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

2,967 篇 会议
174 册 图书
25 篇 期刊文献

馆藏范围

3,165 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
- 1,824 篇 计算机科学与技术...
- 959 篇 软件工程
- 330 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...
- 48 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
649 篇 理学
- 352 篇 数学
- 245 篇 生物学
- 140 篇 物理学
- 135 篇 统计学（可授理学、...
- 95 篇 系统科学
- 63 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

573 篇 machine learning
564 篇 data mining
320 篇 pattern recognit...
209 篇 deep learning
201 篇 feature extracti...
154 篇 support vector m...
145 篇 artificial intel...
129 篇 machine learning...
120 篇 training
117 篇 accuracy
90 篇 data models
89 篇 data mining and ...
71 篇 neural networks
71 篇 classification
67 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 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...
4 篇 school of inform...

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

2,998 篇 英文
154 篇 其他
25 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 3166 条记录，以下是761-770 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：

Skin Cancer Prediction using machine learning and Neural Networks 5

Skin Cancer Prediction using Machine Learning and Neural Net...

引用

5th international conference on Contemporary Computing and Informatics, IC3I 2022

作者： Tyagi, Neha Dhavamani, Logeshwari Al Ansari, Mohammed Saleh Pant, Bhasker Saini, Dilip Kumar Jang Bahadur Dhanraj, Joshuva Arockia Amity University Department of CSE Uttar Pradesh Greater Noida India St. Joseph's College of Engineering Department of Information Technology Chennai India University of Bahrain College of Engineering Department of Chemical Engineering Bahrain Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Swami Rama Himalayan University Swami Ram Nagar Jolly Grant Himalayan School of Science and Technology Department of Computer Science and Engineering Uttarakhand Dehradun India Chennai India

ISBN: (纸本)9798350398267

the apparent similarities between skin conditions have made medical diagnosis difficult. Although melanoma is the most well-known type of skin cancer, other diseases have recently been responsible for a large number of fatalities. One of the biggest challenges in creating a dependable automatic categorization system is the absence of massive data. A deep learning (DL) system for identifying skin cancer is presented in this paper. the rapid development rate of melanoma skin cancer, its massive price of surgery, and its mortality rate have all heightened the need for timely diagnosis of skin disease. Most of the time, treating cancer cells requires time and careful detection. the commitment to deep learning powered by machine learning (ML) has been repeatedly shown in the medical sector. Skin cancer categorization has benefited significantly from growing study attention since it is amenable to visual pattern recognition. Studies have revealed that DL-based image classifications may be utilised to enhance skin cancer diagnosis or are on par with or even outperform human specialists. In this study, we provide a deep learning architecture that can identify skin cancer. Five state-of-the-art convolutional neural networks were trained using transfer learning to provide a simple classifier and a hierarchical (with two stages) classification that can differentiate between seven different species of moles. Experiments were conducted using data from the HAM10000 database, a huge collection of dermatoscopic pictures, with the use of data augmentation methods to boost results. the DenseNet201 network performed well in this experiment, as seen by the high classification accuracies and F-measures achieved with very few false negatives. the simple model outperformed the 2-levels model, with the best result coming from the first level, or a binary classification between nevi and non-nevi. © 2022 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Equation Attention Relationship Network (EARN): A Geometric Deep Metric Framework for learning Similar Math Expression Embedding 25

Equation Attention Relationship Network (EARN): A Geometric ...

引用

25th international conference on pattern recognition (ICPR)

作者： Ahmed, Saleem Davila, Kenny Setlur, Srirangaraj Govindaraju, Venu Univ Buffalo CSE Dept Buffalo NY 14260 USA

ISBN: (纸本)9781728188089

Representational learning in the form of high dimensional embeddings have been used for multiple pattern recognition applications. there has been a significant interest in building embedding based systems for learning representations in the mathematical domain. At the same time, retrieval of structured information such as mathematical expressions is an important need for modern IR systems. In this work, our motivation is to introduce a robust framework for learning representations for similarity based retrieval of mathematical expressions. Given a query by example, the embedding can find the closest matching expression as a function of euclidean distance between them. We leverage recent advancements in image-based and graph-based deep learning algorithms to learn our similarity embeddings. We do this first, by using unimodal encoders in graph space and image space and then, a multi-modal combination of the same. To overcome the lack of training data, we force the networks to learn a deep metric using triplets generated with a heuristic scoring function. We also adopt a custom strategy for mining hard samples to train our neural networks. Our system produces rankings similar to those generated by the original scoring function, but using only a fraction of the time. Our results establish the viability of using such a multi-modal embedding for this task.

关键词： Mathematical Information retrieval Semi-supervised learning Graph matching

来源：评论

学校读者我要写书评

暂无评论

Intelligent inspection of surface defects in metal castings using machine learning

Intelligent inspection of surface defects in metal castings ...

引用

5th international conference on Advances in Steel, Power and Construction Technology

作者： Yousef, Nabhan Parmar, Chandrasinh Sata, Amit Marwadi Univ Morbi Rd Rajkot 360003 India Marwadi Univ Dept Mech Engn Morbi Rd Rajkot 360003 India

Metal casting is considered to be one of oldest manufacturing processes, and its root has been found back to 5000 years ago. It is mainly driven by different sub-processes including pattern making, mold making, melting and pouring. Metal casting is usually employed to produce metallic components that further used in different industrial sectors including aerospace, automobile, chemical, bio-medical, defense, etc. these industrial casting are required to be conformed with desired mechanical properties and absence of defects. the occurrence of defects is mainly related to geometrical inequalities, and surface as well as sub-surface discontinuities. Various techniques are employed to detect these defects however detection of surface discontinuities is relatively challenging as it requires decent technical skills as well as domain knowledge. In the present work, intelligent inspection for detection of surface discontinuities has been developed. Metal casting images were captured using automated camera, and they were further preprocessed for removing noise in images using Gaussian filter. Different feature extraction algorithms Harris, Otsu, Hough and Canny were used to extract various topographical features including corners, contours, discontinuities as well as edges. Two models, Support Vector machine (SVM) and K-Nearest Neighbor (KNN) models were trained on topographical features extracted from more than 1400 images Aluminum metal casting. these models were tested on the data set of more than 350 images. Both mod-els performed better in inspection of discontinuities in metal castings however SVM model provided more accurate results. the accuracy level of both models can further be improved by improving environ-ment conditions, resolution of images as well as incorporating intensity invariants object recognition techniques.(c) 2022 Elsevier Ltd. All rights *** and peer-review under responsibility of the scientific committee of the 5th international Con-

关键词： Metal Casting Detection of Defects Feature Extraction KNN SVM

来源：评论

学校读者我要写书评

暂无评论

Cold-Start Sequential Recommendation with Collaborative Boosted Meta Transitional learning 5

Cold-Start Sequential Recommendation with Collaborative Boos...

引用

5th international conference on data Science and Information Technology, DSIT 2022

作者： Wang, Guoan Wang, Xingjun Tsinghua University Dept. Electronic Engineering Beijing China

ISBN: (数字)9781665498685

ISBN: (纸本)9781665498685

As one of the essential tasks of sequential recom-mendation, it is of vital importance and challenge to capture user preferences exactly according to user behaviors. Actually, a large number of cold-start users have only few behavior records in actual scenarios, which brings the learning of user behavior patterns into dilemma. However, many existing sequential meth-ods can not give a full play of their advantages and achieve desired effect for cold-start users due to the limited interaction data. Despite many works have been proposed to ameliorate the predictive effect in cold-start scene, most of them rely on auxiliary information and little works absorbed in mining from user behavior data purely. In this paper, we propose a novel method dubbed Collaborative boosted Meta Transitional learning (Co-MetaTL) to make use of user historical behaviors more efficiently in cold-start sequential recommendation. Specifically, based on the framework of meta transitional learning, the proposed Co-MetaTL mines the collaborative neighbor relevance and utilize it to enhance the learning process of dynamic pattern in user preferences. We perform comparative experiments on three real-world datasets and the results demonstrate that our proposed method is superior than other methods and bring in at least 7.29 % improvement compared with the state-of-the-art in se-quential cold-start recommendation. © 2022 IEEE.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

Prediction and Detection of car accidents in video by deep learning 5

Prediction and Detection of car accidents in video by deep l...

引用

5th international conference on pattern recognition and Image Analysis, IPRIA 2021

作者： Rezaei, Zahra Ebrahimpour-Komleh, Hossein Statistics and Information Technology Research Institute Judiciary Research Institute University of Kashan Department of Computer and Electrical Engineering Kashan Iran

ISBN: (纸本)9781665426596

Road accidents are considered as one of the leading causes of human fatality in recent decade. Using machine vision in automobile sensors and through warning even a second before accidents occur, a human disaster can be prevented. In order to predict accident at the stage, it is needed to learn temporal and spatial characteristics. In this paper, a primary real-time autonomous accident detection system has been proposed which is established on object detection deep learning in video prediction techniques. the events in video will be the accidents which are predicted several frames before the event. In this technique, 5000 accident images were labeled, and the model was classified using all the existing classes. then, the special events were detected using object detection technique. the proposed model shows an accuracy of 92.98 and a speed of 200 images per second in video. the model can predict the event 0.92 second before accident. this model can be used in inter-city cameras with immediate analysis of meta data, and it has been piloted. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

E2TIMT: Efficient and Effective Modal Adapter for Text Image machine Translation 17th

E2TIMT: Efficient and Effective Modal Adapter for Text Image...

引用

17th international conference on Document Analysis and recognition (ICDAR)

作者： Ma, Cong Zhang, Yaping Tu, Mei Zhao, Yang Zhou, Yu Zong, Chengqing Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Multimodal Artificial Intelligence Beijing 100190 Peoples R China Zhongke Fanyu Technol Co Ltd Fanyu AI Lab Beijing 100190 Peoples R China Samsung Res China Beijing SRC B Beijing Peoples R China

ISBN: (纸本)9783031417306;9783031417313

Text image machine translation (TIMT) aims to translate texts embedded in images from one source language to another target language. Existing methods, both two-stage cascade and one-stage end-to-end architectures, suffer from different issues. the cascade models can benefit from the large-scale optical character recognition (OCR) and MT datasets but the two-stage architecture is redundant. the end-to-end models are efficient but suffer from training data deficiency. To this end, in our paper, we propose an end-to-end TIMT model fully making use of the knowledge from existing OCR and MT datasets to pursue both an effective and efficient framework. More specifically, we build a novel modal adapter effectively bridging the OCR encoder and MT decoder. End-to-end TIMT loss and cross-modal contrastive loss are utilized jointly to align the feature distribution of the OCR and MT tasks. Extensive experiments show that the proposed method outperforms the existing two-stage cascade models and one-stage end-to-end models with a lighter and faster architecture. Furthermore, the ablation studies verify the generalization of our method, where the proposed modal adapter is effective to bridge various OCR and MT models. (Our codes are available at: https://***/EriCongMa/E2TIMT)

关键词： Text image machine translation Modal adapter Cross modal contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Gesture recognition on Textile-Based Pressure Sensor Array

Gesture Recognition on Textile-Based Pressure Sensor Array

引用

Electronic Engineering, Information Technology & Education (EEITE), international conference in

作者： Ilknur Celik Munire Sibel Cetin Kadir Ozlem Cetin Ozgur Atalay Asli Tuncay Atalay Gökhan Ince Computer Engineering Istanbul Technical University Textile Engineering Istanbul Technical University

ISBN: (数字)9798350372878

ISBN: (纸本)9798350372885

Wearable technologies are in pursuit of designing portable devices worn by people. In this paper, gesture recognition on a sleeve having a capacitive textile-based pressure sensor array has been developed. machine learning models are generated to recognize a set of gestures by accumulating capacitance values read from a sensor array during the execution of gestures. the performance of the gesture recognition system is evaluated in the experiments conducted with human test subjects. Real-time gesture prediction is achieved using the trained model. the performed gestures and predicted data are collected and analyzed, resulting in accuracies up to 86'.

关键词： Pressure sensors Performance evaluation Accuracy Education Gesture recognition machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Human Activity recognition: Fight Detection using Long term Recurrent Convolutional Network (LRCN)

Human Activity Recognition: Fight Detection using Long term ...

引用

data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), international conference on

作者： Ngrddy Jhnvi S.K. Bhrdwj Ajay Sharma Shamneesh Sharma Ankur Sodhi Saikat Gochhait School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India Delivery and Student Success upGrad Education Private Limited Bangalore Karnataka India Enterprise Businees and Career Services upGrad Education Private Limited Bangalore Karnataka India Symbiosis Institute of Digital and Telecom Management Constituent of Symbiosis International Deemed University Pune India

ISBN: (数字)9798350368710

ISBN: (纸本)9798350368727

Human Activity recognition for Fight Detection is an important research domain aimed at automatically identifying patterns indicative of physical altercations. Leveraging deep learning models like CNNs and RNNs, this approach extracts features from video frames to recognize fight-related behavioural patterns. the primary objective is to develop a machine learning model capable of autonomously detecting instances of fights in video footage, using techniques such as the Long-term Recurrent Convolutional Network (LRCN). Training involves a comprehensive dataset encompassing examples of both fights and non-fight activities, with model performance evaluated using standard metrics. Each frame undergoes individual analysis by the model to predict the presence of any indications of a fight. the model predicts the action with an accuracy of 98.03% and the movements given as input can be categorized as fights or no fights.

关键词： Training Measurement Industries Predictive models Feature extraction pattern recognition Convolutional neural networks Object recognition Human activity recognition Standards

来源：评论

学校读者我要写书评

暂无评论

A Systematic Survey on COVID 19 Detection and Diagnosis by Utilizing Deep learning Techniques and Modalities of Radiology 2022

A Systematic Survey on COVID 19 Detection and Diagnosis by U...

引用

14th international conference on Contemporary Computing, IC3 2022

作者： Agrawal, Shrishtee Singh, Abhishek Tiwari, Abhishek Mishra, Anushri Tripathi, Abhinandan Department of Computer Science and Engineering Buddha Institute of Technology Gorakhpur India

ISBN: (纸本)9781450396752

One of the most difficult aspects of the present COVID19 pandemic is early identification and diagnosis of COVID19, as well as exact segregation of non-COVID19 individuals at low cost and the sickness is in its early stages. Despite their widespread use in diagnostic centres, diagnostic approaches based solely on radiological imaging have flaws given the disease's novelty. As a result, to evaluate radiological pictures, healthcare practitioners and computer scientists frequently use machine learning and deep learning models. Based on a search strategy, from November 2019 to July 2020, researchers scanned the three different databases of Scopus, PubMed, and Web of Science for this study. machine learning and deep learning are well-established artificial intelligence domains for data mining, analysis, and pattern recognition. Deep learning in which data is passed through many layers and automatically learning the composition of each layer from large dataset and it enables a new way that evaluates the complete image without human guidance to discern which insights are valuable, with applications ranging from object detection to medical image. Deep learning with CNN may have a significant effect on the automatic recognition and extraction of crucial features from X-ray and CT Scan images related to Covid19 analysis. According to the results, models based on deep learning possess amazing abilities to offer a precise and systematic system for detecting and diagnosing COVID19. In the field of COVID19 radiological imaging, deep learning software decreases false positive and false negative errors in the identification and diagnosis of the disease. It is providing a once-in-a-lifetime opportunity to provide patients with quick, inexpensive, and safe diagnostic services while also reducing the epidemic's impact on nursing and medical staff. © 2022 ACM.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Supervised machine learning: Discriminative learning Methods for pattern Classification using HELM

Supervised Machine Learning: Discriminative Learning Methods...

引用

international conference on Inventive Research in Computing Applications (ICIRCA)

作者： N. Shirisha Ajmeera Kiran A. Prashanthi MrKamjula Lakshmi Kanth Reddy MLR Institute of Technology Hyderabad India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Department of Computer Science and Engineering Nalla Narasimha Reddy Education Society's group of Institutions Department of Artificial Intelligence Anurag University Hyderabad

the ability to forecast the data is significantly helped by machine learning's involvement. At the present time, data analysis is playing a very significant part in both the Information Technology (IT) industry and academic institutions. Numerous real-time applications, such as translation in real time, facial recognition, musical compositions, and so on, have been developed through the various initiatives that have been carried out up to this point. According to the standards that must be met by every data analyst, data must first be preprocessed before any predictions can be made on that data. Predictions must also be based exclusively on the preprocessed data. this work demonstrates the data pre-processing along with the prediction of a churn model. the model contains a set of records of various customers, including information regarding whether or not the client possesses credit cards and whether or not the consumer is an active member. this research works on the construction of a hybrid ensemble learning model (abbreviated HELM) to collect heterogeneous weak learners in order to anticipate such analyses. In order to work on the Churn Model classification, a variety of machine learning algorithms are integrated with one another. the findings revealed the efficiency of each machine learning algorithm that was used, in addition to HELM's operational effectiveness.

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317页 << < 73 74 75 76 77 78 79 80 81 82 > >>

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：