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

1,327 篇 会议
11 篇 期刊文献
9 册 图书

馆藏范围

1,347 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

915 篇 工学
- 757 篇 计算机科学与技术...
- 498 篇 软件工程
- 303 篇 信息与通信工程
- 204 篇 电气工程
- 175 篇 生物工程
- 127 篇 生物医学工程（可授...
- 107 篇 光学工程
- 90 篇 控制科学与工程
- 80 篇 电子科学与技术（可...
- 58 篇 仪器科学与技术
- 48 篇 机械工程
- 35 篇 化学工程与技术
- 28 篇 安全科学与工程
- 26 篇 交通运输工程
425 篇 理学
- 189 篇 生物学
- 187 篇 数学
- 151 篇 物理学
- 76 篇 统计学（可授理学、...
- 54 篇 系统科学
- 40 篇 化学
169 篇 管理学
- 106 篇 图书情报与档案管...
- 72 篇 管理科学与工程(可...
- 40 篇 工商管理
146 篇 医学
- 130 篇 临床医学
- 88 篇 基础医学(可授医学...
- 65 篇 药学(可授医学、理...
- 24 篇 公共卫生与预防医...
28 篇 教育学
- 28 篇 教育学
27 篇 法学
- 21 篇 社会学
18 篇 经济学
- 17 篇 应用经济学
16 篇 农学
5 篇 军事学
1 篇 文学
1 篇 历史学

主题

210 篇 machine learning
134 篇 deep learning
78 篇 signal processin...
71 篇 accuracy
70 篇 feature extracti...
68 篇 signal processin...
61 篇 support vector m...
56 篇 machine learning...
45 篇 predictive model...
33 篇 neural networks
32 篇 convolutional ne...
31 篇 random forests
29 篇 computational mo...
29 篇 training
26 篇 natural language...
25 篇 prediction algor...
21 篇 technological in...
20 篇 real-time system...
19 篇 adversarial mach...
18 篇 image processing

机构

16 篇 chitkara centre ...
14 篇 centre of resear...
12 篇 shenyang ligong ...
6 篇 chitkara univers...
6 篇 ai & ds vishwaka...
6 篇 school of inform...
5 篇 department of me...
5 篇 khulna universit...
5 篇 department of co...
4 篇 delhi technologi...
4 篇 heilongjiang uni...
4 篇 department of s&...
4 篇 beijing univ pos...
4 篇 it vishwakarma i...
4 篇 chitkara univers...
4 篇 sri lanka instit...
4 篇 advanced telecom...
4 篇 shenyang ligong ...
4 篇 graduate school ...
3 篇 karunya institut...

作者

6 篇 mehta shiva
5 篇 rasmita panigrah...
4 篇 neelamadhab padh...
4 篇 wang xin
3 篇 m. vigenesh
3 篇 baydeti nagaraju
3 篇 sinambela marzuk...
3 篇 santosh kumar sh...
3 篇 ganapati panda
3 篇 debendra muduli
3 篇 abujar sheikh
3 篇 a. sivanantham
3 篇 li yajie
3 篇 li aihua
3 篇 zhou feng
3 篇 islam md. sanzid...
2 篇 aira kharvel par...
2 篇 nokshangthemba
2 篇 maheswara rao v ...
2 篇 lee tzong-ru

语言

1,271 篇 英文
67 篇 其他
11 篇 中文

检索条件"任意字段=Proceedings of the 2019 2nd International Conference on Signal Processing and Machine Learning"

共 1347 条记录，以下是821-830 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：

Word2Vec and Evolutionary Computing Driven Hybrid Deep learning-Based Sentiment Analysis 1

引用

2nd international conference on Soft Computing and signal processing, ICSCSP 2019

作者： Dhariyal, Bhaskar Ravi, Vadlamani Centre of Excellence in Analytics Institute for Development and Research in Banking Technology Castle Hills Road No. 1 Masab Tank Hyderabad500057 India School of Computer & Information Sciences University of Hyderabad Hyderabad500046 India

ISBN: (数字)9789811524752

ISBN: (纸本)9789811524745

In this study, we propose three novel hybrid deep learning architectures for sentiment classification. We hybridized convolution neural network (CNN) with two evolutionary neural networks, viz. fuzzy logic-driven self-tuned particle swarm optimization-trained neural network (fstPSONN) and differential evolution-trained neural network (DENN) and probabilistic neural network (PNN) for sentiment classification. These deep networks were preceded by Word2Vec that yielded embeddings obtained by Google. In these hybrid deep learning architectures CNN-fstPSONN, CNN-DENN and CNN-PNN, CNN was primarily responsible to accomplish the task of feature extraction and latter were responsible for classification. All the three architecture were developed with three variants of CNN, i.e. CNN-random, CNN-static and CNN-non-static based on the embedding training of embedding layer. We demonstrated the effectiveness of our hybrids on the IMDB movie review dataset. Out all the models, CNN-PNN and CNN-fstPSONN gave a better accuracy of 81.9, 81.5 and 78.0% for the non-static, static and random variants of CNN, respectively. Furthermore, we validate our results by performing t-test analysis of the mean obtained from 10-fold cross-validation, and it turned out that all the three variants are statistically the same. Consequently, we recommend CNN-PNN as preferred architecture owing to its least complexity. © 2020, Springer Nature Singapore Pte Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Tiny Fusion: Tiny Deep Convolutional Neural Network for Real-time Image Fusion 2

Tiny Fusion: Tiny Deep Convolutional Neural Network for Real...

引用

2nd IEEE international conference on Information Communication and signal processing (ICICSP)

作者： Wang, Jixiao Li, Yang Miao, Zhuang Wang, Jiabao Zhao, Xun Army Engn Univ PLA Command & Control Engn Coll Nanjing Peoples R China

ISBN: (纸本)9781728151021

Since convolutional neural networks (CNNs) were used in image fusion field, they have showed state-of-the-art quality beyond traditional methods. However, the existing CNN fusion models have a high computational cost and require high memory capacity, which is impractical for embedded applications or mobile platforms. Inspired by the efficiency of the lightweight network architecture of SqueezeNet, MobileNet, and ShuffleNet, we propose a tiny fusion method for image fusion, which significantly decreasing the number of operations and memory needed while retaining the same fusion quality. Extensive experimental results indicate that tiny deep neural network architectures can be designed for real-time image fusion that are well suited for embedded scenarios. To the best of our knowledge, our method is the first lightweight network architecture for image fusion.

关键词： image fusion tiny networks deep learning

来源：评论

学校读者我要写书评

暂无评论

Chinese Word Segmentation of Ideological and Political Education Based on Unsupervised learning 19

Chinese Word Segmentation of Ideological and Political Educa...

引用

2nd international conference on Big Data Technologies (ICBDT) / 3rd international conference on Business Information Systems Workshop (ICBIS)

作者： Zang, Wen-jing Yang, Xing-hai Liu, Zi-zhao Zhang, Yu-lin Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China Qingdao Univ Sci & Technol Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China

ISBN: (纸本)9781450371926

This paper proposes an unsupervised Chinese word segmentation algorithm for ideological and political education. The algorithm is divided into two parts: language model generation algorithm and the Viterbi algorithm. The language model generation algorithm calculates the conditional probability based on the big texts and determines the number of occurrences between single character and character. Then we can have a character-level N-gram language model. Viterbi algorithm uses the idea of dynamic programming. Viterbi algorithm can use character-level language model to find the optimal word segmentation path. Finally complete the task of Chinese word segmentation supported by big texts. Experiments show that the proposed algorithm has a good recognition rate for vocabulary in the field of ideological and political education. With the characteristics of unsupervised learning, the algorithm can save a lot of labor costs and meet the needs of word segmentation in the field of ideological and political education.

关键词： natural language processing Chinese word segmentation language model unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Computational Intelligence for Technology and Services Computing Analysis of Sentiment Analysis Techniques 2nd

Computational Intelligence for Technology and Services Compu...

引用

2nd international conference on Innovative Computing and Communication, ICICC 2019

作者： Bharti, Puja Verma, Amit Kant Raj, Ravi Krishna, Gopal Netaji Subhas Institute of Technology Patna India

ISBN: (纸本)9789811512858

Emergence towards valuing customer reviews and their opinions is the prime propelling factor for any exploring business. Electronic commerce has clinched the world, and the majority preferring to buy products through these websites online. Due to the increase in demand for e-commerce with customer’s preference towards online purchasing of products over physically moving from shop to shop (offline purchasing), there is the huge amount of information being shared to and fro. The e-commerce websites are loaded with immense volume of data and customer reviews thus being generated. This huge volume of data is in its diversity and its structural randomness. The customers face difficulty in precisely finding the review for a particular feature of a product that they intend to buy. Also, there are mixtures of positive and negative reviews thereby increasing the complexity for customers to find a cogent response. So to avoid this confusion and make this review base more transparent and user friendly, a technique to extract feature-based opinion from a diverse pool of reviews and processing it further to segregate it with respect to the aspects of the product and further classifying it into positive and negative reviews using machine learning-based approach. The analysis of the data generated in huge amount holds the prime centred topic, underlying data analytics. This paper proposes the study and analysis of obtaining the best methodologies on sentiment analysis of consumer reviews in context to the features of a product. The system aims at providing a summary that represents the extent to which the consumers who had already bought the particular product were or were not satisfied with the specific feature of the product. Due to this sentiment analysis, there is a feedback environment being generated for helping customers buy the right product and guiding companies to enhance the features of product suiting consumer’s demand. © 2020, Springer Nature Singapore Pte Ltd.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Image Super Resolution Reconstruction Algorithm Based on Deep learning 2

Image Super Resolution Reconstruction Algorithm Based on Dee...

引用

2nd IEEE international conference on Information Communication and signal processing (ICICSP)

作者： Dou, Huijing Zhang, Wenqian Liang, Xiao Beijing Univ Technol Dept Informat Beijing Peoples R China

ISBN: (纸本)9781728151021

Super Resolution Convolutional Neural Network (SRCNN) solves the problems of poor robustness and complex calculation of traditional image super-resolution reconstruction algorithm, but its training data set and the number of layers of neural network is relatively small, and the edge and texture detail information are not handled well. For the above problems, the Maxout activation function is adopted in this paper to avoid the problems encountered by traditional activation functions such as gradient disappearance or overflow. Then the combination of Maxout and Dropout can train large data set and deepen neural network. Experimental results show that, compared with the classical algorithm, the algorithm proposed in this paper can train a large amount of data, improve the quality of reconstructed images and the generalization ability of the network model, and can enhance the robustness of the model.

关键词： super resolution reconstruction convolutional neural network maxout activation function dropout

来源：评论

学校读者我要写书评

暂无评论

proceedings - 2019 2nd international conference on Intelligent Autonomous Systems, ICoIAS 2019

Proceedings - 2019 2nd International Conference on Intellige...

引用

2nd international conference on Intelligent Autonomous Systems, ICoIAS 2019

ISBN: (纸本)9781728126623

The proceedings contain 35 papers. The topics discussed include: path planning for anti-ship missile using tangent based dubins path;a tractable algorithm for finite-horizon continuous reinforcement learning;hardware-software co-design of an image feature extraction and matching algorithm;graceful fault-tolerant on-chip spike routing algorithm for mesh-based spiking neural networks;risk assessment for integral safety in automated driving;a high efficient architecture for convolution neural network accelerator;a feature extraction method for credit card fraud detection;an accurate phase measuring deflectometry method for 3D reconstruction of mirror-like specular surface;analysis of software rejuvenation policies in a server virtualized system;and research on detection method of low frequency oscillation signal in power system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning for 3D Classification Based on Point Cloud with Local Structure 2

Deep Learning for 3D Classification Based on Point Cloud wit...

引用

2nd IEEE international conference on Information Communication and signal processing (ICICSP)

作者： Song, Yanan Li, Xinyu Gao, Liang Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan Peoples R China

ISBN: (纸本)9781728151021

Point cloud consists of many unordered and unstructured points, which makes the simple deep learning (DL) network hard to capture the local structure of point cloud. This shortcoming limits the ability of the DL network to recognize the fine-grained features of objects. Network structure is changed in some studies for this problem, but this increases the network complexity. This paper proposes an effective preprocessing method for point cloud to deal with this problem. The local region that represents the local structure of point is searched by using a cube with fixed side length. All of the points in the local region are used to construct the feature vector of the center point located at the center of the cube. These feature vectors are input into a simple convolutional neural network. The ModelNet40 shape classification benchmark is used to evaluate the proposed method. Experimental results show that the proposed method improves the classification accuracy of the simple deep learning network.

关键词： Point Cloud 3D Classification Deep learning Local Region Search Data Preprocessing

来源：评论

学校读者我要写书评

暂无评论

learning machine Diagnostics Through Laboratory Experiments

Learning Machine Diagnostics Through Laboratory Experiments

引用

2nd international Symposium on the Education in Mechanism and machine Science (ISEMMS)

作者： Zamorano, M. Gomez, M. J. Castejon, C. Garcia-Prada, J. C. Univ Carlos III Madrid Madrid Spain

ISBN: (纸本)9783030001087;9783030001070

Hands-on-experiments are an important part of education in engineers. This work presents the development of laboratory practices for testing related to signal acquisition tasks that have been performed with students. The tests have been developed in the framework of a subject, where signal processing tools applied to machine diagnostics are taught as an important part of maintenance. Specifically, the type of signals that are used in the subject are time domain vibration signals. With the inclusion of the tests, postgraduate students of engineering learn how to use a machine to obtain vibration signals and how to set the machine for that purpose. Also, they are able to diagnose rotating elements with different faults;such as bearings, and unbalanced shafts. The laboratory practice gives the opportunity to tackle a job for themselves, which is one of the most important skills for the future engineer, as they gain experience.

关键词： Hands-on-experiments Education machine diagnostics signal processing Easy learning

来源：评论

学校读者我要写书评

暂无评论

P300 Based Deception Detection using Convolutional Neural Network 2

P300 Based Deception Detection using Convolutional Neural Ne...

引用

2nd international conference on Communication, Computing and Digital Systems (C-CODE)

作者： Amber, Faryal Yousaf, Adeel Imran, Muhammad Khurshid, Khurram Inst Space Technol Dept Elect Engn Islamabad Pakistan Inst Space Technol Dept Aeronaut & Astronaut Islamabad Pakistan

ISBN: (纸本)9781538696095

Algorithms for automatic lie detection from analysis of brain signals have remained a question of interest that fascinate the research community. Nevertheless, the detection algorithms still lack robustness while processing brain signals. The aim would be to learn whether a person is deceitful or not by detection techniques and suggest a vigorous lie detection algorithm. Moreover, recently proposed algorithms for lie detection have shown to achieve a classification accuracy of around 96%. While different classification algorithms such as Support Vector machines, multilaver neural network, Extreme learning machine, and Linear Discriminant Analysis have proposed which typically utilizes three different types of features like time domain features, frequency domain features, and wavelet features, are anticipated in the literature. Accordingly, in this research paper, we presented a lie detection system front the P300 wave. For automatic optimum feature learning, we applied an approach from deep learning, Convolutional Neural Network (CNN), which is very effective for classification problems. The presented model significantly achieves high accuracy of 99.6%. The experimental outcomes show that the technique put forward achieves the maximum accuracy with a lesser amount of training and testing time and reveal improved performance. Additionally, an all-inclusive discussion on the choice of appropriate CNN architecture and classification results presented in this paper along with a comparison with the prior approaches of lie detection.

关键词： lie detection deception detection P300 wave Deep learning CNN comparison

来源：评论

学校读者我要写书评

暂无评论

A phase noise correction scheme for multi-channel multi-echo SWI processing 1

引用

2nd international conference on machine Intelligence and signal processing, MISP 2019

作者： Madhusoodhanan, Sreekanth Paul, Joseph Suresh Indian Institute of Information Technology and Management-Kerala TrivandrumKerala India

ISBN: (数字)9789811513664

ISBN: (纸本)9789811513657

In a GRE acquisition, effect of noise in each voxel can be minimized through the knowledge of prior information about the phase error, which can result in more robust estimation of susceptibility-related features. However, estimating the error in the given phase image of GRE acquisition is difficult. Moreover, the errors can significantly affect the resolution of the resulting phase mask at regions where the magnitude intensities are significantly low. Even though there are methods like non-linear least square fitting, smoothness introduced by these methods in the filtered phase reduces resolution and contrast-to-noise ratio (CNR). In order to maintain the resolution at voxel level, we propose a new filtering scheme where a series of local weights estimated from the probability density function of the phase measurements conditioned on the magnitude intensity and the noise variance. With an estimate of the local noise variance made available through a noise scan, the CNR improvement attained with the proposed noise correction scheme is compared using magnitude SWI images reconstructed at different acceleration factors. © Springer Nature Singapore Pte Ltd. 2020.

关键词： Errors

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135页 << < 79 80 81 82 83 84 85 86 87 88 > >>

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：