检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

771 篇 会议
25 册 图书
5 篇 期刊文献

馆藏范围

801 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

551 篇 工学
- 438 篇 计算机科学与技术...
- 255 篇 控制科学与工程
- 228 篇 信息与通信工程
- 216 篇 电气工程
- 201 篇 软件工程
- 180 篇 动力工程及工程热...
- 180 篇 安全科学与工程
- 172 篇 网络空间安全
- 170 篇 仪器科学与技术
- 169 篇 交通运输工程
- 32 篇 机械工程
- 32 篇 生物工程
- 30 篇 电子科学与技术（可...
- 20 篇 化学工程与技术
- 19 篇 生物医学工程（可授...
- 17 篇 光学工程
300 篇 理学
- 177 篇 化学
- 68 篇 数学
- 38 篇 物理学
- 36 篇 生物学
- 17 篇 统计学（可授理学、...
- 12 篇 系统科学
248 篇 管理学
- 217 篇 管理科学与工程(可...
- 194 篇 图书情报与档案管...
- 35 篇 工商管理
25 篇 教育学
- 25 篇 教育学
23 篇 医学
- 23 篇 临床医学
- 22 篇 基础医学(可授医学...
22 篇 法学
- 19 篇 社会学
13 篇 经济学
- 13 篇 应用经济学
6 篇 农学
3 篇 军事学
2 篇 文学

主题

106 篇 smart cities
38 篇 deep learning
38 篇 computational mo...
38 篇 training
37 篇 computer archite...
26 篇 costs
26 篇 feature extracti...
23 篇 semantics
21 篇 data models
20 篇 predictive model...
20 篇 machine learning
19 篇 artificial intel...
19 篇 computer vision
17 篇 reinforcement le...
17 篇 visualization
16 篇 heuristic algori...
15 篇 servers
15 篇 hardware
14 篇 real-time system...
13 篇 internet of thin...

机构

13 篇 school of comput...
10 篇 college of compu...
8 篇 school of comput...
6 篇 university polit...
5 篇 school of automa...
5 篇 college of busin...
5 篇 university polit...
5 篇 school of comput...
4 篇 college of compu...
4 篇 faculty of infor...
4 篇 school of comput...
4 篇 school of comput...
4 篇 faculty of busin...
4 篇 school of comput...
4 篇 university of ch...
4 篇 novosibirsk stat...
4 篇 college of compu...
3 篇 dept. of theoret...
3 篇 robai-lab hainan...
3 篇 electrical power...

作者

8 篇 duan yucong
7 篇 peng jun
6 篇 jin hai
5 篇 houhamdi zina
5 篇 athamena belkace...
4 篇 jiang fu
4 篇 li heng
4 篇 mocanu mariana
4 篇 kashef rasha
4 篇 nobuhiro ito
4 篇 tetsushi wakabay...
4 篇 harous saad
4 篇 takeshi uchitane
4 篇 kazunori iwata
3 篇 wang lei
3 篇 khusnutdinov ale...
3 篇 vadim z. manusov
3 篇 trubák kamil
3 篇 yu zhiwen
3 篇 liu weirong

语言

769 篇 英文
31 篇 其他
8 篇 中文
1 篇 俄文

检索条件"任意字段=23rd International Conference on Computer Systems and Technologies, CompSysTech 2022"

共 801 条记录，以下是161-170 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Local-Global-Aware Convolutional Transformer for Hyperspectral Image Classification 23

Local-Global-Aware Convolutional Transformer for Hyperspectr...

引用

23rd IEEE international conference on High Performance Computing and Communications, 7th IEEE international conference on Data Science and systems, 19th IEEE international conference on Smart City and 7th IEEE international conference on Dependability in Sensor, Cloud and Big Data systems and Applications, HPCC-DSS-SmartCity-DependSys 2021

作者： Wang, Yifan Min, Zhichao Jia, Sen College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9781665494571

In recent years, more and more end-to-end deep learning methods have been applied to remote sensing image classification. Convolutional neural networks (CNN) is the most representative one. However, the convolution kernel that makes CNN successful also limits its ability of global perception due to its fixed size. Transformer, as an emerging model, has achieved great success in both computer vision and natural language processing (NLP). Without any convolution module, Transformer is almost entirely composed of Attention mechanism that brings it context-aware ability and makes computational parallelization easier. Therefore, this paper proposes a two-branch convolutional Transformer network, which combines the local feature extraction capabilities of CNN and context-aware capabilities of Transformer to get a better feature representation while modeling dual-path long-range dependence. In addition, we flexibly combine 1D convolutional with linear projection to realize feature embedding while fusing convolutional features. The comparative experiments results on the public dataset confirm the effectiveness of our method, and the ablation experiment proves the necessity of our module and network design. © 2021 IEEE.

关键词： Adaptation models Convolution Smart cities Computational modeling Transformers Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Purpose Driven Balancing of Fairness for Emotional Content Transfer Over DIKW 23

Purpose Driven Balancing of Fairness for Emotional Content T...

引用

作者： Hu, Ting Duan, Yucong Mei, Yingtian School of Computer Science and Technology Hainan University Haikou China

ISBN: (纸本)9781665494571

During emotional interactions and exchange conveying subjective content towards objective existence in Metaverse, stakeholders will encounter various unfair situations in terms of data collection, information exchange and knowledge accumulation. We model emotion as essential content according to our essence computation and reasoning strategy which is mapped to Data, Information, Knowledge and Wisdom(DIKW). Then following our purpose computation and reasoning strategy, we map unfairness as essential DIKW deviations of data deviation, information deviation, knowledge deviation and wisdom/value deviation. Thereafter, we treat unfairness in emotional content and its communication according to essential DIKW semantic level of semantic computation which can be semantically traced to existence semantic level while implemented through basic manipulation of data unfairness, information unfairness and knowledge unfairness on data graph, information graph and knowledge graph. We show the feasibility of our proposed solution through constructing an experimental scenario. © 2021 IEEE.

关键词： Privacy Computational modeling Semantics Legislation Data collection Cognition Data models

来源：评论

学校读者我要写书评

暂无评论

DeepLoc: A Deep Neural Network-based Indoor Positioning Framework 23

DeepLoc: A Deep Neural Network-based Indoor Positioning Fram...

引用

作者： Liu, Saining Ren, Qianqian Li, Jinbao Xu, Hui Heilongjiang University Department of Computer Science and Technology Harbin150080 China Shandong Artificial Intelligence Institute Qilu University of Technology Jinan250014 China

ISBN: (纸本)9781665494571

The growing attention on location-based services has promoted the development of indoor localization studies. Existing techniques mainly use Received Signal Strength Indicator (RSSI) of wireless signals as location fingerprint. Inspired by deep learning techniques for signal processing, we propose a deep neural network-based framework (DeepLoc) to implement Wi-Fi fingerprint positioning. In order to improve localization performance, we further design a network division based optimization algorithm. We first adopt greedy algorithm to locate the user in a sub-area, and then reconstruct a smaller fingerprint database, which is fed into the training model. Finally, we evaluate the proposed framework. Experimental results show that DeepLoc can improve the localization accuracy efficiently and obtain better performance. © 2021 IEEE.

关键词： Location awareness Training Greedy algorithms Deep learning Signal processing algorithms Fingerprint recognition Received signal strength indicator

来源：评论

学校读者我要写书评

暂无评论

Flocking of Battery-Powered Mobile Agents with Energy-Aware Potential Function 23

Flocking of Battery-Powered Mobile Agents with Energy-Aware ...

引用

作者： Jiang, Fu Xia, Yaoxin Li, Heng Zhang, Zhongke Zhang, Xiaoyong Peng, Jun School of Computer Science and Engineering Central South University Changsha China

ISBN: (纸本)9781665494571

Flocking of mobile agents has been well studied in the literature. However, since most practical mobile agents, e.g., robots, UAVs, are typically powered by onboard batteries, it is of practical significance to consider the battery consumption in the control design, and explore how to optimize the distribution of energy consumption. In this paper, we consider the flocking of battery-powered mobile agents using the potential field approach. We first analyze the limitations of the classical potential field method. Next, we propose a new potential function by considering the battery consumption, and design the flocking control law related to the gradient of the proposed potential functions correspondingly. We verified the effectiveness of the proposed method with both simulations and a group of UAVs. The results of experiment verify that the proposed method can optimize the energy consumption of the flocking system when compared with the existing methods, which is benefit to the endurance of the system. © 2021 IEEE.

关键词： Energy consumption Smart cities Control design Mobile agents Batteries Robots Optimization

来源：评论

学校读者我要写书评

暂无评论

A Sequential Recommendation of Hawkes Process Fused with Attention Mechanism 23

A Sequential Recommendation of Hawkes Process Fused with Att...

引用

作者： Wen, Xilin Wang, Jianfang Yang, Xu Zhang, Qiuling School of Computer Science and Technology Henan Polytechnic University JiaoZuo China

ISBN: (纸本)9781665494571

Markov Chain (MC) models and recurrent neural networks (RNN) have attracted much attention in recommender systems because of their dynamic capture of user-item sequential patterns. However, most of these models assume that the user interaction history sequence is continuous without considering the time interval between interactive items on modeling. To counter this, we propose a sequential recommendation algorithm for Hawkes Process with Attention Mechanism (AMHP in short). Our model first uses the self-attention model to evaluate the strength of the relationship between different items in the sequence and ensure the dynamic attenuation problem when considering item strength in user history interaction. Specifically, we regard the recurrence of the same attribute items in the user sequence as a self-excitation of the Hawkes model and construct the short-term and long-term time curve function of the corresponding category of items-time potential factors. Results from our experiments over four benchmark datasets demonstrate our model can capture the dynamics of user behavior and preferences over various state-of-the-art sequential models. © 2021 IEEE.

关键词： Recurrent neural networks Correlation Smart cities Heuristic algorithms Music Markov processes Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Learning Performance Efficiency of College Basketball Players 23

Learning Performance Efficiency of College Basketball Player...

引用

作者： Yahyasoltani, Nasim Farazi, Manzur Annapureddy, Priyanka Marquette University Dept. of Computer Science United States Marquette University Dept. of Mathematics and Statistics United States

ISBN: (纸本)9781665494571

Monitoring workload is essential to evaluate possibility of fatigue or injuries and overall performance of the players. Large players workload in any game including basketball can contribute to the stress and fatigue and overloaded players may get exhausted and exhibit burnout symptoms, which eventually result in their lower efficiency in the game. This paper aims at predicting the efficiency of the basketball players in all positions (Guard, Forward and Center) based on their workload information. Machine Learning (ML) approaches are applied to the dataset for predictive modelling of the variables. The analysis includes: (i) one-model for all player positions and (ii) position-based models for respective player position. The evaluated models from both regression and classification verify that better accuracies can be obtained in the position-based models rather than the one-model for all positions approach. In addition, a smaller set of features with higher information content are obtained using principal component analysis (PCA). The performance analysis of the algorithms indicates that the player's efficiency can be estimated from the workload information which can provide valuable insight and individualized recommendation for optimal performance during the competition. © 2021 IEEE.

关键词： Performance evaluation Smart cities Games Predictive models Fatigue Prediction algorithms Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Distributed Consensus Problem in Federated Learning Paradigm 23

Distributed Consensus Problem in Federated Learning Paradigm

引用

作者： Yan, Xin Qin, Yiming Hu, Xiaodong School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China The University of Hong Kong The Faculty of Education Hong Kong Hong Kong

ISBN: (纸本)9781665494571

Federated learning (FL) framework facilitates more and more applications of deep learning algorithms on the existing network architectures, where the model parameters are aggregated in a centralized manner. However, some of FL participants are often inaccessible, such as in a power shortage or device dormant state. That will force us to explore the probability that the parameter aggregation is operated in an ad hoc manner, which is based on consensus computing. In this paper, we first propose a novel FL paradigm, which supports an ad hoc operation mode for FL participants. Second, a discrete-time dynamic equation and its control law are formulated to satisfy the demands from FL framework, with a quantized caching scheme designed to mask the uncertainties from asynchronous updates and measurement noises. Then, the consensus conditions and the convergence of the consensus protocol are deduced analytically, and a strategy of quantized caching to optimize the convergence speed is provided. Last, the theoretical results are validated by numerical simulations. © 2021 IEEE.

关键词： Uncertainty Smart cities Delay effects Packet loss Collaborative work Particle measurements Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Collaborative Mobile Charging Vehicles Placement: A Reinforcement Learning Approach 23

Collaborative Mobile Charging Vehicles Placement: A Reinforc...

引用

作者： Ni, Jianing Liang, Rupeng Wu, Hao The Key Lab. of Information System Requirement of China Electronics Technology Group Corporation Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781665494571

Nowadays, there are increasing demand from electric vehicles that need to be charged during peak hours in a city. The number of traditional fixed charging stations is limited, which may not be sufficient to satisfy the charging demand of electric vehicle users. Mobile charging vehicles can be scheduled at fixed positions to serve as a fixed charging station, providing charging services for electric vehicle users, for relieving the pressure of mass charging demand. In this paper, the charging scheduling problem of mobile charging vehicle is modeled as a Markov Decision Process(MDP) problem, and a reinforcement learning method based on policy evaluation is adopted to solve this problem. The decision of the specific position to which the mobile charging vehicle is scheduled is determined by this method. In addition, the decision of how to dispatch electric vehicle charging orders is determined by a fixed algorithm. We propose two different order dispatching algorithms. According to the simulation, our proposed reinforcement learning method has superior results in terms of the efficiency of order processing and user satisfaction compared with the traditional greedy method. The two different electric vehicle charging order dispatching algorithms have their own advantages and disadvantages in terms of processing speed and effectiveness. © 2021 IEEE.

关键词： Greedy algorithms Smart cities Simulation Decision making Reinforcement learning Markov processes Charging stations

来源：评论

学校读者我要写书评

暂无评论

On-demand Intelligent Routing Algorithms for the Deterministic Networks 23

On-demand Intelligent Routing Algorithms for the Determinist...

引用

作者： Wu, Zhongli Huang, Wenrui Dai, Zhewei Cao, Yuanyuan Dai, Bin Mo, Yijun School of Electronic Information and Communications Huazhong University of Science and Technology Hubei Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China

ISBN: (纸本)9781665494571

The deterministic network is oriented to various services in the network, ensuring the deterministic requirements of different services in terms of delay, packet loss rate, cost overhead, throughput, security, and reliability. This paper proposes an on-demand routing learning model with a three-layer logical plane that can generate on-demand routing strategies with deterministic QoS (Quality of Services) requirements for different traffic flows. With the help of deep reinforcement learning algorithms, the OdR-TD3 and OdR-SAC algorithms are proposed to generate the suitable routing strategies to meet the deterministic QoS requirements of applications' traffic. The experimental evaluation results show the OdR-TD3 and OdR-SAC algorithm have significant advantages over the DV and SPF algorithms, considering the achievement rate of deterministic QoS requirements. © 2021 IEEE.

关键词： Machine learning algorithms Smart cities Packet loss Quality of service Reinforcement learning Routing Throughput

来源：评论

学校读者我要写书评

暂无评论

Modeling Data, Information and Knowledge for Security Protection of Tasks Scheduling Algorithms in Cloud Computing 23

Modeling Data, Information and Knowledge for Security Protec...

引用

作者： Linxuan, Xin Jiantao, Zhou Lei, Yu Inner Mongolia University Department of Computer Science Inner Mongolia Hohhot China

ISBN: (纸本)9781665494571

As a key element in cloud computing, with the increasing uncertainty and complexity, task scheduling becomes more and more import. How to perform cloud scheduling effectively while safeguarding the data and information meets its bottleneck that prevents cloud computing from moving forward. In order to protect the data under being processed, this essay raises an attribute-based outsourced encryption. which enables users to pass the data on shared equipment while making the data more invisible for hackers. Meanwhile, based on the task scheduling method of deep reinforcement learning (DRL), through intention analysis, consider the user's optimization preferences in task execution, and realize the interaction with the user. reasonable scheduling is performed according to the sensitivity of the data in the task and the credibility of the cloud server. It can be seen from the test results that the algorithm has significant superiority and versatility, can improve the efficiency and security of task scheduling, and has better performance and load balance. © 2021 IEEE.

关键词： Cloud computing Uncertainty Sensitivity Smart cities Scheduling algorithms Reinforcement learning Scheduling

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共81页 << < 13 14 15 16 17 18 19 20 21 22 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：