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

3,133 篇 会议
171 册 图书
28 篇 期刊文献

馆藏范围

3,331 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,241 篇 工学
- 2,038 篇 计算机科学与技术...
- 1,086 篇 软件工程
- 402 篇 信息与通信工程
- 358 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
- 63 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
- 47 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...
718 篇 理学
- 378 篇 数学
- 273 篇 生物学
- 168 篇 物理学
- 147 篇 统计学（可授理学、...
- 104 篇 系统科学
- 70 篇 化学
460 篇 管理学
- 298 篇 图书情报与档案管...
- 200 篇 管理科学与工程(可...
- 96 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

545 篇 data mining
543 篇 machine learning
286 篇 pattern recognit...
239 篇 deep learning
188 篇 feature extracti...
160 篇 support vector m...
156 篇 artificial intel...
120 篇 training
118 篇 accuracy
115 篇 machine learning...
95 篇 data models
91 篇 data mining and ...
75 篇 classification
72 篇 neural networks
70 篇 convolutional ne...
68 篇 predictive model...
67 篇 big data
64 篇 computational mo...
57 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 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...
4 篇 shandong institu...

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

3,198 篇 英文
117 篇 其他
32 篇 中文

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

共 3332 条记录，以下是411-420 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：

A machine learning and Deep learning Integrated Model to Detect Criminal Activities 4

A Machine Learning and Deep Learning Integrated Model to Det...

引用

4th international conference on Big data Analytics and Practices, IBDAP 2023

作者： Arpa, Kanij Fatema Mittra, Tanni Ferdous, Tasnim Jahan, Nusrat Khan Tayna, Riffat Ara Hasan, Mahamudul Ahmmad Rashid, Mohammad Rifat Ali, Md Sawkat East West University Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350300192

Crime is considered an intended execution of an act that is harmful to society and punishable under criminal law. Bangladesh as a developing country has experienced severe crime-related issues in recent years due to the constantly growing criminal activities. the law enforcement sector of Bangladesh is dedicated to implementing the law and reducing fear of offense to make Bangladesh a secure place to live. Despite this, the traditional ways of detecting crimes in Bangladesh are currently slow and less effective because they are not getting enough technological support. As a result, most of the time the crimes get reported after the occurrence. So to attain efficiency in policing activities it has become significant to develop such a system that can notify the police department before the occurrence of a crime. In our proposed model, we develop a system that can prevent crime by detecting and notifying real-time criminal activities beforehand. To carry out this concept, we build a central system consisting of three modules i.e. criminal activity identification module, weapon detection module, and criminal detection module. Each of the modules is centrally connected and can give an alert when any type of abnormality occurs. We use Deep learning and machine learning algorithms to perform criminal activity detection and face recognition of criminals. For each of the modules, we collect and prepare our own data set. We perform various experiments to investigate the effectiveness of the method. the evaluation result shows that our proposed method performs impressively in identifying criminal activities and criminals. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Enterprise Risk Prediction Model and Control Using Cloud Computing and Deep learning 4

Research on Enterprise Risk Prediction Model and Control Usi...

引用

4th international Signal Processing, Communications and Engineering Management conference, ISPCEM 2024

作者： Jiang, Yuanyuan Li, Long Guangxi Vocational Normal University Nanning Guangxi China Nanning Vocational and Technical University Nanning Guangxi China

ISBN: (纸本)9798331528676

this paper proposes an enterprise risk prediction model combining cloud computing, Long Short-Term Memory (LSTM) and LightGBM, aiming to improve the real-time performance and accuracy of enterprise risk prediction. Firstly, the large-scale data processing ability of cloud computing platform was used to collect, clean and preprocess multi-source data from finance, market, industry and other sources. then, LSTM networks are employed to capture the time series characteristics of enterprise risks, effectively extracting both long-term trends and short-term fluctuations in risk indicators through its memory units. After extracting these time-dependent features with LSTM, LightGBM (Light Gradient Boosting machine) is utilized to model the non-time series data. LightGBM's efficient decision tree algorithm excels at handling large-scale datasets quickly, thereby enhancing the model's predictive performance. Finally, the model is deployed on a cloud computing platform, enabling real-time risk prediction and control. this approach not only improves the accuracy of enterprise risk prediction but also offers excellent scalability and flexibility, making it a robust solution for enterprise risk management. ©2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

GAN-Enhanced Deep learning Approach for Forecasting the Potentially Toxic Cyanobacteria in Dams 4th

GAN-Enhanced Deep Learning Approach for Forecasting the Pote...

引用

4th international conference on Intelligent Systems and pattern recognition-ISPR

作者： Amara, Nour Djihane Dendani, Nadjette Berrezzek, Amira Khemissa, Hana Saoudi, Amel Azizi, Nabiha Badji Mokhtar Univ Dept Comp Sci Annaba Algeria Badji Mokhtar Univ Dept Biochem Annaba Algeria

ISBN: (纸本)9783031821523;9783031821530

this research delves into the phenomenon of Cyanobacterial Harmful Algal Blooms (CyanoHABs), which are caused by cyanobacteria and pose significant threats to freshwater ecosystems such as lakes, rivers, reservoirs, and dams, due to the production of cyanotoxins that endanger human and animal health. the primary objective of this study is to protect public health, water resources and to improve efficient bloom management techniques using advanced Artificial Intelligence (AI) models to forecast the onset of CyanoHABs in freshwater ecosystems. Our approach employs a Generative Adversarial Network (GAN)enhanced deep learning (DL) model in comparison with traditional regression methods such as Multi-Linear Regression (MLR), Support Vector Regression (SVR) refined through hyperparameter tuning, Decision Tree Regression (DTR), and Random Forest Regression (RFR). Our study demonstrates the effectiveness of GANs in synthesizing new data points that are diverse and realistic, thereby enriching existing datasets and enhancing the performance of DL models. Notably, the outstanding forecasting accuracy of the GAN-enhanced 1Dimensional Convolutional Neural Network (1D CNN) model, achieving an impressive R-squared (R2) value of 0.98, underscores its efficacy in predicting occurrences of CyanoHABs.

关键词： Toxins Cyanobacteria Deep learning 1Dimensional Convolutional Neural Network Generative Adversarial Network

来源：评论

学校读者我要写书评

暂无评论

Improving End-to-End Text Image Translation From the Auxiliary Text Translation Task 26

Improving End-to-End Text Image Translation From the Auxilia...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Ma, Cong Zhang, Yaping Tu, Mei Han, Xu Wu, Linghui Zhao, Yang Zhou, Yu Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit NLPR 95 Zhongguan East Rd 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: (数字)9781665490627

ISBN: (纸本)9781665490627

End-to-end text image translation (TIT), which aims at translating the source language embedded in images to the target language, has attracted intensive attention in recent research. However, data sparsity limits the performance of end-to-end text image translation. Multi-task learning is a non-trivial way to alleviate this problem via exploring knowledge from complementary related tasks. In this paper, we propose a novel text translation enhanced text image translation, which trains the end-to-end model with text translation as an auxiliary task. By sharing model parameters and multi-task training, our model is able to take full advantage of easily-available large-scale text parallel corpus. Extensive experimental results show our proposed method outperforms existing end-to-end methods, and the joint multi-task learning with both text translation and recognition tasks achieves better results, proving translation and recognition auxiliary tasks are complementary. (1)

关键词： Training Image recognition Text recognition Optical character recognition Multitasking Decoding machine translation

来源：评论

学校读者我要写书评

暂无评论

An Efficient Real-Time Word-Level recognition of Indian Sign Language 4th

An Efficient Real-Time Word-Level Recognition of Indian Sign...

引用

4th international conference on Innovations in Computational Intelligence and Computer Vision, ICICV 2024

作者： Chaitanya Madhav, R. Shet, Prasad Mohan Murali, K.S. Likhith, R. Mamatha, H.R. Department of Computer Science PES University Karnataka Bengaluru India

ISBN: (纸本)9789819769919

Advancements in technology have catalyzed innovations in machine learning and artificial intelligence, particularly in image recognition. While existing research has predominantly focused on static sign recognition for Sign Language, this study proposes a real-time dynamic sign recognition of Indian Sign Language. Given the fundamental importance of communication, especially for the hearing and speech-impaired, this research addresses the critical need for instant translation of sign language into text. To resolve this communication gap, this research introduces a comprehensive dataset using references from the "Indian Sign Language Research and Training Centre New Delhi" an official government-backed YouTube Channel dedicated to Indian Sign Language, which standardizes Indian Sign Language across the country. the dataset comprises 60 signs encompassing verbs, animals, vegetables, legal terms, fruits, emotions and more. the authors utilized Mediapipe as a feature extractor to train a total of nine models, including seven deep learning models namely LSTM, CNN, GRU, Bidirectional LSTM, Stacked LSTM, Hybrid CNN-GRU, and Convolutional LSTM, along with two machine learning models, namely Random Forest and XGBoost. Notably, the Convolutional LSTM model achieved the highest accuracy of 99.88%. Reliable evaluation metrics like Mean Average Precision, Confusion Matrix, Accuracy, F1-Score were employed, which shows the correctness of the signs predicted and ensures the precision of dynamic sign recognition. the culmination of this research results in a real-time system capable of instantaneously identifying dynamic signs. this contribution spans diverse domains such as pattern recognition, Computer Vision, Video recognition, etc., addressing key challenges like the need for gloves or additional sensors, the requirement for many videos to train a single sign, utilization of simple signs, high processing power demand, signer dependency, occlusions, pushing the boundaries of sig

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Behavior-Based Insider threat Detection Using a Deep Neural Network 4th

Behavior-Based Insider Threat Detection Using a Deep Neural ...

引用

4th international conference on Intelligent Systems and pattern recognition-ISPR

作者： Besnaci, Samiha Hafidi, Mohamed Lamia, Mahnane Univ Annaba Dept Comp Sci LRS Lab Annaba Algeria

ISBN: (纸本)9783031821554;9783031821561

One of the toughest cybersecurity issues today are insider threats for which no good solution has been provided to limit their damage through commonly used security solutions. Which could cause serious damage to the assets of the organization. this article begins by presenting a comprehensive multidisciplinary survey of insider threats and the various AI technologies in use. then, we proposed a method to detect internal threats by analyzing user behavior. A series of activities and events that are analyzed to extract features to effectively detect malicious activity from normal activity. the selected feature vectors are used to train the model. the convolutional neural network (CNN) is used during the implementation phase to detect insider threats of fixed-size feature vectors. the data used to conduct the experiments is public data related to internal threats cert r4.2. the experimental results of the proposed model show that it can successfully detect insider threats with an accuracy of 0.9558 in the best cases.

关键词： Insider threat CNN User Behavior Insider threat Detection security deep learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time AI Driven Shooting Posture Assessment and Correction for Professional and Military Training Using machine learning, OpenCV, and MediaPipe 4

Real-Time AI Driven Shooting Posture Assessment and Correcti...

引用

4th international conference on Technological Advancements in Computational Sciences, ICTACS 2024

作者： Sarswat, Dhairya Moradabad Institute of Technology Aktu University Computer Science and Engineering Dept. U.P. Moradabad India

ISBN: (纸本)9798350387490

Shooting is one of the most popular Olympic Games in India As for now Shooting contributed 4 out of 35 Olympic medals for the country. thus, the presented paper aims to expose some advanced training methodologies in order to achieve the maximum potential of this kind of sport. this paper also describes an implementation of an AI-based system for shooting posture evaluation and feedback by employing computer vision and sophisticated posture recognition methods in real-time control system. For image acquisition and processing, the system incorporates OpenCV and, for body landmarks detection, it uses MediaPipe's pose estimation models. It therefore computes outstanding angles as well as changes in relation to these postures to allow users to correct their positioning. Refinement of the training process in the usage of weapons is evident by adoption of the proposed solution that has displayed efficient concerning the professional shooters, military personnel, and the target consumers. the ability of the system to give real-time accurate feedback on the participants' posture while at the same time increasing the training quality and performance efficiency minimizes the gap between conventional and contemporary technological approaches in shooting training. this research also discusses the utility of the system in multiple shooting disciplines and situations. through the use of real-time video data and through the utilization of sophisticated machine learning algorithms, the system is able to tailor feedback depending on the shooting position or shooting posture or tactic that the user signifies to the system. thus, the proper combination of real-time posture assessment guarantees that users get necessary feedback instantly and apply it in the process of enhancing their technique. the research therefore establishes the role of the system in enhancing training efficiency and effectiveness;though this study could be relevant to other fields such as security, the application

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Efficient Dense-Graph Convolutional Network with Inductive Prior Augmentations for Unsupervised Micro-Gesture recognition 26

Efficient Dense-Graph Convolutional Network with Inductive P...

引用

26th international conference on pattern recognition / 8th international Workshop on Image mining - theory and Applications (IMTA)

作者： Shah, Atif Chen, Haoyu Shi, Henglin Zhao, Guoying Univ Oulu Ctr Machine Vis & Signal Anal CMVS Oulu Finland

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Skeleton-based action/gesture recognition has already witnessed excellent progress on processing large-scale, laboratory-based datasets with pre-defined skeleton joint topology. However, it's still an unsolved task when it comes to real-world scenarios with practical limitations such as small-scaled dataset sizes, few-labeled samples, and various skeleton topologies. In this paper, we work on the recognition of micro-gestures, which are subtle body gestures collected in real-world scenarios. Specifically, we utilize contrastive learning to heritage the knowledge from known large-scale datasets for enhancing the learning on fewer samples of micro-gestures. To overcome the gap caused by various domain distributions and structure topologies between the datasets, we compute skeleton representations from augmented sequences via momentum-based efficient and scalable encoders as additional inductive priors. Importantly, we propose an effective dense-graph based unsupervised architecture that resorts to a queue-based dictionary to store positive and negative keys for better contrast with queries to learn substantially efficient and discriminant patterns in the feature space. Together with cross-dataset experimental results show that our model significantly improves the accuracies on two micro-gesture datasets, SMG by 7.4% and iMiGUE by 18.41% advocating its superiority.

关键词： Dictionaries Computer architecture Skeleton Robustness data models Topology pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Predictive Modeling: Comparative Analysis of Decision Tree and Neural Network Approaches with Feature Selection 7

Enhancing Predictive Modeling: Comparative Analysis of Decis...

引用

7th international conference on New Media Studies, CONMEDIA 2023

作者： Adhli, Yuma Luqman Oetama, Raymond Sunardi Universitas Multimedia Nusantara Information System Department Tangerang Indonesia

ISBN: (纸本)9798350307504

this research is focused on enhancing the efficacy of direct marketing for bank deposit products through data mining analysis. the primary challenge lies in accurately predicting and targeting prospective customers. the study conducts a comparative analysis between two machine learning techniques: Decision Trees and Neural Networks. the research findings reveal that the original Neural Network achieves an impressive accuracy of 96.20%, substantiating its proficiency in effectually classifying data instances. the precision score of 0.6344 contributes to precise and accurate positive predictions, and the F-Score of 0.5086 reflects a well-balanced performance across various evaluation metrics. the forward approach adopted in this study maintains a high accuracy rate of 96.23% and markedly improves precision to 0.6733 while upholding a harmonized F-Score of 0.4720. Both methods underscore the effectiveness of the Neural Network in meticulous data classification and the facilitation of accurate positive predictions. the original and forward approaches possess distinct merits, heightening predictive accuracy and fostering pattern recognition within direct marketing strategies for bank deposit products. © 2023 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Multi-Model Supervised machine learning Techniques for Heart Stroke Prediction 4

Multi-Model Supervised Machine Learning Techniques for Heart...

引用

4th international conference on Expert Clouds and Applications, ICOECA 2024

作者： Kumar, Kundavaram Joseph Sujith thanka, M. Roshni Edwin, E. Bijolin Stewart Kirubakaran, S. Ebenezer, V. Joy, Priscilla Karunya Institute of technology and sciences Department of CSE Tamil Nadu Coimbatore India Karunya Institute of technology and sciences Department of DSCS Tamil Nadu Coimbatore India Karunya Institute of Technology and Sciences Division of CSE Tamil Nadu Coimbatore India

ISBN: (纸本)9798350385793

this research presents a supervised machine learning approach for heart attack prediction using several models. Prompt care and preventative measures may be possible with early recognition of heart attacks, which pose a significant danger to health. this study proposes a new method that integrates the strengths of many machine learning models to improve the precision of the generated predictions. Blood pressure, cholesterol levels, age, gender, medical history, and other risk indicators are all part of the study's dataset. the dataset is preprocessed for learning the missing values and standardizing the features. three separate ML algorithms-logistic regression, random forest, and support vector classifier (SVC)-are then trained by using the preprocessed data. the prediction ability is enhanced by stacking using the differences between each model. then, performance metrics, including F1-score, recall, accuracy, and precision are used to evaluate the stacked model. the results of the experiments demonstrate that the multi-model approach outperforms the individual models, leading to more reliable and precise predictions. the proposed technique shows the potential to predict heart attacks and assist doctors in identifying people at high risk of experiencing a heart stroke. © 2024 IEEE.

关键词： Self-supervised learning

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334页 << < 38 39 40 41 42 43 44 45 46 47 > >>

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：