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

3,150 篇 会议
173 册 图书
27 篇 期刊文献

馆藏范围

3,349 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,240 篇 工学
- 2,038 篇 计算机科学与技术...
- 1,085 篇 软件工程
- 402 篇 信息与通信工程
- 356 篇 电气工程
- 249 篇 生物工程
- 169 篇 控制科学与工程
- 157 篇 生物医学工程（可授...
- 73 篇 光学工程
- 73 篇 化学工程与技术
- 68 篇 机械工程
- 62 篇 仪器科学与技术
- 59 篇 电子科学与技术（可...
- 58 篇 安全科学与工程
- 46 篇 交通运输工程
- 38 篇 材料科学与工程（可...
- 38 篇 动力工程及工程热...
717 篇 理学
- 377 篇 数学
- 272 篇 生物学
- 169 篇 物理学
- 147 篇 统计学（可授理学、...
- 104 篇 系统科学
- 69 篇 化学
459 篇 管理学
- 298 篇 图书情报与档案管...
- 199 篇 管理科学与工程(可...
- 95 篇 工商管理
300 篇 医学
- 273 篇 临床医学
- 125 篇 基础医学(可授医学...
- 70 篇 药学(可授医学、理...
- 53 篇 公共卫生与预防医...
64 篇 法学
- 57 篇 社会学
32 篇 经济学
31 篇 教育学
28 篇 农学
6 篇 艺术学
3 篇 军事学
1 篇 文学

主题

549 篇 data mining
549 篇 machine learning
291 篇 pattern recognit...
243 篇 deep learning
192 篇 feature extracti...
163 篇 support vector m...
156 篇 artificial intel...
127 篇 accuracy
123 篇 training
117 篇 machine learning...
100 篇 data models
93 篇 data mining and ...
75 篇 classification
73 篇 convolutional ne...
72 篇 neural networks
70 篇 predictive model...
69 篇 computational mo...
68 篇 big data
58 篇 sentiment analys...
55 篇 learning systems

机构

10 篇 chinese academy ...
9 篇 chitkara centre ...
8 篇 zhejiang univers...
7 篇 guangdong univer...
7 篇 centre of resear...
6 篇 central south un...
6 篇 unsw sydney
6 篇 college of compu...
5 篇 badji mokhtar un...
5 篇 indian institute...
5 篇 xi'an university...
5 篇 indian statistic...
5 篇 southwest jiaoto...
5 篇 kobe university ...
5 篇 southern univers...
4 篇 columbia univers...
4 篇 chitkara univers...
4 篇 shanghai jiao to...
4 篇 institute of big...
4 篇 centre for patte...

作者

12 篇 de-shuang huang
12 篇 venkatesh svetha
8 篇 petra perner
7 篇 phung dinh
7 篇 jacek m. zurada
7 篇 krasotkina olga
7 篇 mottl vadim
6 篇 zheng-guang wu
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 hongyi li
6 篇 chaojie li
6 篇 biao luo
6 篇 lotfi a. zadeh
6 篇 kang-hyun jo
6 篇 leszek rutkowski
6 篇 long cheng
6 篇 zhongzhi shi
5 篇 zhang yan
5 篇 vitoantonio bevi...

语言

3,035 篇 英文
298 篇 其他
38 篇 中文

检索条件"任意字段=4th International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3350 条记录，以下是771-780 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：

Online Multi-label Streaming Feature Selection Based on Neighborhood Approximation Error Rate and Label Correlation 11th

Online Multi-label Streaming Feature Selection Based on Nei...

引用

11th international Joint conference on Rough Sets, IJCRS 2025

作者： Pan, Siping Zhong, Juda Mao, Yu Lin, Yaojin School of Computer Science Minnan Normal University Fujian Zhangzhou363000 China Key Laboratory of Data Science and Intelligence Application Minnan Normal University Fujian Zhangzhou363000 China

ISBN: (纸本)9783031927430

Multi-label learning has garnered significant attention and application in the domains of machine learning, data mining, and pattern recognition. However, existing multi-label learning algorithms often fall short in adequately capturing the complex dynamic correlations among labels. To address this limitation, this paper proposes an online multi-label stream feature selection algorithm based on neigh-borhood approximation error rate and label correlation. Initially, the similarity between labels is computed, and correlated labels are partitioned into multiple subsets. the strongly correlated label sets thus obtained serve as the label space for the subsequent algorithm. Subsequently, instance boundaries are introduced to granulate all instances. Within the multi-label neighborhood approximation system, neighborhoods are determined based on the average intervals of samples, and a method for calculating feature importance is provided, offering a quantitative basis for feature selection. Finally, a dynamic stream feature selection framework is designed to iteratively select a subset of features that minimize the approximation error, thereby enhancing the efficiency and accuracy of feature selection. Experimental results demonstrate that the proposed algorithm consistently outperforms five other multi-label feature selection algorithms across all evaluation metrics. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Minimal Electrode EEG for BCI Emotion Detection

Minimal Electrode EEG for BCI Emotion Detection

引用

Neural Networks, Information and Communication Engineering (NNICE), international conference on

作者： Yuxin Li Hao Fang Wen Liu Chuantong Cheng Hongda Chen School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou China Institute for Imaging Data and Communications School of Engineering The University of Edinburgh Edinburgh UK State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Chinese Academy of Sciences Beijing China Brain Machine Fusion Intelligence Institute Jiangsu Industrial Technology Research Institute Suzhou China

Electroencephalography (EEG)-based emotion recognition is a potential research direction in the field of brain-computer interfaces (BCIs). However, its deployment on wearable devices still suffers from the challenges of low accuracy, heavy computation, and complex electrode placement. this study focuses on advancing the efficiency and cost-effectiveness of EEG-based BCIs for emotion recognition. Our approach begins with an investigation of electrode placement in relation to emotion detection, leveraging the SEED dataset to identify an optimal configuration that uses a minimal number of electrodes while maintaining high recognition accuracy. Employing a variety of machine learning and deep learning algorithms, we compare detection accuracy across different electrode combinations. through these experiments and subsequent analysis, we identify an effective combination of two electrodes, T7 and T8, with the SVM method achieving an impressive 92.8 % accuracy. this finding laid the foundation for the design of our wearable, closed-loop BCI device with EEG-based emotion recognition capability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Radar PRI Modulation pattern recognition Based on Recurrent Neural Network

Research on Radar PRI Modulation Pattern Recognition Based o...

引用

Computer Vision, Image and Deep learning (CVIDL), international conference on

作者： Wei Qu Gang Yao Lei Meng Department of Electronics and Optics Space Engineering University Beijing China Beijing Institute of Tracking and Telecommunications Technology Beijing China Beijing Remote Sensing Information Research Instituteline Beijing China

In this paper, the Recurrent Neural Network (RNN) model is introduced into the identification of radar emitters, which verifies the feasibility of RNN application to radar emitter identification, and the design process is simplified and the radar emitter identification method is easy to apply in engineering. Based on the radar emission source recognition model, the Pulse Repetition Interval(PRI) modulation pattern recognition research based on recurrent neural network was carried out. Firstly, aiming at the problems of gradient vanishing and gradient explosion in RNN, a PRI modulation pattern recognition method based on LSTM is proposed, and the recognition method process is introduced in detail. According to the characteristics of pulse train data, a data preprocessing method suitable for recurrent neural network is proposed. Finally, simulation verifies the effectiveness of the proposed method and tests the performance of the algorithm under different interference conditions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Image recognition based on Reinforcement learning

Research on Image Recognition based on Reinforcement Learnin...

引用

Computer Vision, Image and Deep learning (CVIDL), international conference on

作者： Jiabin Luo Rongzhen Luo School of Mathematics and Statistics Northeastern University at Qinhuangdao Hebei China Department of Mechanical Engineering University Baoding Campus of North China Electric Power University Hebei China

Nowadays, the images recognition has become a fundamental component in computer vision and assist to identify the objectives in the complex images. With the development of images processing methods, the image-level objectives recognition accuracy has been greatly enhanced by utilizing the machine learning models or neural networks. However, existing methods are mainly concentrated on the primary features of input images and concentrate on some certain areas, which ignore the environment features and the deep investigation of the image data-set. In this paper, we propose a novel image recognition method to identify the objectives and obtain the policy gradients for decreasing orders. Furthermore, we compare our proposed models with existing traditional machine learning methods to evaluate the performance of recognition accuracy. From our extensive experimental results, we can conclude that our proposed methods can achieve the subjective detection from numerous images data-set with reasonable computation costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On site excavation experiments and big data statistical verification of torque penetration index 4

On site excavation experiments and big data statistical veri...

引用

4th international conference on machine learning and Computer Application, ICMLCA 2023

作者： Cao, Yuxin Xiao, Haohan He, Maozhou Xu, Quanbin Fan, Litao Power China Railway Construction Investment Group Co. Ltd Beijing100070 China Key Laboratory of Simulation and Regulation of Water Cycle in River Basin China Institute of Water Re-sources and Hydropower Research Beijing100038 China Power China Southern Construction Investment Group Co. Ltd Shenzhen518055 China

ISBN: (纸本)9798400709449

During the excavation process of Tunnel Boring machines (TBM), a large amount of data is collected in real time. It has become increasingly important to assess the quality of surrounding rock by indirectly understanding excavation parameters. Based on this vast dataset from excavation sites, this study proposes a novel Torque Penetration Index (TPI), which is better suited for evaluating the state of the surrounding rock during TBM excavation. the TPI was validated through statistical analysis of on-site excavation experimental data and the large dataset. the research findings indicate that on the original excavation cross-section, there is a significant linear relationship between the cutterhead torque (T) and the advance rate (p), with the majority of Tĝ1/4p linear regression coefficients exceeding 0.4. this implies that the TPI can serve as a reliable index for evaluating the mechanical rock breaking capacity during excavation. this discovery holds significant importance for assessing the state of surrounding rock and optimizing the TBM excavation process, providing new perspectives and methods for excavation projects. In conclusion, through in-depth analysis of TBM excavation data, the proposed TPI index in this study offers a new perspective for evaluating the state of surrounding rock. It is expected to be widely applicable in practical engineering and provides strong support for the performance optimization of TBM excavation systems. © 2023 ACM.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

MCANet: Multimodal Caption Aware Training-Free Video Anomaly Detection via Large Language Model 27th

MCANet: Multimodal Caption Aware Training-Free Video Anomaly...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Dev, Prabhu Prasad Hazari, Raju Das, Pranesh Machine Learning Laboratory Department of Computer Science and Engineering National Institute of Technology Calicut India

ISBN: (纸本)9783031781247

Towards Video Anomaly Detection (VAD), existing methods require labor-intensive data collection and model retraining, making them costly and domain-specific. the proposed method, termed as Multi-modal Caption Aware Network (MCANet), introduces a novel paradigm that identifies anomalies in video sequences without requiring prior domain knowledge. this training-free VAD approach dynamically generates and analyzes textual descriptions of video frames by utilizing off-the-shelf vision-language model (VLM), audio-language model (ALM) and large language model (LLM). MCANet has four primary modules. the first module utilizes image-text similarities to clean noisy captions generated by the image captioning model, while the second module applies audio-text similarities to refine noisy captions produced by the audio captioning model. the third module employs a LLM to consolidate scene dynamics over time. Finally, the fourth module enhances the results by aggregating scores from semantically similar frames based on video-text similarity. To validate the effectiveness of the proposed method, experiments are conducted on two large-scale benchmark datasets (UCF-Crime and XD-Violence). Experimental results demonstrate that MCANet surpasses existing unsupervised and one-class approaches without requiring any training or data collection. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evaluating Performance of Adam Optimization by Proposing Energy Index 4th

Evaluating Performance of Adam Optimization by Proposing E...

引用

4th international conference on Recent Trends in Image Processing and pattern recognition, RTIP2R 2021

作者： Bhandari, Mohan Parajuli, Pramod Chapagain, Pralhad Gaur, Loveleen Nepal College of Information Technology Lalitpur Nepal CG Institutue of Management Kathmandu Nepal Amity International Business School Amity University Noida India

ISBN: (纸本)9783031070044

the adjustment of learning rate (η ), bias and additional parameters throughout back propagation are crucial for the performance of machine learning algorithms. Regarding optimization for algorithms, adam optimization technique tune the learning parameters by utilising the exponential decay of past gradients and their squares. However, the optimizer requires the engagement of frequently occurring features from the datasets that play a significant role for performance improvement in machine learning algorithms. In this paper, the energy model of a neuron is designed to calculate the energy index from frequently occurring features and introduced in adam optimizer. the classification performance of the proposed energy modeled adam optimizer is experimented on Logistic Regression (single layered) and Support Vector machine (hyperplane based) machine learning algorithms utlising CIFAR10, MNIST and Fashion MNIST datasets. Optimized with proposed optimizer, Logistic Regression achieved training accuracy of 90.79%, 99.02% and 95.87% whereas Support Vector machine achieved training accuracy of 39.04%, 80.80% and 82.29% for CIFAR10, MNIST and Fashion MNIST datasets respectively. © 2022, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Handwritten Digit recognition using Ensemble learning techniques: A Comparative performance Analysis 4

Handwritten Digit Recognition using Ensemble learning techni...

引用

4th international conference on Advances in Computing, Communication Control and Networking, ICAC3N 2022

作者： Afreen, Saima Kumar, Pradeep Maulana Azad National Urdu University Department of Computer Science and Information Technology Hyderabad India

ISBN: (纸本)9781665474368

the detection of some digits written by humans may seem very easy;however, in reality, it is a very challenging and tedious task to extract text from real images because of the wide variety of font sizes, shapes, textures and backgrounds, etc. this study aimed to recognize handwritten digit images by extracting the features from datasets. then theses learned characteristics are subsequently submitted to the classifier to improve the overall performance. the Bagging and boosting techniques of ensemble learning were performed by integrating different base models. Each single base model corrected the errors of the previous model. Six bagging and boosting ensemble learning algorithms were used to recognize the handwritten digit images. therefore, with 98% of accuracy, the extreme gradient boosting machine outperformed the other methods in terms of overall performance. A detailed analysis of the allocation of data among the base learners and their overall performance, including the model correctness, computation time, and error rate, was evaluated and projected. © 2022 IEEE.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

Consistency-based semi-supervised learning for point cloud classification 4

Consistency-based semi-supervised learning for point cloud c...

引用

4th international conference on pattern recognition and Artificial Intelligence, PRAI 2021

作者： Chen, Lingli Zhang, Yan Lin, Yanan Jiang, Mengxi Huang, Yunan Lei, Yunqi Xiamen University Department of Computer Science and Technology Xiamen China

ISBN: (纸本)9781665413220

Under the strong supervision information of a large number of training samples with ground-truth labels, the point cloud classification techniques have achieved great success. However, in real tasks, it is difficult to get strong supervision information like fully ground-truth labels due to the high cost of the data labeling process. thus, it is desirable to work with weak supervision. this paper presents a semi-supervised learning framework based on consistency constraints on the point cloud to solve the classification task. the key to the framework mainly includes consistency constraints and pseudo-label generation. the former uses consistency constraints to encourage the model to output consistent predictions on the original and the perturbed point cloud, which avoids overfitting due to limited labeled data. the latter generates high-quality pseudo-labels for unlabeled point clouds to strengthen the discriminative supervision of the model. By fully mining the labeled and unlabeled point clouds, the generalization ability of the model is improved. On the 3D point cloud benchmark ModelNet40 [19], with only 10% labeled data, our proposed approach performs comparable results to the supervised approaches. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Role of data mining and machine learning in Software Reusability 4

Role of Data Mining and Machine Learning in Software Reusabi...

引用

4th international conference on Innovative Computing (ICIC)

作者： Qayyum, Rabia Rubaab, Joveria Riaz, Umer Arif, Fahim NUST Mil Coll Signals Islamabad Pakistan

ISBN: (纸本)9781665400916

machine learning and data mining have opened new streams in research and software development. Likewise, integration of machine learning with software development life cycle has provided opportunities for well-organized and effective development. Software reusability is an important aspect of SDLC. therefore, automation of software reusability plays a dynamic role in SDLC. It curtails the cost and effort required for development of a software product. this paper provides a taxonomical mapping of reuse metrics and corresponding machine learning techniques applicable. Artificial intelligence techniques i.e., neural networks and clustering are nominated in the paper to check their applicability for automation of software reusability. A model is created to identify best machine learning practice amongst the nominated techniques for automation of software reusability. Evaluation of model based on survey results identifies ANN: the best technique among neural networks and clustering.

关键词： Component based software engineering (CBSE) Artificial Intelligence (AI) Artificial Intelligence in software engineering application levels (AI-SEAL) clustering classification neural network

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335页 << < 74 75 76 77 78 79 80 81 82 83 > >>

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：