检索结果-内蒙古大学图书馆

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIS 2024

作者： Chaganti, Koushik Reddy Kumar, B. Naveen Gutta, Pruthvi Krishna Elicherla, Sivananda Lahari Reddy Nagesh, C. Raghavendar, K. University of the Cumberlands Dept. of Computer and Information Systems KY United States Vignan Institute of Technology and Science Department of Information Technology Hyderabad India Tesla Dept of It AustinTX United States Dayananda Sagar University Dept of Cse Bangalore India Srinivasa Ramanujan Institute of Technology Dept of Cse Anantapur India Teegala Krishna Reddy Engineering College Dept of Cse Hyderabad India

ISBN: (纸本)9798331529635

The management of food supply chains relates to just about the most imperative issues concerning sustainability, quality, and traceability, where existing methodologies usually fail to meet the demands caused by data privacy, lack of transparency, and inefficiencies concerning collaboration among stakeholders. This compromises data security, and thus there arises single points of failure. Conversely, traditional traceability frameworks fail to incite wide-scale participation and lack real-time accuracy. Having these limitations in mind, we introduce a hybrid framework consisting of three advanced methodologies: Decentralized Federated Learning with Blockchain Anchoring (DFLBA), Dynamic Tokenized Traceability Framework (DTTF), and Adaptive Supply Chain Graph Neural Networks (ASCGNN) process. DFLBA would support privacy-preserving machine learning as such that collaborative training of yield prediction and crop monitoring models by stakeholders without revealing raw data will be feasible. Blockchain anchoring ensures logs of training updates are tamper-proof, thus increasing trust and transparency. DTTF introduces tokenized incentives that enhance traceability in real-time: every product has a digital twin represented by blockchain-anchored tokens updated by stakeholders. Smart contracts enforce the compliance that will improve participation and lifecycle data accuracy. ASCGNN models the food supply chain as a dynamic graph, leveraging graph neural networks to capture stakeholder interdependencies, optimize operations, and detect fraud. Blockchain integration ensures reliability and transparency by securing edge weights. The suggested framework has demonstrated good impact, like 95% model accuracy for yield prediction, 99% traceability coverage, and 92% prediction accuracy for bottlenecks of the supply chain. It provides a scalable, privacy-preserving, and transparent solution that enhances the efficiency of food supply chains, and positively impacts stakeholders in a

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Technique to Parameterize Congestion Control in 6TiSCH IIoT Networks

arXiv

引用

arXiv 2024年

作者： Chakraborty, Kushal Dutta, Aritra Kumar Hussain, Mohammad Avesh Mohiuddin, Syed Raafay Choudhury, Nikumani Matam, Rakesh Mukherjee, Mithun Dept. of Computer Science & Information Systems Birla Institute of Technology & Science Hyderabad Pilani India Dept. of Computer Science & Engineering Indian Institute of Information Technology Guwahati India Nanjing University of Information Science and Technology Nanjing China

The Industrial Internet of Things (IIoT) refers to the use of interconnected smart devices, sensors, and other technologies to create a network of intelligent systems that can monitor and manage industrial processes. 6TiSCH (IPv6 over the Time Slotted Channel Hopping mode of IEEE 802.15.4e) as an enabling technology facilitates low-power and low-latency communication between IoT devices in industrial environments. The Routing Protocol for Low power and lossy networks (RPL), which is used as the de-facto routing protocol for 6TiSCH networks is observed to suffer from several limitations, especially during congestion in the network. Therefore, there is an immediate need for some modifications to the RPL to deal with this problem. Under traffic load which keeps on changing continuously at different instants of time, the proposed mechanism aims at finding the appropriate parent for a node that can forward the packet to the destination through the least congested path with minimal packet loss. This facilitates congestion management under dynamic traffic loads. For this, a new metric for routing using the concept of exponential weighting has been proposed, which takes the number of packets present in the queue of the node into account when choosing the parent at a particular instance of time. Additionally, the paper proposes a parent selection and swapping mechanism for congested networks. Performance evaluations are carried out in order to validate the proposed work. The results show an improvement in the performance of RPL under heavy and dynamic traffic loads. © 2024, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Improvement of Protection Factor for a Controlled Laboratory computer Network Using Artificial Intelligence

Improvement of Protection Factor for a Controlled Laboratory...

引用

engineering, Science and Advanced Technology (ICESAT), International Conference on

作者： Raid W. Daoud Enas F. Aziz Zaki M. Abdullah Ziyaad H. Saleh Electrical Tech. Dept. Northern Technical University Kirkuk Iraq Computer Systems Dept. Northern Technical University Kirkuk Iraq Petroleum Systems and Control Dept. College of Petroleum Processes Engineering Tikrit Iraq

computer networks provide exceptional privacy, primarily for testing and other educational activities. However, the security of computer networks is an exceptionally touchy subject, mainly when applied in labs and tests for educational purposes. Any software system created on a server typically requires a username and password to access a collection of computers on a particular network. The proposed work devised and implemented a neural network feedback network with four inputs (I.P. address, MAC address, user number, and time) and an output that represents the user's acceptance or rejection. A few instances of the data and numbers needed to train the neural network include the lab's address, the student's name, the academic stage's address, etc. Good results were obtained through the company's training and education, which was tested on more than 200 models, and the response aligned with the data. No user can access the network without first being recognized by the proposed network by comparing the pre-trained data to ensure they are authorized to take the exam or enter for any other reason.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study of the Influence of Rolling Modes on the Operation of Interconnected Electric Drives of a Rolling Mill 4

Study of the Influence of Rolling Modes on the Operation of ...

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Tytiuk, Valerii Busher, Victor Kalinin, Alexey Chornyi, Oleksii Druzhinin, Valeriy Halushko, Dmytro Department of Electromechanics Kryvyi Rih National University Kryvyi Rih Ukraine Dept. of Electrical Engineering and Electronics National University "Odessa Maritime Academy" Odessa Ukraine Department of Informative computer systems Abylkas Saginov Karaganda Technical University NPJSC Karaganda Kazakhstan Institute of Electromechanics Energy Saving and Automatic Control Systems Kremenchuk Mykhailo Ostrogradskyi National University Kremenchuk Ukraine Department of Power Engineering Karaganda Industrial University NPJSC Temirtau Kazakhstan Dept. of Electrical Engineering Ukrainian State University of Science and Technologies Dnipro Ukraine

ISBN: (纸本)9798350395532

The paper is devoted to study of the influence of rolling modes on the performance of powerful interconnected electric drives of a hot rolling mill under the action of an electromagnetic coupling circuit between the electric drives of the roughing and finishing groups. The action of the electromagnetic coupling circuit manifests itself in the form of the influence of impact loads of synchronous electric drives on the angular velocity of direct current electric drives of the finishing group of the mill. The parameters of the electromagnetic coupling circuit are determined by the power supply scheme and equipment parameters. Values of impact loads applied to a synchronous motor depend on the rolling process parameters, in particular, the chemical composition of the rolled steel and the temperature of the ingot. The paper presents the results of calculating the rolling power for various rolling mode parameters. Using mathematical modeling in Simulink, numerical estimates of the influence of rolling modes on the magnitude of the voltage drop in the power supply unit and the drop in the angular velocity of the electric drive of the finishing group were obtained on the example of a wide-strip hot rolling mill 1700 of ArcelorMittal Temirtau JSC. © 2023 IEEE.

关键词： Hot rolling

来源：评论

学校读者我要写书评

暂无评论

Jumping behavior Analysis after Identification of Daycare Children's Activities utilizing YOLOv8 Algorithm

Jumping behavior Analysis after Identification of Daycare Ch...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Tiya Bisla Ritik Shukla Mansi Dhawan Md. Rahatul Islam Keiichi Horio Dept. of Computer Science & Engineering Dronacharya Group of Institutions Greater Noida India Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology Fukuoka Japan

ISBN: (数字)9798350385922

ISBN: (纸本)9798350385939

Monitoring human activities to ensure the safety and welfare of humans is essential in the present age of mindfulness. Human Activity Recognition (HAR) offers a technical method to detect and identify human actions in real-time. We used YOLOv8s, a deep learning system, to recognize a kindergartener's behaviors and positions. After recognizing the student's movements, an assessment determines jumps per second and jump duration. We utilized our dataset, named Kid Action Recognition (KAR). The KAR (Kid Action Recognition) dataset consisted of 6489 photos. We manually labeled all photos using ***. We analyzed and trained the data in a Google Colaboratory setting with an A-100 GPU. The model demonstrates an overall accuracy of 88.7% and an F1 score of 86.6%. The recall score is 89.5%, and the precision is 83.9%. The model excelled in all parameters and can effectively identify student activities, making it suitable for potential use in institutions such as daycare centers and schools.

关键词： Training Obesity Accuracy Prevention and mitigation Graphics processing units Real-time systems Internet

来源：评论

学校读者我要写书评

暂无评论

AutoMediVision:A Deep Learning System for Accurate Pharmaceutical pill identification

AutoMediVision:A Deep Learning System for Accurate Pharmaceu...

引用

Data Science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： G Rajeswarappa B. Venkata Sivaiah M. Navya Y. Lasya Shaik Mohammad Sameer V. Varun Kumar Department of CSE G Pulla Reddy Engineering College Kurnool Dept. of Data Science School of Computing Mohan Babu University (Erstwhile Sree Vidyanikethan Engineering College) Tirupathi India Dept. of Computer Science and Systems Engineering(CSSE) Sree Vidyanikethan Engineering College Tirupati India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The goal of this project is to build a high performance system that offers prediction of pill information from images, the pill name, medical use and recommended dosage by using MobileNet which is a lightweight and efficient deep learning model. This system serves as an important tool for healthcare professionals and patients as it offers a means of reducing risk because of the large number of medications out there. For this task, MobileNet was chosen for its high accuracy and good balance between computational efficiency and high accuracy, and hence can be deployed on mobile devices. Having trained the model on a wide variety of pills with class wise annotations, it generalized well for diverse pills. The output of the system is the pill name, primary medical indications and common dosage instructions that help in safer medication management by supporting healthcare providers in providing better care and patient safety.

关键词： Deep learning Accuracy Computational modeling Medical services Mobile handsets Safety Standards Research and development Biomedical imaging Pharmaceuticals

来源：评论

学校读者我要写书评

暂无评论

Taxonomy of Proactive Detection Methods of Drunk Driving for Enhancing Traffic Safety

Taxonomy of Proactive Detection Methods of Drunk Driving for...

引用

IEEE International Symposium on Embedded Multicore Socs (MCSoC)

作者： Richard Preston Swiley Razan Alsulieman Ahmed Sherif Mohamed Elsersy Kasem Khalil School of Computing Sciences and Computer Engineering University of Southern Mississippi MS USA Computer and Information Systems Dept. Higher Colleges of Technology AlAin Abu Dhabi UAE Electrical and Computer Engineering Department University of Mississippi MS USA

ISBN: (数字)9798331530471

ISBN: (纸本)9798331530488

Drunk driving continues to be a substantial public health issue, leading to a multitude of accidents and deaths on a global scale. Conventional techniques for identifying drunk driving, such as breathalyzers and field sobriety tests, tend to be reactive rather than proactive. This paper surveys the existing methods for detecting drunk driving to enhance traffic safety. The technologies studied can proactively detect impaired driving behaviors by combining machine learning (ML) approaches with real-time data processing. The study outlines various classifications based on measured metrics and driving behavior.

关键词： Surveys Visualization Technological innovation Accuracy Face recognition Taxonomy Road safety Sensor systems Driver behavior Vehicles

来源：评论

学校读者我要写书评

暂无评论

Decentralized Spectrum Sharing Networks Based on Blockchains

Decentralized Spectrum Sharing Networks Based on Blockchains

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Shuyue Ai Yuna Jiang Qiang Li Xiaohu Ge Aduwati Sali School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Dept. of Computer and Communication Systems Engineering Faculty of EngineeringUPM WiPNET Research Centre

ISBN: (数字)9798350361261

ISBN: (纸本)9798350361278

The dynamic spectrum sharing technology in cognitive radio can effectively improve the utilization rate of spectrum and relieve the current spectrum pressure. To realize spectrum sharing without trust between SUs and PUs belonging to various operators, a decentralized spectrum sharing scheme based on blockchain is proposed in this paper. A latency model and a decentralization degree model of blockchain-enabled spectrum sharing network are formulated. Network scale law in this paper is defined as the change law of structure and scale in a network. Based on the proposed decentralization degree and latency model, the scale law of blockchain networks under the constraints of latency and decentralization is studied. The simulation analyzes the change of the proportion of consensus nodes in the blockchain network with different requirements for latency and decentralization. The results show that when blockchain networks have both low latency and decentralization characteristics, the upper limit of the total number of nodes is 390, and the value range of the proportion of consensus nodes is between 0.13 and 0.56.

关键词： Blockchains Cognitive radio Low latency communication Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Unrelated Parallel Machine Scheduling with Release Dates, Setup Times, and Machine Eligibility

Reinforcement Learning for Unrelated Parallel Machine Schedu...

引用

Simulation Winter Conference

作者： Sang-Hyun Cho Hyun-Jung Kim Lars Mönch Dept. of Industrial and Systems Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea Dept. of Mathematics and Computer Science University of Hagen Universitätsstraße 1 Hagen GERMANY

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

This paper presents a novel approach for solving unrelated parallel machine scheduling problems through reinforcement learning. Notably, we consider three main constraints: release date, machine eligibility, and sequence- and machine-dependent setup time to minimize total weighted tardiness. Our work presents a new graph representation for solving the problem and utilizes graph neural networks combined with reinforcement learning. Experimental results show that our proposed method outperforms traditional dispatching rules and an apparent tardiness cost-based algorithm. Furthermore, since we represent and solve the problem using graphs, our method can be used regardless of the number of jobs or machines once trained.

关键词： Metalearning Adaptation models Heuristic algorithms Stochastic processes Reinforcement learning Parallel machines Dynamic scheduling Size measurement Dispatching Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

An Introduction to Power Electronics Design Methodology

An Introduction to Power Electronics Design Methodology

引用

Design Methodologies Conference (DMC), IEEE

作者： SM Sajjad Hossain Rafin Hossam Hussein Osama A. Mohammed Dept. of Electrical and Computer Engineering Energy Systems Research Laboratory Florida International University Miami Florida USA

The development of effective and dependable electronic systems for a variety of applications, from renewable energy systems and electric vehicles to industrial automation and consumer electronics, depends heavily on power electronics design techniques. Moreover, the power electronics design technique offers a methodical way to create high-performance, dependable, and efficient electronic systems, which helps scholars and engineers address the unique requirements of varied applications while taking thermal management, electromagnetic interference, and safety considerations by integrating theoretical analysis, simulation tools, prototyping, and testing. The effectiveness of this methodology is further increased by the ongoing development of power semiconductor and design methodologies, which makes it possible to realize cutting-edge and environmentally friendly power electronic solutions for the modern world. Considering above mentioned importance, this paper is written as an initial guideline for scholars and engineers to design power electronic systems.

关键词：

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：