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

23,360 篇 会议
2,978 篇 期刊文献
11 篇 学位论文

馆藏范围

26,349 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,693 篇 工学
- 3,419 篇 计算机科学与技术...
- 3,186 篇 电气工程
- 1,829 篇 信息与通信工程
- 643 篇 控制科学与工程
- 538 篇 软件工程
- 488 篇 仪器科学与技术
- 305 篇 测绘科学与技术
- 300 篇 机械工程
- 284 篇 生物医学工程（可授...
- 148 篇 电子科学与技术（可...
- 114 篇 生物工程
- 108 篇 交通运输工程
- 107 篇 环境科学与工程（可...
- 75 篇 网络空间安全
- 56 篇 航空宇航科学与技...
- 41 篇 材料科学与工程（可...
849 篇 理学
- 194 篇 物理学
- 160 篇 生物学
- 141 篇 地球物理学
- 126 篇 数学
- 122 篇 系统科学
- 97 篇 地理学
- 51 篇 化学
- 43 篇 统计学（可授理学、...
526 篇 管理学
- 481 篇 管理科学与工程(可...
498 篇 医学
- 374 篇 临床医学
- 100 篇 基础医学(可授医学...
195 篇 农学
- 99 篇 作物学
- 80 篇 农业资源与环境
75 篇 文学
- 70 篇 新闻传播学
23 篇 教育学
21 篇 经济学
19 篇 艺术学
13 篇 法学
7 篇 军事学
2 篇 历史学

主题

26,349 篇 classification a...
6,478 篇 feature extracti...
5,192 篇 training
4,697 篇 accuracy
4,379 篇 support vector m...
3,199 篇 machine learning...
2,675 篇 prediction algor...
2,641 篇 clustering algor...
2,490 篇 algorithm design...
2,356 篇 data mining
2,259 篇 machine learning
1,603 篇 data models
1,405 篇 deep learning
1,361 篇 optimization
1,336 篇 decision trees
1,174 篇 predictive model...
1,165 篇 testing
1,140 篇 computational mo...
1,095 篇 neural networks
1,020 篇 databases

机构

63 篇 chitkara univers...
23 篇 centre of resear...
23 篇 college of infor...
19 篇 school of comput...
18 篇 tsinghua univers...
18 篇 university of ch...
17 篇 chitkara centre ...
17 篇 school of inform...
17 篇 department of co...
16 篇 school of comput...
16 篇 school of comput...
16 篇 school of electr...
14 篇 computer science...
14 篇 univ chinese aca...
14 篇 microsoft resear...
14 篇 school of comput...
13 篇 school of electr...
13 篇 school of electr...
13 篇 school of comput...
12 篇 princess nourah ...

作者

29 篇 wei li
22 篇 hui wang
22 篇 jun wang
21 篇 lei wang
17 篇 xia sun
17 篇 yang yang
16 篇 jing zhang
15 篇 jun zhang
15 篇 liu yang
14 篇 xi chen
14 篇 li zhang
14 篇 jie li
13 篇 jian wang
13 篇 rakesh kumar
13 篇 jie yang
13 篇 jun shi
13 篇 chen chen
12 篇 bing xue
12 篇 ahmad jalal
12 篇 xuegang hu

语言

26,212 篇 英文
90 篇 其他
33 篇 中文
4 篇 土耳其文
2 篇 法文
1 篇 西班牙文
1 篇 俄文

检索条件"主题词=Classification Algorithms"

共 26349 条记录，以下是4821-4830 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：

Estimate and Reduce Uncertainty in Uncertain Graphs

Estimate and Reduce Uncertainty in Uncertain Graphs

引用

International Conference on Data Science and Advanced Analytics (DSAA)

作者： Naheed Anjum Arafat Ehsan Bonabi Mobaraki Arijit Khan Yllka Velaj Francesco Bonchi Nanyang Technological University Singapore Aalborg University Denmark University of Vienna Austria CENTAI Italy Eurecat Spain

ISBN: (数字)9798350364941

ISBN: (纸本)9798350364958

Computing basic network properties and machine learning (ML) model outputs, e.g., reachability, shortest path distance, triangle count, node classification, etc., are key to understand large and complex graphs. We study two fundamental problems: (1) Given a graph with uncertain edges and a real-valued network property or an ML model, estimate the uncertainty associated with evaluating the property or the ML model's output over the uncertain graph. (2) Given a limited budget on the number of edges, find the $k-\mathbf{best}$ edges whose probability update will reduce the aforementioned uncertainty maximally. We formulate both problems using the information-theoretic notion of entropy and then characterize the hardness of our problems. We next devise approximate solutions with theoretical soundness and greedy subgraph selection-based efficient algorithms. Our empirical evaluation and case study with real-world and synthetic datasets demonstrate that the proposed solutions are more effective and efficient than baselines and are several orders of magnitude faster than exact approaches.

关键词： Maximum likelihood estimation Uncertainty Computational modeling Machine learning Approximation algorithms Entropy classification algorithms Information theory Synthetic data Indexing

来源：评论

学校读者我要写书评

暂无评论

Data Veracity Analysis in Social Media - A Review

Data Veracity Analysis in Social Media - A Review

引用

Big Data Analytics and Practices (IBDAP), International Conference on

作者： Mohamed Amine Bellouqi Ismail Assayad Laboratoire Informatique et Système (LIS) Faculty of Sciences Hassan II University of Casablanca Casablanca Morocco Laboratoire Informatique et Système (LIS) Faculty of Sciences ENSEM Hassan II University of Casablanca Casablanca Morocco

ISBN: (数字)9798350391749

ISBN: (纸本)9798350391756

Due to their exponential growth, social media platforms have become the main source of information for many people. On these platforms, propaganda, fake news, and misinformation are widely disseminated, raising serious questions about the accuracy and veracity of the data. In this paper, we will cover a review of several key approaches in the context of data veracity analysis on social media, with a particular focus on rumor detection. By exploring these diverse strategies, the purpose of this paper is to contribute to the understanding of the multifaceted techniques applied in ensuring data veracity, specifically in the challenges of rumor detection on social media platforms

关键词： Measurement Accuracy Social networking (online) Reviews Heuristic algorithms Big Data classification algorithms

来源：评论

学校读者我要写书评

暂无评论

FCM Based Spectrum Sensing For NOMA Cognitive Radio Networks

FCM Based Spectrum Sensing For NOMA Cognitive Radio Networks

引用

Communication & Computing (WCONF), World Conference on

作者： Divya Yadav Saikat Majumder Ajay Singh Raghuvanshi Department of Electronics and Communication National Institute of Technology Raipur India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

In this article, we propose a fuzzy c-means (FCM) clustering-based technique for spectrum sensing (SS) in power-domain non-orthogonal multiple access (NOMA) cognitive radio (CR) network. Though, techniques based on supervised and unsupervised machine learning (ML) for cooperative spectrum sensing (CSS) techniques in NOMA exist in literature, they are relatively more computationally complex and have poor accuracy. Proposed method considers NOMA spectrum sensing as a multiple-hypothesis problem and classifies the signal received through multiple secondary users (SU) using the FCM algorithm. Our results show that proposed technique is superior to the existing techniques in terms of accuracy and is significantly less complex for same performance.

关键词： Training NOMA Time-frequency analysis Accuracy Cooperative communication Sensors classification algorithms Cognitive radio Testing Radio spectrum management

来源：评论

学校读者我要写书评

暂无评论

Detection and Mitigation of Bias in Under Exposure Estimation for Face Image Quality Assessment

Detection and Mitigation of Bias in Under Exposure Estimatio...

引用

International Conference of the Biometrics Special Interest Group (BIOSIG)

作者： André Dörsch Christian Rathgeb Marcel Grimmer Christoph Busch da/sec – Biometrics and Security Research Group Hochschule Darmstadt Darmstadt Germany

ISBN: (数字)9798350373714

ISBN: (纸本)9798350373721

The increasing employment of large scale biometric systems such as the European “Entry-Exit System” and planned national initiatives such as the “Live Enrolment” procedure require quality assessment algorithms to ensure reliable recognition accuracy. Among other factors, facial image quality and hence face recognition accuracy can be negatively impacted by underexposure. Therefore, quality assessment algorithms analyse the exposure of live-captured facial images. To this end, mainly handcrafted measures have been proposed which are also referenced in current standards. However, this work shows that handcrafted measures, which use basic statistical approaches to analyse facial brightness patterns, exhibit racial bias. It is found that these algorithms disproportionately classify images of black people as underexposed as they do not take into account natural differences in skin color, particularly when relying on average pixel brightness values. To ensure fair biometric quality assessment, we have fine-tuned a data-efficient image transformer (DeiT) on synthetic data. The resulting underexposure estimation outperforms state-of-the-art algorithms in detection accuracy and biometric fairness. Precisely, an Equal Error Rate (EER) of approximately 7% is achieved. Our findings highlight the importance of developing robust and fair biometric classification methods to mitigate discrimination and ensure fair performance for all users, regardless of their skin color.

关键词： Image quality Accuracy Image color analysis Error analysis Face recognition Estimation Transformers Skin Quality assessment classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Determining Positive-Negative Emotions in Male and Female Based on EEG Signals using Machine Learning algorithms

Determining Positive-Negative Emotions in Male and Female Ba...

引用

International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)

作者： Yuri Pamungkas Edwin Nugroho Njoto Medical Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Medicine Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350355314

ISBN: (纸本)9798350355321

Emotionsare vital in everyday human life as a controller of behavior, decision-making and as a means to determine product marketing strategy/ market research. All of these things are very dependent on human emotional conditions. In addition, in the development of the computational affective field, brain signal-based emotion recognition (EEG) has become a trending topic of current research. Therefore, we attempted to compare positive-negative emotions in men and women based on EEG using a Machine Learning algorithm in this study. A total of 20 male and 20 female participants recorded their EEG signals in the frontopolar and frontal areas of the brain. Then the EEG data is processed by filtering, removing artifact, and decomposing it into three sub-bands (alpha, beta, and gamma). The extracted signal features are Mean Absolute Deviation and Power Spectral Density. Based on the signal feature analysis results, it is known that the signal feature values (MAD and PSD) for women tend to be higher than for men. Meanwhile, several algorithms are used to classify positive and negative emotions, such as Naive Bayes, K-Nearest Neighbor, Support Vector Machine, and Random Forest. Based on the results of classification, the best accuracy rate was 95.8% (on positive emotions for male & female gender), 92.2% (on negative emotions for male & female gender), and 79.8% (on positive-negative emotions for male & female gender) using Random Forest algorithm.

关键词： Support vector machines Emotion recognition Machine learning algorithms Accuracy Nearest neighbor methods Feature extraction Market research Electroencephalography classification algorithms Random forests

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition and Music Recommendation System based on Facial Expression

Emotion Recognition and Music Recommendation System based on...

引用

International Conference on Advances in Information Technology (ICAIT)

作者： Akhilraj V. Gadagkar Santhosh S Shifana Begum Ashwin Shenoy M Department of CSE Nitte (Deemed to be University) NMAM Institute of Technology Nitte India Department of ISE Nitte (Deemed to be University) NMAM Institute of Technology Nitte India Department of CSE Srinivas University Institute of Engineering and Technology Mukka Mangaluru India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The unique and distinct characteristics of the human face make it challenging to comprehend and recognise facial expressions. Facial expressions include emotions such as sadness, happiness, disgust, surprise, fear, and anger. This work aims to identify faces in an image, analyse facial features such as eyes, cheeks, and lips, and categorise them into four emotions: happiness, anger, neutrality, and sorrow. The training data undergoes a sequence of filters and processes before being evaluated alongside their labels to determine the accuracy of classification in a classification report. Dependable emotion-based classification systems can greatly assist us in interpreting their significance. Listening to music is a crucial habit that helps alleviate stress. However, it could be counterproductive if the music does not match the listener's present emotion. Furthermore, there is no music player capable of selecting songs according to the user's emotions. This study introduces an emotion-based music player that recommends songs according to the user's emotions, such as sadness, happiness, neutrality, and anger. The music player consists of three modules: Emotion Module, Music classification Module, and Recommendation Module. The Emotion Module uses a facial image as input and employs a Convolutional Neural Network algorithm to determine the individual's current mood. The Recommendation Module recommends music to users based on their emotions, matching them with the mood of the song while also considering user preferences.

关键词： Deep learning Emotion recognition Mood Face recognition Real-time systems User experience classification algorithms Reliability Facial features Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Development of a Model for Predicting Student Academic Performance Based on Academic Indicators

Development of a Model for Predicting Student Academic Perfo...

引用

International Conference on Control Systems, Mathematical Modelling, Automation and Energy Efficiency (SUMMA)

作者： Y.A. Tsygankov A.Iu. Solovev M.S. Sergeychik Automated and information control systems department Stary Oskol technological institute (branch) NUST “MISIS” Stary Oskol Russia

ISBN: (数字)9798331532178

ISBN: (纸本)9798331532185

The primary experiments proved the principal separability of objects based on a set of features characterizing students. In the course of further experiments, the development of classification models was performed to classify students into classes based on the selected features. In the course of the experiments, both types of models and algorithms for preprocessing of data sets were varied. From the resulting set of models, the best one was selected based on analyzing the performance on the test sample. After that, to visualize the work of the analytical system, a dashboard presenting the main academic indicators in different sections was developed.

关键词： Analytical models Machine learning algorithms Data visualization Prototypes Predictive models Prediction algorithms Data models Mathematical models classification algorithms Visual databases

来源：评论

学校读者我要写书评

暂无评论

Automated Gait Event Detection in Sports: A Novel Approach Using Ant Colony and XGBoost

Automated Gait Event Detection in Sports: A Novel Approach U...

引用

Frontiers of Information Technology (FIT)

作者： Wasim Wahid Muhammad Hanzla Hameed ur Rahman Ahmad Jalal Dept. of Creative Technology Air University Islamabad Pakistan Dept. of Computer Science Air University Islamabad Pakistan Dept. of Computer Gaming Development Air University Islamabad Pakistan

ISBN: (数字)9798331510503

ISBN: (纸本)9798331510510

Advanced techniques for body part detection and marker-less sensor-based cue selection is needed for automated human posture estimation (A-HPE) systems to efficiently identify complicated activity movements. The complicated motions during sports and fitness activities and the differences in lighting conditions make it difficult to identify human activities using vision sensors. This study presents an innovative approach to automatically recognize distinct gait events (GEDs) in sporting activities. Our system integrates techniques for detecting individuals and extracting crucial body points to establish a skeletal framework. Subsequently, we employ analyses on these key points and body features, using methods such as histograms of oriented gradients (HOG) and joint angle computations. To address the variability of sports movements, we utilize two robust algorithms: ant colony optimization and XGBoost. These algorithms facilitate the classification of movements and the assignment of labels to each event. Evaluation on a publicly available dataset of Olympic sports demonstrates that our GED system achieves an accuracy of 88.81%, surpassing existing methodologies. Application for the suggested approach in man-machine interactions include augmented reality, service bots, e-health fitness, and surveillance of security.

关键词： Histograms Accuracy Lighting Vision sensors Video surveillance classification algorithms Human activity recognition Security Optical flow Sports

来源：评论

学校读者我要写书评

暂无评论

Time Series Class-Incremental Learning with Residual Mamba Encoder

Time Series Class-Incremental Learning with Residual Mamba E...

引用

Computers and Artificial Intelligence Technologies (CAIT), International Conference on

作者： Bailing Zhang Kexuan Zhou School of Computer and Data Engineering NingboTech University Ningbo China College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

Class-incremental learning aims to enable systems to adapt to new classes over time without forgetting existing knowledge, a critical challenge in dynamic, non-stationary environments such as time series classification. While significant progress has been made in class-incremental learning for images and text, time series data remains underexplored. In this paper, we investigate the effectiveness of the Mamba model, based on Structured State Space Models (SSMs), in time series class-incremental learning. We utilize a residual Mamba encoder and compare it with mainstream 1D-CNN and PathTST’s TST encoders across various class-incremental learning algorithms. To our knowledge, this is the first application of the Mamba model to time series class-incremental learning. Extensive experiments demonstrate that the residual Mamba encoder achieves comparable or superior performance and computational efficiency, particularly on time-series-specific algorithms.

关键词： Measurement Computers Adaptation models Incremental learning Computational modeling Time series analysis Learning (artificial intelligence) State-space methods Computational efficiency classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Plant Identification and Analysis of Medicinal Properties Using Image Processing and CNN with MobileNetV2 and AlexNet

Plant Identification and Analysis of Medicinal Properties Us...

引用

Innovation and Novelty in Engineering and Technology (INNOVA), International Conference on

作者： Rakesh Bandla J. Swetha Priyanka Yashash Chandra Dumpali Sunil Kumar M. Hattaraki Dept.of ECE Vardhaman College of Engineering Hyderabad India Dept.of ECE B.L.D.E.A 's V. P. Dr. P. G. Halakatti College of Engineering and Technology Vijayapura Karnataka India

ISBN: (数字)9798331505134

ISBN: (纸本)9798331505141

Medicinal plants have been valued for their diverse botanical traits and healing properties, also playing a crucial role in pharmacy and ecological conservation. Identification of these medicinal plants leaves and with their properties is necessary to increase the traditional methods of using a particular leaf. Machine Learning (ML) based algorithms were used to analyze the detecting plant leaves. This study aims to streamline the identification process, enhancing accuracy and accessibility of plant leaves particularly. The existing method performance was analyzed using various metrics namely accuracy, f1-score, recall and precision. The outcomes of this study have the potential to support the preservation of traditional knowledge, contribute to pharmaceutical advancements and aid in the conservation of bio-diversity. Accurate and rapid identification of these plants is essential for various purposes, including the development of herbal medicine, scientific research, and environmental protection.

关键词： Medicinal plants Training Machine learning algorithms Accuracy Feature extraction classification algorithms Biodiversity Environmental management Protection Biomedical imaging

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 << < 479 480 481 482 483 484 485 486 487 488 > >>

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：