检索结果-内蒙古大学图书馆

29th IEEE Asia Pacific Conference on Communications, APCC 2024

作者： Liang, Chengchao Guo, Yihang Wu, Zhanglei Chai, Rong Carleton Univ Depart. of Systems and Computer Eng OttawaON Canada Chongqing Univ. Posts & Telecom School of Communication and Information Engineering Chongqing China

ISBN: (纸本)9798331517816

In future space-ground integrated networks, a satellite-based core network can reduce frequent signaling interactions between satellites and ground stations, thereby enhancing network architecture and supporting global communications. Users can achieve end-to-end communication through the satellitebased User Plane Function (UPF). However, the high dynamics of Low Earth Orbit (LEO) satellites result in frequent inter-satellite handovers, significantly affecting user service continuity. Existing satellite handover strategies are overly simplistic and fail to ensure the Quality of Service (QoS). Additionally, ground users compete for satellite links based on limited observations, leading to network congestion. This paper proposes a loadbalanced, distributed, multi-agent deep reinforcement learning method for satellite handover. We formulate a combinatorial optimization problem to maximize the total utility of user-satellite associations across various service types. Each user acts based on local information and engages in distributed matching with satellites. Simulation results indicate that our method ensures QoS for various service types, optimizes load balancing, and outperforms basic handover strategies in terms of handover success rate and frequency. © 2024 IEEE.

关键词： Satellite links

来源：评论

学校读者我要写书评

暂无评论

An ontology-based mechanism for assembling learning objects

An ontology-based mechanism for assembling learning objects

引用

Advanced Industrial Conference on Telecommunications/Service Assurance with Partial and Intermittent Resources Conference/E-Learning on Telecommunications Workshop AICT/SAPIR/ELETE 2005

作者： Santacruz-Valencia, Liliana Patricia Aedo, Ignacio Navarro, Antonio Kloos, Carlos Delgado Telematic Engineering Depart.-Carlos III University of Madrid Avda. de la Universidad 30 28911 Madrid Spain Computer Science Depart. Carlos III University of Madrid Avda. de la Universidad 30 28911 Madrid Spain Computer Science Depart.-Complutense University of Madrid C/Prof. Jose Garcia Santesmases s/n 28040 Madrid Spain

ISBN: (纸本)0769523889

This paper presents OntoGlue, an ontology-based mechanism for assembling learning objects. This mechanism introduces the concept of associated knowledge, which represents the set of requirements that a learning object needs in order to be used and a set of competencies that the learning object provides after its comprehension. According OntoGlue, in order to assemble two learning objects, the requirements of one learning object must be covered by the competencies of the other. In addition, to facilitate interoperability between different domains (vocabularies), the concepts that conforms the associated knowledge are selected among the classes of educational ontologies. © 2005 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Efficient edge detection and object segmentation using Gabor filters 42

Efficient edge detection and object segmentation using Gabor...

引用

42nd Annual Southeast Regional Conference, ACM-SE 42

作者： Ji, Yiming Chang, Kai H. Hung, Chi-Cheng Depart. of Computer Science and Software Engineering Auburn University United States School of Computing and Software Engineering Southern Polytechnic State University United States

ISBN: (纸本)1581138709

Gabor filter is a widely used feature extraction method, especially in image texture analysis. The selection of optimal filter parameters is usually problematic and unclear. This study analyzes the filter design essentials and proposes two different methods to segment the Gabor filtered multi-channel images. The first method integrates Gabor filters with labeling algorithm for edge detection and object segmentation. The second method uses the K-means clustering with simulated annealing for image segmentation of a stack of Gabor filtered multi-channel images. Various experiments with real images demonstrate the effectiveness of these approaches. Copyright 2004 ACM.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Implementation of a preliminary natural user interface for video on demand systems

引用

9th FTRA InternationalConference on Future information Technology, FutureTech 2014

作者： Yim, Jaegeol Lee, Kangjai Kim, Haengseon Depart of Computer Engineering Dongguk University at Gyeongju Gyeongju Gyeongbuk Korea Republic of Depart of Computer Information Suwon Science College Suwon Gyeongki Korea Republic of

ISBN: (纸本)9783642550379

Video on Demand (VOD) is so popular that most of Internet traffic is for VOD service. If the user interface of VOD system can recognize user's gesture then even a disabled person can easily controll the system to enjoy the service. Kinect is an example device that recognizes user's gesture and voice and is widely used for games. Therefore, this paper proposes a Kinect based VOD user interface, describes our implementation of VOD system with the user interface, and discusses our experimental tests of the VOD system. © 2014 Springer-Verlag Berlin Heidelberg.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Study of the traffic flow on the various sloping way

Study of the traffic flow on the various sloping way

引用

2010 6th International Conference on Natural Computation, ICNC'10

作者： Wen, Jian Tian, Huanhuan Xue, Yu Inst. of Physical Science and Engineering Guangxi University Nanning 53004 China Depart. of Physics and Information Science Yulin Normal University Yulin 537000 China

ISBN: (纸本)9781424459612

Under the periodic boundary condition, applying the NaSch model with the different maximal velocity on the various types of the sloping way, which include sag, uphill and downhill, the effect of gravitational force upon traffic flow are taken into account. The computer simulation are carried out, the fundamental diagrams and the typical space-time diagrams for the traffic flow on the sag, the uphill, and downhill are obtained. A platform in the fundamental diagrams for the traffic flow on the uphill, and the length of the plat is related to the maximal velocity on the uphill. © 2010 IEEE.

关键词： Cellular automata NaSch model Traffic flow

来源：评论

学校读者我要写书评

暂无评论

Design of physical activity recommendation system

Design of physical activity recommendation system

引用

Informatics 2008 and Data Mining 2008, MCCSIS'08 - IADIS Multi Conference on computer science and information Systems

作者： Sami, Ashkan Nagatomi, Ryoichi Terabe, Masahiro Hashimoto, Kazuo Graduate School of Biomedical Engineering Tohoku University Sendai 980-8575 Japan Depart. of Computer Science and Engineering Shiraz University Shiraz 71348 - 51154 Iran

ISBN: (纸本)9789728924638

Leisure-time physical activity (LTPA) has been shown to be an effective way of preventing diseases. However 50% of the people who start any type of sports or LTPA drop out of the program within 6 months. Even though a lot of research on exercise adherence has been performed, no common consensus on all the leading factors to adherence exists. Cultural differences make studies in other countries not suitable for Japan. In this paper we present designs of recommender systems to recommend LTPA to adults. Due to complexities of problem domain and vast number of possible LTPA, first we assume people with similar lifestyle may follow each other better than others as far as exercise is concerned. Based on lifestyle data in complete health check-ups (Ningendoku) that is performed in Japan, we find similar people. In addition, based on expertise and detailed information of different sports and activities we build ontology trees and tables for different attributes of LTPA, these ontologies are used to calculate distances of different LTPA. Health-care professionals in preliminary discussion showed a lot of interest on our system. © 2008 IADIS.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Network and operating system support for digital audio and video: Third international workshop La Jolla, California, USA, november 12-13, 1992 proceedings 3rd

Network and operating system support for digital audio and v...

引用

3rd International Workshop on Network and Operating System Support for Digital Audio and Video, 1992

作者： Venkat Rangan, P. Depart. of Computer Science & Engineering University of California at San Diego 9500 Gilman Drive La JollaCA92093-0114 United States

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Models for Multiple Face Mask Detection under a Complex Big Data Environment 4th

Deep Learning Models for Multiple Face Mask Detection under ...

引用

4th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2022

作者： Rekha, V. Manoharan, J Samuel. Hemalatha, R. Saravanan, D. Dept. of Computer Science Rajalakshmi Engineering College Thandalam Chennai India Dept. of ECE Sir Isaac Newton College of Engineering and Technology Nagapattinam India Depart. of Information Technology Annamalai University Chidhambaram India

The Covid-19 (coronavirus) pandemic creates a worldwide health crisis. According to the WHO, the effective protection system is wearing a face mask in public places. Many studies proved that carrying a face mask is also one of the precautions to decrease the possibility of viral transmission. Strict monitoring of face mask being worn by people is now enforced in many countries. Manual observation and monitoring is quite tedious. Hence, automated systems have been researched using well-kwown face mask detection methods. However, this research paper, deals with some deep learning models which can be effectively used to detect multiple face masks in a crowded environment when the amount of incoming data from sensors is huge or in otherwise stated to a Big data problem. Hence, standalone face detection models are not quite suited. Deep learning models are required in such Big data scenario which forms the essence of this study. © 2023 The Authors. Published by Elsevier B.V.

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Locating License Plate Based on Edge Features of Intensity and Saturation Subimages

Locating License Plate Based on Edge Features of Intensity a...

引用

International Conference on Innovative Computing, information and Control (ICICIC)

作者： Chien-Chou Lin Wen-Huei Huang Depart. of Computer Science and Information Engineering Shu Te University Kaohsiung Taiwan

This paper proposes a novel license plate localization algorithm for automatic license plate recognition (LPR) systems. The proposed approach uses color edge information to refine the edge points extracted in a gray-level image. In the proposed LPR system, input images are processed as follows: (1) de- interlacing by the proposed vertical median filter firstly; (2) locating license plates by detecting edge in the intensity and the saturation subimages; (3) identifying the numbers by matching the seven invariants of characters. In our experiments, 368 images are tested during two hours test. The license plate location rate of success is 97.0% with 11 images failed to locate.

关键词： Licenses Image edge detection Filters Character recognition Feature extraction Data mining Testing Interpolation computer science Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

ReActXGB: A Hybrid Binary Convolutional Neural Network Architecture for Improved Performance and Computational Efficiency

arXiv

引用

arXiv 2024年

作者： Chu, Po-Hsun Chen, Ching-Han Depart. of Computer Science and Information Engineering National Central University Taoyuan Taiwan

Binary convolutional neural networks (BCNNs) provide a potential solution to reduce the memory requirements and computational costs associated with deep neural networks (DNNs). However, achieving a trade-off between performance and computational resources remains a significant challenge. Furthermore, the fully connected layer of BCNNs has evolved into a significant computational bottleneck. This is mainly due to the conventional practice of excluding the input layer and fully connected layer from binarization to prevent a substantial loss in accuracy. In this paper, we propose a hybrid model named ReActXGB, where we replace the fully convolutional layer of ReActNet-A with XGBoost. This modification targets to narrow the performance gap between BCNNs and real-valued networks while maintaining lower computational costs. Experimental results on the FashionMNIST benchmark demonstrate that ReActXGB outperforms ReActNet-A by 1.47% in top-1 accuracy, along with a reduction of 7.14% in floating-point operations (FLOPs) and 1.02% in model size. Copyright © 2024, The Authors. All rights reserved.

关键词： Computational efficiency

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：