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

2,973 篇 会议
176 册 图书
24 篇 期刊文献

馆藏范围

3,172 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,043 篇 工学
- 1,825 篇 计算机科学与技术...
- 960 篇 软件工程
- 329 篇 电气工程
- 313 篇 信息与通信工程
- 214 篇 控制科学与工程
- 207 篇 生物工程
- 149 篇 生物医学工程（可授...
- 71 篇 光学工程
- 64 篇 机械工程
- 62 篇 化学工程与技术
- 51 篇 电子科学与技术（可...
- 47 篇 仪器科学与技术
- 46 篇 安全科学与工程
- 36 篇 交通运输工程
648 篇 理学
- 352 篇 数学
- 244 篇 生物学
- 140 篇 物理学
- 135 篇 统计学（可授理学、...
- 95 篇 系统科学
- 62 篇 化学
408 篇 管理学
- 244 篇 图书情报与档案管...
- 182 篇 管理科学与工程(可...
- 83 篇 工商管理
262 篇 医学
- 241 篇 临床医学
- 123 篇 基础医学(可授医学...
- 74 篇 药学(可授医学、理...
- 40 篇 公共卫生与预防医...
46 篇 法学
- 42 篇 社会学
38 篇 教育学
- 32 篇 教育学
33 篇 经济学
- 31 篇 应用经济学
23 篇 农学
6 篇 艺术学
4 篇 文学

主题

575 篇 machine learning
564 篇 data mining
323 篇 pattern recognit...
212 篇 deep learning
201 篇 feature extracti...
154 篇 support vector m...
145 篇 artificial intel...
129 篇 machine learning...
120 篇 accuracy
120 篇 training
91 篇 data mining and ...
90 篇 data models
72 篇 neural networks
71 篇 classification
69 篇 predictive model...
66 篇 face recognition
61 篇 learning systems
52 篇 computer imaging...
50 篇 convolutional ne...
48 篇 classification a...

机构

9 篇 school of comput...
9 篇 chinese academy ...
8 篇 zhejiang univers...
8 篇 chitkara univers...
7 篇 guangdong univer...
7 篇 school of inform...
6 篇 xi'an university...
6 篇 indian statistic...
6 篇 central south un...
6 篇 department of co...
6 篇 unsw sydney
6 篇 xi'an university...
6 篇 southern univers...
5 篇 indian institute...
5 篇 study group aust...
5 篇 peking universit...
4 篇 centre for patte...
4 篇 chongqing univer...
4 篇 national laborat...
4 篇 sun yat sen univ...

作者

11 篇 de-shuang huang
8 篇 petra perner
7 篇 krasotkina olga
7 篇 mottl vadim
7 篇 ying tan
6 篇 zheng-guang wu
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 phung dinh
6 篇 venkatesh svetha
6 篇 hongyi li
6 篇 jacek m. zurada
6 篇 chaojie li
6 篇 biao luo
6 篇 ilias maglogiann...
6 篇 lotfi a. zadeh
6 篇 leszek rutkowski
6 篇 lazaros iliadis
6 篇 long cheng
5 篇 vitoantonio bevi...

语言

2,869 篇 英文
290 篇 其他
34 篇 中文
1 篇 土耳其文

检索条件"任意字段=5th International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3173 条记录，以下是991-1000 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：

Research on a data Risk Identification Technology Based on machine learning

Research on a Data Risk Identification Technology Based on M...

引用

Artificial Intelligence and Electromechanical Automation (AIEA), international conference on

作者： Wuqiang Shen Yechao Wang Chaosheng Yao Zeyuan Zhou Ge Jin Guangdong Power Grid Corporation Joint Laboratory on Cyberspace Security China Southern Power Grid Guangzhou China Guizhou Power Grid Corporation Guizhou China Nari Group Corporation Nanjing China

ISBN: (数字)9798350366174

ISBN: (纸本)9798350366181

With the development of power digitization, network transmission business traffic is increasing day by day. Various attacks and network anomalies have brought new challenges to power network space security. Aiming at the problem of low accuracy in power network traffic data risk identification, this paper studies feature selection and data risk identification, and proposes a new method for power data risk identification. In terms of feature extraction, the feature selection method is used to effectively extract the best subset; In terms of data risk identification, Smote-PSO-XGBoost model is established to efficiently and accurately identify network traffic data risk under unbalanced data sets. Experimental results show that this method has obvious advantages in recognition accuracy compared with KNN, decision tree, etc.

关键词： Accuracy data security Telecommunication traffic machine learning Predictive models Nearest neighbor methods Feature extraction Power systems Optimization Business

来源：评论

学校读者我要写书评

暂无评论

A Deep Knowledge Tracking Model Incorporating the Forgotten Features of Multiple Concepts

A Deep Knowledge Tracking Model Incorporating the Forgotten ...

引用

machine learning and Computer Application (ICMLCA), international conference on

作者： Biao Kong Dongfeng Liu Guangdong University of Technology Guangzhou China

ISBN: (数字)9798331530334

ISBN: (纸本)9798331530341

Knowledge tracking is based on the historical answer records of students to track the changes in their knowledge status. With the rapid development of deep neural networks, they are also widely used in the field of knowledge tracking. Most of the existing deep knowledge tracking models only consider the situation where the question contains only one concept, and cannot solve the problem where the question contains multiple concepts, and they do not consider the effect of forgetting behaviour on the knowledge state change during the learning process. A new deep knowledge tracking model is proposed to solve these problems. this model uses multiple concepts to express the problem and considers the time interval for students to learn the same concepts and the number of times they learn the same concepts as two important forgetting features of the deep knowledge tracking model. these forgetting features exert an influence in the prediction stage of the model and in the knowledge state change stage to increase the interpretability of the model. Experiments on publicly available datasets show that the model prediction process is more realistic and has better prediction accuracy.

关键词： Knowledge engineering Analytical models Accuracy Computational modeling machine learning Computer applications Artificial neural networks Predictive models Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

Beyond Words: Exploring Emotion Detection in Speech Using Sound

Beyond Words: Exploring Emotion Detection in Speech Using So...

引用

Emerging Technology (INCET), international conference for

作者： Ruchika Vaidya Sarthak Gaurkhede Rahul Dattangire K.T.V Redddy Utkarsha Pachraney Divya Biradar Artificial intelligence And Machine Learning Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Data Engineering Publicis Sapient Houston Texas USA Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Computer Science University of Texas at Arlington Arlignton Texas USA

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

Speech emotion recognition (SER) has the possible to revolutionize human-computer interaction and numerous other fields. this paper explores the application of deep learning, mostly Long Short-Term Memory (LSTM) networks, for SER by the Toronto Speech Emotion Set (TESS) dataset. TESS data undergoes rigorous pre-processing, including normalization and feature extraction, to prepare it for the LSTM model. this model choice leverages its ability to capture essential long-term dependencies inside the audio data. through careful selection and optimization of hyperparameters, the LSTM network architecture is fine-tuned to achieve optimal performance. the training process employs optimizers and a loss function to guide the model in learning the complicated relationships between extracted features and conforming emotions. To comprehensively measure the model's efficiency, various metrics are used, together with accuracy, precision, recall, and F1-score. this research underwrites to the advancement of SER by representing the efficiency of deep learning, specifically LSTMs, on the TESS dataset. the findings not only offer valuable insights into model selection, data pre-processing, and performance calculation but also cover the technique for further exploration of deep learning in SER applications.

关键词： Deep learning Training Emotion recognition Accuracy Training data Speech recognition Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Mixtures of Generators for Adversarial learning 25

Hierarchical Mixtures of Generators for Adversarial Learning

引用

25th international conference on pattern recognition (ICPR)

作者： Ahmetoglu, Alper Alpaydin, Ethem Bogazici Univ Dept Comp Engn TR-34342 Istanbul Turkey Ozyegin Univ Dept Comp Sci TR-34794 Istanbul Turkey

ISBN: (纸本)9781728188089

Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. there is a generator that takes a latent vector as input and transforms it into a valid sample from the distribution. there is also a discriminator that is trained to discriminate such fake samples from true samples of the distribution;at the same time, the generator is trained to generate fakes that the discriminator cannot tell apart from the true samples. Instead of learning a global generator, a recent approach involves training multiple generators each responsible from one part of the distribution. In this work, we review such approaches and propose the hierarchical mixture of generators, inspired from the hierarchical mixture of experts model, that learns a tree structure implementing a hierarchical clustering with soft splits in the decision nodes and local generators in the leaves. Since the generators are combined softly, the whole model is continuous and can be trained using gradient-based optimization, just like the original GAN model. Our experiments on five image data sets, namely, MNIST, FashionMNIST, UTZap5OK, Oxford Flowers, and CelebA, show that our proposed model generates samples of high quality and diversity in terms of popular GAN evaluation metrics. the learned hierarchical structure also leads to knowledge extraction.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Human Face Recall by Reconstruction of Real and Synthetic Occlusions

Enhanced Human Face Recall by Reconstruction of Real and Syn...

引用

data Intelligence and Cognitive Informatics (ICDICI), international conference on

作者： Dane Brown Iffat Mollah Computer Science Rhodes University Grahamstown South Africa

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

this study investigates occluded face recognition using a Complete Face Recovery Generative Adversarial Network (CFR-GAN). It directly addresses the complexities of identifying faces obscured by real-world occlusions, while underlining the critical role of high-quality input data. the CFR-GAN is trained on both occluded and rotated face datasets, with synthetic occlusions applied for data augmentation. In Experiment 1, the model achieved a poor result of 15.80% accuracy for reconstructing images with sunglasses and 24.11% for masked faces, but produced a consistent recall rate of 100%. Experiment 2 utilised the Labelled Faces in the Wild (LFW) dataset, where the CFR-GAN yielded an accuracy of 52.27%. Despite improvements with higher-quality inputs, the model introduced artefacts and misaligned features, underscoring the ongoing difficulties in occluded face recognition. the results underscored the importance of data quality, advanced training techniques, and refined evaluation metrics in addressing these real-world challenges. While this work demonstrates promise, further study is required to translate these findings into practical applications in biometric security and related areas.

关键词： Training Measurement Accuracy Image resolution Image recognition Face recognition Lighting machine learning Security Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

machine learning based on Association rules about automatic course data mining 5

Machine Learning based on Association rules about automatic ...

引用

5th international conference on Advanced Electronic Materials, Computers and Software Engineering, AEMCSE 2022

作者： Li, Xuemei Xu, Jiajia De la Salle University -Dasmariñas City of Dasmariñas College of Electronic and Electrical Engineering Anhui Sanlian University Teacher College of Science and Computer Studies - Graduate Studies Cavite Philippines

ISBN: (数字)9781665484749

ISBN: (纸本)9781665484749

there is an intersection of knowledge between two different courses in automation major, and there is a knowledge graph between several courses. this paper takes nine courses of 127 undergraduate automation majors in a university in China as the research object. this paper attempts to find out the interrelationship and correlation intensity between courses, to guide students' self-study and teachers' lesson preparation. the research study employs the quantitative method of research. K-DD (Knowledge Discovery in database) is used in this study. Relevance rules are used in this paper. First, we use the correlation coefficient method to calculate the correlation coefficient between the courses, and then use the correlation rule method to get the relationship between the nine courses. the algorithms in the association rules used in this paper are FP growth and Apriori algorithms. the correlation coefficient between automatic control theory and electronic measurement technology is up to 0.816. when the technical state of electronic measurement is true, the possibility that the automatic control theory is true is 0.867. When the automatic control theory state is true, the probability that the electronic measurement technology is true is 0.839. the correlation between automatic control theory and electronic measurement technology is the highest. the fact shows that there is indeed a strong correlation between the two courses. © 2022 IEEE.

关键词： Association rules

来源：评论

学校读者我要写书评

暂无评论

Trends of Evolutionary machine learning to Address Big data mining 5th

Trends of Evolutionary Machine Learning to Address Big Data ...

引用

5th international conference on Information and Knowledge Systems (ICIKS)

作者： Ben Hamida, Sana Benjelloun, Ghita Hmida, Hmida Univ Paris 09 PSL Res Univ CNRS UMR 7243LAMSADE Paris France Univ Paris 09 PSL Res Univ Paris France Univ Tunis El Manar Tunis Tunisia

ISBN: (纸本)9783030859770;9783030859763

Improving decisions by better mining the available data in an Information System is a common goal in many decision making environments. However, the complexity and the large size of the collected data in modern systems make this goal a challenge for mining methods. Evolutionary data mining Algorithms (EDMA), such as Genetic Programming (GP), are powerful meta-heuristics with an empirically proven efficiency on complex machine learning problems. they are expected to be applied to real-world big data tasks and applications in our daily life. thus, they need, as all machine learning techniques, to be scaled to Big data bases. this paper review some solutions that could be applied to help EDMA to deal with Big data challenges. Two solutions are then selected and explained. the first one is based on the algorithmic manipulation involving the introduction of the active learning paradigm thanks to the active data sampling. the second is based on the processing manipulation involving horizontal scaling thanks to the processing distribution over networked nodes. this work explains how each solution is introduced to GP. As preliminary experiences, the extended GP is applied to solve two complex machine learning problem: the Higgs Boson classification problem and the Pulsar detection problem. Experimental results are then discussed and compared to value the efficiency of each solution.

关键词： Big data mining machine learning Genetic Programming Horizontal parallelization Active learning data sampling Higgs Boson classification Pulsar detection

来源：评论

学校读者我要写书评

暂无评论

Handwriting recognition for Predicting Gender and Handedness Using Deep learning 1

引用

5th international conference on Applied machine learning and data Analytics, AMLDA 2022

作者： Saraswat, Mala Agarwal, Ayushi School of Computer Science Engineering and Technology Bennett University UP Greater Noida India ABES Engineering College UP Ghaziabad India

ISBN: (数字)9783031342226

ISBN: (纸本)9783031342219

this research focuses on predicting the gender and handedness and also combined prediction through Handwriting recognition. In this paper we have analyzed various Deep learning approaches using different CNN models. Our proposed approach uses two data sets IAM English dataset and Real-Time dataset that was collected by us for recognizing the handwriting pattern to perform the defined task. Using different Deep learning approaches, experiments were conducted to analyze the performance on the given two datasets for predicting. Gender and handedness. Experiments showed Google Net using CNN is the most efficient for the prediction and recognition with the handwriting samples. For combined prediction the accuracy rate is around 94% with Real-Time dataset and 95% with the IAM dataset. © 2023, the Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis and Performance Optimization of Convolutional Neural Networks for Travel Direction recognition in Autonomous Vehicles

Comparative Analysis and Performance Optimization of Convolu...

引用

Electronic Communication and Artificial Intelligence (IWECAI), international Workshop on

作者： Xvmeng Mei Hohai University Nanjing China

ISBN: (数字)9798350386943

ISBN: (纸本)9798350386950

As the technology of autonomous vehicles advances, ensuring their safety and reliability across diverse traffic contexts has emerged as a pivotal concern within both research and industrial spheres. Among the myriad challenges, the precise identification and prediction of a vehicle's travel direction stand out as crucial for enabling effective navigation and circumventing potential obstacles. Deep learning techniques, particularly convolutional neural networks (CNNs), have introduced a novel perspective for addressing this issue, owing to their superior capability in feature extraction and pattern recognition. CNNs are adept at autonomously learning complex features from extensive image data, rendering them exceptionally suited for the vision-intensive tasks characteristic of autonomous driving applications. In this research, we not only investigate the deployment of various extant CNN models such as ResNet50, VGG19, and InceptionV3 in the domain of autonomous driving direction recognition but also undertake comparative analyses of these models' performances. Furthermore, we endeavor to augment recognition accuracy by adjusting network parameters. Our objective is to evaluate the efficacy of these models under varying configurations and pinpoint those settings that significantly enhance the accuracy and efficiency of direction recognition, utilizing an academic tone reflective of scholarly discourse.

关键词： Deep learning Analytical models Accuracy Image recognition data models Convolutional neural networks Reliability

来源：评论

学校读者我要写书评

暂无评论

Alignment Offset Based Adaptive Training for Simultaneous machine Translation

Alignment Offset Based Adaptive Training for Simultaneous Ma...

引用

Natural Language Processing (ICNLP), international conference on

作者： Qiqi Liang Yijin Liu Fandong Meng Jinan Xu Yufeng Chen Jie Zhou Beijing Jiaotong University Beijing China Pattern Recognition Center WeChat AI Tencent Inc Beijing China

Given incomplete source sentences as inputs, it is generally difficult for Simultaneous machine Translation (SiMT) models to generate a target token once its aligned source tokens are absent. How to measure such difficulty and further conduct adaptive training for SiMT models are not sufficiently studied. In this paper, we propose a new metric named alignment offset (AO) to quantify the learning difficulty of target tokens for SiMT models. Given a target token, its AO is calculated by the offset between its aligned source tokens and the already received source tokens. Furthermore, we design two AO-based adaptive training methods to improve the training of SiMT models. Firstly, we introduce token-level curriculum learning based on AO, which progressively switches the training process from easy target tokens to difficult ones. Secondly, we assign an appropriate weight to the training loss of each target token according to its AO. Experimental results on four datasets demonstrate that our methods significantly and consistently outperform all the strong baselines.

关键词：

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318页 << < 96 97 98 99 100 101 102 103 104 105 > >>

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：