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

3,204 篇 会议
19 册 图书
10 篇 期刊文献

馆藏范围

3,233 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,933 篇 工学
- 1,731 篇 计算机科学与技术...
- 1,587 篇 软件工程
- 421 篇 信息与通信工程
- 321 篇 控制科学与工程
- 318 篇 生物工程
- 185 篇 生物医学工程（可授...
- 172 篇 电气工程
- 144 篇 机械工程
- 115 篇 电子科学与技术（可...
- 101 篇 光学工程
- 94 篇 安全科学与工程
- 92 篇 化学工程与技术
- 91 篇 动力工程及工程热...
- 79 篇 网络空间安全
891 篇 理学
- 497 篇 数学
- 336 篇 生物学
- 210 篇 统计学（可授理学、...
- 158 篇 物理学
- 154 篇 系统科学
- 84 篇 化学
500 篇 管理学
- 261 篇 管理科学与工程(可...
- 258 篇 图书情报与档案管...
- 160 篇 工商管理
185 篇 医学
- 158 篇 临床医学
- 156 篇 基础医学(可授医学...
- 110 篇 药学(可授医学、理...
- 83 篇 公共卫生与预防医...
133 篇 法学
- 90 篇 社会学
82 篇 经济学
- 82 篇 应用经济学
78 篇 农学
- 75 篇 作物学
66 篇 教育学
4 篇 文学
1 篇 军事学

主题

493 篇 machine learning
103 篇 deep learning
86 篇 software
62 篇 machine learning...
59 篇 support vector m...
52 篇 internet of thin...
49 篇 decision trees
48 篇 artificial intel...
47 篇 forecasting
44 篇 software enginee...
40 篇 training
39 篇 predictive model...
36 篇 feature extracti...
35 篇 neural networks
33 篇 software testing
31 篇 software algorit...
26 篇 reinforcement le...
26 篇 adversarial mach...
25 篇 covid-19
25 篇 object detection

机构

31 篇 college of compu...
31 篇 chitkara univers...
12 篇 karnataka bangal...
12 篇 school of inform...
11 篇 software enginee...
11 篇 department of so...
10 篇 department of so...
10 篇 school of comput...
9 篇 maharishi school...
8 篇 maharishi school...
7 篇 maharishi school...
7 篇 school of comput...
7 篇 daffodil interna...
7 篇 department of co...
7 篇 school of inform...
6 篇 school of comput...
6 篇 school of comput...
6 篇 software enginee...
6 篇 department of co...
6 篇 department of so...

作者

8 篇 patidar sanjay
7 篇 liu han
7 篇 han liu
6 篇 alfurhood badria...
6 篇 ishu sharma
6 篇 sharma ishu
6 篇 badria sulaiman ...
5 篇 bitto abu kowshi...
5 篇 dharshana kasthu...
5 篇 ali raja hashim
5 篇 yibeltal assefa
5 篇 assefa yibeltal
5 篇 ajmeera kiran
5 篇 raja hashim ali
5 篇 sethia divyashik...
4 篇 heyn hans-martin
4 篇 krishna aneesh
4 篇 william p.
4 篇 iqbal muhammad w...
4 篇 zain ul abideen

语言

1,910 篇 英文
1,322 篇 其他
53 篇 中文
1 篇 德文

检索条件"任意字段=2023 International Conference on Software Engineering and Machine Learning, CONF-SEML 2023"

共 3233 条记录，以下是3181-3190 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：

Reducing False Positives in Intrusion Detection System Alerts: A Novel Aggregation and Correlation Model 15th

Reducing False Positives in Intrusion Detection System Alert...

引用

15th EAI international conference on Digital Forensics and Cyber Crime, ICDF2C 2024

作者： Hadi, Hassan Jalil Cao, Yue Hussain, Faisal Bashir Ahamad, Naveed Alshara, Mohammed Ali Ullah, Insaf Javed, Yasir He, Yinglong Jamil, Abdul Majid School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science Bahria University Islamabad Pakistan College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Institute for Analytics and Data Science University of Essex ColchesterCO4 3SQ United Kingdom University of Surrey Guildford United Kingdom

ISBN: (纸本)9783031893629

Network security involves safeguarding and preventing unauthorized access to networks through various methodologies, including access control, firewalls, and intrusion detection and prevention systems (IDS/IPS). Despite the escalating frequency of network attacks, traditional tools like antivirus software and firewalls often fall short. In contrast, IDS/IPS solutions are increasingly favored for robust network protection due to their effectiveness. However, the integration of machine learning and signature-based approaches has led to a significant increase in false positives, making the manual analysis and identification of genuine alerts labor-intensive. Additionally, conventional processes may impede IDS performance, even with the use of alert aggregation and correlation techniques that aim to efficiently eliminate redundant or duplicate alerts. This work introduces a model for alert aggregation and correlation based on similarity-based correlation to mitigate anomaly-based alerts, employing a Security Event Correlator (SEC). Initially, an Anomaly Detection System (ADS), akin to IDS, is deployed. The alerts generated by the ADS serve as inputs for the proposed SEC, which preprocesses the alerts to systematically remove redundancies and duplicates. Aggregation is then executed based on extracted features, followed by correlation to prioritize the remaining alerts by considering their frequency and features. The proposed model has successfully achieved a remarkable 99.0% accuracy rate in removing redundant and duplicate alerts. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

SAMRS: scaling-up remote sensing segmentation dataset with segment anything model 23

SAMRS: scaling-up remote sensing segmentation dataset with s...

引用

Proceedings of the 37th international conference on Neural Information Processing Systems

作者： Di Wang Jing Zhang Bo Du Minqiang Xu Lin Liu Dacheng Tao Liangpei Zhang School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence and Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Computer Science Faculty of Engineering The University of Sydney Australia National Engineering Research Center of Speech and Language Information Processing China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China

The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level. In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS. SAMRS totally possesses 105,090 images and 1,668,241 instances, surpassing existing high-resolution RS segmentation datasets in size by several orders of magnitude. It provides object category, location, and instance information that can be used for semantic segmentation, instance segmentation, and object detection, either individually or in combination. We also provide a comprehensive analysis of SAMRS from various aspects. Moreover, preliminary experiments highlight the importance of conducting segmentation pre-training with SAMRS to address task discrepancies and alleviate the limitations posed by limited training data during fine-tuning. The code and dataset will be available at https://***/ViTAE-Transformer/SAMRS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reservoir Flood Prediction Service Based on Seq2seq Model 17th

Reservoir Flood Prediction Service Based on Seq2seq Model

引用

CCF 17th international conference on Service Science, CCF ICSS 2024

作者： Liu, Lincong Liu, Shijun Pan, Li School of Software Engineering Shandong University Jinan China

ISBN: (纸本)9789819757596

Reliable reservoir flood prediction model is an indispensable part to improve the digital construction of small and medium-sized reservoirs. Flood flow, as one of the important bases for measuring flood prediction, its prediction accuracy directly affects the effectiveness of reservoir flood prevention and control. The traditional flood flow prediction model often can’t get real-time and comprehensive data in time, which leads to the idealized prediction effect can’t be realized, so for this situation, this paper proposes a reservoir flood flow prediction model based on Seq2seq model. Based on the Seq2seq model, this model not only integrates the LSTM network as a recurrent processing unit to facilitate the capture of temporal information and long-term dependencies in the data, but also uses the attention mechanism to reduce the loss of information in the transmission process and improve the model’s generalization ability. At the same time, the model is compared with a variety of flood prediction machine learning models, and also compared with the prediction model based on the traditional flood flow statistics model, and then this paper further verifies the model’s improvement in prediction accuracy by comprehensively comparing the results of five evaluation indexes. Finally, the modeling service has been applied in the real environment, which again proves the effectiveness of the present service. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

MMF-DRL: Multimodal Fusion-Deep Reinforcement learning Approach with Domain-Specific Features for Classifying Time Series Data 23

MMF-DRL: Multimodal Fusion-Deep Reinforcement Learning Appro...

引用

Proceedings of the 33rd Annual international conference on Computer Science and software engineering

作者： Sharma Asmita Lakhanpal Pranshul Litoiu Marin Sergio Lauren E. Mukhopadhyay Sumona California Polytechnic State University San Luis Obispo California USA Lassonde School of Engineering York University Toronto Ontario Canada Faculty of Health York University Toronto Ontario Canada

In this work, we try to address the two challenging problems in machine learning (ML) which are: (a) the need for large amounts of labeled images for training supervised classifiers and (b) the supervised classification for time series data. We formulate the problem as an image classification task by transforming time series into domain-specific 2D features such as the scalogram and recurrence plot (RP). Such domain-specific features provide additional information to the models in contrast to raw time series data and enable us to take advantage of powerful state-of-the-art image classifiers for learning the patterns from these textured images. However, the requirement for large amounts of labeled image data is a major drawback in image classification. Thus, to address this problem, we propose to develop a multimodal fusion-deep reinforcement learning (MMF-DRL) approach as an alternative technique to traditional supervised image classifiers for the classification of time series. The two modalities scalograms and RP are fused together to make a multimodal dataset which is then fed into various models for comparison between supervised and RL approaches for time series classification. Our approach produces better accuracy than the state-of-the-art ChronoNet while needing fewer training examples. We validated our MMF-DRL approach using two different physiological time series datasets. Our results show the merit of using multiple modalities and RL in achieving better classification performance than training on a single modality. Moreover, with our approach, we got the highest accuracy of 90.20% and 89.63% respectively for the two datasets with less training data in contrast to the state-of-the-art SL model ChronoNet which gave 87.62% and 88.02% accuracy respectively for the two datasets with higher training data.

关键词： Deep Reinforcement learning Time Series Data Multimodal Fusion DQN Classification Feature engineering Recurrence Plot Scalogram

来源：评论

学校读者我要写书评

暂无评论

Utilizing Digital Twin Simulation Technologies to Build ICS Cyber Ranges 2nd

Utilizing Digital Twin Simulation Technologies to Build ICS ...

引用

2nd international conference on Network Simulation and Evaluation, NSE 2023

作者： Zhou, Haifeng Li, Mohan Sun, Yanbin Cyberspace Institute of Advanced Technology GuangzhouUniversity Guangzhou China Guangdong Key Laboratory of Industrial Control System Security Guangzhou China

ISBN: (纸本)9789819745180

With the integration of IT and OT, cyberattacks against ICS have been on the rise recently, and more and more advanced methods are resorted to by attackers to break down the physical system. To do further research in cybersecurity on ICS, building a cyber range is an economical, practical, and necessary approach considering the requirements of availability for the onsite production devices. Using all physical devices to build a cyber range is unrealistic and inflexible due to the high cost while pure software simulation lacks authenticity. Meanwhile, digital twin, a prevalent concept in recent years, shows its potential in ICS cyber ranges for its authenticity and flexibility due to the improvements in modeling methods and network communication. Therefore, the framework, implementation methods, and applications of using digital twin technology to build an ICS cyber range are discussed in this paper. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Paraphrase Detection in Indian Languages Using Deep learning 1st

Paraphrase Detection in Indian Languages Using Deep Learnin...

引用

1st international conference on Speech and Language Technologies for Low-resource Languages, SPELLL 2022

作者： Thenmozhi, Durairaj Mahibha, C. Jerin Kayalvizhi, S. Rakesh, M. Vivek, Y. Poojesshwaran, V. Sri Sivasubramaniya Nadar College of Engineering Kalavakkam India Meenakshi Sundararajan Engineering College Chennai India

ISBN: (纸本)9783031332302

Multiple sentences that reveal the same meaning are considered to be paraphrases. Paraphrases restate a given text, passage or statement using different words in which the original context and the meaning are kept intact. It can be used to expand, clarify or summarize the content of essays, research papers and journals. Semantic identity of sentences are detected during the process of paraphrase detection. Paraphrase detection can be related to different applications, like plagiarism detection, text summarizing, text mining, question answering, and query ranking, in the domain of Natural Language Processing. Effective paraphrase detection could be implemented if the semantics of the language and their interactions are adequately captured. The process of paraphrase detection is considered to be a difficult and challenging task due to the wide range of complex morphological structures and vocabulary that prevails in most of the Indian languages. The approaches that exist for paraphrase detection include machine learning techniques like Multinomial Logistic Regression model and Recursive Auto Encoders, which lacks in hand-crafted feature engineering. The problem could be solved when deep learning approaches are used for paraphrase detection. In the proposed system, the classification of paraphrase, semi-paraphrase and non-paraphrase sentences are implemented using an ensemble of three deep learning algorithms which includes BERT (Bidirectional Encoder Representations from Transformers), USE (Universal Sentence Encoder) and Seq2Seq (Sequence to Sequence). The DPIL corpus has been used for the evaluation of the proposed system and the highest accuracy obtained considering languages Hindi and Punjabi are 85.22% and 85.80% respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Malware Detection in URL Using machine learning Approach 14th

Malware Detection in URL Using Machine Learning Approach

引用

12th international Advanced Computing conference, IACC 2022

作者： Kumar, Rajesh Talwar, Rachit Sharma, Manik Kumari, Suchi Goel, Shivani Malhotra, Kanika Ahmed, Faiz College of Engineering and Design Alliance University Bangalore Bengaluru India Department of CSE Bharati Vidyapeeth’s College of Engineering New Delhi India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9783031356438

The most common technique to host fraudulent or harmful content, such as spam, malicious ads, etc., is using a Uniform Resource Locator (URL). Malicious URLs hold harmful contents that cause loss of information, malware installation, and monetary loss of the victims. Hence, it is necessary to detect such URLs and take some action on such threats. Earlier, one database is maintained to blacklist such URLs and a URL is compared with the available database of blacklisted URLs. If the URL is found in the database then the browser considers the URL suspicious and blocks it. But, this method is ineffective in finding newly discovered URLs. By suggesting a solution based on machine learning, this problem can be resolved. This research aims to investigate how machine-learning techniques can be used to identify harmful URLs. © 2023, Springer Nature Switzerland AG.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Development and Initial Validation of Two Simulation Workflows Using GATE for a Total-Body PET/CT Scanner

Development and Initial Validation of Two Simulation Workflo...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： C. Pommranz E. Elmoujarkach J. Cabello W. Lan M. Rafecas J. Mannheim A. Santangelo C. La Fougère B. Pichler F. Schmidt Department of Preclinical Imaging and Radiopharmacy Werner Siemens Imaging Center Eberhard Karls University Tuebingen Tuebingen Baden-Württemberg Germany Institute for Astronomy and Astrophysics Eberhard Karls University Tuebingen Tuebingen Baden-Württemberg Germany Institute of Medical Engineering University of Lübeck Lübeck Schleswig-Holstein Germany Siemens Medical Solutions USA Inc. Knoxville Tennessee United States of America Department of Nuclear Medicine and Clinical Molecular Imaging University Hospital Tuebingen Tuebingen Baden-Württemberg Germany Cluster of Excellence iFIT (EXC 2180) "Image Guided and Functionally Instructed Tumor Therapies" University of Tuebingen Tuebingen Germany

Monte Carlo simulation studies potentially support understanding and characterizing new total-body PET/CT scanners such as the Biograph Vision Quadra (Siemens Healthineers), which enable a broad field of novel applications. This work aims to develop and validate two simulation workflows using the Geant4 Application for Emission Tomography (GATE). Workflow 1 is designed to model the response of the Biograph Vision Quadra as closely as possible by using a custom readout and digitizer modeling tool with an integrated coincidence sorter. Further, the same image reconstruction is performed as for real scan data with the e7 tools (Siemens Healthineers). Workflow 2 is developed for increased flexibility based on open-source software and the Customizable and Advanced software for Tomographic Reconstruction (CASToR) code for image reconstruction. Phantom simulation studies were performed to validate the workflows against measurement data. Using the normalization matrix of the real scanner with an adapted calibration factor, Workflow 1 demonstrated an excellent quantification accuracy with differences of less than 1% for three different phantoms. Image quality analysis using an IEC phantom simulation with 60 s scan time showed good agreements of contrast recovery coefficients and lung residual error with experimental data. The anthropomorphic XCAT phantom was used for patient-like simulations. The successful NEMA-NU validation of the simulation workflows will enable the investigation of scenarios which practically cannot be tested on patients. Further, the generation of training and validation data sets including simulation ground truth data for machine learning algorithms will be enabled.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AntiCopyPaster: Extracting Code Duplicates As Soon As They Are Introduced in the IDE 22

AntiCopyPaster: Extracting Code Duplicates As Soon As They A...

引用

Proceedings of the 37th IEEE/ACM international conference on Automated software engineering

作者： Eman Abdullah Alomar Anton Ivanov Zarina Kurbatova Yaroslav Golubev Mohamed Wiem Mkaouer Ali Ouni Timofey Bryksin Le Nguyen Amit Kini Aditya Thakur Stevens Institute of Technology United States of America HSE University Russian Federation Huawei Russia JetBrains Research Serbia Rochester Institute of Technology United States of America Ecole de Technologie Superieure (ETS) Canada JetBrains Research Cyprus Rochester Institute of Technology USA

ISBN: (纸本)9781450394758

We developed a plugin for IntelliJ IDEA called AntiCopyPaster, which tracks the pasting of code fragments inside the IDE and suggests the appropriate Extract Method refactoring to combat the propagation of duplicates. Unlike the existing approaches, our tool is integrated with the developer’s workflow, and pro-actively recommends refactorings. Since not all code fragments need to be extracted, we develop a classification model to make this decision. When a developer copies and pastes a code fragment, the plugin searches for duplicates in the currently opened file, waits for a short period of time to allow the developer to edit the code, and finally inferences the refactoring decision based on a number of features. Our experimental study on a large dataset of 18,942 code fragments mined from 13 Apache projects shows that AntiCopyPaster correctly recommends Extract Method refactorings with an F-score of 0.82. Furthermore, our survey of 59 developers reflects their satisfaction with the developed plugin’s operation. The plugin and its source code are publicly available on GitHub at https://***/JetBrains-Research/anti-copy-paster. The demonstration video can be found on YouTube: https://***/_wwHg-qFjJY.

关键词： refactoring software quality machine learning

来源：评论

学校读者我要写书评

暂无评论

Monocular Vision-Based Prediction of Cut-In Manoeuvres with LSTM Networks 1

引用

Science, engineering Management and Information Technology First international conference, SEMIT 2022

作者： Nalcakan, Yagiz Bastanlar, Yalin Izmir Institute of Technology Izmir Urla Turkey TTTech Auto Turkey Software Izmir Turkey

ISBN: (数字)9783031403958

ISBN: (纸本)9783031403941

Advanced driver assistance and automated driving systems should be capable of predicting and avoiding dangerous situations. In this paper, we first discuss the importance of predicting dangerous lane changes and provide its description as a machine learning problem. After summarizing the previous work, we propose a method to predict potentially dangerous lane changes (cut-ins) of the vehicles in front. We follow a computer vision-based approach that only employs a single in-vehicle RGB camera, and we classify the target vehicle’s maneuver based on the recent video frames. Our algorithm consists of a CNN-based vehicle detection and tracking step and an LSTM-based maneuver classification step. It is computationally efficient compared to other vision-based methods since it exploits a small number of features for the classification step rather than feeding CNNs with RGB frames. We evaluated our approach on a publicly available driving dataset and a lane change detection dataset. We obtained 0.9585 accuracy with the side-aware two-class (cut-in vs. lane-pass) classification model. Experiment results also reveal that our approach outperforms state-of-the-art approaches when used for lane change detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

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324页 << < 315 316 317 318 319 320 321 322 323 324 > >>

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：