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

2,990 篇 会议
38 篇 期刊文献
7 册 图书

馆藏范围

3,035 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,770 篇 工学
- 1,418 篇 计算机科学与技术...
- 687 篇 软件工程
- 492 篇 电气工程
- 407 篇 信息与通信工程
- 214 篇 控制科学与工程
- 130 篇 生物工程
- 79 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 59 篇 机械工程
- 55 篇 仪器科学与技术
- 48 篇 光学工程
- 40 篇 网络空间安全
- 31 篇 动力工程及工程热...
- 31 篇 安全科学与工程
- 25 篇 石油与天然气工程
- 23 篇 化学工程与技术
- 22 篇 材料科学与工程（可...
- 22 篇 交通运输工程
- 21 篇 测绘科学与技术
518 篇 理学
- 225 篇 物理学
- 191 篇 数学
- 143 篇 生物学
- 59 篇 统计学（可授理学、...
- 40 篇 系统科学
- 28 篇 化学
213 篇 管理学
- 145 篇 管理科学与工程(可...
- 89 篇 图书情报与档案管...
- 32 篇 工商管理
136 篇 医学
- 113 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
18 篇 文学
14 篇 农学
11 篇 教育学
9 篇 经济学
2 篇 军事学

主题

593 篇 neural networks
179 篇 training
169 篇 deep learning
168 篇 artificial neura...
142 篇 computational mo...
129 篇 feature extracti...
123 篇 convolutional ne...
117 篇 neural network
89 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
76 篇 computer archite...
75 篇 distributed comp...
75 篇 accuracy
65 篇 signal processin...
62 篇 distributed proc...
61 篇 data models
61 篇 recurrent neural...
51 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 department of co...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,773 篇 英文
254 篇 其他
12 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 3035 条记录，以下是1731-1740 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：

Big Data Analytics based on PANFIS MapReduce 3

Big Data Analytics based on PANFIS MapReduce

引用

3rd INNS conference on Big Data and Deep Learning (INNS BDDL)

作者： Za'in, Choiru Pratama, Mahardhika Lughofer, Edwin Ferdaus, Meftahul Cai, Qing Prasad, Mukesh La Trobe Univ Melbourne Vic Australia Nanyang Technol Univ Singapore Singapore Johannes Kepler Univ Linz Linz Australia Univ New South Wales Canberra ACT Australia Univ Technol Sydney Sydney NSW Australia Univ Technol Sydney FEIT Sch Software Ctr Artificial Intelligence Sydney NSW Australia

In this paper, a big data analytic framework is introduced for processing high-frequency data stream. This framework architecture is developed by combining an advanced evolving learning algorithm namely Parsimonious network Fuzzy Inference System (PANFIS) with MapReduce parallel computation, where PANFIS has the capability of processing data stream in large volume. Big datasets are learnt chunk by chunk by processors in MapReduce environment and the results are fused by rule merging method, that reduces the complexity of the rules. The performance measurement has been conducted, and the results are showing that the MapReduce framework along with PANFIS evolving system helps to reduce the processing time around 22 percent in average in comparison with the PANFIS algorithm without reducing performance in accuracy. (C) 2018 The Authors. Published by Elsevier Ltd.

关键词： Big data stream analytic distributed evolving algorithm Scalable real-time data mining Parallel learning Rule merging strategy

来源：评论

学校读者我要写书评

暂无评论

Surgical Aid Visualization System for Glioblastoma Tumor Identification based on Deep Learning and In-Vivo Hyperspectral Images of Human Patients

Surgical Aid Visualization System for Glioblastoma Tumor Ide...

引用

conference on Medical Imaging - Image-Guided Procedures, Robotic Interventions, and Modeling

作者： Fabelo, Himar Halicek, Martin Ortega, Samuel Szolna, Adam Morera, Jesus Sarmiento, Roberto Callico, Gustavo M. Fei, Baowei Univ Texas Dallas Dept Bioengn Richardson TX 75083 USA Univ Las Palmas Gran Canaria Inst Appl Microelect Las Palmas Gran Canaria Spain Emory Univ Dept Biomed Engn Atlanta GA 30322 USA Georgia Inst Tech Atlanta GA USA Univ Hosp Doctor Negrin Gran Canaria Dept Neurosurg Las Palmas Gran Canaria Spain Univ Texas Southwestern Med Ctr Dallas Adv Imaging Res Ctr Dallas TX 75390 USA Univ Texas Southwestern Med Ctr Dallas Dept Radiol Dallas TX 75390 USA

ISBN: (纸本)9781510625501

Brain cancer surgery has the goal of performing an accurate resection of the tumor and preserving as much as possible the quality of life of the patient. There is a clinical need to develop non-invasive techniques that can provide reliable assistance for tumor resection in real-time during surgical procedures. Hyperspectral imaging (HSI) arises as a new, non-invasive and non-ionizing technique that can assist neurosurgeons during this difficult task. In this paper, we explore the use of deep learning (DL) techniques for processing hyperspectral (HS) images of in-vivo human brain tissue. We developed a surgical aid visualization system capable of offering guidance to the operating surgeon to achieve a successful and accurate tumor resection. The employed HS database is composed of 26 in-vivo hypercubes from 16 different human patients, among which 258,810 labelled pixels were used for evaluation. The proposed DL methods achieve an overall accuracy of 95% and 85% for binary and multiclass classifications, respectively. The proposed visualization system is able to generate a classification map that is formed by the combination of the DL map and an unsupervised clustering via a majority voting algorithm. This map can be adjusted by the operating surgeon to find the suitable configuration for the current situation during the surgical procedure.

关键词： Brain tumor cancer surgery hyperspectral imaging intraoperative imaging deep learning supervised classification convolutional neural network (CNN) classifier

来源：评论

学校读者我要写书评

暂无评论

Single Image Super-Resolution Reconstruction of Enhanced Loss Function with Multi-GPU Training

Single Image Super-Resolution Reconstruction of Enhanced Los...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Jianqiang Huang Kai Li Xiaoying Wang Department of Computer Technology and Application Qinghai University China Department of Computer Science and Technology Tsinghua University China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

According to research on super-resolution (SR), SR image reconstruction using generated anti-networks can produce images that are more realistic than using convolutional neural networks. At present, SR technology based on convolutional neural networks ignores the impact of loss function on image reconstruction; the results lack detail and accuracy. In this paper, we use SR method and combine Generative Adversarial networks to design a super-resolution (Lapras-GAN) model of the enhanced loss function. The proposed enhancement loss function is a Mix loss function that combines the multiscale SSIM and L1 loss functions to obtain realistic images. We performed qualitative and quantitative analysis of the performance of different loss functions and demonstrated the advantages of the Mix loss function. In addition, the neural network is accelerated by multiple GPUs of multiple nodes, which can be 3-4 times faster than a single node single GPU. Experimental results show that the proposed Lapras-GAN method can generate images consistent with images produced by human perception. Further comparisons show that our Lapras-GAN has excellent performance and test time in the PIRM2018 experimental test data set. Finally, we obtained a perception index of 1.83 and a test time of 0.031s in the PIRM2018 competition test set.

关键词： Training Gallium nitride Graphics processing units Mathematical model neural networks Deep learning Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

DCNN-BiGRU Text Classification Model Based on BERT Embedding

DCNN-BiGRU Text Classification Model Based on BERT Embedding

引用

IEEE International Symposium on Parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： He Huang Xiao-Yuan Jing Fei Wu Yong-Fang Yao Xin-Yu Zhang Xi-Wei Dong College of Computer Science Guangdong University of Petrochemical Technology Guangdong China College of Automation Nanjing University of Posts and Telecommunications Nanjing China School of Computer Wuhan University Wuhan China School of Information Science and Technology Jiujiang University Jiujiang China

ISBN: (纸本)9781728152103

Text Classification is a hot topic in natural language processing. In view of the strong correlation the structure of natural language, direct translation the text into vector will lead to too high dimension. In addition, traditional word vector usually maps words with a single vector, which cannot represent the polyseme of words and affect the accuracy of the final classification. In this paper, we propose a novel DCNN-BiGRU (Deep Convolutional neural network Bidirection Gated Recurrent) text classification model based on BERT(Bidirectional Encoder Representations from Transformer) embedding. The model adopts the BERT to train the language model of word semantic representation. The semantic vector is generated dynamically according to the context of the word, and then it is put into the DCNN-BiGRU hybrid model. By doing so, the semantic vector not only contains the local features of text but also the context features of text. Experiments on CCERT Chinese email sample set and movie comment data set verify the validity of this model.

关键词： feature extraction information filtering learning (artificial intelligence) natural language processing pattern classification recurrent neural nets text analysis Natural Language processing recurrent neural nets text processing Information filtering Pattern recognition Bit error rate test Text categorization Feature extraction Word modelling languages

来源：评论

学校读者我要写书评

暂无评论

Detecting Interest-Factor Influenced Abnormal Evaluation of Teaching via Multimodal Embedding and Priori Knowledge Based neural network

Detecting Interest-Factor Influenced Abnormal Evaluation of ...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Yu Mao Yifan Zhu Sifan Zhang Dexiu Zhang Fuquan Zhang Xiaozhong Fan School of Computer Science and Technology Beijing Institute of Technology Beijing China School of Computer Science Minnan Normal University Zhangzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Student evaluations of teaching (SET) helps to quantitatively measure the teaching performance of classes. However, concerns arouse when the result of SET and students' final grades are highly positively correlated, which means the students may make the evaluation based on the final grades they take. For the purpose of avoiding retaliation and mutual reward rating, some methods based on statistics or rules are used to detect the presence of anomaly evaluation. Whereas, the problem is still challenging since the characteristics of this abnormal evaluation are implicit and multimodal. Besides, additional information such as the domain of subject, instructors' teaching style, and the reputation spread by students also requires corresponding prior knowledge to supplement the abnormal evaluation detection model. Therefore, in this paper, we proposed a multimodal embedding and prior knowledge based neural network to detect potential so called Interest Factor Influenced Abnormal Evaluation (IFAE). The method proposed in this paper uses SDNE and PV-DM to embed the evaluation network between students and teachers and the comment text of students. Taking into account the continuity of mutual evaluation between students and teachers during the teaching cycles and the different emphasis of students' comment texts on teachers, the features of students and teachers are comprehensively constructed. Then, the attention mechanism is used in the comment text to perform final prediction jointly with above features. The experiment result shows that our proposed model outperforms other state-of-art models which based on single type of features on F1 score by 9.25%.

关键词： Education Feature extraction neural networks Data mining Knowledge based systems Computer science Quality control

来源：评论

学校读者我要写书评

暂无评论

Intelligent Identification Method for Natural Disasters along Transmission Lines Based on Inter-Frame Difference and Regional Convolution neural network

Intelligent Identification Method for Natural Disasters alon...

引用

IEEE International conference on Big Data and Cloud Computing (BdCloud)

作者： Fangrong Zhou Junbo Huang Bing Sun Gang Wen Ye Tian Electric Power Research Institute Yunnan Power Grid Company Ltd Yunnan China Yunnan Power Grid Co. Ltd Yunnan China China Information Communication Technologies Group Corporation Wuhan China

ISBN: (数字)9781728143286

ISBN: (纸本)9781728143293

Special and high-voltage transmission lines are often installed in mountainous areas, and the traffic is inconvenient. Therefore, power grid operation and maintenance personnel often use unmanned aerial vehicles along the line and environmental conditions to find potential safety hazards. However, domestic and foreign scholars need to improve the identification and monitoring of hidden images of aerial image defects, especially for landslides, mudslides, ice coatings and other disasters. In this paper, the inter-frame difference and convolutional neural network is used to identify the natural disasters along the transmission line. Firstly, the image denoising technique is used to pre-process the original camera image. Secondly, the inter-frame difference technology is used to extract the natural disaster characteristics, and the disaster pre-judgment is realized. Convolutional neural networks accurately identify aerial images and analyze the types of disasters. The experimental results show that the method used in this paper can timely discover natural disasters along the transmission line and accurately analyze the types of disasters, which has high engineering practical value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of No-Go Game Algorithm Based on Reinforcement Learning

Design of No-Go Game Algorithm Based on Reinforcement Learni...

引用

IEEE International Symposium on Parallel and distributed processing with Applications and IEEE International conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Jianbo Bo Shuqin Li Rui Geng Jiaming Tong Beijing Information Science and Technology University Beijing China

ISBN: (纸本)9781728152103

The research focus of computer chess is how to use computer to abstract and formalize the logical thinking activities of human beings in chess game. This paper designs and implements a No-Go algorithm based on reinforcement learning. During the game, MCTS algorithm is used to explore the legal situation under the current situation. In this process, the convolutional neural network is used to evaluate the explored situation. Then, the neural network is trained to evaluate the situation with the results of the match, so as to achieve the effect of self-improving algorithm without human experience. In addition, the author used the Union-Find to find the legal landing point on the chessboard. Finally, the experiment shows that this type of No-Go algorithm based on reinforcement learning can be improved by itself and reach a certain level of chess ability, which improves the efficiency of searching legal moves compared with the traditional No-Go chessboard traversal method.

关键词： computer games convolutional neural nets learning (artificial intelligence) Monte Carlo methods tree searching Tree searching Computer Games learning (artificial intelligence) Monte Carlo technique Human Learning algorithms automatic game Video Games Hunting Game theory Game animals Computers

来源：评论

学校读者我要写书评

暂无评论

A Novel Hierarchical Edge Computing Solution Based on Deep Learning for distributed Image Recognition in IoT Systems

A Novel Hierarchical Edge Computing Solution Based on Deep L...

引用

International conference on Information Technology (INCIT)

作者： Nitis Monburinon Salahuddin Muhammad Salim Zabir Natthasak Vechprasit Satoshi Utsumi Norio Shiratori Faculty of Information Technology Thai-Nichi Institute of Technology Bangkok Thailand Department of Creative Engineering Tsuruoka College Tsuruoka Japan Faculty of Symbiotic Systems Science Fukushima University Fukushima Japan Research and Development Initiative Chuo University Tokyo Japan

ISBN: (纸本)9781728110202

Traditionally, IoT systems utilize cloud computing platforms for ease of deployment. However, such platforms are resource-intensive, relatively expensive, and lead to longer response time due to network latency. Hence, cloud computing may not always be suitable for unusually large scale deployment. Various edge computing solutions have been proposed to overcome the above issues. However, most of such solutions rely upon expensive edge servers, which make them unsuitable for distributed applications like image recognition in agricultural fields. In this paper, we propose a hierarchical edge computing-based image recognition system in which the major processing is carried out at low-cost gateway devices like Raspberry Pi. As an example case, we address the issue of recognition of animals intruding in agricultural fields. We implement a dynamic learning method, in which a convolutional neural network is dynamically trained to recognize potential target classes based on a specific deployment environment. The AI detection module is then loaded on to the lowest level of edge servers on gateway devices for detection of animals and providing feedback. Experiments show that our proposed recognition system can perform offline image classification tasks with up to seven times higher accuracy and more than two times faster evaluation time in comparison with general-purpose cloud recognition systems. Besides, it consumes less than 6% of the network bandwidth and only a fraction of the energy as well as other computational resources compared with existing approaches.

关键词： Internet of Things Cloud computing Animals Image edge detection Edge computing Servers

来源：评论

学校读者我要写书评

暂无评论

27th Italian Workshop on neural networks, WIRN 2017

27th Italian Workshop on Neural Networks, WIRN 2017

引用

27th Italian Workshop on neural networks, WIRN 2017

ISBN: (纸本)9783319569031

The proceedings contain 36 papers. The special focus in this conference is on neural networks. The topics include: Redefining information processing through neural computing models;a neural approach for hybrid events discrimination at stromboli volcano;fully automatic multispectral MR image segmentation of prostate gland based on the fuzzy C-means clustering algorithm;accurate computation of drude-lorentz model coefficients of single negative magnetic metamaterials using a micro-genetic algorithm approach;effective blind source separation based on the adam algorithm;depth-based hand pose recognizer using learning vector quantization;correlation dimension-based recognition of simple juggling movements;cortical phase transitions as an effect of topology of neural network;human fall detection by using an innovative floor acoustic senso;an improved hilbert-huang transform for non-linear and time-variant signals;privacy-preserving data mining for distributed medical scenarios;rule base reduction using conflicting and reinforcement measures;an application of internet traffic prediction with deep neural network;convolutional neural networks with 3-D kernels for voice activity detection in a multiroom environment;a hybrid variable selection approach for NN-based classification in industrial context;advanced neural networks systems for unbalanced industrial datasets;quantum-inspired evolutionary multiobjective optimization for a dynamic production scheduling approach;a neural network-based approach for steam turbine monitoring;a predictive model of artificial neural network for fuel consumption in engine control system;SOM-based analysis to relate non-uniformities in magnetic measurements to hot strip mill process conditions and artificial neural network analysis and erp in intimate partner violence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High performance scalable hardware SOM architecture for real-time vector quantization 3

High performance scalable hardware SOM architecture for real...

引用

3rd IEEE International conference on Image processing, Applications and Systems (IPAS)

作者： Jovanovic, Slavisa Rabah, Hassan Weber, Serge Univ Lorraine Inst Jean Lamour UMR 7198 Nancy France

ISBN: (纸本)9781728102474

Real-time vector quantization requires high performances and high configurability. Unsupervised neural networks such as Self-organizing maps (SOMs) have been commonly used as vector quantizers in many application domains, mainly in software. The software counterparts of SOMs are highly flexible with limited performances and cannot be used in real-time applications where tight timing constraints require high performances. The flexibility of software SOMs and the performances of their hardware counterparts must be coupled to obtain highly configurable, scalable and application independent SOMs. In this paper, a massively parallel hardware implementation of a scalable and flexible self-organizing map (SOM) is presented. The scalability and flexibility are obtained by using highly connected communication approach tailored to SOM needs, while the distributed clusters of neuro-processors are at the origin of high performances. The proposed architecture is validated on different map sizes (up to 16 x 16) with different vector widths (up to 256) applied for real-time vector quantization.

关键词： Self-Organizing Map network-on-Chip Vector Quantization Big Data

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304页 << < 170 171 172 173 174 175 176 177 178 179 > >>

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：