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

6,793 篇 会议
630 册 图书
130 篇 期刊文献

馆藏范围

7,552 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

3,899 篇 工学
- 3,090 篇 计算机科学与技术...
- 1,403 篇 软件工程
- 794 篇 电气工程
- 679 篇 信息与通信工程
- 503 篇 控制科学与工程
- 299 篇 生物工程
- 281 篇 生物医学工程（可授...
- 265 篇 机械工程
- 191 篇 光学工程
- 163 篇 电子科学与技术（可...
- 145 篇 仪器科学与技术
- 140 篇 化学工程与技术
- 59 篇 安全科学与工程
- 45 篇 材料科学与工程（可...
- 36 篇 交通运输工程
1,222 篇 理学
- 673 篇 数学
- 356 篇 物理学
- 334 篇 生物学
- 198 篇 统计学（可授理学、...
- 147 篇 化学
- 105 篇 系统科学
553 篇 管理学
- 314 篇 管理科学与工程(可...
- 255 篇 图书情报与档案管...
- 59 篇 工商管理
274 篇 医学
- 230 篇 临床医学
- 109 篇 基础医学(可授医学...
- 75 篇 药学(可授医学、理...
66 篇 法学
- 62 篇 社会学
51 篇 艺术学
- 49 篇 设计学（可授艺术学...
42 篇 农学
- 39 篇 作物学
21 篇 教育学
19 篇 文学
18 篇 经济学
5 篇 军事学

主题

3,150 篇 pattern recognit...
535 篇 feature extracti...
429 篇 artificial intel...
385 篇 neural networks
295 篇 data mining
278 篇 machine learning
234 篇 face recognition
224 篇 pattern matching
215 篇 support vector m...
203 篇 image segmentati...
194 篇 pattern classifi...
193 篇 computer imaging...
183 篇 computer science
182 篇 local binary pat...
168 篇 computational mo...
159 篇 computer vision
147 篇 humans
146 篇 testing
142 篇 accuracy
141 篇 training

机构

40 篇 school of comput...
38 篇 national laborat...
25 篇 institute of ima...
24 篇 center for resea...
24 篇 computer vision ...
22 篇 institute of ima...
22 篇 university of ch...
21 篇 department of co...
20 篇 indian statistic...
19 篇 national laborat...
19 篇 institute of com...
16 篇 tongji universit...
16 篇 chinese academy ...
15 篇 institute for pa...
14 篇 national center ...
14 篇 chinese acad sci...
14 篇 częstochowa univ...
13 篇 agh university o...
13 篇 school of electr...
12 篇 indian stat inst...

作者

35 篇 yang jie
31 篇 de-shuang huang
25 篇 tieniu tan
23 篇 umapada pal
19 篇 ryszard tadeusie...
19 篇 liang wang
18 篇 ajith abraham
17 篇 marcin korytkows...
17 篇 lu hanqing
17 篇 jacek m. zurada
17 篇 leszek rutkowski
16 篇 jie yang
16 篇 zhenan sun
16 篇 shamsuddin siti ...
16 篇 pal umapada
15 篇 wang da-han
15 篇 chew lim tan
15 篇 rafał scherer
14 篇 xu changsheng
14 篇 lotfi a. zadeh

语言

7,403 篇 英文
84 篇 其他
77 篇 中文

检索条件"任意字段=International Conference of Soft Computing and Pattern Recognition"

共 7554 条记录，以下是981-990 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：

pattern Storage & Recalling Using Hopfield Neural Network and HOG Feature Based SVM Classifier: An Experiment with Handwritten Odia Numerals

Pattern Storage & Recalling Using Hopfield Neural Network an...

引用

Emerging Smart computing and Informatics (ESCI), conference on

作者： Naman Sharma Karan Kalra Pradeepta Kumar Sarangi Lekha Rani Merry Saxena Santosh Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Siksha ‘O’ Anusandhan University Bhubaneshwar

Handwritten Odia text identification is very useful for the society and also a challenging task as it may include a variety of writing styles, complicated character-touching, and abundant categories of character class. This work implements two different classifiers for handwritten Odia numerals. The first experiment involves the implementation of a Hopfield neural network with binary image as the feature set. Using the feature extraction technique based on the Histogram of Oriented Gradients (HOG), a Support Vector Machine (SVM) classifier is implemented in a second experiment. Different cell sizes have been used to extract HOG features and finally the best cell size with optimal features have been used. The data set has been created on Microsoft Paint by drawing the digits manually and also collected from different users. The Hopfield model has been implemented with four different data sets (0% noise, 10% noise, 20% noise and 30% noise). Addition of noise to the data has been done through programming. Both the models (Hop field and SVM) have been implemented through MATLAB and the data set has been used for testing the models. Results prove that the Hopfield model's performance is higher than the SVM classifier whereas, the recognition accuracy for Hopfield model is decreasing with increase in noise percentage and could be considered as poor performance.

关键词： Support vector machines Computational modeling Hopfield neural networks Writing Programming Feature extraction Mathematical models

来源：评论

学校读者我要写书评

暂无评论

CDNN: A Novel Methodology Development to Detect Online Social Network Cyberbullying Threats Using Convoluted Deep Neural Network Principle

CDNN: A Novel Methodology Development to Detect Online Socia...

引用

Innovative computing, Intelligent Communication and Smart Electrical Systems (ICSES), international conference on

作者： S. Niranjana D. Vidyanadha Babu K. Malathy S. Durga Devi K. Kishore Babu C Karthikeyan. Department of AI & DS Rajalakshmi Institute of Technology Chennai Department of AIMLDS QIS College of Engineering and Technology Vengamukkapalem ONGOLE Andhra Pradesh Department of MCA S.A. Engineering College (Autonomous) Chennai Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Department of AIMLDS QIS College of Engineering and Technology Vengamukkapalem ONGOLE AndhraPradesh Department of ECE R.M.K. Engineering College Kavaraipettai Chennai

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Advanced methods for effective detection and prevention are required due to the growing prevalence of cyberbullying on online social networks. The Convoluted Deep Neural Network Principle (CDNN) is employed in this research to introduce a novel method for identifying cyberbullying threats. In order to extract hierarchical features from a variety of data inputs, the CDNN framework incorporates multiple layers of convolutional networks. The proposed model is cross-validated with the conventional classifier called Support Vector Machine (SVM) to evaluate the efficiency of the proposed scheme. The model captures the complex structures typical of cyberbullying behavior by processing these inputs through a successive convolution and pooling layers. We have performed a series of in-depth experiments to test this model with the ability to identify or classify cyberbullying incidents using a dataset that contained all manner of social networking interactions. The results we get prove that the performance of the CDNN-based approach outperforms traditional methods and other related deep learning models, in which it shows the detection accuracy rate as high as 98.02% detected by our model. More importantly, the robustness of CDNN toward different types of contents provided for cyberbullying can be mainly enhanced by its ability to handle multimodal data sources. Results emphasize the effectiveness of CDNN in tackling very complex issues related to recognition of cyberbullying and the precise platform for monitoring online activities.

关键词： Support vector machines Deep learning Training Adaptation models Accuracy soft sensors Transfer learning Cyberbullying Feature extraction Threat assessment

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Facial Attribute Prediction against Adversarial Attacks 2021

Robust Deep Facial Attribute Prediction against Adversarial ...

引用

7th international conference on computing and Artificial Intelligence, ICCAI 2021

作者： Fang, Kun Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)9781450389501

Face recognition has always been a hot topic in research, and has also widely been applied in industry areas and daily life. Nowadays, face recognition models with excellent performance are mostly based on deep neural networks (DNN). However, recently researchers find that images added invisible perturbations could successfully fool neural networks, which is known as the so-called adversarial attack. The perturbed images, also known as adversarial examples, are almost the same as the original images, but neural network could give different and wrong predictions with high confidence on these adversarial examples. Such a phenomenon indicates the vulnerable robustness of neural network and thus casts a shadow on the security of DNN-based face recognition models. Therefore, in this paper, we focus on the facial attribute prediction task in face recognition, investigate the influence of adversarial attack on facial attribute prediction and give a solution on improving the robustness of facial attribute prediction models. Extensive experiment results illustrate that the solution could indeed produce much more robust results in facial attribute prediction against adversarial attacks. © 2021 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

6th international conference on soft computing and its Engineering Applications, icsoftComp 2024

6th International Conference on Soft Computing and its Engin...

引用

6th international conference on soft computing and its Engineering Applications, icsoftComp 2024

ISBN: (纸本)9783031880384

The proceedings contain 31 papers. The special focus in this conference is on soft computing and its Engineering Applications. The topics include: Optimizing XGBoost for Blockchain Malicious Node Detection by Metaheuristics;a Correct-by-Construction Model for Request-Based Access Control;Lattice-Based Post Quantum Cryptography Using Variations of Learning with Error (LWE);a Spatio-Temporal Explainable Deep Learning Approach for Frame Classification from Book Flipping Videos;adapting a Modern Siamese Framework for 360∘ Video Object Tracking;detecting Deepfake Images with Enhanced Generative Adversarial Networks;CRITIC and TOPSIS-Enhanced Fuzzy Clustering (CTEFC) Protocol for IoT-Based WSNs;ambiguous Sets and Various Distance Measurements;The Study on Face recognition Using Between Convolutional Neural Network (CNN) and Local Binary Histogram (LBPH) with Censored Facial Images;an Air-Written Real-Time English Isolated Numeral recognition;The PV-ALE Dataset: Enhancing Apple Leaf Disease Classification Through Transfer Learning with Convolutional Neural Networks;Impact of SMOGN on Regression Models for Crop Yield Prediction in Mizoram Agriculture;deep Learning for Sustainable Apple Farming: Disease Detection in Leaves;forecasting Coffee Prices with Facebook Prophet: A Machine Learning Approach;Enhancing Hindi Named Entity recognition Using XLM-RoBERTa;neural Network Architectures for Machine Translation: Enhancing Quality Education Through Improved Access to Multilingual Resources;optimizing Error Detection in Generated Code Using Metaheuristic Optimized Natural Language Processing;enhancing Graph Based Models for Automatic Program Repair;enhancing Grapheme-to-Phoneme Conversion for Bengali Speech recognition: Leveraging Dialectical Variations and Morphophonemic Rules;Determinants of Generative AI-Based Chatbot Adoption in Customer Support;toxNet: A Multi-layer Network Approach to Toxicity Analysis Using Graph Neural Networks;multiphase Sentiment Analysis Model for Auto

关键词：

来源：评论

学校读者我要写书评

暂无评论

Challenges and Limitations in Data Mining

Challenges and Limitations in Data Mining

引用

6th international conference on Computational Intelligence in pattern recognition, CIPR 2024

作者： Abdullahi, Akibu Mahmoud Htet, Sai Ahkar Riskhan, Basheer School of Computing and Informatics Albukhary International University Jalan Tune Abdul Razak Kedah Alor Setar Malaysia

ISBN: (纸本)9789819780921

Privacy protection has been one of the main issues in data mining for the past few years due to the swift advancement of the technology used in data processing, storage, and the Internet. Finding relevant patterns and insights in massive datasets is made possible in great part by data mining. However, it also faces various challenges and limitations that can hinder its effectiveness and accuracy. This chapter aims to explore the challenges and limitations of data mining and provide insights into potential solutions. A comprehensive literature review is conducted to identify the existing research and approaches in this domain. The problem statement is defined, and research inquiries are developed to guide the investigation. The methodology involves analyzing relevant studies, identifying common challenges, and proposing possible strategies to overcome them. The results of this study participate to a better comprehension of the challenges and limitations in data mining and provide valuable insights for researchers and practitioners in the field. It also covers a number of upcoming difficulties and concerns in data mining, which are crucial to doing more study in this developing area. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Classification Data mining Knowledge discovery Regression

来源：评论

学校读者我要写书评

暂无评论

6th international conference on soft computing and its Engineering Applications, icsoftComp 2024

6th International Conference on Soft Computing and its Engin...

引用

6th international conference on soft computing and its Engineering Applications, icsoftComp 2024

ISBN: (纸本)9783031880414

关键词：

来源：评论

学校读者我要写书评

暂无评论

Passive BLE Sensing for Indoor pattern recognition and Tracking 18

Passive BLE Sensing for Indoor Pattern Recognition and Track...

引用

18th international conference on Mobile Systems and Pervasive computing, MobiSPC 2021, The 16th international conference on Future Networks and Communications, FNC 2021 and the 11th international conference on Sustainable Energy Information Technology, SEIT 2021

作者： Afyouni, Imad Musleh, Mashaal Basalamah, Anas Tariq, Zaid Bin Department of Computer Science University of Sharjah United Arab Emirates Computer Science and Engineering Department University of Minnesota United Arab Emirates Rensselaer Polytechnic Institute TroyNY United States Computer Engineering Department Umm Al Qura University Saudi Arabia

Crowd-centric sensing using smart phones enables a diverse range of applications evolving from large outdoor environments (e.g., smart cities) to small-scale indoor environments (e.g., smart homes, smart buildings). Tracking users' patterns in indoor environments is a valuable and challenging aspect that is not yet fully addressed. Active indoor localization systems are generally energy-inefficient and cannot be applied to crowd monitoring applications. This paper focuses on the development of a passive and energy-efficient indoor tracking and pattern recognition technique on top of a managed Bluetooth Low-Energy (BLE) network. Particularly, our system model is based on a passive monitoring of a network of BLE tags, which continuously broadcast their unique identifiers, and the current timestamp. Multiple protocols were implemented to extract moving objects' locations in indoors. The trajectory building process consists of different phases: 1) data sampling, 2) outlier detection and removal, 3) location estimation with a weighted centroid approach, 4) spatio-temporal map matching, and finally 5) trajectory smoothing. A series of experiments was conducted to demonstrate the efficiency and accuracy of the proposed approach, with respect to active triggering approaches and BLE-based localization systems. © 2021 Elsevier B.V.. All rights reserved.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Clipping-based Neural Network Post Training Quantization for Object Detection

Clipping-based Neural Network Post Training Quantization for...

引用

Control, Electronics and Computer Technology (ICCECT), IEEE international conference on

作者： Cui Liqun Hu Lei School of Soft Ware Liaoning Technical University Huludao China

Convolutional Neural Networks (CNN) have achieved amazing breakthroughs in computer vision, speech recognition, and other fields. However, with the development of deep learning, the number of weights in the neural network is increasing, consuming a lot of storage and computing resources. The high storage cost and computational complexity severely restrict the deployment of deep learning on embedded mobile devices. Therefore, the compression and acceleration of convolutional neural networks becomes particularly important. Therefore, in order to compress the size of the target detection model and speed up the calculation, this paper proposes a post-training quantization method for clip limit operation, limits are performed on the input data stream and weight parameters during training, then uses the parameter quantization method to quantize the model parameters from 32-bit floating point to 8-bit Integer. Under the premise of no impact on the performance of the algorithm, the model can be effectively compressed and the calculation speed can be improved. On the public data set PASCAL VOC2012, the performance of this algorithm is evaluated by two classic target detection algorithms, Faster R-CNN and YOLO V3. The experimental results show that compared with the original model, it saves 75% of the storage space and improves the calculation speed 2 times faster; FPS is also improved compared to standard quantization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Sleeping Posture recognition Method Based on Pressure Sensor

Research on Sleeping Posture Recognition Method Based on Pre...

引用

10th international conference on Applied Human Factors and Ergonomics (AHFE) / international conference on Human Factors and Ergonomics in Healthcare and Medical Devices

作者： Wang, Huabing Wan, Changyuan South China Univ Technol Design Sch Guangzhou Peoples R China

ISBN: (纸本)9783030204518;9783030204501

Using the structure of the butterfly pillow is the most simplest identification method, combined with the pressure sensor. The resistance value of the pressure sensor is obtained by analog-to-digital converter (A/D). The change of resistance of pressure sensors under different sleeping postures is analyzed, then pattern matching system is used to realize pattern matching and sleep position recognition. The recognition rate of sleeping position in the NISS is 95.6%, and the recognition rate in ISS mode is 92.5%. The recognition method proposed in this paper does not interfere with the user's normal sleep experience. Combining the existing technology and methods to optimize the recognition of sleeping posture, the recognition rate of sleeping posture is still very high,which can help people with poor sleep to greatly optimize the sleep quality.

关键词： Pressure sensor Butterfly pillow Sleeping position Position recognition pattern matching

来源：评论

学校读者我要写书评

暂无评论

Morphological Classification of Galaxies using Enhanced Deep Learning Model

Morphological Classification of Galaxies using Enhanced Deep...

引用

Communication, computing and Industry 4.0 (C2I4), international conference on

作者： Rohan Nemade Suraj Jha Harsh Anand Saravanan Chandrasekaran Department of Computer Science and Engineering SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350379884

ISBN: (纸本)9798350379891

Galaxies in astrophysics are one of its fundamental, their morphological classification remains an essential key to unlock countless doors about the structure, formation and history of our Universe. For nearly a century, astronomers have assigned galaxies to perceptual categories such as ellipticals, spirals and irregulars. However, the extraordinary expansion of the galaxy database catalysed and instigated by sky surveys of ever-increasing scales rendered this classification more manual than practical. Because of the learning capability and its scaling nature, to learn hierarchical abstract features from the visual data Convolutional Neural Networks (CNN) are powerful tools to recognize complex patterns and structures in images, such as spiral arms or central bulges that contribute significantly to accurate morphological classification. That is why CNN are particularly well suited to the problem of galaxy classification. While traditional classification work used to solve the problem, it is not feasible for today's huge amounts of generated data. This attempt to build and train a CNN model using galaxy images as our domain. The Enhanced CNN model can achieve the high accuracy to morphological type of galaxies. The Enhanced CNN increase both efficiency and classification accuracy, particularly when processing large dataset. The Galaxy Zoo dataset indicated that our study can provide a tool for other astronomical research in future. The Enhanced CNN gain the overall accuracy rate are 95.29% with the performance indicator were calculated including average precision, recall, F1-score and Area under curve (AUC) is 0.9513, 0.9531, 0.9525 and 0.9853 respectively. The Enhanced CNN outperforms the various existing state-of-the models.

关键词： Deep learning Surveys Representation learning Visualization Accuracy Spirals Shape Robustness pattern recognition Convolutional neural networks

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500页 << < 95 96 97 98 99 100 101 102 103 104 > >>

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：