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

3,117 篇 会议
141 册 图书
22 篇 期刊文献

馆藏范围

3,279 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

2,140 篇 工学
- 1,954 篇 计算机科学与技术...
- 1,096 篇 软件工程
- 404 篇 信息与通信工程
- 285 篇 电气工程
- 267 篇 生物工程
- 217 篇 控制科学与工程
- 172 篇 生物医学工程（可授...
- 79 篇 化学工程与技术
- 73 篇 光学工程
- 72 篇 机械工程
- 67 篇 仪器科学与技术
- 65 篇 电子科学与技术（可...
- 62 篇 安全科学与工程
- 55 篇 动力工程及工程热...
- 54 篇 网络空间安全
776 篇 理学
- 429 篇 数学
- 295 篇 生物学
- 151 篇 统计学（可授理学、...
- 148 篇 物理学
- 127 篇 系统科学
- 89 篇 化学
505 篇 管理学
- 306 篇 图书情报与档案管...
- 231 篇 管理科学与工程(可...
- 95 篇 工商管理
218 篇 医学
- 193 篇 临床医学
- 125 篇 基础医学(可授医学...
- 87 篇 药学(可授医学、理...
- 55 篇 公共卫生与预防医...
72 篇 法学
- 70 篇 社会学
51 篇 教育学
- 47 篇 教育学
35 篇 经济学
31 篇 农学
6 篇 艺术学
4 篇 军事学
1 篇 文学

主题

568 篇 data mining
542 篇 machine learning
241 篇 pattern recognit...
195 篇 deep learning
174 篇 feature extracti...
154 篇 artificial intel...
153 篇 support vector m...
113 篇 accuracy
113 篇 machine learning...
110 篇 training
93 篇 data models
80 篇 neural networks
77 篇 data mining and ...
65 篇 classification
62 篇 sentiment analys...
61 篇 classification a...
59 篇 big data
57 篇 predictive model...
50 篇 face recognition
48 篇 prediction algor...

机构

7 篇 maharishi school...
6 篇 guangdong univer...
5 篇 galgotias univer...
5 篇 centre of interd...
5 篇 pune
5 篇 chitkara univers...
5 篇 uttaranchal univ...
5 篇 uttaranchal inst...
5 篇 institute of aut...
4 篇 shanghai jiao to...
4 篇 chitkara univers...
4 篇 school of inform...
4 篇 indian statistic...
4 篇 south china univ...
4 篇 zhejiang univers...
4 篇 maharishi school...
4 篇 department of cs...
4 篇 university of ca...
4 篇 school of comput...
4 篇 department of co...

作者

9 篇 de-shuang huang
7 篇 coenen frans
7 篇 venkatesh svetha
7 篇 petra perner
7 篇 tianrui li
6 篇 ryszard tadeusie...
6 篇 marcin korytkows...
6 篇 jacek m. zurada
6 篇 krasotkina olga
6 篇 lotfi a. zadeh
6 篇 mottl vadim
6 篇 leszek rutkowski
5 篇 vitoantonio bevi...
5 篇 sankar k. pal
4 篇 waiyamai kitsana
4 篇 sozo inoue
4 篇 sergei o. kuznet...
4 篇 duoqian miao
4 篇 shengli xie
4 篇 hepu deng

语言

2,834 篇 英文
436 篇 其他
45 篇 中文
1 篇 西班牙文
1 篇 土耳其文

检索条件"任意字段=3rd International Conference on Machine Learning and Data Mining in Pattern Recognition"

共 3280 条记录，以下是1181-1190 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：

Advancing Brain-Computer Interfaces: A Deep learning Approach for Enhanced Neural Signal Processing 3

Advancing Brain-Computer Interfaces: A Deep Learning Approac...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Dharmendra, Kaku Riya Verma, Deepak Kumar Vats, Satvik Marwadi University Department of Computer Engineering Rajkot India Madan Mohan Malaviya University of Technology Department of Computer Science and Engineering U.P. Gorakhpur India

ISBN: (纸本)9798331542375

Brain-to-computer interfaces (BCIs) are a developing technology that has led to a straight link among the human brain and various systems. The complexity and lack of predictability of brain signals make the development of a trustworthy, accurate BCI system. In this study, we look into how advanced deep learning approaches like Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Graph Isomorphism Networks (GIN), and Convolutional Neural Network (CNN) can be used to improve neural signal processing performance in BCI. LSTM and GRU are good at discovering the temporally related EEG sequences, while CNNs extract the spatial feature of raw EEG data very well. We model and analyze graph-structured data from functional brain networks using GIN, revealing insights into spatial dynamics and inter-channel connections. Both graph-based and spatiotemporal features are integrated as proposed in the framework, and a deep learning architecture is constructed for signal decoding and classification that allows for a higher signal decoding and classification accuracy. Our experimental results on publicly available EEG datasets demonstrate that this approach outperforms standalone deep learning models and traditional machine learning approaches. It designs its solutions to attain higher accuracy, robustness, and the ability to generalize across various BCI tasks, including cognitive state recognition and motor imagery classification. The result indicates that our model LSTM is 96.92%, CNN is 95.95%, GRU is 95.40%, and GIN is 88.68%. Finally, this study demonstrates how advanced deep learning techniques can address the current limitations of BCI systems, opening the door for more reliable and successful real-world applications. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Requirements Prediction for Medical Products Based on Named Entity recognition

Requirements Prediction for Medical Products Based on Named ...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 international conference on

作者： Peiguang Ruan Ruanchong Liu Bo Guo Zhepeng Liu Chengying Zhang Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai China The First Clinical Medicine School Guangdong Pharmaceutical University Guangzhou China School of Finance and Trade Zhuhai College of Science and Technology Zhuhai China College of Engineering Shantou University Shantou China School of Management Xihua University Chengdu China

Medical product demand forecasting is a necessary condition for building a medical intelligent system, and is an important means to alleviate the lack of medical resources, and the form of medical product demand is mainly unstructured text, including the number of medicines, medical record texts. These medical texts contain a large number of medical terms related to the patient health situation and medical terms are the most direct embodiment of medical knowledge. However, existing methods for requirements are concentrated on the neural network or machine learning algorithms, which ignores the tremendous information in the medical terms. In this work, we utilize the named entity recognition method to predict the demand of the medical products. Efficiently identifying these medical terms from medical texts is a key factor in ensuring the high performance of medical intelligence systems. Therefore, the goal of the medical named entity recognition task is to extract medically significant symptoms, medical history, diseases, etc. from medical texts and realize the downstream prediction task. From our extensive experiment simulation and comparison with existing prediction methods, we can conclude the proposed method can achieve the precise prediction accuracy with reasonable computation costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential Benefits of machine learning for Optimizing Real-Time data Analysis

Exploring the Potential Benefits of Machine Learning for Opt...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), international conference on

作者： Ravindra Kumar Nitin N. Sakhare N. Thangarasu K.K. Senthilkumar Pawan S. Wawage A Rengarajan Department of Civil Engineering Vivekananda Global University Jaipur India Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA Department of Computer Science Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Information Technology Vishwakarma Institute of Information Technology Pune INDIA Department of Computer Science and Information Technology Jain (Deemed to be University) Bangalore Karnataka India

This studies paper examines the capability blessings of implementing device getting to know algorithms to optimize real-time information evaluation. The subjects mentioned consist of techniques for predicting traits in actual-time information, the ability of gadget studying algorithms to discover anomalies and outliers in datasets, and how using records mining and herbal language processing (NLP) can improve the accuracy of real-time facts insights. It also evaluates the demanding situations that can arise while applying machine gaining knowledge of algorithms to actual-time statistics, along with scalability problems and overfitting of records. In end, the authors argue that system studying has notable potential to enhance the accuracy and timing of actual-time facts analysis, and that they provide steerage on choosing and enforcing appropriate gadget getting to know algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Activity recognition Using Wearable Sensors in IoT Environments: Challenges and Opportunities 3

Human Activity Recognition Using Wearable Sensors in IoT Env...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Singh, B.P. Baxi, Paramjit Parhi, Manoranjan Ahluwalia, Gunveen Sollapur, Shrishail B. Divakaran, Sindu Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Chitkara University Centre of Research Impact and Outcome Punjab Rajpura140417 India Centre for Data Sciences Odisha Bhubaneswar India Chitkara University Chitkara Centre for Research and Development Himachal Pradesh Baddi174103 India Karnataka Bangalore India Sathyabama Institute of Science and Technology Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331542375

One of those applications, Human Activity recognition, uses wearable sensors, made possible by the rapid rise and development of Internet of Things technology. HAR is the automated process of identifying and classifying human activities from sensor data with wearable devices such as smart watches/fabric bands. Given its utility in healthcare, HAR has immense possibilities, especially within IOT environments such as health & fitness, safety, and security. But, at the same time, it introduces new challenges of handling massive real-time sensor data streams and providing privacy for people when their daily routines are reconstructed, as well as developing accurate and reliable algorithms. In addition, human activities are diverse, and the data that sensors collect may also differ, making HAR in IOT very complicated. HAR can also provide various opportunities, e.g., real-time monitoring and analysis of human activities, personalized health/fitness advice, and safe/smart environmental improvements. Implementing artificial intelligence and machine learning models in HAR can also improve performance. HAR based on wearable sensors in an IOT environment holds promise for changing our views of and tracking human activities to a new level that could be applied to many different sectors and improve quality of life. © 2025 IEEE.

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Natural Scene Text recognition System Based on Deep learning 3

Design and Implementation of Natural Scene Text Recognition ...

引用

3rd international conference on Artificial Intelligence and Advanced Manufacture, AIAM 2021

作者： Liang, Feilong Tencent Music Entertainment Group Guangdong Shenzhen China

ISBN: (纸本)9781450385046

With the popularization and rapid development of information technology such as modern multimedia and mobile Internet, people have more and more ways to obtain natural landscape images. How to collect and extract necessary information from rich images becomes more and more important. With the current popularization and development of technologies such as artificial intelligence and deep machine learning, the application requirements for effectively obtaining text resources are also expanding rapidly. This paper aims to study the design and implementation of a natural scene text recognition system based on deep learning. Based on the analysis of system functional requirements, system non-functional requirements and text detection methods, each functional module of the system is designed in detail, and finally in SVT. The performance of the algorithm in this article is analyzed on the public data set, and the test results are compared with the existing algorithms. The test results show that the method and recognition results used in this paper are significantly higher than other methods, and the text recognition results have reached a very high accuracy. © 2021 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Empirical Study to Select a Place to Stay in NCR Area Using data mining and machine learning 3

Empirical Study to Select a Place to Stay in NCR Area Using ...

引用

3rd IEEE international conference on Automation and Computation, AUTOCOM 2025

作者： Jain, Nitin Chauhan, Surendra Singh Goel, Ajay Rastogi, Ashish Kumar Raj, Alok Agrawal, Priyanka Chandigarh University Mohali India Srm University Haryana Sonipat India Bhai Gurdas Institute of Engineering & Technology Punjab Sangrur-148001 India Iilm University Greater Noida India XenonStack Pvt. Ltd. Punjab Mohali India XenonStack Pvt. Ltd. Punjab Mohali India

ISBN: (纸本)9798331542375

From starting of the human civilization, the peoples are traveling to one place to another place for different kinds of works such as business, tourism etc. and they are need accommodation to stay there. Before the 21st century, there was a limited option to search the places for accommodation. In the digital world there are options are increasingly in comparison with the previous time. Now if someone going for a vacation for a short term, he or she can find a hotel or lodge for the same, but when students migrate one place to another or a person transfer to another city or place than he need to find a suitable place to stay for a long time. In this research paper, we try to find the best solution for this kind of problem. Here we discuss the result with some predetermined parameters. These parameters set and trained on the collected data from different type of people from different geolocations. After it, the collected data is fed to the K-Means algorithm. This algorithm is used for the making the clusters. After it by using REST API, the output of K-Means algorithms is shown on a Map. © 2025 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

data mining and Visualization to Understand Employee Attrition and Work Performance

Data Mining and Visualization to Understand Employee Attriti...

引用

Computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Mohammed Gollapalli Ata-Ur Rahman Abdurrahman Osama Ahmad Alfaify Muhammad Yassin Ahmad Alabdullah Department of Computer Information Systems College of Computer Science & Information Technology Imam Abdulrahman Bin Faisal University Dammam Saudi Arabia Department of Computer Science College of Computer Science & Information Technology Imam Abdulrahman Bin Faisal University Dammam Saudi Arabia

Throughout the course of careers, a large number of employees encounter a variety of normal life events that can have an impact on their performance and job environment satisfaction. Under these circumstances, some employees are compelled to leave their positions, not because of issues with their work environment, but due to personal circumstances. This is what we refer to as Employee Attrition, a pervasive phenomenon affecting numerous businesses and work environments in the present day. Employee attrition could occur in a variety of ways and be determined by several entities. Therefore, we look into various conditions, causes, indicators, and entities in order to study the attrition problem and determine its answers and enhancements. This study investigated the attrition of employees based on IBM data repository, together with the machine learning based experimental analysis and knowledge discoveries, to identify the most effective approaches to the attrition problem. The experimental data contained 1,471 records with 35 distinct characteristics. We formally employed Nave Bayes Classifier in this study using WEKA datamining software, and adequate knowledge has been extracted to better comprehend employee turnover and their work performance facets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision Making and recognition of String Characters using NN-Fuzzy Implication System

Decision Making and Recognition of String Characters using N...

引用

3rd international conference on machine learning and data Engineering, ICMLDE 2024

作者： Henge, Santosh Kumar Bhagat, Avinash Mandal, Sanjeev Kumar Viraati, Nikhil Reddy Singh, Ravleen Kedhar, K. Rushi Department of Computer Science and Engineering School of Computer Science and Artificial Intelligence SR University Warangal506371 India School of Computer Applications Lovely Professional University Punjab Phagwara India Bangalore India Department of Data Insights Crisp Shared Services 7160 Columbia Gateway Dr Columbia United States Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP Vaddewaram India BE-CSE RV Institute of Technology and Management Bengaluru India

This research proposes the neural network (NN)-fuzzy logic control (FLC)-based methodology, which is designed with two stages of execution. Stage-1 is composed with the NN approach;it takes the input from the scanned image, the input from the classified clustered group, processes it with hidden layers, and generates the final output, which is input to the FLC in stage 2. The input of stage 2 converts the input into fuzzified data (0s and 1s) and trains the FLC system with fuzzified set values. The trained data has been simulated for further stages in the FLC-based decision-making approach and integrated to identify the character patterns based on the trained dataset. FLC-based planting and normalization techniques are integrated for re-training the data. The dataset has been framed with more than 6200 handwritten image characters, which were written by 235 writers. It aligned with the pre-processing, classification, and filtering stages and achieved a 99.8% recognition rate. © 2025 The Author(s).

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Enhancing Intrusion Detection in Wireless Sensor Networks Using Deep Convolutional Neural Networks

Enhancing Intrusion Detection in Wireless Sensor Networks Us...

引用

Smart Systems for applications in Electrical Sciences (ICSSES), international conference on

作者： Nishar Ahamed Manzoor Muhammad Firdaus Akbar M. Arul Prasanna School of Electrical and Electronic Engineering Engineering Campus Universiti Sains Malaysia Nibong Tebal Pulau Pinang Malaysia Department of Electrical and Electronics Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

The rapidly growing number of Internet users has made security more and more crucial. Researchers have developed a number of intrusion detection systems that use data mining techniques to find intruders. Several articles offer datadriven techniques to safeguard the Wireless Sensor Network (WSN) toward such assaults. These techniques use either classic machine learning (ML) models. These approaches have disadvantages, such as relying on raw characteristics for intrusion detection, which lead to a low level of detection accuracy. This paper proposes an Intrusion Detection System (IDS) to prevent these problems that successfully detects intruders in wireless networks, ensuring secure data exchange by implementing an enhanced deep learning model to identify different sorts of assaults in the WSN. Deep convolutional Neural Network (DCNN) is recommended for avoiding different incursions. Proposed framework effectively addresses potential threats between the application's and access network layers. The proposed work implemented by Python software tool and performed efficiently obtain the results. The results of proposed system are compared to state of art. This study analyzes relevance of results and their future prognosis. This study introduces a proposed DCNN classifier that demonstrates an impressive accuracy of 97.3% and a sensitivity of 92.4%, as determined through comparative analysis of the datasets.

关键词： Deep learning Wireless sensor networks Accuracy Sensitivity Wireless networks System performance Intrusion detection Smart systems Convolutional neural networks Software tools

来源：评论

学校读者我要写书评

暂无评论

Support Vector machines: Unveiling the Power and Versatility of SVMs in Modern machine learning

Support Vector Machines: Unveiling the Power and Versatility...

引用

international conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： K Saravanan R.Banu Prakash C. Balakrishnan Gade Venkata Prasanna Kumar R Siva Subramanian M. Anita Department of Information Technology R.M.D. Engineering College Kavaraipettai Dept of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept of CSE S.A Engineering College Engineering Insight Software International PVT Ltd Dept of CSE R.M.K College of Engineering and Technology Dept of IT Easwari Engineering College

Support vector machines, or SVMs, have become a really big deal in machine learning because of how good they are at classification and regression problems. This article explores in-depth knowledge about SVMs in ML algorithms. First from the history of SVMs, starting with when they were first thought up and addresses some important stuff different researchers have done with them over time. Next, get into the math and theory behind how SVMs work things like margins support vectors, and optimization problems and also discuss different ways SVMs have been tweaked and changed, like versions for multiple classes, support vector regression one-class SVMs, and twin SVMs. Another key part of SVMs is kernel functions here we spend a bunch of time breaking those down and explaining what they do to transform data so SVMs can work with it better. Further on, we look at some real-world uses for SVMs, like in image recognition natural language processing, bioinformatics, and finance. Even though SVMs have been around for a while they’re still super relevant today, so here summarize the most important discoveries about them and think about ways SVMs might keep evolving or being used differently as machine learning keeps moving fast. Overall, the goal here is to give you a deep dive into Support Vector machines - where they began, the technical details, how they are applied, and where they might go in the future helpful in better understanding the SVM in ML Algorithm.

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328页 << < 115 116 117 118 119 120 121 122 123 124 > >>

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：