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

4,080 篇 会议
36 篇 期刊文献
26 册 图书

馆藏范围

4,142 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,769 篇 工学
- 2,433 篇 计算机科学与技术...
- 2,074 篇 软件工程
- 910 篇 信息与通信工程
- 518 篇 生物工程
- 306 篇 控制科学与工程
- 299 篇 电气工程
- 296 篇 生物医学工程（可授...
- 159 篇 光学工程
- 158 篇 电子科学与技术（可...
- 156 篇 化学工程与技术
- 141 篇 安全科学与工程
- 137 篇 交通运输工程
- 124 篇 动力工程及工程热...
- 118 篇 机械工程
- 105 篇 仪器科学与技术
- 94 篇 材料科学与工程（可...
- 94 篇 网络空间安全
1,568 篇 理学
- 915 篇 数学
- 551 篇 生物学
- 344 篇 统计学（可授理学、...
- 258 篇 系统科学
- 251 篇 物理学
- 169 篇 化学
1,079 篇 管理学
- 793 篇 图书情报与档案管...
- 434 篇 管理科学与工程(可...
- 239 篇 工商管理
261 篇 医学
- 248 篇 临床医学
- 241 篇 基础医学(可授医学...
- 172 篇 药学(可授医学、理...
173 篇 法学
- 152 篇 社会学
82 篇 农学
78 篇 教育学
77 篇 经济学
5 篇 军事学
2 篇 文学
2 篇 艺术学
1 篇 哲学
1 篇 历史学

主题

360 篇 data mining
196 篇 machine learning...
185 篇 machine learning
165 篇 prediction algor...
163 篇 feature extracti...
148 篇 predictive model...
142 篇 deep learning
138 篇 big data
136 篇 training
133 篇 data models
114 篇 clustering algor...
109 篇 support vector m...
101 篇 computational mo...
98 篇 classification (...
85 篇 forecasting
84 篇 neural networks
81 篇 classification a...
81 篇 sentiment analys...
78 篇 heuristic algori...
70 篇 decision trees

机构

20 篇 faculty of infor...
16 篇 school of inform...
16 篇 school of inform...
13 篇 university of ch...
13 篇 vietnam national...
12 篇 school of inform...
12 篇 institute of inf...
12 篇 school of comput...
11 篇 beijing universi...
11 篇 school of inform...
11 篇 school of comput...
10 篇 school of comput...
10 篇 college of infor...
10 篇 school of inform...
10 篇 school of cyber ...
9 篇 school of electr...
9 篇 university of in...
8 篇 chengdu universi...
8 篇 school of inform...
8 篇 college of compu...

作者

9 篇 li yang
8 篇 wang lei
8 篇 liu yang
8 篇 guo kun
8 篇 gu shenming
7 篇 yang yang
7 篇 wang chao
7 篇 wang tao
7 篇 wang wei
7 篇 zhang yan
7 篇 wang xin
7 篇 li wei
7 篇 zhang liang
7 篇 zhang han
6 篇 li xin
6 篇 xu hao
6 篇 behera h.s.
6 篇 ye jun
6 篇 zhang kun
6 篇 rachmadita andre...

语言

3,587 篇 英文
550 篇 其他
59 篇 中文

检索条件"任意字段=2022 International Conference on Algorithms, Data Mining, and Information Technology, ADMIT 2022"

共 4142 条记录，以下是4041-4050 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：

Prevention of Road Accidents by Improving Stress Resilience of Drivers using Machine Learning

Prevention of Road Accidents by Improving Stress Resilience ...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE international conference on

作者： A Sabareesan N Sabari Rohith N Vikash R Yuvaraj V Lakshmanan Department of Information Technology Sri Eshwar College of Engineering Coimbatore India

ISBN: (纸本)9781665491129

The recognition of epileptic seizures via method of means of classifying electroencephalography (EEG) cautions into ictal and interictal guidelines is an irritating test, as it recognizes the seizure and seizure-loosened conditions a patient who has epilepsy. In going before works, numerous gadgets learning based methods had been brought to research1and decipher EEG alarms for the explanation of their right kind. Be that as it may, non-straight and non-work area bound traits of EEG makes make it complex aware of get whole records around those 1dynamic biomedical cautions. To adapt to this issue, this paper makes a specialty of1extracting the greatest segregating and recognizing elements of seizure EEG accounts to expand a strategy that utilizes e ach fluffy basically based absolutely and ordinary gadget getting to know algorithms to treat epileptic seizures. The recommended structure divides unidentified EEG signal fragments interictal and ictal instructions. Utilizing empirical evaluation, the version is being tested on benchmark datasets, explicitly the Bonn and Kids’ Clinic of Boston Massachusetts Establishment of Innovation (CHB-MIT) datasets. The proposed works of art are utilized grow beneath VWNB (Worth Weighted Gullible Bayes). While everything about systems as far as concerns me is limited of their precision of their individual applications, that the total of techniques while applied pleasantly has a superior general sort of exactness.

关键词： Support vector machines Wireless communication Training Road accidents Brain modeling Electroencephalography data models

来源：评论

学校读者我要写书评

暂无评论

Interference elimination in IRS-enabled indoor mmw-D2D communication

Interference elimination in IRS-enabled indoor mmw-D2D commu...

引用

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Bingjie Han Xin Chen Libo Jiao Dongchao Guo School of Control Engineering Beijing Information Science & Technology University Beijing China School of Computer Science Beijing Information Science & Technology University Beijing China

In this paper, we study the interference elimination in intelligent reflecting surface (IRS) enabled indoor millimeter-wave device to device (mmw-D2D) communication. In order to improve spectrum utilization and transmission rate, we consider assisting IRS by the anti-phase signal reflection to reduce the co-channel interference in indoor mmw-D2D communication. We establish the system model of the IRS selection and enablement on interference elimatation (IRS-SEIE) problem based on integer programming theory. Then, we prove that IRS-SEIE problem is an NP-hard problem by transforming it into a knapsack problem. Therefore, we propose a heuristic algorithm based on genetic algorithm to obtain the optimal solution. Comparison experiments with particle swarm optimization (PSO), monte carlo (MC) algorithm and without IRS show that proposed algorithm's rate is 24.36%, 48.47% and 103.03% higher than them. And it can also reduce the blocking probability by 25.53%, 45.81% and 62.34%.

关键词： Wireless communication Power demand Surface waves Heuristic algorithms System performance Interference elimination Reflection

来源：评论

学校读者我要写书评

暂无评论

Gaussian Decay Function-based Improved Moment Matching for Ocular Artifacts Removal

Gaussian Decay Function-based Improved Moment Matching for O...

引用

IEEE international conference on Bioinformatics and Biomedicine (BIBM)

作者： Hua Jiang Qiuxia Shi Siying Liu Jiuying Zhang Qinglin Zhao Bin Hu Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Key Laboratory of Special Functional Materials and Structural Design Ministry of Education Lanzhou University Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences Chinese Academy of Sciences Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University & Institute of Semiconductors Engineering Research Center of Open Source Software and Real-Time System (Lanzhou University) Ministry of Education Key Laboratory of Special Functional Materials and Structural Design (Lanzhou University) Ministry of Education Lanzhou China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Electroencephalogram (EEG) equipped with high time resolution that distracted by incoherent brain sources which including ocular artifacts (OAs) generating by blinks is of great significance. Therefore, these OAs got corrected before extracting information from EEG is indispensable. Improved Moment Matching (IMM) is a high-speed denoising algorithm suitable for removing OA in multi-channel EEG, which is an improvement of the moment matching method used to remove stripe noise in hyperspectral images. On foundation of this, this paper proposes an optimization algorithm for IMM based on Gaussian decay function (IMM_G). In the first place, the construction of the reference signal is optimized via utilizing a Gaussian decay function, thereby preventing the signal distortion caused by the filter. And then, a method for judging the to-be-processed interval is proposed to realizes the individualized processing of different channels. As a result, through quantitative comparison experiments with simulated data and real data from the UAIS laboratory, it was identified that IMM_G showed less time complexity, significantly enhanced arithmetic speed and denoising consequence while the detail retention ability of the original method for the non-blinking region of multi-channel EEG data is maintained. Hence, this method could be extensively used in High-density EEG (hdEEG) OAs removal scene.

关键词： Electrooculography Noise reduction Filtering algorithms Distortion Electroencephalography Recording Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Decomposition of power system inspection services for 5G cloud-edge-end collaboration

Decomposition of power system inspection services for 5G clo...

引用

international Wireless Communications and Mobile Computing conference, IWCMC

作者： Hui Xiang Yucheng Wang Yuxiang Lv Yawen Dong Hongyan Wang Yang Yang Liangkang Wei Fanqin Zhou Lei Feng Anhui Jiyuan Software Co. Ltd State Grid Information &#x0026 Telecommunication Group Hefei China State Key Laboratory of Networking and Switching Technology BUPT Beijing China

With the development of the smart power grid, the requirements for intelligent, vivid, and real-time power system inspection services are getting higher. 5G, artificial intelligence, edge computing, big data, virtual reality, and other information technologies bring breakthroughs for power system inspection services evolution, but in the meanwhile, making the services more complex and draining large amounts of computing resources. In the 5G networks with collaborative computing enabled in cloud-edge-end nodes, how to reasonably decompose a complex power system inspection service into multiple task clusters becomes a prerequisite for the efficient distributed deployment of the service and its rapid execution. This paper proposes an approach for the decomposition of intelligent power system inspection services. It considers the computing resource requirements of the functional components in a power system inspection service as well as the interactions between them, perceives the computing capabilities of heterogeneous nodes, such as cloud, edge, and collaborative end terminal in 5G networks, and decomposes the service into multiple task clusters which retain the original logical structure. Simulation results show that the approach can produce suitable results, which can reduce the expected service execution time and improve the utilization of network resources.

关键词： Wireless communication Cloud computing Solid modeling 5G mobile communication Computational modeling Heuristic algorithms Collaboration

来源：评论

学校读者我要写书评

暂无评论

FedTADBench: Federated Time-series Anomaly Detection Benchmark

FedTADBench: Federated Time-series Anomaly Detection Benchma...

引用

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Fanxing Liu Cheng Zeng Le Zhang Yingjie Zhou Qing Mu Yanru Zhang Ling Zhang Ce Zhu College of Computer Science Sichuan University China School of Information and Communication Engineering University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China College of Polymer Science and Engineering Sichuan University China West China School of Public Health Sichuan University China

Time series anomaly detection strives to uncover potential abnormal behaviors and patterns from temporal data, and has fundamental significance in diverse application scenarios. Constructing an effective detection model usually requires adequate training data stored in a centralized manner, however, this requirement sometimes could not be satisfied in realistic scenarios. As a prevailing approach to address the above problem, federated learning has demonstrated its power to cooperate with the distributed data available while protecting the privacy of data providers. However, it is still unclear that how existing time series anomaly detection algorithms perform with decentralized data storage and privacy protection through federated learning. To study this, we conduct a federated time series anomaly detection benchmark, named FedTADBench, which involves five representative time series anomaly detection algorithms and four popular federated learning methods. We would like to answer the following questions: (l)How is the performance of time series anomaly detection algorithms when meeting federated learning? (2) Which federated learning method is the most appropriate one for time series anomaly detection? (3) How do federated time series anomaly detection approaches perform on different partitions of data in clients? Numbers of results as well as corresponding analysis are provided from extensive experiments with various settings. The source code of our benchmark is publicly available at https://***/fanxindiu2020/FedTADBench.

关键词： data privacy Federated learning Source coding Time series analysis Distributed databases Training data Memory

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Teaching System Based on RGB-D Human-Computer Interaction 21

Design and Implementation of Teaching System Based on RGB-D ...

引用

2021 4th international conference on Education technology Management

作者： Ying Guo LeLe Zhang Tongao Ge Haoran Yang Guowei Zhao Hui Li School of Information Science and Technology _ Qingdao University of Science and Technology _ lab509 Qingdao University of Science and Technology China School of Information Science and engineering _ Yanshan University _ lab231 Yanshan University China

ISBN: (纸本)9781450385800

The traditional teaching model has shortcomings such as single presentation method and difficult storage of writing on the blackboard, The emergence of multimedia teaching will change the form of chalk and blackboard in traditional teaching and improve teaching efficiency. However, there are also defects such as relying on input device control, which affects teaching quality. The control method based on human-computer interaction can solve this drawback and improve the interaction between teachers and students. Therefore, this paper designs a teaching system based on RGB-D human-computer interaction. This system uses Kinect to obtain depth images to identify the skeleton model of the human body. By analyzing the needs of the teaching system, designing corresponding control actions and acquiring three-dimensional data of key joint points for these actions, Analyze this data to get the main feature information and auxiliary judgment information of the movement, Design a control action recognition algorithm based on this information, Finally, comprehensive control requirements and control actions are designed to design a teaching control system to realize auxiliary control of common teaching functions. After testing, the correct rate of the system's various action recognition algorithms is about 95%, and the real-time, stability and other indicators meet the requirements of teaching control, and the system performance is good.

关键词： Motion detection algorithm Human-computer interaction Kinect

来源：评论

学校读者我要写书评

暂无评论

Escaping saddle points with bias-variance reduced local perturbed SGD for communication efficient nonconvex distributed learning 22

Escaping saddle points with bias-variance reduced local pert...

引用

Proceedings of the 36th international conference on Neural information Processing Systems

作者： Tomoya Murata Taiji Suzuki NTT DATA Mathematical Systems Inc. Tokyo Japan and Graduate School of Information Science and Technology The University of Tokyo Graduate School of Information Science and Technology The University of Tokyo and Center for Advanced Intelligence Project RIKEN Tokyo Japan

ISBN: (纸本)9781713871088

In recent centralized nonconvex distributed learning and federated learning, local methods are one of the promising approaches to reduce communication time. However, existing work has mainly focused on studying first-order optimality guarantees. On the other side, second-order optimality guaranteed algorithms, i.e., algorithms escaping saddle points, have been extensively studied in the non-distributed optimization literature. In this paper, we study a new local algorithm called Bias-Variance Reduced Local Perturbed SGD (BVR-L-PSGD), that combines the existing bias-variance reduced gradient estimator with parameter perturbation to find second-order optimal points in centralized nonconvex distributed optimization. BVR-L-PSGD enjoys second-order optimality with nearly the same communication complexity as the best known one of BVR-L-SGD to find first-order optimality. Particularly, the communication complexity is better than non-local methods when the local datasets heterogeneity is smaller than the smoothness of the local loss. In an extreme case, the communication complexity approaches to $\widetilde \Theta(1)$ when the local datasets heterogeneity goes to zero. Numerical results validate our theoretical findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Medical Recommendation System using Machine Learning Techniques & Natural Language Processing

Automated Medical Recommendation System using Machine Learni...

引用

Communication, Computing and Industry 4.0 (C2I4), international conference on

作者： Likith V P M. Farida Begam Magadum Neeraj Shashikant Department of Information Science and Engineering CMR Institute of Technology Bengaluru India

ISBN: (数字)9781665474979

ISBN: (纸本)9781665474986

The suggested work in this paper relates to the automation in the medical field in terms of how the diagnosis of irregularities has been going on in the industry and what the future in the said field looks like with the advancing technology. With the advent of application of machine learning approaches, we have observed a significant rise in the performance of detection and prediction with each passing year. With the current norms being that a patient is to perform the necessary tests and wait for a significant period of time to gain a consultation with an esteemed doctor. The methodologies used by other authors from the research papers that we gathered were either using image corpus or using machine learning techniques to detect and identify cancer, while others have used Natural Language Processing techniques to extract information from handwritten or printed texts and have developed models based on it. We have addressed the problem with a unified approach that combines both machine learning and Natural Language Processing techniques in tandem to extract data and correlations which may have been ignored by the other models. The image corpus and handwritten notes would together give better insights and help improve the accuracy of the model. Bearing in mind the objective of relieving novice doctors from feeling perplexed, in addition to answering questions that patients might have, our model aims to allow such medical professionals make better informed decisions in their diagnosis and prognosis procedures. The chatbot, to serve this purpose, will be based on Bidirectional Encoder Representations from Transformers (BERT), which has demonstrated ground-breaking performance in tasks involving natural language understanding, including sentiment analysis, semantic role labelling, sentence classification, and the disambiguation of polysemous words. We aim to not only successfully diagnose and provide prognosis for cancer, but also to detect the chances of remission. Our

关键词： Object oriented modeling Semantics Machine learning Medical services Feature extraction Transformers data mining

来源：评论

学校读者我要写书评

暂无评论

Application of Capsule Network to Tablet Identification 21

Application of Capsule Network to Tablet Identification

引用

Proceedings of the 2021 4th international conference on algorithms, Computing and Artificial Intelligence

作者： Wenliang He Minling Zhu Computer School Beijing Information Science & Technology University China

ISBN: (纸本)9781450385053

To address the problem of pill defect recognition, we propose to apply capsule neural network for pill defect recognition. The effects of dynamic routing iteration rounds and different compression function constant term schemes on the performance of the capsule neural network are investigated in the context of small data sets, and the model effects are verified experimentally. The experimental results show that both the number of dynamic routing iteration rounds and different compression function constant term schemes can affect the performance of the capsule neural network, and it is essential to choose an appropriate scheme in the process of training the model. The capsule neural network is found to be suitable for the field of pill defect recognition through *** CONCEPTS • Computing methodologies∼Visual content-based indexing

关键词： capsule network image recognition Deep learning dynamic routing pill identification

来源：评论

学校读者我要写书评

暂无评论

Extraction of SIFT Features for Identifying Disaster Hit areas using Machine Learning Techniques

Extraction of SIFT Features for Identifying Disaster Hit are...

引用

Knowledge Engineering and Communication Systems (ICKECS), international conference on

作者： V. Suresh Kumar Ahmed Alemran Shashi Kant Gupta Bramah Hazela Chandra Kumar Dixit Bhadrappa Haralayya Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai India Physics department Medicine college-Misan university Al Amarah Iraq Department of CSE Integral University Lucknow India Computer Science & Engineering Amity School of Engineering & Technology Lucknow Amity University Uttar Pradesh India Department of Physics Dr. Shakuntala Misra National Rehabilitation University Lucknow India Department of MBA Lingaraj Appa Engineering College Bidar Bidar India

Beyond the death toll, disasters have major and often devastating social and economic ramifications, including financial damage and loss. As a result of recent advances in artificial intelligence (AI), particularly in machine learning (ML) and deep learning (DL), disasters can be better managed. An emphasis has been placed on disaster and hazard prediction studies as well as assessments of risk and susceptibility and the detection of disasters as well as the implementation of early warning systems and disaster monitoring. A number of current disaster management applications have also been examined. The findings are discussed, and suggestions for further research are offered. As computing power rises and data availability expands, new flood detection methods are being developed using machine learning. To better understand nonlinear systems and make flood forecasts, machine learning has become a go-to tool. Hydrologic and hydraulic models that explain physical processes can be used in flood forecasting in conventional ways to predict hazard factors. Although these models may be used to gain a better understanding of a system, they frequently need a large amount of computing and data resources. Methods based on machine learning have the potential to enhance accuracy while also decreasing calculation time and model creation costs. As a result of this study, we now have a better understanding of the current status of flood forecasting using machine learning algorithms. This paper proposes a machine learning model for SIFT extraction. Once the extraction is done comparative analysis is done with the SVM and Fine Tree classifiers to prove the efficiency of the proposed model.

关键词： Support vector machines Biological system modeling Computational modeling Machine learning Predictive models Feature extraction Mathematical models

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415页 << < 401 402 403 404 405 406 407 408 409 410 > >>

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：