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

23,401 篇 会议
2,989 篇 期刊文献
16 篇 学位论文

馆藏范围

26,406 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,695 篇 工学
- 3,420 篇 计算机科学与技术...
- 3,187 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...
850 篇 理学
- 194 篇 物理学
- 161 篇 生物学
- 141 篇 地球物理学
- 127 篇 数学
- 122 篇 系统科学
- 97 篇 地理学
- 51 篇 化学
- 44 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

26,406 篇 classification a...
6,495 篇 feature extracti...
5,204 篇 training
4,726 篇 accuracy
4,388 篇 support vector m...
3,208 篇 machine learning...
2,683 篇 prediction algor...
2,645 篇 clustering algor...
2,490 篇 algorithm design...
2,359 篇 data mining
2,262 篇 machine learning
1,607 篇 data models
1,410 篇 deep learning
1,373 篇 optimization
1,340 篇 decision trees
1,180 篇 predictive model...
1,168 篇 testing
1,144 篇 computational mo...
1,098 篇 neural networks
1,022 篇 databases

机构

64 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...
16 篇 computer science...
16 篇 school of comput...
16 篇 school of comput...
16 篇 department of co...
16 篇 school of electr...
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...
13 篇 school of comput...

作者

29 篇 wei li
23 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

26,269 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 26406 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：

Machine Learning based Classifier and Feature Extractor for Intrusion Detection

Machine Learning based Classifier and Feature Extractor for ...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： Nidhi Srivastav Rajiv Singh Department of Computer Science Banasthali Vidyapith Rajasthan India Swami Keshvanand Institute of Science & Technology Management & Gramothan Rajasthan India Department of Computer Science Centre for Artificial Intelligence Banasthali Vidyapith Rajasthan India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Cyberattacks, or attacks on computer networks, now affect practically every device linked to the Internet on a daily basis. Unseen Cyberattacks create a huge problem in these devices. Thus, some methods or techniques tried to be employed that can encounter unseen attack along with known attacks. ML and DL based IDS are being used to encounter them. This research will show a variety of methods used to protect against various types of cyberattacks. After being applied to datasets, the classification algorithms are compared in accordance with precision, accuracy, recall, F1 score. The classification algorithms used in the paper are the LR, Naïve Bayes and KNN as classifier and PCA as feature extractor. Importance of feature extraction is also presented in the paper by taking performance of specified classifier for different feature values in account. Deep learning classification algorithms have been critically reviewed using specified performance criteria.

关键词： Deep learning Accuracy Intrusion detection Forestry Feature extraction classification algorithms Bayes methods

来源：评论

学校读者我要写书评

暂无评论

Enhancing Financial Trading Strategies: A Comprehensive Sentiment Analysis Pipeline

Enhancing Financial Trading Strategies: A Comprehensive Sent...

引用

Signal Processing and Advance Research in Computing (SPARC), International Conference on

作者： Baljinder Singh Mandeep Kaur Gurbinder Singh Brar Computer Science and Engineering CT University Ludhiana Punjab India School of Computer Science and Engineering Lovely Professional University Phagwara Punjab India

ISBN: (数字)9798350385205

ISBN: (纸本)9798350385212

Sentiment analysis plays a crucial role in understanding market dynamics and making informed decisions in financial trading. This paper proposes a comprehensive sentiment analysis pipeline tailored to financial markets, integrating machine learning techniques and swarm intelligence for feature selection. The pipeline encompasses pre-processing, feature extraction, swarm-based feature selection, training, classification, and evaluation stages. Pre-processing involves text normalization techniques such as tokenization, lowercasing, and stop words removal. Feature extraction utilizes TF-IDF values and similarity measures to represent text data. Swarm intelligence algorithms are employed for feature selection, optimizing the subset of features based on classifier performance. Machine learning classifiers are trained on the selected features to predict sentiment labels, and evaluation metrics assess the pipeline’s performance. The effectiveness of the pipeline is demonstrated through experiments on financial datasets, highlighting the importance of parameter tuning and algorithmic optimization. This research contributes to advancing sentiment analysis in financial markets, providing a robust framework for decision-making in trading and investment.

关键词： Sentiment analysis Machine learning algorithms Pipelines Signal processing algorithms Machine learning Feature extraction Prediction algorithms classification algorithms Particle swarm optimization Tuning

来源：评论

学校读者我要写书评

暂无评论

Spectrum Normalization-Based Adversarial Network and CNN for Electricity Theft Detection

Spectrum Normalization-Based Adversarial Network and CNN for...

引用

Energy, Power and Grid (ICEPG), International Conference on

作者： Chenyang Zheng Yuli Wu School of Electrical and Control Engineering Liaoning Project Technology University Huludao China

ISBN: (数字)9798350377798

ISBN: (纸本)9798350377804

Power theft is the main reason for the non-technical loss of the power grid. The massive user power consumption data provides a basis for the data-driven power theft detection. However, the imbalance of the data seriously affects the effect of power theft detection. Aiming at the data imbalance in power theft detection, an oversampling method and Convolutional Neural Network (CNN) power theft detection classification model are proposed. Through the confrontation training of SNGAN generator and discriminator, the generator is prompted to generate false samples similar to real power theft samples, judge the diversity, fidelity and accuracy of SNGAN generated samples by Inception Score and structural similarity index (SSIM), and use the generated samples with good validation effect to enhance the original power theft data. The CNN convolution classification model with the same network structure as SNGAN is trained on the enhanced data set, and conduct power theft detection on the test set. The results show that compared with the traditional sampling algorithm and GAN derived sampling algorithm, SNGAN oversampling method generates samples with more realistic value and has smaller false detection rate. Compared with the traditional classification model, the convolution classification model equipped with SNGAN sampling algorithm has higher detection rate and AUC value, which meet the requirements of power theft detection.

关键词： Training Power demand Convolution Neural networks Data models Generators Probability distribution Power grids classification algorithms Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Addressing Retail Object Detection Challenges through Dual Network Integration

Addressing Retail Object Detection Challenges through Dual N...

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Caleb Stilp Cheol-Hong Min Department of Electrical and Computer Engineering University of Saint Thomas Saint Paul United States of America

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

The use of autonomous systems within the retail environment is currently hampered by the challenges object detection networks face when trying to locate and classify products. These challenges arise from densely packed product arrangements, limited training data, and frequent product up-dates. Existing object detection methods such as R-CNN and YOLO exhibit limitations in scalability and accuracy when applied to these complex environments. This work explores a new vision algorithm designed specifically for retail applications by integrating two distinct networks to address the dual object detection tasks of localization and classification. The first task utilizes RetinaNet to localize densely packed products, relying on its ability to detect small overlapping objects. Then, a Siamese Neural Network (SNN) is used to generate embeddings of local-ized product images. SNNs learn to create feature embed dings with minimal training data and can support the addition of new classifications without requiring network retraining. This separation of localization and classification tasks allows each network to be fine-tuned for its specific purpose, resulting in a final object detection algorithm that can adequately perform in the retail landscape.

关键词： Location awareness YOLO Autonomous systems Scalability Neural networks Training data Object detection Inventory management classification algorithms Robots

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Quality Control of Boron in Rubberwood Industry by Using MATLAB Driven RGB Imaging

Revolutionizing Quality Control of Boron in Rubberwood Indus...

引用

IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)

作者： Suratsavadee K. Korkua Siraporn Sakphrom Krit Funsian Pannipa Chaowana Santanu Kumar Dash Kamon Thinsurat School of Engineering and Technology Walailak University Nakhon Si Thammarat Thailand Dieffenbacher TH Ltd. Bangkok Thailand Technology Information Forecasting and Assessment Council Vellore Institute of Technology Vellore Tamil Nadu India

ISBN: (数字)9798350352290

ISBN: (纸本)9798350352306

This paper proposes a fast, convenient, and effective technique to detect the percentage of boric acid equivalent in rubberwood which may significantly reduce cost in wood industries when a conventional observing method requiring an expert is unnecessary. Color thresholds was constructed to identify digital images using MATLAB to process the RGB color ratio from boron testing performed on timber samples. Photographed boron treated timber samples was infiltrated with curcumin reagent then the RGB color ratio was calculated to show the percentage of boric acid equivalent. The G to R and B to G ratios were presented and the proposed algorithm was used for processing colors to determine the percentage of boric acid equivalent. The results showed that the algorithm is promising with high accuracy when the percentage of boric acid equivalent of real samples from the factory were detected with no error although color classification error to determine the percentage of boric acid equivalent using the G to R and B to G ratio algorithm is presented.

关键词： Boron Accuracy Image color analysis Process control Quality control Wood industry Production facilities classification algorithms MATLAB Testing

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Detection using an Optimized Deep Learning Approach

Brain Tumor Detection using an Optimized Deep Learning Appro...

引用

Electrical Power Engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Prajna Paramita Debata P N Pratikshya Sanket Padhy Shiva Agarwal Sakshi Bansal Department of Computer Science and Engineering Siksha ‘O’ Anusandhan deemed to be University Bhubaneswar Odisha India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

Brain tumor poses significant challenges in diagnosis and treatment, necessitating accurate and timely detection methods. This study presents a deep learning approach for the detection of brain tumors from medical imaging data. Here, an optimized Convolutional Neural Network (CNN) strategy is implemented for early-stage Brain Tumor Detection. The CNN classifier considers many hyperparameters i.e., number of batches, learning rate, kernel size, weight and bias which may lead to suboptimal result. Here, Differential Evolution (DE) algorithm optimized CNN (DE-CNN), Harmony Search (HS) algorithm optimized CNN (HS-CNN), and Simulated Annealing (SA) algorithm optimized CNN (SA-CNN) are applied to optimize the hyper parameters of CNN. The training and testing accuracy, validation loss, precision and recall values of these three models are compared to reveal the robust model for brain tumor detection. Through extensive experimentation and validation on real-world clinical MRI images, SA-CNN approach demonstrates superior accuracy i.e., 99.63% as compared to other methods.

关键词： Deep learning Training Accuracy Magnetic resonance imaging Simulated annealing Brain modeling classification algorithms Convolutional neural networks Biomedical imaging Testing

来源：评论

学校读者我要写书评

暂无评论

Candidate Selection of Water Shut-Off in Oil and Gas Industry Using Random Forest

Candidate Selection of Water Shut-Off in Oil and Gas Industr...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： Aditya Pramada Wicaksono Achmad Choiruddin Interdisciplinary School of Management and Technology Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Statistics Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

The water production is a major issue faced by most of oil and gas companies. The increase of water production leads to an increase of maintenance cost, failure in fulfilling energy (oil and gas) needs, and loss of profit due to decline of oil and gas production. To address the escalating water production issue, most of the companies, one of which is PT Indo Migas, employ water shut-off (WSO) activities aiming for mitigating water production, thus maximizing oil and gas recovery from reservoirs. Despite these efforts, the success rate of WSO activities at PT Indo Migas remains low as historical WSO results are not taking into account in candidate selection, leading to financial losses and operational complexities. To overcome this challenge, this study introduces a predictive model based on the random forest algorithm to improve WSO candidate selection. The model utilizes historical operational data and relevant reservoir, production, and geological data to analyze and classify potential WSO candidate. Key findings indicate that variables such as water production, well depth, and reservoir pressure significantly influence the WSO candidate selection process. Through data analysis and model development, the predictive model identifies 12 out of 65 wells as suitable candidates for WSO activities. The model achieves an accuracy rate of 83 % and sensitivity of 100 % despite of little amount of trained data. The implementation of the developed model's recommendations can give significant managerial implications for PT Indo Migas and similar companies in the oil and gas sector.

关键词： Analytical models Sensitivity Oils Production Companies Predictive models Reservoirs Prediction algorithms Data models classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation by Hybrid Data Resampling: Towards Enhanced Performance in Automatic Cardiac Arrhythmia Detection

Data Augmentation by Hybrid Data Resampling: Towards Enhance...

引用

IEEE Calcutta Conference (CALCON)

作者： Debasmita Pal Sumitra Mukhopadhyay Rajarshi Gupta Radio Physics and Electronics University of Calcutta Kolkata India Electrical Engg. Applied Physics University of Calcutta Kolkata India

ISBN: (数字)9798331516666

ISBN: (纸本)9798331516673

Real-time automatic cardiac arrhythmia detection (CAD) can enhance timely medical intervention thereby reducing mortality caused by it. One of the most concerning challenges in automatic CAD using machine learning approaches is inherent data imbalance between different types of abnormal beat classes, which results in the biasing of the classifier towards majority classes during training of the classifier. In this paper, an offline data balancing technique is proposed which is a combination of graded boundary-sensitive majority class undersampling (GBMU) and adaptive scattering-based minority class oversampling (ASMO). The algorithm was evaluated with MIT BIH arrhythmia dataset with 15 types of heartbeats. This hybrid data resampling increases the overall F1- score by 15.28% and reduces the false positive rate (FPR) and false negative rate (FNR) by ${1 1. 3 \%}$ and ${3 9. 4 1 \%}$ respectively using a simple classification flow which would otherwise result in compromised detection accuracy for minority classes.

关键词： Training Solid modeling Accuracy Heart beat Arrhythmia Signal processing algorithms Signal processing Feature extraction Real-time systems classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Leveraging ML with XGBoost, CatBoost and LGBoost Classifiers to Optimize Water Quality Assessment and Prediction

Leveraging ML with XGBoost, CatBoost and LGBoost Classifiers...

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Preet Singh Taniya Hasija K R Ramkumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

Water is a key valuable resource for the survival of every living being. Water quality is an important concern at the global level as the pollution level continues to rise. Therefore, there is a need to develop methods to control and classify the water based on impurities present. The Machine Learning (ML) classification approach classifies the labels of the dataset for efficient categorical analysis. The Telangana state water quality dataset is taken for analysis purposes. The water quality is divided into 4 major classes. The three classification models used for this comparative analysis are XGBoost, LGBoost and CatBoost. According to the comparative analysis, the overall accuracy of CatBoost is higher out of all the classifiers used. However, the F1-score for the LGBoost classifier is higher for the water quality of class 1. This classification is essential in making smart decisions about sustainable water resource treatment and for taking action toward use to guarantee the quality of drinking water.

关键词： Accuracy Purification Impurities Water quality Prediction algorithms Water pollution classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Customer Churn Analysis and Risk Prediction in E-Commerce

Customer Churn Analysis and Risk Prediction in E-Commerce

引用

International Conference on Advances in Information Technology (ICAIT)

作者： Mysara S Poorna Deepa R Sandra evangelyn J W Siamala Devi S Department of Information Technology Sri Krishna College of Technology Coimbatore India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

With global advancement, Information Technology has led to the growth of numerous Service Providers, which, in turn, has resulted in fierce competition between them. For Service Providers, the most prevalent obstacle is the handling of customer churn, retention, and satisfaction of customers for successful market sustenance. In today's competitive market, predicting and managing churn is essential for businesses to identify different types of churners and take appropriate action to keep consumers and revenues. The goal of churn models is to detect early signs of customer attrition and identify those who are most likely to leave on their own will. This work proposes a way for assessing Machine Learning (ML) for classification.

关键词： Machine learning algorithms Forestry Predictive models Prediction algorithms classification algorithms Electronic commerce Information technology

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：