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

3,134 篇 会议
20 册 图书
18 篇 期刊文献

馆藏范围

3,172 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,131 篇 工学
- 1,886 篇 计算机科学与技术...
- 1,008 篇 软件工程
- 265 篇 控制科学与工程
- 257 篇 电气工程
- 244 篇 信息与通信工程
- 197 篇 生物工程
- 155 篇 交通运输工程
- 106 篇 生物医学工程（可授...
- 96 篇 机械工程
- 61 篇 光学工程
- 58 篇 安全科学与工程
- 57 篇 电子科学与技术（可...
- 49 篇 材料科学与工程（可...
- 47 篇 动力工程及工程热...
- 41 篇 建筑学
- 36 篇 土木工程
517 篇 理学
- 266 篇 数学
- 203 篇 生物学
- 123 篇 统计学（可授理学、...
- 90 篇 物理学
- 58 篇 系统科学
409 篇 管理学
- 268 篇 管理科学与工程(可...
- 165 篇 图书情报与档案管...
- 100 篇 工商管理
203 篇 教育学
- 200 篇 教育学
166 篇 医学
- 161 篇 临床医学
- 80 篇 基础医学(可授医学...
- 52 篇 药学(可授医学、理...
- 33 篇 公共卫生与预防医...
69 篇 法学
- 58 篇 社会学
31 篇 经济学
18 篇 农学
7 篇 文学
1 篇 艺术学

主题

295 篇 machine learning
291 篇 deep learning
142 篇 training
125 篇 data models
120 篇 neural networks
114 篇 accuracy
105 篇 feature extracti...
101 篇 data mining
87 篇 predictive model...
83 篇 artificial intel...
82 篇 computational mo...
68 篇 machine learning...
62 篇 students
57 篇 reinforcement le...
57 篇 real-time system...
47 篇 convolutional ne...
45 篇 big data
43 篇 internet of thin...
42 篇 support vector m...
42 篇 training data

机构

30 篇 school of comput...
11 篇 institute of inf...
9 篇 kazan natl res t...
9 篇 school of cyber ...
7 篇 school of comput...
6 篇 school of inform...
5 篇 inesc tec porto
5 篇 hefei univ techn...
5 篇 wroclaw univ sci...
4 篇 univ michigan an...
4 篇 school of automa...
4 篇 chinese acad sci...
4 篇 college of compu...
4 篇 univ minho algor...
4 篇 university of ba...
4 篇 school of mechan...
4 篇 xi an jiao tong ...
4 篇 nanyang technol ...
4 篇 singapore manage...
4 篇 university of mi...

作者

7 篇 yang yang
7 篇 santos matilde
6 篇 peng jun
6 篇 taghi m. khoshgo...
6 篇 wang fei
5 篇 li peng
5 篇 horvath tomas
5 篇 wozniak michal
5 篇 machado jose
5 篇 r.c. luo
4 篇 zhang tao
4 篇 lee seong-whan
4 篇 ksieniewicz pawe...
4 篇 zhang lei
4 篇 yang yi
4 篇 novais paulo
4 篇 li li
4 篇 trong-hop do
4 篇 liu qin
4 篇 shimizu jun

语言

3,039 篇 英文
125 篇 其他
15 篇 中文

检索条件"任意字段=21st International Conference on Intelligent Data Engineering and Automated Learning"

共 3172 条记录，以下是851-860 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：

Rational Orthogonal Wavelet Pulse and Feature Extraction Method Based on Auditory Frequency Cepstral Coefficient for Underwater Target Localization 21

Rational Orthogonal Wavelet Pulse and Feature Extraction Met...

引用

21st international conference on Wavelet Analysis and Pattern Recognition, ICWAPR 2023

作者： Guo, Tiantian Lim, Eng Gee Lopez-Benitez, Miguel Fei, Ma Limin, Yu Department of Communications and Networking Suzhou China University of Liverpool Department of Electrical Engineering and Electronics Merseyside Liverpool United Kingdom ARIES Research Centre Antonio de Nebrija University Madrid28040 Spain Department Applied Mathematics Suzhou China

ISBN: (纸本)9798350303810

Underwater target localization has always been a challenging and important research topic in underwater acoustic sensing, especially when the underwater target is moving. This paper uses three pulse signals for system design: continuous wave, linear frequency modulated signal and rational orthogonal wavelet signal. We use a geometric underwater channel model to generate a database of underwater signals with specified geometric parameters of ocean environments to simulate the ocean. The received pulses signal are converted into feature maps as the classifier's input. In this paper, Short-time Fourier transform, Mel-frequency cepstral coefficient, Gammatone frequency cepstral coefficient and Perceptual linear prediction coefficient are applied to construct different feature maps. The classifier uses a lightweight CNN model. Experiments demonstrate the superiority of wavelet pulse signals in underwater target localization. The multipath effect will also contribute to underwater acoustic sensing. © 2023 IEEE.

关键词： CNN Gammatone frequency cepstral coefficient Mel frequency cepstral coefficient Rational orthogonal wavelet Underwater communication

来源：评论

学校读者我要写书评

暂无评论

Research on Feature Optimization Scheme Based on data Feature Enhancement 21

Research on Feature Optimization Scheme Based on Data Featur...

引用

21st IEEE international conference on Software Quality, Reliability and Security (QRS)

作者： Deng, Zhi Shi, Zhao Wang, Zhenxin Liu, Tao Northwestern Polytech Univ Sch Comp Sci Xian Peoples R China Anhui Polytech Univ Coll Comp & Informat Wuhu Peoples R China

ISBN: (纸本)9781665478366

Based on the common knowledge in the field of feature engineering that "data and features determine the upper limit of the model, and models and algorithms just approach the upper limit", this article believes that the knowledge of feature engineering can be used to extract features from the original data to the maximum. Used by algorithms and models to improve the accuracy of algorithms and models. Based on the above considerations, this paper proposes a feature optimization scheme based on data feature enhancement (DFET) to improve the performance of deep learning models in natural language processing. The DFET feature optimization scheme uses machine learning classification algorithms to weaken noise features and adopts a sliding window data enhancement is performed in the form of a window, the ignored features are selected through the form of windows, and low-dimensional data with significant features are generated. This part of the data is added to the original model training to fine-tune the model training, and then optimize the model to meet the requirements of improving accuracy. The paper examines the security bug report prediction problem in the field of natural language processing to verify the impact of data feature optimization on the performance optimization of deep learning models. Experiments show that compared with the basic deep learning model, the model after the DFET feature optimization scheme can show more excellent feature learning ability in text classification and prediction.

关键词： Deep learning Feature engineering Natural Language Processing Security Bug Report Prediction

来源：评论

学校读者我要写书评

暂无评论

Versatile feature learning with graph convolutions and graph structures 21

Versatile feature learning with graph convolutions and graph...

引用

21st IEEE international conference on data Mining (IEEE ICDM)

作者： Cong, Guojing Lim, Seung-Hwan Oakridge Natl Lab Oakridge TN 37830 USA

ISBN: (纸本)9781665424271

Graphs represent real world relationships, and graph embedding projects nodes in a graph to a latent space that can help simplify downstream tasks. Recent development of graph convolutions in deep learning significantly improves the performance of many learning tasks on graphs. Unfortunately, prior embedding methods either do not embed graphs with node features, or fail to produce high-quality embeddings for downstream learning tasks that result in large performance gap in comparison to direct learning on graphs. We present a versatile and effective embedding method, Conv2Vec, for embedding graphs with or without node features. It is based on graph convolutions with objective functions motivated by concepts and structures from classical graph algorithms. Conv2Vec produce high-quality embedding for both plain graphs and graphs with node features for downstream tasks. We evaluate the embeddings generated by Conv2Vec with a transductive node classification task. With the generated embeddings and very simple machine learning approaches, we are able to achieve accuracies similar to those achieved by direct learning with graph convolutions. Interestingly, if we strip the node features from the graph and thus learning an embedding has to rely entirely on the graph topology, node classification with our embedding significantly outperforms direct learning with various graph convolutions. This suggests that structures from classical graph algorithms may play an important role in learning on graphs.

关键词： Deep learning GNN Graph Embedding Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Metagenome2Vec: Building Contextualized Representations for Scalable Metagenome Analysis 21

Metagenome2Vec: Building Contextualized Representations for ...

引用

21st IEEE international conference on data Mining (IEEE ICDM)

作者： Aakur, Sathyanarayanan N. Indla, Vineela Indla, Vennela Narayanan, Sai Bagavathi, Arunkumar Ramnath, Vishalini Laguduva Ramachandran, Akhilesh Oklahoma State Univ Stillwater OK 74078 USA

ISBN: (纸本)9781665424271

Advances in next-generation metagenome sequencing have the potential to revolutionize the point-of-care diagnosis of novel pathogen infections, which could help prevent potential widespread transmission of diseases. Given the high volume of metagenome sequences, there is a need for scalable frameworks to analyze and segment metagenome sequences from clinical samples, which can be highly imbalanced. There is an increased need for learning robust representations from metagenome reads since pathogens within a family can have highly similar genome structures (some more than 90%) and hence enable the segmentation and identification of novel pathogen sequences with limited labeled data. In this work, we propose Metagenome2Vec - a contextualized representation that captures the global structural properties inherent in metagenome data and local contextualized properties through self-supervised representation learning. We show that the learned representations can help detect six (6) related pathogens from clinical samples with less than 100 labeled sequences. Extensive experiments on simulated and clinical metagenome data show that the proposed representation encodes compositional properties that can generalize beyond annotations to segment novel pathogens in an unsupervised setting.

关键词： Scalable Metagenome Analysis Deep Representation learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Clinical Activity Recognition with Bidirectional RNNs and Accelerometer-ECG Fusion

Enhancing Clinical Activity Recognition with Bidirectional R...

引用

international conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON

作者： Sakorn Mekruksavanich Ponnipa Jantawong Anuchit Jitpattanakul Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Department of Mathematics Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798350381559

ISBN: (纸本)9798350381566

The ongoing monitoring of human activities has several applications in digital health. However, precisely identifying activities in medical settings is difficult because of the intricate nature of actions and patient differences. This study presents a sophisticated approach using deep learning to combine accelerometer and ECG data from wearable devices to identify clinical activities. The suggested approach involves using a dual-stream convolutional-recurrent neural network to capture spatial and temporal patterns accurately. An assessment was carried out using a dataset that is accessible to the public, including records of activities undertaken by both healthy individuals and patients diagnosed with pneumoconiosis. An analysis was conducted on five deep learning architectures, which included convolutional, recurrent, and bidirectional recurrent networks. The results demonstrated that bidirectional gated recurrent units exhibited the most fantastic accuracy, ranging from 97% to 99%, for both the healthy and sick categories. This performance is significantly above that of the long short-term memory and convolutional neural network models. The results indicate that combining convolutional feature extraction and bidirectional sequential modeling allows for the effective learning of valuable features from multi-modal clinical time-series data. The results enhance the monitoring of human activities in clinical settings by combining specific deep neural networks designed for mobile health applications.

关键词： Deep learning Accuracy Convolution Electrocardiography Feature extraction data models Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

learning Personal Human Biases and Representations for Subjective Tasks in Natural Language Processing 21

Learning Personal Human Biases and Representations for Subje...

引用

21st IEEE international conference on data Mining (IEEE ICDM)

作者： Kocon, Jan Gruza, Marcin Bielaniewicz, Julita Grimling, Damian Kanclerz, Kamil Milkowski, Piotr Kazienko, Przemyslaw Wroclaw Univ Sci & Technol Dept Artificial Intelligence Wroclaw Poland Sentimenti Sp Zoo Poznan Poland

ISBN: (纸本)9781665423984

Many tasks in natural language processing like offensive, toxic, or emotional text classification are subjective by nature. Humans tend to perceive textual content in their own individual way. Existing methods commonly rely on the agreed output values, the same for all consumers. Here, we propose personalized solutions to subjective tasks. Our four new deep learning models take into account not only the content but also the specificity of a given human. The models represent different approaches to learning the representation and processing data about text readers. The experiments were carried out on four datasets: Wikipedia discussion texts labelled with attack, aggression, and toxicity, as well as opinions annotated with ten numerical emotional categories. Emotional data was considered as multivariate regression (multitask), whereas Wikipedia data as independent classifications. All our models based on human biases and their representations significantly improve the prediction quality in subjective tasks evaluated from the individual's perspective.

关键词： subjective NLP tasks personalization hate speech aggression emotions learning human representation human bias text classification

来源：评论

学校读者我要写书评

暂无评论

Discrete Task-Space Automatic Curriculum learning for Robotic Grasping 21

Discrete Task-Space Automatic Curriculum Learning for Roboti...

引用

21st international conference on Control, Automation and Systems (ICCAS)

作者： Kurkcu, Anil Acar, Cihan Campolo, Domenico Tee, Keng Peng ASTAR Inst Infocomm Res Singapore Singapore Nanyang Technol Univ Dept Mech & Aerosp Engn Singapore Singapore

ISBN: (纸本)9788993215212

Deep reinforcement learning algorithms struggle in the domain of robotics where data collection is time consuming and in some cases safety-constrained. For sample-efficiency, curriculum learning has shown good results in deep learning-based methods. However, the issue lies on the generation of the curriculum itself, which the field of automatic curriculum learning is trying to solve. We present an automatic curriculum learning algorithm for discrete task-space scenarios. Our curriculum generation is based on difficulty measure between tasks and learning progress metric within a task. We apply our algorithm to a grasp learning problem involving 49 diverse objects. Our results show that a policy trained based on a curriculum is both sample efficient compared to learning from scratch and able to learn tasks that the latter could not learn within a reasonable amount of time.

关键词： Curriculum learning Deep Reinforcement learning Robotic Grasping

来源：评论

学校读者我要写书评

暂无评论

A statistically-Guided Deep Network Transformation and Moderation Framework for data with Spatial Heterogeneity 21

A Statistically-Guided Deep Network Transformation and Moder...

引用

21st IEEE international conference on data Mining (IEEE ICDM)

作者： Xie, Yiqun He, Erhu Jia, Xiaowei Bao, Han Zhou, Xun Ghosh, Rahul Ravirathinam, Praveen Univ Maryland College Pk MD 20742 USA Univ Pittsburgh Pittsburgh PA 15260 USA Univ Iowa Iowa City IA 52242 USA Univ Minnesota Minneapolis MN 55455 USA

ISBN: (纸本)9781665423984

Spatial data are ubiquitous, massively collected, and widely used to support critical decision-making in many societal domains, including public health (e.g., COVID-19 pandemic control), agricultural crop monitoring, transportation, etc. While recent advances in machine learning and deep learning offer new promising ways to mine such rich datasets (e.g., satellite imagery, COVID statistics), spatial heterogeneity - an intrinsic characteristic embedded in spatial data - poses a major challenge as data distributions or generative processes often vary across space at different scales, with their spatial extents unknown. Recent studies (e.g., SVANN, spatial ensemble) targeting this difficult problem either require a known space-partitioning as the input, or can only support very limited number of partitions or classes (e.g., two) due to the decrease in training data size and the complexity of analysis. To address these limitations, we propose a model-agnostic framework to automatically transform a deep learning model into a spatial-heterogeneity-aware architecture, where the learning of arbitrary space partitionings is guided by a learning-engaged generalization of multivariate scan statistic and parameters are shared based on spatial relationships. We also propose a spatial moderator to generalize learned space partitionings to new test regions. Experiment results on real-world datasets show that the spatial transformation and moderation framework can effectively capture flexibly-shaped heterogeneous footprints and substantially improve prediction performances.

关键词： Deep learning statistics spatial heterogeneity

来源：评论

学校读者我要写书评

暂无评论

AD-CGAN: Contrastive Generative Adversarial Network for Anomaly Detection 21st

AD-CGAN: Contrastive Generative Adversarial Network for Anom...

引用

21st international conference on Image Analysis and Processing (ICIAP)

作者： Sevyeri, Laya Rafiee Fevens, Thomas Concordia Univ Gina Cody Sch Engn & Comp Sci Montreal PQ Canada

ISBN: (纸本)9783031064272;9783031064265

Anomaly detection (AD), a fundamental challenge in machine learning, aims to find samples that do not belong to the distribution of the training data. Among unsupervised anomaly detection models, models based on generative adversarial networks show promising results. These models mainly rely on the rich representations learned from the normal training data to find anomalies. However, their performance is bounded by the limitations of GANs, known as mode collapse, in learning complex training distribution. This work presents a new GAN-based anomaly detection model with a combination of contrastive learning to mitigate the negative effect of mode collapse in more complex distributions. Our unsupervised Anomaly Detection model based on Contrastive Generative Adversarial Network, AD-CGAN, contrasts a sample with local feature maps of itself instead of only contrasting the given sample with other instances as in conventional contrastive learning approaches. Contrastive loss in AD-CGAN helps the model learn more discriminative representations of normal samples. Furthermore, we consider a new normality score to target anomalous samples. The normality score is defined on the encoded representations of samples obtained from the model. Extensive experiments showed AD-CGAN outperforms its counterparts on multiple benchmarks with a significant improvement in ROC-AUC over the previously proposed reconstruction-based approaches.

关键词： Anomaly detection Contrastive learning Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Domain-Robust Pre-Training Method for the Sensor-Based Human Activity Recognition 21

Domain-Robust Pre-Training Method for the Sensor-Based Human...

引用

21st international conference on Machine learning and Cybernetics, ICMLC 2022

作者： Zhao, Zhong-Kai Hasegawa, Tatsuhito University of Fukui Graduate School of Engineering Fukui071002 Japan

ISBN: (数字)9781665488327

ISBN: (纸本)9781665488327

Transfer learning improves problem-solving efficiency by transferring the learned knowledge from the source domain to the target domain. In transfer learning, using a large amount of data for pre-training is beneficial to improve the robustness of the model. data differ significantly when the domain changes in Sensor-Based human activity recognition (HAR). Currently, in HAR, data usage is relatively independent, lacking source domains with massive data and rich labels. This paper proposes a new pre-training method using multiple domain datasets to construct a domain-robust pre-training model. We divide the pre-training dataset into basic and complex activities scenarios by considering the difference in activity classification. We evaluate the classification scenarios that are most beneficial for sensor-based HAR based on the constituted dataset and using deep convolutional networks. We show that our method verified the influence of the source domain on transfer learning in sensor-based HAR. By constructing a sizeable correlated source domain, our method can enhance the generalization ability of the network model. This paper also demonstrated that large-scale and basic activity classification datasets can be better used as pre-training models to participate in HAR classification tasks. © 2022 IEEE.

关键词： Large dataset

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 << < 82 83 84 85 86 87 88 89 90 91 > >>

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：