas Rio Grande Valley 1201 W Univ Dr Edinburg TX 78539 USA

Achieving control of Laser Powder Bed Fusion ( L-PBF) over the quality of the print is the main motivation for finding an optimum set of parameters in the process. Surface roughness is one of the characteristics of the print that impacts the performance of the desired functionality. This research focus is to relate the build angle with the surface roughness on the L-PBF printed specimens and utilize machine learning methods for roughness estimation of geometric features with varying build angles. The EOS M290 L-PBF printer was used to print Inconel-718 coupons using standard process parameters while varying build angles from 20 to 90 degrees at fixed 5-degree intervals. The specimens' surface was analyzed using metrology tools and the data obtained was used for training the machine learning models. Machine learning methods are used to create regression models for estimating the roughness of the specimens using the build angle and location of the sample on the substrate. The findings of this study provide build angle-based predictive estimation of surface roughness of printed L-PBF parts. The machine learning model will help to make reliable decisions on choosing the build angle of a complex part based on the desired surface roughness of its geometric features.

关键词： Additive manufacturing laser powder bed fusion surface roughness machine learning neural network

来源：评论

学校读者我要写书评

暂无评论

A Secure Deep Q-Reinforcement Learning Framework for network Intrusion Detection in IoT-Fog systems

A Secure Deep Q-Reinforcement Learning Framework for Network...

引用

2024 OPJU International Technology conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Bebortta, Sujit Tripathy, Subhranshu Sekhar Sharma, Vandana Behera, Jnana Ranjan Nayak, Aishwarya Ravenshaw University Department of Computer Science Cuttack753003 India Kiit Deemed to Be University School of Computer Engineering Bhubaneswar751024 India Department of Computational Sciences Delhi NCR Campus India Kiit Deemed to Be University School of Electronics Bhubaneswar751024 India Driems University Department of Computer Sceince & Engineering Cuttack74022 India

ISBN: (纸本)9798350373783

IoT-Fog system security depends on intrusion detection system (IDS) since the growing number of internet-of-Things (IoT) devices has increased the attack surface for cyber threats. The dynamic nature of cyberattacks often makes it difficult for traditional IDS techniques to stay up to date. Because it can adapt to changing threat landscapes, deep Q-reinforcement learning (DQRL) has become a potential technique for ID in IoT-Fog situations. In this paper, an IDS system for IoT-Fog networks based on DQRL is proposed. The suggested solution makes use of fog nodes' distributed computing power to provide real-time IDS with excellent accuracy and minimal latency. With feedback from the network environment, the DQRL agent learns to recognize and categorize network traffic patterns as either normal or intrusive. Adaptive exploration techniques, effective reward functions, and deep neural networks for feature extraction are adopted by the system to improve predictive performance. The evaluation findings show that, in terms of detection accuracy, precision, recall and f-measure, the proposed DQRL provides flexibility to changing threat patterns as compared to conventional IDS techniques. A vast array of cyberattacks, such as malware infections, denial-of-service (DoS) attacks, and command-and-control communications, are successfully recognized and categorized by the system. It is possible that the suggested solution will be crucial in safeguarding IoT-Fog networks and preventing cyberattacks © 2024 IEEE.

关键词： network intrusion

来源：评论

学校读者我要写书评

暂无评论

DASH rate control using game theory to consider user video preference 36

DASH rate control using game theory to consider user video p...

引用

36th International conference on Information networking (ICOIN)

作者： Yanagisawa, Takumi Miyata, Sumiko Shibaura Inst Technol Koto Ku Toyosu 3-7-5 Tokyo 1350061 Japan

ISBN: (纸本)9781665413329

Dynamic adaptive streaming over HTTP (DASH) is the most widespread internet video delivery service system. In DASH, a bitrate is selected dynamically to appropriately share the bandwidth of the server among multiple users. While most of the existing rate-selection methods have been based on improving quality of service (QoS), quality of experience (QoE) methods that express user satisfaction with the quality of video content have been attracting the attention of service providers and network providers. In addition, some studies show that user preference affects QoE. Therefore, we both propose and demonstrate the effectiveness of a rate-selection method based on game theory that considers user preference for video streaming.

关键词： Adaptive systems Bit rate quality of service Bandwidth Streaming media quality of experience Servers

来源：评论

学校读者我要写书评

暂无评论

Multi-agent Reinforcement Learning for Energy Saving in Multi-Cell Massive MIMO systems 1

Multi-agent Reinforcement Learning for Energy Saving in Mult...

引用

1st IEEE International conference on Machine Learning for Communication and networking (IEEE ICMLCN)

作者： Cai, Tianzhang Wang, Qichen Zhang, Shuai Demir, Ozlem Tugfe Cavdar, Cicek KTH Royal Inst Technol Dept Comp Sci Stockholm Sweden TOBB ETU Dept Elect Engn Ankara Turkiye

ISBN: (纸本)9798350343205;9798350343199

We develop a multi-agent reinforcement learning (MARL) algorithm to minimize the total energy consumption of multiple massive MIMO (multiple-input multiple-output) base stations (BSs) in a multi-cell network while preserving the overall quality-of-service (QoS) by making decisions on the multi-level advanced sleep modes (ASMs) and antenna switching of these BSs. The problem is modeled as a decentralized partially observable Markov decision process (DEC-POMDP) to enable collaboration between individual BSs, which is necessary to tackle inter-cell interference. A multi-agent proximal policy optimization (MAPPO) algorithm is designed to learn a collaborative BS control policy. To enhance its scalability, a modified version called MAPPO-neighbor policy is further proposed. Simulation results demonstrate that the trained MAPPO agent achieves better performance compared to baseline policies. Specifically, compared to the auto sleep mode 1 (symbol-level sleeping) algorithm, the MAPPO-neighbor policy reduces power consumption by approximately 8.7% during low-traffic hours and improves energy efficiency by approximately 19% during high-traffic hours, respectively.

关键词： BS control for energy saving antenna switching massive MIMO multi-agent reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on Deterministic Communication Model for Industrial internet Based on OPC UA-TSN 5

Research on Deterministic Communication Model for Industrial...

引用

5th International conference on Information Technologies and Electrical Engineering, ICITEE 2022

作者： Chai, Anying Zhu, Hao Xue, Qiang Li, Mingshi Ma, Xian Wang, Shiyu Liaoning Branch of China Academy of Industrial Lnternet China Academy of Industrial Internet Shenyang China Institute of Standardization Technology China Academy of Industrial Internet Beijing China Institute of Software China Industrial Control Systems Cyber Emergency Response Team Beijing China Liaoning Branch of China Academy of Industrial Internet China Academy of Industrial Internet Beijing China Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781450396806

The Industrial internet accelerates the network integration and collaborative communication of IT and OT, and has become the critical technical support for smart factories. Using OPC UA as the industrial network communication infrastructure can realize the interconnection and intercommunication of heterogeneous network devices, breaking information islands and data barriers. However, with the diversification of industrial data types and the continuous increase of data volume, the single communication mode based on OPC UA has poor performance in real-time data transmission and high network delay. It is difficult to meet high real-time and high reliability requirements. Aiming at the above problems, this paper proposes a deterministic communication model for Industrial internet based on OPC UA-TSN. Integrate the two communication architectures of OPC UA and TSN, and use OPC UA as the communication specification for heterogeneous network devices to realize the interconnection and intercommunication of the underlying industrial network. We use TSN to replace traditional industrial Ethernet as the network data transmission medium to ensure the deterministic transmission of time-sensitive data. In addition, an OPC UA-TSN message mapping method and an OPC UA-TSN network configuration scheme are constructed to realize the intercommunication between OPC UA and TSN. At the same time, we propose a frame-preemptive dynamic scheduling algorithm for TSN (FPDS), which reasonably allocates bandwidth resources to each priority data stream. The experimental results show that this model realizes the network communication between OPC UA and TSN. It can schedule different types of data streams, effectively reducing the transmission delay of time-sensitive data. This model ensures the efficient utilization of TSN queues and improves the quality of service level of the smart factory communication network. © 2022 ACM.

关键词： Heterogeneous networks

来源：评论

学校读者我要写书评

暂无评论

Transmission control and Optimization in Next-generation Hybrid Wireless networks: An Online Reinforcement Learning Approach 15

Transmission Control and Optimization in Next-generation Hyb...

引用

conference on Sensors and systems for Space Applications XV

作者： Dinha, Son Liu, Hang Zhao, Qi Li, Yi DeCortec, Nicholas Chen, Genshe Catholic Univ Amer Washington DC 20064 USA Intelligent Fus Technol Inc Germantown MD 20876 USA US Army Combat Capabil Dev Orlando FL 32826 USA

ISBN: (纸本)9781510651197;9781510651180

Next-generation (5G & beyond) cellular networks promise much higher throughput and lower latency. However, mobile users experiencing poor channel quality not only suffer low data-rate connections with the base station but also reduce cell's aggregate throughput and increase overall delay. In this paper, we consider a hybrid cellular and mobile ad hoc Device-to-Device (D2D) network that leverages the advantages of both wide-area cellular coverage and high-speed ad hoc D2D relaying to enhance network performance and scalability. Dedicated relay devices, such as Unmanned Aerial Vehicles (UAVs)/drones, can also be deployed to further improve network connectivity and thus throughput. The base station may send the packets destined for a mobile user with poor cellular channel quality to a proxy mobile device with better cellular channel quality. The proxy mobile device will relay the packets to the destination, thereby significanltly improving network throughput and delay. We formulate the data transmission problem and design an online reinforcement learning-based algorithm to achieve the best transmission performance.

关键词： HyNet Massive MIMO Transmission control

来源：评论

学校读者我要写书评

暂无评论

Design of network Data Monitoring and control System Based on internet of Things Technology

Design of Network Data Monitoring and Control System Based o...

引用

Integrated Circuits and Communication systems (ICICACS), IEEE International conference on

作者： Xiaolu Zhang Wuqiang Shen Lei Cui Guangdong Power Grid Guangdong China

This article is supported by wireless sensing technology, wireless communication technology, and software development technology of the internet of Things. A power quality monitoring system based on the internet of Things is proposed, and comprehensive evaluation of power quality is studied. A power quality data collection platform is constructed, and a new type of internet of Things transmission technology is used to achieve multi-point collection of power quality data, The reliable transmission and efficient processing of power quality information have been achieved using TCP/IP wireless communication technology and middleware technology. The results indicate that an indicator measurement evaluation matrix is established to determine the comprehensive weight of power quality evaluation indicators, overcome the one-sidedness of a single weighting method, and make the evaluation results more scientific and accurate by comparing the advantages and disadvantages of different comprehensive evaluation methods in order to improve the accuracy of evaluation methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Smart Helmet for Air quality and Harmful Event Finding for the Mining Industry 2

Machine Learning-based Smart Helmet for Air Quality and Harm...

引用

2nd International conference on Automation, Computing and Renewable systems, ICACRS 2023

作者： Tamilselvan Gunavathi, S. Muthusamy, M. Anithdharsan, S. Department of ECE Kalaignarkarunanidhi Institute of Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9798350340235

The protection of the mines below ground must be enhanced since catastrophes in subterranean mines are extremely major concerns these days. The problems experienced by miners operating underground include gas explosion, temperatures, etc. If any tragedy happens in mine or any miner is wounded, all the guilt immediately falls on supervisor. So there must be interaction among miners, supervisors and control station. Therefore, the goal of the proposed system is to alter a current mining safety. Helmet represents a piece of the safety equipment miner should wear when mining. The idea is for making the helmet more secure by adding network. This added system is used to sense the circumstances around the miner employed underground and all of real-time values are wirelessly current on the internet through the IoT so that control stations get to know the specific environmental circumstances in which miner employed and if any unusual events occur they are able to offer rescue as quickly as possible. The device also contains the LCD and siren to let fellow workers know when any unpleasant occurrence happens with miner. The suggested system employs multiple sensors as Gas Sensor, DHT11 Sensors, accelerometer, vibrations and IR Sensor. Here the IR sensors is employed as helmet removal sensor. And additionally in this system we utilize machine learning to analyze the employee health, Cardiovascular disease is one of the primary ailments impacting the people throughout the globe. There are various risk factors which contribute to heart disease. The combined use of logistic regression modeling with neural network gives a revolutionary strategy for forecasting the heart disease. Initially a logistic regression analysis is done to find the primary risk variables for predicting the illness. It generates the significant risk variables that are beneficial for forecasting cardiovascular disease according to statistical p-value. The threat variables those aren't taking the substantial ef

关键词： Accelerometer Cardiovascular dht11 Sensors internet of Things

来源：评论

学校读者我要写书评

暂无评论

Deep Neural network based Secured control of Flying Vehicle in Urban Environment 2

Deep Neural Network based Secured Control of Flying Vehicle ...

引用

2nd IEEE International conference on Smart systems and Emerging Technologies (SMARTTECH)

作者： Zaidi, Adeel Kazim, Muhammad Zhang, Lixian Azar, Ahmad Taher Koubaa, Anis Benjdira, Bilel Ammar, Adel Abdelkader, Mohammad Harbin Inst Technol Res Inst Intelligent Control & Syst Harbin 150080 Peoples R China Prince Sultan Univ Coliege Comp & Informat Sci Riyadh Saudi Arabia Benha Univ Fac Comp & Artificial Intelligence Banha Egypt Prince Sultan Univ Robot & Internet Of Things Lab RIOTU Riyadh Saudi Arabia

ISBN: (数字)9781665409735

ISBN: (纸本)9781665409735

Aerial transport for daily inter- and intra-urban passenger mobility has been a human dream for decades ago. Now, the dream is near to be realized after the great technological advances achieved recently. As urban populations' size increases, traffic congestion and air pollution remain major threats to economic growth. However, questions concerning safe and secure autonomous flying vehicles remain to be answered, especially in a highly dynamic environment. This research paper presents a Deep Neural network (DNN) algorithm as an additional component that avoids obstacles and increases the tracking efficiency of Cascaded Proportional Integral Derivative with Feed Forward (PID+FF) controller for flying vehicles. In the current paper, we introduce KaNET: a convolution neural network designed to safely drive and improve tracking performance. Simultaneously, cascaded PID+FF algorithms are applied to regulate the attitude/altitude of a flying vehicle. To ensure a safe and secure flight in a dynamic environment, the proposed KaNET generates two outputs for each input image. The first output is the probability of a collision allowing the flying vehicle to recognize and react quickly to hazardous situations. The second output represents a steering angle that helps the vehicle to keep flying and avoiding obstacles. The cascaded PID+FF is used to control and maintain the desired position and orientation of the flying vehicle. Results have shown that the proposed approach improves tracking accuracy and avoids obstacles in highly dynamic environments.

关键词： Flying vehicle Fixed wing Quadrotor Deep Neural network control

来源：评论

学校读者我要写书评

暂无评论

Development and assessment of an IoT system for monitoring air and soil quality in the agricultural sector 36

Development and assessment of an IoT system for monitoring a...

引用

36th International conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy systems, ECOS 2023

作者： Gomes, Pedro R. Nicolau, António Ferreira, Ana Cristina Ramos, Bruna Ferreira, João Costa, José Santos, Filipe Santos, Eduardo Teixeira, Gonçalo COMEGI Universidade Lusíada Portugal CITAD Universidade Lusíada Portugal MEtRICs and ALGORITMI Universityof Minho Guimarães Portugal ALGORITMI Universityof Minho Guimarães Portugal

ISBN: (纸本)9781713874928

Currently, there is a set of variables that directly and indirectly influence the level and quality of life of human beings. Climate change, pandemic situations and wars raise questions about their survival. Thus, the development of systems allowing efficient monitoring of the surrounding environment seems appropriate. In this sense, since the agricultural sector is a pillar of modern societies, the application of technologies such as IoT (internet of Things), for its sustainable development is the motivation for this multidisciplinary work. The work carried out uses emerging technologies, wireless communication networks, alternative energy sources, control systems and friendly human-machine interfaces. Communication between the devices uses LoRa (Long Range) technology due to its low consumption. Depending on the location to be monitored, alternative sources of energy, solar and hydropower, are selected individually, using an algorithm that monitors the power available at each instant. Data acquired such as temperature and humidity by several network nodes (peripheral towers), communicate to a gateway (main tower). These data are stored, treated statistically, and presented in a user-friendly application for different users. The system was installed in an urban vegetable garden in the Vila Nova de Famalicão municipality. After its operational validation, the temperatures and humidity values were registered. In conclusion, the developed system is low cost, autonomous, modular, flexible, has a low energy consumption and uses alternative energies, allowing the optimization of techniques and types of cultivation. © (2023) by ECOS 2023 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

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：