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

2,644 篇 会议
61 篇 期刊文献
38 册 图书
3 篇 学位论文

馆藏范围

2,746 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,237 篇 工学
- 1,991 篇 计算机科学与技术...
- 779 篇 软件工程
- 488 篇 电气工程
- 437 篇 信息与通信工程
- 174 篇 控制科学与工程
- 167 篇 生物工程
- 119 篇 生物医学工程（可授...
- 56 篇 仪器科学与技术
- 55 篇 化学工程与技术
- 50 篇 安全科学与工程
- 46 篇 机械工程
- 42 篇 电子科学与技术（可...
- 38 篇 光学工程
- 26 篇 动力工程及工程热...
537 篇 理学
- 279 篇 数学
- 187 篇 生物学
- 114 篇 物理学
- 108 篇 系统科学
- 108 篇 统计学（可授理学、...
- 54 篇 化学
266 篇 管理学
- 141 篇 图书情报与档案管...
- 136 篇 管理科学与工程(可...
- 64 篇 工商管理
146 篇 医学
- 122 篇 临床医学
- 56 篇 基础医学(可授医学...
- 36 篇 药学(可授医学、理...
- 27 篇 特种医学
- 25 篇 医学技术（可授医学...
41 篇 法学
- 33 篇 社会学
35 篇 教育学
- 28 篇 教育学
22 篇 经济学
22 篇 农学
8 篇 文学
5 篇 艺术学
1 篇 军事学

主题

897 篇 machine learning
218 篇 deep learning
123 篇 feature extracti...
106 篇 training
103 篇 machine learning...
85 篇 classification
72 篇 cloud computing
70 篇 support vector m...
70 篇 neural networks
62 篇 big data
60 篇 data mining
60 篇 computational mo...
53 篇 artificial intel...
49 篇 sentiment analys...
45 篇 predictive model...
43 篇 intrusion detect...
40 篇 reinforcement le...
38 篇 data models
35 篇 neural network
34 篇 internet of thin...

机构

12 篇 univ chinese aca...
11 篇 institute of mac...
7 篇 school of comput...
7 篇 fudan university
7 篇 school of electr...
7 篇 guangxi academy ...
6 篇 università di ca...
6 篇 infn sezione di ...
6 篇 north-west unive...
6 篇 in2p3 lpc campus...
6 篇 institut univers...
6 篇 national centre ...
6 篇 tno technical sc...
6 篇 université de st...
6 篇 nikhef national ...
6 篇 university würzb...
6 篇 université de ha...
6 篇 university of jo...
6 篇 university moham...
6 篇 astrocent nicola...

作者

14 篇 qin xiao
8 篇 yuan chang-an
8 篇 huang de-shuang
7 篇 chen hao
7 篇 yuan changan
7 篇 wu hongjie
7 篇 zhao xingming
6 篇 chen a.
6 篇 benoit d.m.
6 篇 ferrara g.
6 篇 ardid m.
6 篇 calvo d.
6 篇 gagliardini s.
6 篇 eddymaoui a.
6 篇 kulikovskiy v.
6 篇 labalme m.
6 篇 gal t.
6 篇 bozza c.
6 篇 khatun a.
6 篇 kalekin o.

语言

2,639 篇 英文
69 篇 中文
39 篇 其他

检索条件"任意字段=2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017"

共 2746 条记录，以下是131-140 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：

Trimmer: Cost-Efficient Deep learning Auto-tuning for Cloud Datacenters 15

Trimmer: Cost-Efficient Deep Learning Auto-tuning for Cloud ...

引用

15th IEEE international conference on Cloud computing (IEEE CLOUD) / IEEE World Congress on Services (IEEE SERVICES)

作者： Borowiec, Damian Yeung, Gingfung Friday, Adrian Harper, Richard H. R. Garraghan, Peter Univ Lancaster Lancaster England

ISBN: (数字)9781665481373

ISBN: (纸本)9781665481373

Cloud datacenters capable of provisioning high performance machine learning-as-a-Service (MLaaS) at reduced resource cost is achieved via auto-tuning" automated tensor program optimization of Deep learning models to minimize inference latency within a hardware device. However given the extensive heterogeneity of Deep learning models, libraries, and hardware devices, performing auto-tuning within Cloud datacenters incurs a significant time, compute resource, and energy cost of which state-of-the-art auto-tuning is not designed to mitigate. In this paper we propose Trimmer, a high performance and cost-efficient Deep learning auto-tuning framework for Cloud datacenters. Trimmer maximizes DL model performance and tensor program cost-efficiency by preempting tensor program implementations exhibiting poor optimization improvement;and applying an ML-based filtering method to replace expensive low performing tensor programs to provide greater likelihood of selecting low latency tensor programs. Through an empirical study exploring the cost of DL model optimization techniques, our analysis indicates that 26-43% of total energy is expended on measuring tensor program implementations that do not positively contribute towards auto-tuning. Experiment results show that Trimmer achieves high auto-tuning cost-efficiency across different DL models, and reduces auto-tuning energy use by 21.8-40.9% for Cloud clusters whilst achieving DL model latency equivalent to state-of-the-art techniques.

关键词： Deep learning Cloud datacenter MLaaS machine learning systems Energy Sustainable AI

来源：评论

学校读者我要写书评

暂无评论

A systematic review of Human Aspects in Industry 4.0 and 5.0: Cybersecurity Awareness and soft Skills 27

A systematic review of Human Aspects in Industry 4.0 and 5.0...

引用

27th IEEE international conference on Intelligent Engineering Systems, INES 2023

作者： Takacs, Judit Modne Pogatsnik, Monika Obuda University Alba Regia Technical Faculty Szekesfehervar Hungary

ISBN: (纸本)9798350328516

This systematic review aims to explore how the critical role of human participation in cyberspace is reassessed, given the growing importance of Industry 4.0 and 5.0. The focus of the review will be to explore the implications for the labor market and the training of the workforce, in particular the need for the development of soft skills and cyber security awareness. Literature is lacking on the role of cyberspace, cyberawareness and soft skills, their interdependencies and the implications and consequences of developing them. This systematic review provides an overview of the empirical research on soft skills and cybersecurity awareness in the context of industrial revolutions. The development of soft skills and cybersecurity awareness is key to successful adaptation and competitiveness for both individuals and the labor market. In accordance with the screening criteria, 32 articles were identified and were selected for inclusion in the final summary for the period 2017-2022 from a total of 5921 articles. This study examines the human-machine collaboration of Industry 4.0 and 5.0 in cyberspace from a labor market and workforce training perspective. The study highlights the increasing importance of combining technical and soft skills, including digital literacy, emotional intelligence, empathy, and adaptability, for engineers and IT specialists working in this industry. To address the digital and cybersecurity skills gap, the study also highlights the need for continuous skills development, on-the-job learning, and mentoring support. © 2023 IEEE.

关键词： Industry 4.0

来源：评论

学校读者我要写书评

暂无评论

Omnidirectional walking of a quadruped robot enabled by compressible tendon-driven soft actuators

Omnidirectional walking of a quadruped robot enabled by comp...

引用

IEEE/RSJ international conference on Intelligent Robots and Systems (IROS)

作者： Ji, Qinglei Fu, Shuo Feng, Lei Andrikopoulos, George Wang, Xi Vincent Wang, Lihui KTH Royal Inst Technol Dept Prod Engn S-10044 Stockholm Sweden KTH Royal Inst Technol Dept Machine Design S-10044 Stockholm Sweden

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

Using soft actuators as legs, soft quadruped robots have shown great potential in traversing unstructured and complex terrains and environments. However, unlike rigid robots whose gaits can be generated using foot pattern design and kinematic model of the rigid legs, the gait generation of soft quadruped robots remains challenging due to the high DoFs of the soft actuators and the uncertain deformations during their contact with the ground. This study is based on a quadruped robot using four Compressible Tendon-driven soft Actuators (CTSAs) as the legs, with the actuator's compression motion being utilized to improve the walking performance of the robot. For the gait design, an inverse kinematics model considering the compression of the CTSA is developed and validated in simulation. Based on this model, walking gaits realizing different motion speeds and directions are generated. Closed loop direction and speed controllers are developed for increasing the robustness and precision of the robot walking. Simulation and experimental results show that omnidirectional locomotion and complex walking tasks can be realized by tuning the gait parameters and the motions are resistant to external disturbances.

关键词： Modeling Control learning for soft Robots soft Sensors and Actuators Motion Control Tendon/Wire Mechanism

来源：评论

学校读者我要写书评

暂无评论

Enhancing AI - Powered Malware Detection by Parallel Ensemble learning

Enhancing AI - Powered Malware Detection by Parallel Ensembl...

引用

2023 RIVF international conference on computing and Communication Technologies, RIVF 2023

作者： Vo, Hoang V. Nguyen, Phong H. Nguyen, Hau T. Vu, Duy B. Nguyen, Hoa N. VNU University of Engineering and Technology Vietnam National University at Hanoi Department of Information Systems Viet Nam

ISBN: (纸本)9798350315844

The efficacy of signature-based malware detection is limited in detecting novel forms of malware that are created through obfuscation and deformation methods. AI-powered techniques are extensively utilized to detect malware by employing classification models that analyze its behavioral patterns. This research presents a novel malware detection approach, referred to as PEMA, which integrates multiple effective AI models that are carefully chosen through an automated machine learning framework. Parallel ensemble learning with XGBoost, CatBoost, and LightGBM algorithms is employed by PEMA to make deep malware analysis faster and more accurate. Since PEMA was put together using three separate models, it can lessen the likelihood that it will be susceptible to poisoning and adversarial attacks. The performance of PEMA is verified by experimenting with well-known datasets, such as the EMBER 2017 and 2018, for evaluation purposes. As a result, PEMA attained Fl scores of 99.41% and 97.64%, respectively. Furthermore, it exhibits superior performance compared to other recent methods utilizing the same datasets and improves significant detection time. © 2023 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

Analysis of Intrusion Detection System by Applying machine learning Using KNIME Tool 6th

Analysis of Intrusion Detection System by Applying Machine L...

引用

6th international conference on Recent Innovations in computing, ICRIC 2023

作者： Chavan, Vishwanath D. Kaladeep Yalagi, Pratibha C. Walchand Institute of Technology Maharashtra Solapur India

ISBN: (纸本)9789819728381

Intrusion detection helps a lot for information security which enables companies to identify possible security risks and breaches to take immediate action. For monitoring network traffic, the intrusion detection system (IDS) alerts users to any suspicious or malicious activity. In this research, we primarily addressed intrusion detection and classification using machine learning approaches in conjunction with the Konstanz Information Miner (KNIME) tool. Detection of intrusion is implemented using the selection of features which involves one variate and it ranks features based on their relevance using information gathered from the KNIME node. Intrusion detection system applications are helpful for analyzing network data and identifying strange patterns that may indicate security flaws. To prepare the data and extract features, the CICIDS2017 dataset is used. Using KNIME nodes, a variety of classifiers were investigated in order to improve performance and compare with other classifiers. Performance evaluation is done based on F-measure, recall, accuracy, and precision. Decision Trees’ accuracy is 96.04%, Random Forests is 99.70%, Naïve Bayes is 98.99%, and Gradient-Boosted Trees is 89.90%. Random Forest performs better compares to others. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Improved machine learning Algorithms for Fraud Detection in Fintech Companies 5th

Improved Machine Learning Algorithms for Fraud Detection in ...

引用

5th international conference on Financial Technology-ICFT

作者： Nwachukwu, Chukwuemeka Akwiwu-Uzoma, Chukwuebuka Ovuehor, Samuel Durodola-Tunde, Kehinde Univ Bradford Dept Appl AI & Data Analyt Bradford W Yorkshire England Univ Dundee Dept Comp Dundee Scotland

ISBN: (纸本)9789819638109;9789819638116

The rapid adoption of mobile money is due to the penetration of smart devices and the reduced cost of computing power. Today, many rural dwellers use mobile smart devices (Ofcom, 2022). A financial solution that creates a transaction system through mobile smart devices is instrumental in closing the financial inclusion gap. Mobile money offers digital financial service providers access to an untapped market that is profitable. There has been a shift from traditional banking to digital banking services (mobile money). This is due to a rapid increase in mobile phone penetration and reliance on domestic remittances in many households (Mauree and Kohli, 2013). With the broad internet usage, modern technologies, and the current growth of digital financial service providers, there is a need for financial institutions to mitigate against financial crimes and fraudulent activities (Wewege et al., 2020). The sporadic expansion of digital transformation has made digital financial services providers vulnerable to cyber risks. The continuous partnerships with third parties, technology providers and fintech companies have heightened their vulnerability to cyber-attacks (Tsys, 2017). More people are prioritizing their delicate personal data against hacking, identity theft, cyberattacks and money laundering. Digital banks with lesser security infrastructure and small fintech companies are more prone to financial fraud and cyber risks. Hence, digital financial service providers and fintech companies should continuously update their security infrastructure (Wewege et al., 2020). This study focuses on how fintech companies can maximize improved machine learning algorithms for fraud detection.

关键词： machine learning Mobile Money Fraud Detection

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection System for Identifying Simultaneous Attacks using Multi-Task learning and Deep learning 2

An Intrusion Detection System for Identifying Simultaneous A...

引用

2nd international conference on computing and Information Technology, ICCIT 2022

作者： Albelwi, Saleh A. University of Tabuk Industrial Innovation and Robotics Center Faculty of Computing and Information Technologhy Tabuk Saudi Arabia

ISBN: (纸本)9781665436052

Though both machine learning and deep learning have made great progress in developing intrusion detection systems (IDSs), two critical problems remain. The first is the ever-evolving nature of malicious activity. Data flows and packets can contain several types of attacks simultaneously, while machine learning and deep learning algorithms can only learn a single task at a time. Second, the publicly available datasets are created to evaluate only one type of attack. In order to address these issues, this paper proposes a Multi-Task learning (MTL) model for an IDS based on deep neural networks (DNNs), which has the ability to detect several types of attacks simultaneously. To do this, we concatenated each corresponding sample in both the UNSW-NB15 and CICIDS2017 datasets into one feature vector. This guarantees that a portion of the data flows, in both the training and testing sets, contains two threats at one time. The experimental results demonstrate that the proposed system maximizes performance. © 2022 IEEE.

关键词： Linearization

来源：评论

学校读者我要写书评

暂无评论

Transfer learning from ImageNet to the Domain of Pigmented Nevi 1

引用

22nd international conference on Artificial Intelligence and soft computing, ICAISC 2023

作者： Surówka, Grzegorz Department of Physics Astronomy and Applied Computer Science Jagiellonian University ul. Lojasiewicza 11 Krakow30-348 Poland

ISBN: (数字)9783031425059

ISBN: (纸本)9783031425042

The transfer learning method enables the use of a pretrained convolutional network to efficiently model a secondary domain with less data. In this article 18 public convolutional networks of different architecture and depth, pretrained on ImageNet, are tested on three optimizers (Adam, Rmsprop and SGDM), ten learning rate values and two diverse data sets (ISIC 2017 and Melanoma-ML), to choose the best one for the malignant melanoma vs. atypical (but benign) nevi classification. This is important since both types of the pigmented skin lesions can be visually very similar and difficult to distinguish. For the well-known ISIC 2017 data set, we found the best accuracy of 94.36 ± 1.66% for the ResNet 101 convolutional network with the SGDM optimizer and the learning rate of 6e-4. We show our results against the literature on the subject. The best pretrained model(s) can be easily implemented in dermoscopy systems/applications to assist skin/general physicians of all levels of training and experience and patients for premedical self-examination. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Computer aided diagnosis

来源：评论

学校读者我要写书评

暂无评论

Protecting the IoT Devices from DDoS Attack Using Blockchain-Based Multi-code-Driven Trust Mechanism 1

引用

4th international conference on Computer Vision, High-Performance computing, Smart Devices, and Networks, CHSN 2023

作者： Jayanarayana Reddy, D. Jahnavi, Addula Indhu, Pothula Latha, Mekala Hema Department of CSE G. Pullaiah College of Engineering and Technology Kurnool India Kurnool India

ISBN: (数字)9789819777945

ISBN: (纸本)9789819777938

The Internet of things (IoT) offers a promising platform for developing mission-critical programs. However, these programs often depend on a centralised storage architecture, which poses significant challenges such as security, privacy, and a single point of failure. Recently, blockchain technology has emerged as a key component in IoT application development. Blockchain can address issues related to data privacy, security, and third-party dependence in IoT applications. Both individuals and communities can benefit from integrating blockchain with IoT. Nonetheless, a DDoS attack on a mining pool in 2017 exposed significant vulnerabilities in blockchain-enabled IoT systems. Additionally, the data generated by these programs is vast. machine learning (ML) is an effective analytical tool that facilitates fully autonomous analysis and decision-making with large datasets. This research proposes a novel distributed intrusion detection system (IDS) utilising fog computing to detect DDoS attacks on mining pools in blockchain-enabled IoT networks, addressing the aforementioned challenges. It introduces an energy-efficient, decentralised, blockchain-based multi-mobile code-driven method for detecting internal threats in sensor node-powered IoT. The results indicate that the proposed approach outperforms existing alternatives. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Blockchain-based multi-mobile code driven solution Distributed Denial of Service Internet of Things machine learning

来源：评论

学校读者我要写书评

暂无评论

A graph-based machine learning approach to predicting digital lifecycle campaign engagement 21

A graph-based machine learning approach to predicting digita...

引用

5th international conference on machine learning and soft computing, icmlsc 2021

作者： Duvvuri, Venkata Department of Technology Leadership and Innovation Purdue UniversityOracle Corporation United States

ISBN: (纸本)9781450387613

Digital campaigns can be launched using a variety of channels, prominently display banner, social media, search, email and SMS. Quite a bit of research has been taken up to optimize such individual channel's performance. Due to integrated marketing needs to serve and nurture the customer over a lifetime, such campaigns are increasingly stringed together into a digital life cycle campaign (DLC) using graph structured representation, also called as marketing campaign orchestrations (MCO). Such DLC campaigns are quite complex and long in duration, including a variety of channels intermixed on multiple platforms. We suggest a novel way to measure engagement rates of such DLCs when prior historical campaign data is available for a well-defined marketing campaign orchestration. We additionally develop a way to predict performance of a new or modified DLC leveraging machine learning and graph techniques given historical DLC performances. We show that such predictions are more accurate in common scenarios when enterprises develop diverse DLCs. © 2021 Owner/Author.

关键词： Life cycle

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275页 << < 10 11 12 13 14 15 16 17 18 19 > >>

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：