检索结果-内蒙古大学图书馆

International Conference on Information and Communication Technology Convergence (ICTC)

作者： Yeunwoong Kyung Donghun Lee Jaewook Lee Youngjun Kim Haneul Ko Seungmin Oh Jaehwan Lee Div. of Info. & Comm. Eng. Kongju National University Cheonan Korea Dep. of Info. and Comm. Engineering Pukyong National University Busan Korea School of Computer Science and Eng. Kyungnam University Changwon Korea Dep. of Electronic Eng. Kyung Hee University Yongin-si Korea Dep. of Computer Science and Eng. Kongju National University Cheonan Korea

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

The 5G LAN-type service refers to a service that supports communication between users within a group through the 5G system. It provides functions similar to those of traditional Local Area Networks (LAN) or Virtual Private Networks (VPN), but it gains attention across various services due to the enhanced performance of 5G such as high throughput, low latency, mobility management, and security. The 3rd Generation Partnership Project (3GPP) introduced the 5G LAN-type service in Release 16 and defined the architecture, protocols, and requirements to support the 5G LAN-type service. In this paper, we briefly examine the architecture and components of the 5G network based on the 3GPP standard and introduce the structure and protocols for supporting 5G LAN-type services in a 5G network.

关键词： Protocols 5G mobile communication Robot control Standardization Throughput Virtual private networks Security 3GPP Low latency communication Local area networks

来源：评论

学校读者我要写书评

暂无评论

Solving the vehicle routing problem with deep reinforcement learning

arXiv

引用

arXiv 2022年

作者： Foà, Simone Coppola, Corrado Grani, Giorgio Palagi, Laura Sapienza University of Rome Dep. of Computer Science Control and Management Engineering Rome Italy Sapienza University of Rome Dep. of Statistical Science Rome Italy

Recently, the applications of the methodologies of Reinforcement Learning (RL) to NP-Hard Combinatorial optimization problems has become a popular topic. This is essentially due to the nature of the traditional combinatorial algorithms, often based on a trial-and-error process. RL aims at automating this process. At this regard, this paper focuses on the application of RL for the Vehicle Routing Problem (VRP), a famous combinatorial problem that belongs to the class of NP-Hard problems. In this work, as first, the problem is modeled as a Markov Decision Process (MDP) and then the PPO method (which belongs to the Actor-Critic class of Reinforcement learning methods) is applied. In a second phase, the neural architecture behind the Actor and Critic has been established, choosing to adopt a neural architecture based on the Convolutional neural networks, both for the Actor and the Critic. This choice resulted effective to address problems of different sizes. Experiments performed on a wide range of instances show that the algorithm has good generalization capabilities and can reach good solutions in a short time. Comparisons between the algorithm proposed and the state-of-the-art solver OR − TOOLS show that the latter still outperforms the Reinforcement learning algorithm. However, there are future research perspectives, that aim to upgrade the current performance of the algorithm *** Codes 90-08 © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Comparison of Global Planners for Trajectory Planning of Mobile Robots in an Unknown Environment with Dynamic Obstacles

Experimental Comparison of Global Planners for Trajectory Pl...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Zehra Tüfekçi Gökhan Erdemir Department of Computer Engineering Istinye University İstanbul Turkiye Department of Computer Science and Engineering Istanbul Sabahattin Zaim University Dep. of Engineering Management & Technology University of Tennessee at Chattanooga Tennessee USA

Interacting with their workspace, detecting obstacles, and real-time path planning in the field to reach the goal in the unknown environment are current working areas of mobile robotics. Working in an unknown environment with dynamic obstacles is a challenging topic for autonomous robots, which need to protect themselves from the dynamic obstacles they encounter, not damage the obstacle, and re-plan their path according to their new position. This study performed an experimental comparison of three different global planners for trajectory planning of mobile robots in an unknown environment with dynamic obstacles. Global Planner, Carrot Planner, and NavfnROS planners in the ROS package were used as global planners in two different mazes with dynamic obstacles. The durations from the start to the goal point in the two designed environments were determined for each global planner.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine-Learning-Assisted Optimization of Type-II Superlattices for Enhanced Vertical Hole Mobility

Machine-Learning-Assisted Optimization of Type-II Superlatti...

引用

International Conference on Numerical Simulation of Optoelectronic Devices, (NUSOD)

作者： John Glennon Enrico Bellotti Div. of Material Science and Engineering Boston University Boston Massachusetts USA Dep. of Electrical and Computer Engineering Div. of Material Science and Engineering Boston University Boston Massachusetts USA

Gaussian process regression is used to develop a model for predicting the superlattice (SL) structures grown on a 6.3 Å lattice. This model is used to search for optimized hole transport properties. Nonequilibrium Green’s functions calculations are used to determine the vertical hole mobility of the structure which is compared with both the calculated and experimental results for an experimental SL grown on a GaSb substrate. Ultimately, a simple analytical model is used to approximate and compare the quantum efficiency of a photodiode containing each structure demonstrating an improvement in device performance using the optimized SL structure.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Health home-monitoring system based on IoT 7

Health home-monitoring system based on IoT

引用

7th IEEE International Symposium on Electrical and Electronics engineering, ISEEE 2021

作者： Ionescu, Bogdan Craciun, Marian Petrea, George Epure, Silviu Arama, Catalin Vlad, Ciprian 'Dunarea de Jos' University of Galati Dep. of IT and Digital Communications Romania 'Dunarea de Jos' University of Galati Dep. of Computer Science and Information Technology Romania 'Dunarea de Jos' University of Galati Dep. of Electronics and Telecommunications Romania 'Dunarea de Jos' University of Galati Dep. of Automation and Electrical Engineering Romania

ISBN: (纸本)9781665437998

The recent COVID-19 pandemic highlighted that there is a lot of work to do regarding the integration of digital technologies in healthcare. Actual trending offers the possibility to patients to have permanent knowledge about their health status and not to go to have a general check when some symptoms appear. Internet of Things (IoT) has also reached the medical area and can offer high quality solutions. After this step is taken the data collected and stored locally or remote in the cloud cand be easily reached, analyzed and health monitoring for each patient is much improved. © 2021 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Classification of Hermite Gaussian Beams for 5G and Beyond Free-Space Optical Backhaul Links

Machine Learning Classification of Hermite Gaussian Beams fo...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： A. Chehri A. Ahmed M. Z. Shakir Dep. of Math. and Computer Science Royal Military College of Canada Kingston Canada School of Electronic Engineering and Computer Science Queen Mary University of London University of the West of Scotland UK

Free space optical (FSO) communication offers an excellent opportunity to develop energy-efficient, secure, and ultrafast data links for 5G and beyond applications, including heterogeneous networks with massive connectivity and wireless backhauls for cellular systems. However, the effect of an optical beam's pointing inaccuracy combined with the impact of climate factors must be considered in the FSO communication system. In this paper, we first evaluate the performance reliability and availability of NRZ-based mode division multiplexing (MDM)-FSO backhaul. In particular, a single wavelength laser is used to transmit four different optical beams, using four different wavelengths. It also explores and classifies four beams used for capacity enhancement in mode division multiplexed MDM-FSO backhaul links. Several Machine Learning (ML) models are used to classify the four optical modes. Results indicate successful transmission of 80 Gbps. Furthermore, the primary findings indicate that the ML model exhibits an impressive accuracy rate of approximately 97% in classifying four distinct beams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secure Password Using EEG-based BrainPrint System: Unlock Smartphone Password Using Brain-computer Interface Technology

Secure Password Using EEG-based BrainPrint System: Unlock Sm...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zuwaina Alkhyeli Ayesha Alshehhi Mazna Alhemeiri Salma Aldhanhani Khalil AlBalushi Fatima Ali AlNuaimi Abdelkader Nasreddine Belkacem Dep. Computer Science and Software Engineering CIT UAE University Al Ain UAE Dep. Information Systems and Security CIT UAE University Al Ain UAE Dep. Computer & Network Engineering CIT United Arab Emirates University Al Ain UAE TII Autonomous Robotics Research Center Abu Dhabi UAE

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

As security becomes a strong factor in daily activities, finding secure ways to unlock machines and smartphones is a challenge due to hardware limitations and the high risk of hacking. Considering the level of security and privacy in the digital world, attackers tend to be one step ahead. Therefore, this technical paper introduces a brain-computer interface (BCI) for increasing subject-based security using unique biometric features as a solution to build complex passwords. The BCI measures brain changes and extracts relevant bio-features from each subject using non-invasive electroencephalogram (EEG) tests. The proposed system allows users to gain access to their devices using brain waves (bypass) instead of inserting their password manually (normal path), which saves the user time and upgrades the level of privacy as no physical actions are required during this process. This system is also well suited for individuals with mobility impairments. We used the P300-based BCI controlling paradigm which dep.nds on reading the electrical brain activity of the user when observing a particular object. The other feature of the system is that it can extract unique features of each individual brain to produce a network that uniquely identifies them, which is used as a security layer. Users need to enter their unique network to access their device with failed attempts requiring an EEG test to identify the user. The system plays an active role in facilitating user processes for authentication while accessing devices. The system establishes an urgent call whenever the user’s brain currents command it to. The project outcomes were assessed by simulating the BCI before real-time implementation to determine errors and resolve the validity of the project scope.

关键词： Privacy Authentication Passwords Feature extraction Brain-computer interfaces Electroencephalography Security

来源：评论

学校读者我要写书评

暂无评论

Low-Voltage Stress CI-based Quadratic Boost Converter for Distributed Energy Resources

Low-Voltage Stress CI-based Quadratic Boost Converter for Di...

引用

Power Electronic and Drive Systems and Technologies Conference (PEDSTC)

作者： Morteza Dezhbord Milad Babalou Sobhan Mohamadian Carlo Cecati Dep. Information Engineering Computer Science and Mathematics University of L’Aquila L’Aquila Italy Dept. Electrical Engineering Shahid Beheshti University Tehran Iran

This research introduces a high step-up DC-DC converter for renewable energy sources (RESs) that has lower voltage stress on its single switch. With one linked coupled inductor (CI), a quadratic boost converter plus a couple of multiplier units are utilized as circuits for primary and secondary, respectively. The energy from the leakage inductance can be recycled, increasing efficiency and reducing voltage stress. The proposed converter has a higher voltage gain and lower switch stress when compared to similar existing quadratic converter topologies. The operation principles and mathematical analysis of the proposed converter are thoroughly studied. Following that, a comparison of several structures is presented. Finally, simulation results of PSCAD software are shown to further verify the theoretical study.

关键词： Renewable energy sources Inductance Simulation Voltage Switches software Topology

来源：评论

学校读者我要写书评

暂无评论

System for Talent Acquisition: Integrating AI, Automation, and Data Analysis in HR

System for Talent Acquisition: Integrating AI, Automation, a...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Gulnara Abitova Ayanbek Serikov Vladimir Nikulin Mira Rakhimzhanova Gulnur Shuteyeva Korlan Kulniyazova dep. computer engineeering Astana IT University Astana Kazakhstan dept. electical engineering and computer science Binghamton University Binghamton USA dept. system anslysis and managemnt Eurasian National University Astana Kazakhstan

This article presents a novel system designed for human resources (HR) companies, aiming to predict an individual's personality based on resume analysis through the integration of advanced information technology tools. At the core of this system is Airable, serving as the central database, which is seamlessly I integrated with various other tools such as *** for document handling, GitHub for code repository management, and OpenAI for advanced AI algorithms. The integration and automation of these diverse tools are skillfully orchestrated using Make, a no-code solution that streamlines the workflow and enhances efficiency. This innovative approach allows HR companies to leverage technology for more accurate personality predictions, thereby improving their recruitment processes and decision-making strategies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PUSH: a primal heuristic based on Feasibility PUmp and SHifting

arXiv

引用

arXiv 2022年

作者： Agasucci, Valerio Coppola, Corrado Grani, Giorgio Sapienza University of Rome Dep. of Computer Science Control and Management Engineering Rome Italy Sapienza University of Rome Dep. of Statistical Sciences Rome Italy

This work describes PUSH, a primal heuristic combining Feasibility Pump and Shifting. The main idea is to replace the rounding phase of the Feasibility Pump with a suitable adaptation of the Shifting and other rounding heuristics. The algorithm presents different strategies, dep.nding on the nature of the partial rounding obtained. In particular, we distinguish when the partial solution is feasible, infeasible with potential candidates and infeasible without candidates. We used a threshold to indicate the percentage of variables to round with our algorithm and which other to round to the nearest integer. Most importantly, our algorithm tackles directly equality constraints without duplicating rows. We select the parameters of our algorithm on the 19 instances provided for the Mip Competition 2022. Finally, we compared our approach to other start heuristics, like Simple Rounding, Rounding, Shifting and Feasibility Pump on the first 800 MIPLIB2017 instances ordered by the number of non *** Codes 90-08 Copyright © 2022, The Authors. All rights reserved.

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：