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
26 册 图书
5 篇 期刊文献

馆藏范围

802 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
20 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

770 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 802 条记录，以下是331-340 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：

Segmentation of Brain Tumors from MRI Images Using Deep Neural Networks 23

Segmentation of Brain Tumors from MRI Images Using Deep Neur...

引用

23rd international conference on Control systems and computer Science technologies, CSCS 2021

作者： Roznov, Andrei Dobrescu, Radu Popescu, Dan Ichim, Loretta University Politehnica of Bucharest Faculty of Automatic Control and Computer Science Bucharest Romania University Politehnica of Bucharest Institute of Virology Faculty of Automatic Control and Computer Science Bucharest Romania

ISBN: (纸本)9781665439398

Brain tumor is formed by the uncontrolled growth of cancerous (malign) or non-cancerous (benign) unhealthy cells in the brain. In the present world brain tumor is a very dangerous disease and the main reason for many deaths. Magnetic Resonance Imaging (MRI) is mostly used to produce medical images for the brain tumor analysis. This paper has two objectives, first one is to identify if the MRI images has or not brain tumor using Convolutional Neural Network algorithm based on ResNet50 architecture. For second objective, image segmentation, we propose a generalized focal loss function based on Tversky index. Compared to the commonly used Dice loss, the proposed loss function achieves better precision and recall when training on small structures such as lesions. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Resolution of Inferring Hi-C Data Integrating U-Net and ResNet Networks 23rd

Enhancing Resolution of Inferring Hi-C Data Integrating U-Ne...

引用

23rd international conference on Parallel and Distributed Computing, Applications, and technologies, PDCAT 2022

作者： Zhao, Fengjiao Li, Na Zhong, Cheng School of Computer Electronics and Information Guangxi University Guangxi Nanning530004 China Key Laboratory of Parallel and Distributed Computing Technology in Guangxi Universities Guangxi Nanning530004 China

ISBN: (纸本)9783031299261

The Hi-C data is the basis of three-dimensional chromosome structure reconstruction. In this paper, a method integrating U-Net and ResNET network is proposed to infer high resolution Hi-C data from existing low-resolution Hi-C data. Firstly, the U-Net is used as the backbone network to make full use of the shallow layer details and deep layer essential features of Hi-C data. Secondly, the residual module is introduced into the coding path and decoding path of the network to increase the depth of the model and prevent network degradation. Finally, the down sampling is used to reduce the calculation amount to decrease the required running time for the network model. The experimental results on real datasets showed that the proposed method had better performance than existing methods, and the inferred high resolution Hi-C data was closer to the real Hi-C data. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

SINGING BEAT TRACKING WITH SELF-SUPERVISED FRONT-END AND LINEAR TRANSFORMERS 23

SINGING BEAT TRACKING WITH SELF-SUPERVISED FRONT-END AND LIN...

引用

23rd international Society for Music Information Retrieval conference, ISMIR 2022

作者： Heydari, Mojtaba Duan, Zhiyao Department of Electrical and Computer Engineering University of Rochester 500 Wilson Blvd RochesterNY14627 United States

ISBN: (纸本)9781732729926

Tracking beats of singing voices without the presence of musical accompaniment can find many applications in music production, automatic song arrangement, and social media interaction. Its main challenge is the lack of strong rhythmic and harmonic patterns that are important for music rhythmic analysis in general. Even for human listeners, this can be a challenging task. As a result, existing music beat tracking systems fail to deliver satisfactory performance on singing voices. In this paper, we propose singing beat tracking as a novel task, and propose the first approach to solving this task. Our approach leverages semantic information of singing voices by employing pre-trained self-supervised WavLM and DistilHuBERT speech representations as the front-end and uses a self-attention encoder layer to predict beats. To train and test the system, we obtain separated singing voices and their beat annotations using source separation and beat tracking on complete songs, followed by manual corrections. Experiments on the 741 separated vocal tracks of the GTZAN dataset show that the proposed system outperforms several state-of-the-art music beat tracking methods by a large margin in terms of beat tracking accuracy. Ablation studies also confirm the advantages of pre-trained self-supervised speech representations over generic spectral features. © M. Heydari and Z. Duan.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Aerial Drone Platform for Asset Tracking Using an Active Gimbal 23

Aerial Drone Platform for Asset Tracking Using an Active Gim...

引用

23rd international conference on Control systems and computer Science technologies, CSCS 2021

作者： Patru, George-Cristian Vasilescu, Iuliu Rosner, Daniel Tudose, Dan Politehnica University of Bucharest Computer Science Department Bucharest Romania

ISBN: (纸本)9781665439398

We present a low cost quadrotor drone platform capable of visual servoing using an on-board camera placed on an active gimbal and on-board computation. The drone was built using basic off-the-shelf components and a few custom 3D printed parts and open source software. We plan to use this platform for visual inspection using autonomous navigation including takeoff, tracking and landing. Most commercial platforms that we investigated are significantly more expensive and are not flexible enough for the task we envision. We demonstrate the performance of our system on a simple task of visual servoing above a fiduciary marker. A key element is the active gimbal which is driven to maintain the target in the center of the field-of-view, regardless of the drone maneuvers. © 2021 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Federated Learning with non-IID Data: Algorithm and System Design 23

Semi-Supervised Federated Learning with non-IID Data: Algori...

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： Zhang, Zhe Ma, Shiyao Nie, Jiangtian Wu, Yi Yan, Qiang Xu, Xiaoke Niyato, Dusit School of Data Science and Technology Heilongjiang University Harbin150080 China Cryptology and Network Security Laboratory of Heilongjiang University Harbin150080 China College of Information and Communication Engineering Dalian Minzu University China School of Computer Science and Engineering Nanyang Technological University Singapore WeBank Co. Ltd. China

ISBN: (纸本)9781665494571

Federated Learning (FL) allows edge devices (or clients) to keep data locally while simultaneously training a shared high-quality global model. However, current research is generally based on an assumption that the training data of local clients have ground-truth. Furthermore, FL faces the challenge of statistical heterogeneity, i.e., the distribution of the client's local training data is non-independent identically distributed (non-IID). In this paper, we present a robust semi-supervised FL system design, where the system aims to solve the problem of data availability and non-IID in FL. In particular, this paper focuses on studying the labels-at-server scenario where there is only a limited amount of labeled data on the server and only unlabeled data on the clients. In our system design, we propose a novel method to tackle the problems, which we refer to as Federated Mixing (FedMix). FedMix improves the naive combination of FL and semi-supervised learning methods and designs parameter decomposition strategies for disjointed learning of labeled, unlabeled data, and global models. To alleviate the non-IID problem, we propose a novel aggregation rule based on the frequency of the client's participation in training, namely the FedFreq aggregation algorithm, which can adjust the weight of the corresponding local model according to this frequency. Extensive evaluations conducted on CIFAR-10 dataset show that the performance of our proposed method is significantly better than those of the current baseline. It is worth noting that our system is robust to different non-IID levels of client data. © 2021 IEEE.

关键词： Training Smart cities Design methodology Training data Semisupervised learning Collaborative work Data models

来源：评论

学校读者我要写书评

暂无评论

computer-Aided Analysis of Hybrid Dynamical systems in the ISMA Environment 23

Computer-Aided Analysis of Hybrid Dynamical Systems in the I...

引用

23rd IEEE international conference of Young Professionals in Electron Devices and Materials, EDM 2022

作者： Garder, Aleksey V. Shornikov, Yury V. Novosibirsk State Technical University Faculty of Automation and Computer Engineering Novosibirsk Russia Novosibirsk State Technical University Institute of Automation and Electrometry of the Siberian Branch of the Russian Academy of Sciences Faculty of Automation and Computer Engineering Novosibirsk Russia

ISBN: (纸本)9781665498043

The numerical analysis of complex event-continuous processes represented by the class of Cauchy problems with constraints on an event function is considered. The processes are specified in the developed unique textual-graphical language LISMA using Harel statecharts. The program models are edited, numerically analyzed, and their results are processed in the computer-aided analysis environment ISMA. The numerical analysis is performed using a collection of traditional and developed original explicit numerical integration methods of variable order and step with extended stability domains and an original algorithm detecting unilateral events in hybrid systems. The efficiency of the original methods has been tested on typical examples of hybrid systems. The chosen visual specification of program models satisfies the representation semantics of discrete-continuous processes with complex operational mode switching logic. Moreover, such a specification is understandable to an end user, who is rather interested in analyzing complex dynamic processes using simple and comprehensible tools for composing and editing models and being able to change the model structure and parameters fast. © 2022 IEEE.

关键词： computer aided analysis

来源：评论

学校读者我要写书评

暂无评论

DMF-MPC: A Dual-Stage and Multi-Step Forecasting Model Based Cooling System Control Method for Data Center Energy Cost Minimization 23

DMF-MPC: A Dual-Stage and Multi-Step Forecasting Model Based...

引用

作者： He, Xinrui Chen, Weiduo Dong, Xiaoshe Wang, Qiang Liu, Jialin Dong, Fan Su, Yuanqi School of Computer Science and Technology of Xi'an Jiaotong University Xi'an Jiaotong University Xi'an China

ISBN: (纸本)9781665494571

Nowadays, surveys show that the cooling system accounts for 30% of the energy consumption of data centers. The challenge of designing an effective cooling control system to minimize data center energy consumption cost as much as feasible while maintaining normal operation is a pressing one to address. The traditional cooling control method produces excessive cooling energy consumption, which causes a large amount of energy waste and economic expenses;Moreover, the existing Model Predictive Control (MPC) method based on the physical model has high modeling difficulty and model migration cost, and can only provide short-term control strategy. In this paper, we propose an MPC method based on a dual-stage and multi-step forecasting model (DMF-MPC), which can forecast the cooling system energy consumption in data centers accurately and provide a cost-saving control strategy of the cooling system for the next 24 hours on a combination of the peak-valley time-of-use (TOU) electricity price. We firstly propose a dual-stage and multi-step forecasting model (DMFM), a pure data-driven deep learning model, which adopts the historical server features of data centers, future weather factors, and cooling control to forecast the cooling system energy consumption for the multiple future periods, also a multi-step iterative training method is proposed in the training process to reduce the multi-step forecasting errors. In the control part of DMF-MPC, we introduce an optimal control model for the data center cooling system based on DMFM. The cost-saving control strategy for the next 24 hours under the peak-valley TOU electricity price standard can be obtained by solving the model through optimization algorithms. Finally, the effectiveness of the method is verified by validating DMF-MPC in a real campus high-performance computing (HPC) data center located in China. Our method achieves a 15%-25% cost reduction in the experiment. © 2021 IEEE.

关键词： Training Data centers Energy consumption Costs Cooling Computational modeling Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Learning-based Task Offloading in Dynamic Orbital Edge Computing Network 23

Learning-based Task Offloading in Dynamic Orbital Edge Compu...

引用

作者： Fang, Jiang Liu, Haitao Sun, Jiyan Li, Ting Liu, Yinlong Guo, Zhaorui Zhuang, Shangyuan Geng, Liru Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Computer Network Information Center Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665494571

In existing satellite communication model (SCM), satellites receive remote commands from ground station, then downlink raw sensed data to ground station directly. To tackle the challenges of high delay, intermittent downlink and congested ground station, edge computing for SCM is proposed, in which the flying satellites can locally process raw data. In SCM, the computing resources are time-variant and difficult to be obtained accurately due to rapid mobility of satellites. Multi-armed bandit (MAB) is a well-known scheme that has great potential to achieve nearly optimal task offloading for edge computing in mobility cases. However, existing MAB based works are difficult to apply in SCM. First, the distance difference between each satellite may be very large and the existing works have ignored the distance factor in exploration. This may cause huge errors for exploration cost evaluation and inevitable offloading failures. Second, the exploration and exploitation may have several order of magnitude difference while the existing work only use a constant to adjust the trade-off between the exploration and exploitation. As a result, it may take a long learning process to balance the trade-off, causing low offloading efficiency. To address the above challenges, in this work, we propose DMUCB as a Distance-aware and Mobility-aware task offloading algorithm based on MAB theory. The offloading decisions are made without any prior knowledge of computing resources. First, DMUCB provide a novel exploration method by jointly considering the distance, task size and the accumulative selected times to achieve an accurate exploration cost. Second, the difference of exploration and the new exploitation is largely reduced by our well-designed normalization mechanism for fast converge to the optimal offloading. Third, we present a time-variant parameter to effectively adapt the dynamic satellite communication environment. Simulation results show that DMUCB achieves close-to-optimal tas

关键词： Satellites Costs Smart cities Simulation Parallel processing Downlink Orbits

来源：评论

学校读者我要写书评

暂无评论

Frend for Edge Servers: Reduce Server Number! Keeping Service Quality! 23

Frend for Edge Servers: Reduce Server Number! Keeping Servic...

引用

作者： Li, Pengmiao Zhang, Yuchao Wang, Wendong Zhao, Kaichuan Lian, Bo Xu, Ke Zhang, Zhili Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Kuaishou Company Beijing China Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9781665494571

To keep pace with the exploding data volume raised from geographical distribution edge networks, more and more edge servers have been built in recent years. As the computing power and storage capacity are different on each server, requests have to be transferred from one server to another before finally being responded and returned back to users. Such server-to-server transmission naturally introduce non negligible latency, which inevitably affects the quality of service (QoS). To eliminate this transmission latency, Internet Service Providers (ISPs) are building or renting more edge servers (both computing servers and storage servers) to reduce transmission distance and enhance the server configuration, which brings great costs. Fortunately, through a large number of real trace analysis, we found that it is possible to reduce server number while keeping the QoS! In this paper, we first disclose three key characteristics from Kuaishou Company: (1) Unbalanced request frequencies on dif-ferent servers;(2) Imprecise latency measure on server-to-server transmission;(3) Nonlinear latency reduction to server number increment. Based on these findings, we propose a frequency-aware edge storage server deployment strategy Frend that is an improved Genetic Algorithm to optimize the number of edge storage servers by the internal diffusion capability that is a new latency measure called S2SL. Through a series of experiments using real application data, we demonstrate that while achieving the same S2SL, Frend can reduce the number of required edge storage servers by up to 56% compared with the state-of-the-art Anveshak method. © 2021 IEEE.

关键词： Costs Smart cities Web and internet services Buildings Quality of service Companies Frequency measurement

来源：评论

学校读者我要写书评

暂无评论

An Advantage Actor-Critic Deep Reinforcement Learning Method for Power Management in HPC systems 23rd

An Advantage Actor-Critic Deep Reinforcement Learning Method...

引用

23rd international conference on Parallel and Distributed Computing, Applications, and technologies, PDCAT 2022

作者： Khasyah, Fitra Rahmani Santiyuda, Kadek Gemilang Kaunang, Gabriel Makhrus, Faizal Amrizal, Muhammad Alfian Takizawa, Hiroyuki Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta55281 Indonesia Cyberscience Center Tohoku University Sendai980-8578 Japan

ISBN: (纸本)9783031299261

A primary concern when deploying a High-Performance Computing (HPC) system is its high energy consumption. Typical HPC systems consist of hundreds to thousands of compute nodes that consume huge amount of electrical power even during their idle states. One way to increase the energy efficiency is to apply the backfilling method to the First Come First Serve (FCFS) job scheduler (FCFS+Backfilling). The backfilling method allows jobs that arrive later than the first job in the queue to be executed earlier if the starting time of the first job is not affected, therefore increasing the throughput and the energy efficiency of the system. Nodes that are idle for a specific amount of time can also be switched off to further improve the energy efficiency. However, switching off nodes based only on their idle time can also impair the energy efficiency and the throughput instead of improving them. As an example, new jobs may immediately arrive after nodes are switched off, hence missing the chance of directly executing the jobs via backfilling. This paper proposed a Deep Reinforcement Learning (DRL)-based method to predict the most appropriate timing to switch on/off nodes. A DRL agent is trained with Advantage Actor-Critic algorithm to decide which nodes must be switched on/off at a specific timestep. Our simulation results on NASA iPSC/860 HPC historical job dataset show that the proposed method can reduce the total energy consumption compared to most of the conventional timeout policies that switch off nodes after they became idle for some period of time. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Reinforcement learning

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 << < 30 31 32 33 34 35 36 37 38 39 > >>

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：