检索结果-内蒙古大学图书馆

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Garg, Aakansha Arya, Rajeev Singh, Maheshwari Prasad Wireless Sensor Network Lab Department of Electronics and Communication Engineering Patna India Department of Computer Science and Engineering National Institute of Technology Patna India

ISBN: (纸本)9789819743582

The growth of 6G results in rising data transmission rate in static scenario. To achieve fast communication and computation with quality service in high-speed train is a challenge. This is due to fast handover and Doppler shift. To effectively communicate in high-speed train, the placement of a mobile relay (MR) with small server at the rooftop of train coach is proposed. The base station sends channel state information to mobile relay which stores it in the stack. The resource assignment has been conducted by an improved grey wolf optimization algorithm. The focus is at improving throughput with reduction in latency and energy consumption. The simulation outcomes manifests that the presented algorithm carry-out finer in comparison of the Hungarian algorithm. The accomplished results are refined almost three times in respect of energy consumption, latency, and throughput. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Statistical physical view of statistical inference in Bayesian linear regression model

引用

Physical Review E 2024年第3期110卷 034118页

作者： Kazuaki Murayama Department of Computer and Network Engineering Graduate School of Informatics and Engineering

This paper considers similarities between statistical physics and Bayes inference through the Bayesian linear regression model. Some similarities have been discussed previously, such as the analogy between the marginal likelihood in Bayes inference and the partition function in statistical mechanics. In particular, this paper considers the proposal to associate discrete sample size with inverse temperature [C. H. LaMont and P. A. Wiggins, Phys. Rev. E 99, 052140 (2019)]. The previous study suggested that incorporating this similarity motivates the derivation of analogs of thermodynamic functions such as energy and entropy. The study also anticipated that those analogous functions have potential to describe Bayes estimation from physical points of view and to provide physical insights into mechanisms of estimation. This paper incorporates a macroscopic perspective as an asymptotics similar to the thermodynamic limit into the previous suggestion. Its motivation stems from the statistical mechanical concept of deriving thermodynamic functions that characterize macroscopic properties of macroscopic systems. This incorporation not only allows analogs of macroscopic thermodynamic functions to be considered but also suggests a candidate for an analog of inverse temperature with continuity, which is partly consistent with the previous proposal to associate the discrete sample size with inverse temperature. On the basis of this suggestion, we analyze analogs of macroscopic thermodynamic functions for a Bayesian linear regression model which is the basis of various machine learning models. We further investigate, through the behavior of these functions, how Bayes estimation is described from the perspective of physics and what kind of physical insight is obtained. As a result, the estimation of regression coefficients, which is the primary task of regression, appears to be described by the physical picture of balance between decreasing energy and increasing entropy as in equi

关键词： Classical statistical mechanics Bayesian methods

来源：评论

学校读者我要写书评

暂无评论

Inverse Scattering of Two-dimensional Circular Cylindrical Conductors by Convolutional Neural network 4

Inverse Scattering of Two-dimensional Circular Cylindrical C...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Chen, Po-Hsiang Hsu, Hsiu-Hui Chiu, Chien-Ching Chien, Wei Yu, Kai-Xu Tamkang University Department of Electrical and Computer Engineering New Taipei City Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan City Taiwan

ISBN: (纸本)9798350360721

We used a Convolutional Neural network (CNN) to reconstruct the electromagnetic imaging of a perfect conductor in half-space through the traverse magnetic wave. Since the conventional iterative algorithm is time-consuming, we developed a real-time electromagnetic imaging technique to apply to the CNN to reconstruct the half-space conducting cylinders. The sizes and positions of the cylinders were calculated through the Direct Sampling Method (DSM) in the scattered field. The original ground truth was fed to CNN for training to predict accurate sizes and positions of the shape. The accurate size and position of the shape for the perfect conductor were reconstructed. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Developing an Esports Assistant System for First Person Shooting Game Based on Multimodal Learning 14th

Developing an Esports Assistant System for First Person Shoo...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Chiu, Wei-Hsiang Hung, Jason C. Ma, Hao-Shang Huang, Chun-Hong Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan City Taiwan

ISBN: (纸本)9789819623945

We plan to develop a specialized training system to enhance the competitive skills of players in the first-person shooter game "Valorant", aiming to improve their abilities and tactical understanding within the game. We will adopt a multimodal image-text fusion technique to enhance the model’s learning of sample similarity. Specifically, we will use the cross-entropy function to maximize the diagonal values of the similarity matrix, thereby capturing the features of similar samples and reducing the similarity between dissimilar samples. Through this process, we ensure that the model can map the same entity across different modalities into similar embedding representations, while distinguishing unrelated samples. Our goal is to find a way of embedding representation during the learning process that enables the model to better understand and represent multimodal data. We will utilize the YOLOv7 model for object detection to identify destructible skills. Based on the results of object detection, we will generate relevant textual descriptions for each object. This will enable novice players to quickly understand the function of diverse and complex skills and take appropriate actions when encountering them. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Spectrum Slicer Placement Optimization by Betweenness Centrality in Elastic Optical network 14

Spectrum Slicer Placement Optimization by Betweenness Centra...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Hachiya, Tsubasa Kitsuwan, Nattapong The University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan

ISBN: (纸本)9798350313277

This paper proposes a more effective placement way of slicers to increase bandwidth efficiency in elastic optical network (EON). EON enhances the potential of the network by dividing available bandwidth into a small region called "slot"and assigns bandwidth to communication requests dynamically. Spectrum slicing also improves the availability of bandwidth. However, these technologies cause bandwidth waste due to the lost opportunities of spectrum slicing with the incomplete placement of slicers. We provide more optimal placement of spectrum slicers to advance bandwidth efficiency. Betweenness centrality (BC) shows the importance of nodes in sight of network routing. It allows us to predict which node will be crowded and plan better slicer installation assignments in advance. We simulate how effective the proposed method is to reduce communication conflicts with the index allocation blocking ratio. As a result of simulations, the proposed method reduces communication conflicts by up to 91.01% compared to a previous BC method. © 2023 IEEE.

关键词： Elastic optical network optimization spectrum slicing

来源：评论

学校读者我要写书评

暂无评论

A System for Constructing Spanning Trees in Graph networks that Utilize Integer Linear Programming to Enhance Link Fault Tolerances 14

A System for Constructing Spanning Trees in Graph Networks t...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： The, Hieu Tran Fujita, Kosuke Kitsuwan, Nattapong The University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan

ISBN: (纸本)9798350313277

In this paper, we formulate to optimize the problem related to network failure using the integer linear programming (ILP) method. We aim to minimize the number of spanning trees needed to protect the network in case of link and/or link-node failure. Compared to the traditional approach of constructing spanning trees using heuristic algorithms, our method has successfully reduced the number of trees required for node or link-node failure protection by up to 50%. Reducing the number of spanning trees saves memory requirements for the network route and simplifies network configuration. © 2023 IEEE.

关键词： integer linear programming link failure network protection reducing memory spanning trees

来源：评论

学校读者我要写书评

暂无评论

Cache Node Placement for Maximum Traffic Minimization in Content-Centric networking 14

Cache Node Placement for Maximum Traffic Minimization in Con...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Nakajima, Shohei Kitsuwan, Nattapong The University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan

ISBN: (纸本)9798350313277

Content-centric networking (CCN) is a network architecture based on content. The conventional network architecture uses IP address to route packets based on location. In CCN, which routes packets based on content name, a cache function can be attached to nodes. Getting contents from cache nodes alleviates traffic congestion in the network. In the case that the cache function is not attached to all nodes in the network, it is necessary to decide where cache nodes are placed. Congestion tends to occur around cache nodes when using the conventional method. We formulate a problem of cache node placement as an integer linear programming (ILP) considering the population of each node. The ILP formulation determines the cache node placement to minimize the value of the maximum traffic. This result shows the proposed ILP approach reduces the maximum traffic by 59% on average. © 2023 IEEE.

关键词： Content-centric networking maximum traffic optimization

来源：评论

学校读者我要写书评

暂无评论

Robust Particle Swarm Optimization Algorithm for Modeling the Effectof Oxides Thermal Properties on AMIG 304L Stainless Steel Welds

引用

computer Modeling in engineering & Sciences 2024年第11期141卷 1809-1825页

作者： Rachid Djoudjou Abdeljlil Chihaoui Hedhibi Kamel Touileb Abousoufiane Ouis Sahbi Boubaker Hani Said Abdo Department of Mechanical Engineering College of Engineering in Al-KharjPrince Sattam bin Abdulaziz UniversityP.O.Box 655Al-Kharj16273Saudi Arabia Department of Computer and Network Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah21959Saudi Arabia Laboratory of Mechanics of Sousse(LMS) National Engineering School of SousseUniversity of SousseSousse4054Tunisia Center of Excellence for Research in Engineering Materials(CEREM) King Saud UniversityP.O.Box 800Al-Riyadh11421Saudi Arabia Department of Metallurgical and Materials Engineering Faculty of Petroleum and Mining EngineeringSuez UniversitySuez43512Egypt

There are several advantages to the MIG(Metal Inert Gas)process,which explains its increased use in variouswelding sectors,such as automotive,marine,and construction.A variant of the MIG process,where the sameequipment is employed except for the deposition of a thin layer of flux before the welding operation,is the AMIG(Activated Metal Inert Gas)*** study focuses on investigating the impact of physical properties ofindividual metallic oxide fluxes for 304L stainless steel welding joint morphology and to what extent it can helpdetermine a relationship among weld depth penetration,the aspect ratio,and the input physical properties ofthe *** types of oxides,TiO_(2),SiO_(2),Fe_(2)O_(3),Cr_(2)O_(3),and Mn_(2)O_(3),are tested on butt joint design withoutpreparation of the edges.A robust algorithm based on the particle swarm optimization(PSO)technique is appliedto optimally tune the models’parameters,such as the quadratic error between the actual outputs(depth and aspectratio),and the error estimated by the models’outputs is *** results showed that the proposed PSOmodel is first and foremost robust against uncertainties in measurement devices and modeling errors,and second,that it is capable of accurately representing and quantifying the weld depth penetration and the weld aspect ratioto the oxides’thermal properties.

关键词： Activated metal inert gas welding stainless steel activating flux oxides’thermal properties particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Neural network-based Approach for Forecasting Water Demand

引用

computers, Materials & Continua 2022年第10期73卷 1365-1383页

作者： Al-Batool Al-Ghamdi Souad Kamel Mashael Khayyat Department of Computer Science and Artificial Intelligence College of Computer Sciences and EngineeringUniversity of JeddahJeddah 21959Saudi Arabia Department of Computer and Network Engineering College of Computer Sciences and EngineeringUniversity of JeddahJeddah 21959Saudi Arabia Department of Information Systems and Technology College of Computer Sciences and EngineeringUniversity of JeddahJeddah 21959Saudi Arabia

Water is a vital *** supports a multitude of industries,civilizations,and ***,climatic conditions impact water availability,particularly in desert areas where the temperature is high,and rain is ***,it is crucial to forecast water demand to provide it to sectors either on regular or emergency *** study aims to develop an accurate model to forecast daily water demand under the impact of climatic *** forecasting is known as a multivariate time series because it uses both the historical data of water demand and climatic conditions to forecast the *** on the collected data of Jeddah city,Saudi Arabia in the period between 2004 and 2018,we develop a hybrid approach that uses Artificial Neural networks(ANN)for forecasting and Particle Swarm Optimization algorithm(PSO)for tuning ANNs’*** on the Root Mean Square Error(RMSE)metric,results show that the(PSO-ANN)is an accurate model for multivariate time series ***,the first day is the most difficult day for prediction(highest error rate),while the second day is the easiest to predict(lowest error rate).Finally,correlation analysis shows that the dew point is the most climatic factor affecting water demand.

关键词： Water demand forecasting artificial neural network multivariate time series climatic conditions particle swarm optimization hybrid algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimizing network Resilience with Segment Routing: A Comparative Study of SR TI-LFA and rLFA 4

Optimizing Network Resilience with Segment Routing: A Compar...

引用

4th IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and computer engineering, MI-STA 2024

作者： Eluheshi, Adel Ali Mansour, Mahmud Saud, Najia Ben Libyan Academy Department of Electrical Engineering and Computer Tripoli Libya University of Tripoli Department of Network Tripoli Libya

ISBN: (纸本)9798350372632

network operators are confronted with the demanding requirements resulting from the evolution of IP networks. As a result, it has become necessary to provide rigorous Service Level Agreements (SLAs) that are in line with these requirements. However, traditional IP networks lack the necessary flexibility, scalability, and manageability to meet these demands. In order to address these limitations, the Segment Routing (SR) architecture has been developed. SR is based on source-routing and tunneling paradigms, which enable IP/MPLS and IPV6 networks to operate in a simplified and more scalable manner. The focus of this paper is on network protection (resiliency) using Topology Independent Loop-Free Alternatives Fast Re-Route (TI-LFA FRR) using MPLS as underly technology. SR overcomes the limitations of previous network protection mechanisms in terms of coverage and optimal path selection. To show the effectiveness of SR TI-LFA in comparison to its predecessor, Remote Loop-Free Alternate (rLFA), we have implemented various scenarios. These scenarios are designed to highlight the superior capabilities of TI-LFA. © 2024 IEEE.

关键词： network routing

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：