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

11,418 篇 会议
103 篇 期刊文献
44 册 图书

馆藏范围

11,565 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

7,887 篇 工学
- 6,413 篇 计算机科学与技术...
- 3,788 篇 软件工程
- 1,496 篇 控制科学与工程
- 1,378 篇 电气工程
- 1,236 篇 信息与通信工程
- 873 篇 生物工程
- 557 篇 机械工程
- 430 篇 动力工程及工程热...
- 418 篇 生物医学工程（可授...
- 382 篇 交通运输工程
- 362 篇 电子科学与技术（可...
- 269 篇 光学工程
- 260 篇 安全科学与工程
- 236 篇 材料科学与工程（可...
- 223 篇 化学工程与技术
2,875 篇 理学
- 1,791 篇 数学
- 930 篇 生物学
- 485 篇 物理学
- 450 篇 统计学（可授理学、...
- 321 篇 系统科学
- 199 篇 化学
1,743 篇 管理学
- 1,292 篇 管理科学与工程(可...
- 586 篇 工商管理
- 537 篇 图书情报与档案管...
497 篇 医学
- 368 篇 临床医学
- 345 篇 基础医学(可授医学...
- 184 篇 药学(可授医学、理...
354 篇 教育学
- 344 篇 教育学
209 篇 法学
- 191 篇 社会学
204 篇 经济学
- 204 篇 应用经济学
113 篇 农学
28 篇 军事学
23 篇 文学
7 篇 艺术学

主题

969 篇 deep learning
869 篇 optimization
766 篇 machine learning
537 篇 accuracy
404 篇 reinforcement le...
277 篇 training
274 篇 computational mo...
269 篇 feature extracti...
263 篇 predictive model...
220 篇 real-time system...
205 篇 neural networks
202 篇 support vector m...
179 篇 particle swarm o...
150 篇 convolutional ne...
148 篇 genetic algorith...
147 篇 adversarial mach...
140 篇 machine learning...
139 篇 learning systems
133 篇 data models
131 篇 analytical model...

机构

56 篇 chitkara univers...
31 篇 chitkara centre ...
22 篇 chitkara univers...
19 篇 university of ch...
14 篇 university of sc...
14 篇 misr int univ fa...
14 篇 school of comput...
13 篇 univ chinese aca...
13 篇 institutes for r...
12 篇 centre of resear...
12 篇 al-farahidi univ...
12 篇 lviv polytech na...
11 篇 guangdong provin...
11 篇 lovely professio...
11 篇 lovely professio...
11 篇 school of comput...
11 篇 the islamic univ...
11 篇 national energy ...
11 篇 king mongkuts un...
10 篇 wuhan university...

作者

15 篇 wang tao
13 篇 liu yang
13 篇 yang yang
13 篇 wang wei
13 篇 wang hao
13 篇 liu wei
11 篇 zhang jie
10 篇 zhang tao
10 篇 lima jose
10 篇 wang lei
10 篇 li hao
9 篇 hassanien aboul ...
8 篇 shiva mehta
8 篇 zhang lei
8 篇 aleven vincent
8 篇 liu jun
8 篇 wang chao
8 篇 singh jagendra
8 篇 pereira ana i.
8 篇 nojima yusuke

语言

10,789 篇 英文
750 篇 其他
52 篇 中文
1 篇 西班牙文
1 篇 法文
1 篇 俄文
1 篇 土耳其文

检索条件"任意字段=4th Conference on Learning and Intelligent Optimization"

共 11565 条记录，以下是611-620 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：

Understanding Model Extraction Games 4

Understanding Model Extraction Games

引用

IEEE 4th International conference on Trust, Privacy and Security in intelligent Systems, and Applications (IEEE TPS-ISA)

作者： Xian, Xun Hong, Mingyi Ding, Jie Univ Minnesota Minneapolis MN 55455 USA

ISBN: (纸本)9781665474085

the privacy of machine learning models has become a significant concern in many emerging Machine-learning-as-a-Service applications, where prediction services based on welltrained models are offered to users via the pay-per-query scheme. However, the lack of a defense mechanism can impose a high risk on the privacy of the server's model since an adversary could efficiently steal the model by querying only a few `good' data points. the game between a server's defense and an adversary's attack inevitably leads to an arms race dilemma, as commonly seen in Adversarial Machine learning. To study the fundamental tradeoffs between model utility from a benign user's view and privacy from an adversary's view, we develop new metrics to quantify such tradeoffs, analyze their theoretical properties, and develop an optimization problem to understand the optimal adversarial attack and defense strategies. the developed concepts and theory match the empirical findings on the `equilibrium' between privacy and utility. In terms of optimization, the key ingredient that enables our results is a unified representation of the attack-defense problem as a min-max bi-level problem. the developed results are demonstrated by examples and empirical experiments.

关键词： Adversarial learning Bi level optimization Machine learning security Minimax optimization

来源：评论

学校读者我要写书评

暂无评论

Smart Park - An intelligent Parking Management System 4

Smart Park - An Intelligent Parking Management System

引用

4th International conference on Power, Energy, Control and Transmission Systems, ICPECTS 2024

作者： Kiruppazhini, S. Krishnapriya, K. Shrimukhi, S. Meera, S. Sri Sairam Engineering College Computer Science and Engineering Chennai India

ISBN: (数字)9798331508845

ISBN: (纸本)9798331508845

this paper presents a smart parking system to reduce traffic congestion in urban areas. It provides real-time information about parking space availability in accordance with various vehicles and their sizes. Using Artificial Intelligence and Machine learning, the system facilitates streamlined vehicular flow and manages parking allotments in commercial spaces. Vehicle detection models deployed across parking facilities provide occupancy data and are used for creating a dynamic feedback loop. this helps in reducing search time and lowering congestion in parking spaces. this provides scalable solutions regarding parking spaces in commercial areas. As a supplementary service, the system would suggest nearby parking spaces in case of unavailability. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Research on Office Digitalization Situation Assessment Based on Deep learning 4

Research on Office Digitalization Situation Assessment Based...

引用

4th International conference on Computer Science, Electronic Information Engineering and intelligent Control Technology, CEI 2024

作者： Liu, Peng Wu, Xiaojiang Wang, Dazhong Zhang, Yuxi China Electric Power Research Institute Beijing China

ISBN: (纸本)9798350378542

To improve the problem that traditional algorithms cannot evaluate the security situation of complex office networks, this paper studies a deep learning based office digital situation assessment method to address the challenges brought by the increasing complexity of network environments to network security assessment. the study proposes an evaluation model consisting of three stages: data acquisition, analysis, and evaluation, aimed at automatically extracting features through deep learning technology to improve the accuracy and efficiency of digital state assessment in office environments. the model utilizes autoencoders for data dimensionality reduction and uses deep neural networks to classify and predict data, in order to analyze behavioral patterns and changes in office environments. In addition, the study also introduced an improved autoencoder algorithm, which improves the dimensionality reduction effect through sparsity constraints and correction coefficients, and uses Dropout technology to prevent overfitting and enhance the model's generalization ability. the experimental part uses TensorFlow framework and NSL-KDD dataset for training and testing, and the results show that the proposed method outperforms existing algorithms in multiple evaluation metrics, especially showing significant accuracy improvement in U2R attack mode. © 2024 IEEE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Service Classification using Deep learning Models: A Comprehensive Analysis 4

Service Classification using Deep Learning Models: A Compreh...

引用

4th International conference on Emerging Systems and intelligent Computing, ESIC 2024

作者： Das, Malabika Somyakanta, Kasturi Swain, Sujata Kumari, Rina Mohanty, Suneeta Bandyopadhyay, Anjan Kiit University School of Computer Engineering Bhubaneswar India

ISBN: (纸本)9798350349856

the process of automatically categorizing services is crucial for identifying, choosing, and integrating services. Lately, in this field the use of algorithms for machine learning has proliferated. While these techniques have shown potential, their evaluation has primarily been on web services datasets that are relatively small and balanced. this restricts their applicability in real-world scenarios. In this study, a novel deep neural network is presented that is capable of automatically converting the simple representations of the service name and description into sophisticated integrated characteristics. this is achieved without the need for feature engineering or restrictions on length. the network is then used to predict the classification of services across 50 different categories. We conducted a comprehensive experiment utilising a dataset of 10,000 real web services to compare the way we approached with five distinct machine learning approaches in order to validate the effectiveness of our strategy. According to the results, our suggested deep neural network model performs better than the others in terms of resilience and classification accuracy. © 2024 IEEE.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Push System for Teaching Resources Based on User Profile 4

Design of Intelligent Push System for Teaching Resources Bas...

引用

4th International conference on Computer Vision, Image and Deep learning, CVIDL 2023

作者： Li, Wenyue Bai, Yajuan Meng, Lingchun Guangdong University of Foreign Studies Modern Education Technology Center Guangzhou China

ISBN: (纸本)9798350326444

Aiming at the personalized online learning needs of teachers and students, this paper proposes an intelligent push system based on user profile. the system first accurately depicts user profiles from different dimensions such as user attributes, behavior, and interests;secondly, users are divided to different identity types according their learning levels;finally, combining with hybrid recommendation algorithms, it filters and pushes learning resources that meet the learning interests and needs of users. the test results indicate that the system can provide personalized services to users, improve user satisfaction and resource recommendation efficiency, and thus improve resource utilization efficiency. © 2023 IEEE.

关键词： User profile

来源：评论

学校读者我要写书评

暂无评论

Enhanced Ransomware Detection using a Hybrid Quantum-Classical Convolutional Neural Network with Boosted Sooty Tern optimization 4

Enhanced Ransomware Detection using a Hybrid Quantum-Classic...

引用

4th International conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Chaithanya, B.N. Patil, Renuka R. Gitam School of Technology Gitam University Department of Computer Science and Engineering Nagadenahalli Bengaluru India

ISBN: (纸本)9798331523923

Ransomware attacks threaten organizations by encrypting files or locking systems and keeping them inaccessible unless a ransom is paid. Early detection of ransomware attacks helps organizations avoid financial losses, theft of data, and harm to their reputations. this early detection will also reduce the risks related to malicious activities. Detection by signature-based or heuristic approaches tends to be traditional and fails when evolvement in ransomware attacks is considered. thus, a need for innovative techniques of deep learning and optimization algorithms can be observed. the method proposed in this study focuses on developing a novel multi-stage framework for detecting ransomware attacks. Firstly, correlation coefficient-based min-max normalization (CCMMN) for data preprocessing is used since it makes the data elements more uniform and makes the detection system more efficient. Feature selection is then carried out and optimized using the hybrid Osprey optimization algorithm with an enhancing sparrow search algorithm (OOA-ESSA) to arrive at the most relevant feature for classification. Last, this paper applies a hybrid quantum-classical convolutional neural network with boosted sooty tern optimization (HQCCNN-BSTO) in ransomware detection. the classic model is replaced by a quantum and hybrid classical neural network that may be complemented by an optimization algorithm to increase the speed and efficiency of the detection. the method that has been proposed here offers a flexible and efficient approach to the problems associated with the detection of ransomware threats in the practical environment. thus, high effectiveness is proved by the 99% accuracy rate of the suggested method. this exceptional outcome proves the robustness of the approach and its ability to adapt to various patterns of dependence and data changes. © 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

Construction of a Reliability Measurement Scheme for Deep learning Vision Algorithms based on Failure Modes 4

Construction of a Reliability Measurement Scheme for Deep Le...

引用

4th International conference on intelligent Technology and Embedded Systems, ICITES 2024

作者： Ai, Xiaotian Wang, Pengqi Meng, Lingzhong Ren, Hongping Dong, Qian Yang, Guang Aviation Industry Corporation of China Ltd Shenyang Aircraft Design and Research Institute Shenyang China Chinese Academy of Sciences Institute of Software Beijing China

ISBN: (纸本)9798331506292

With the application of vision algorithms in multitask scenarios such as image classification, object detection and object tracking, the traditional software reliability measurement scheme is difficult to meet the needs of new technologies. therefore, the research related to the reliability measurement of deep learning vision algorithms has become an urgent need. In this paper, we collect and analyse failure cases in five vision application scenarios, such as image classification, object detection, object tracking, and semantic segmentation, to carry out failure analysis and fault tree analysis. Using the defective causes of the failure cases, ten reliability measurements of deep learning vision algorithms are established, covering four stages: dataset, algorithm training, algorithm inference and algorithm deployment. through experiments, the influence of each index in the reliability measurement scheme was analysed. the experimental results show that all the measurements in the reliability measurement scheme constructed in this paper have a certain degree of influence, and the three measurements of data balance defect, interference data, and data accuracy defect have the highest influence on the vision task. © 2024 IEEE.

关键词： Data reliability

来源：评论

学校读者我要写书评

暂无评论

Towards Holistic Analysis of Wireless Capsule Endoscopic Videos: A Taxonomy-Driven Machine learning Framework for Clinically Comprehensive WCE Frame Level Analysis 4

Towards Holistic Analysis of Wireless Capsule Endoscopic Vid...

引用

4th IEEE Interdisciplinary conference on Electrics and Computer (INTCEC)

作者： Wahab, Haroon Goel, Rita Alamgir, Maida Mehmood, Irfan Muhammad, Khan Ugail, Hassan Univ Bradford Ctr Visual Comp & Intelligent Syst Sch Comp Sci AI & Elect Bradford W Yorkshire England Sungkyunkwan Univ Dept Appl Artificial Intelligence Visual Analyt Knowledge Lab VIS2KNOW Seoul 03063 South Korea

ISBN: (纸本)9798350349467;9798350349450

Manual perusal of capsule endoscopic videos is laborious due to their length, redundancy, and poor quality frames, risking misdetection. Limited representation of diverse anomalies and subtle lesions led to less generalized approaches targeting only individual or few anomalous findings. To deploy automated analysis in clinical settings effectively, a holistic, end-to-end approach is crucial, distinguishing between frame-level analysis and disease-level diagnosis. this study proposes a holistic framework for frame-level analysis based on a taxonomy of findings, leveraging clinical consensus. Clinical knowledge implicit in the taxonomy can enhance Computer Aided Diagnostics (CAD) systems. Convolutional Neural Networks (CNNs) trained at appropriate granularity levels in the taxonomy show improved performance metrics. Validation on the Kvasir-capsule dataset demonstrates a 2-4% performance boost. Taxonomy-based inference scores effectively resolve mimicked anomalies without additional learning.

关键词： Capsule Endoscopy Deep learning Machine learning Precision Diagnostics Small Bowel Visual computing

来源：评论

学校读者我要写书评

暂无评论

Implementing Resource-Aware Scheduling Algorithm for Improving Cost optimization in Cloud Computing 4

Implementing Resource-Aware Scheduling Algorithm for Improvi...

引用

4th International conference on Sentiment Analysis and Deep learning, ICSADL 2025

作者： Reddy, Kiran Jagannadha Udayaraju, Pamula Pamaiahgari, Venkata Pradeep Reddy Kumar, V. Dilip Walmart BentonvilleAR United States Srm University Department of Cse AP India Wendys International Llc OH United States SRKR Engineering College Department of CSE India

ISBN: (纸本)9798331523923

An uncountable number of computational resources are shared for various applications using a transformative technology called Cloud Computing. It is an emerging technology that can offer scalable and on-demand resources. However, cost optimization and resource allocation are critical issues due to the increasing number of cloud user and their request. It can be solved by optimising resource allocation by reducing the task/user queue. It is possible only if the requested resource is free;otherwise, it must schedule the same or relevant resource. this paper demonstrates a Resource-Aware Scheduling (RAS) algorithm to increase the speed of resource allocation by mapping the user request with the resource availability. the proposed algorithm examines the log information of the resources, workload behaviour, resource availability, price, task efficiency, and reduced wastage and allocates the resources dynamically. To do that, it maps user information with resource information and schedules based on availability and priority. the simulation-based experiment is carried out in a private cloud space and demonstrates the resource allocation, utilization, response time, and cost. It is also compared with the traditional scheduling algorithm to evaluate the performance of the RAS. the evaluation found that the RAS model is more suitable for cloud resource allocation. © 2025 IEEE.

关键词： Cloud Computing Cost optimization Resource Allocation Resource-Aware Scheduling Scheduling

来源：评论

学校读者我要写书评

暂无评论

Microgrid Capacity Configuration optimization Based on Multi-population Cooperative Grey Wolf Algorithm 4

Microgrid Capacity Configuration Optimization Based on Multi...

引用

4th International conference on intelligent Power and Systems, ICIPS 2024

作者： Wen, Xiaoyao Yang, Jiahao Zhang, Jingrui Tsai, Wen-Chang Xiamen University Department of Instrumental and Electrical Engineering Xiamen China Xiamen University Tan Kah Kee College School of Mechanical and Electrical Engineering & Automation Zhangzhou China

ISBN: (纸本)9798331532765

With the rapid development of renewable energy, independent microgrids integrating distributed energy sources such as wind and solar power have become a research focus due to their excellent cost-effectiveness and energy efficiency. In microgrid design, optimal capacity allocation is crucial for improving resource utilization and reducing operational costs. Grey Wolf optimization (GWO) algorithms which show great potential in solving optimal allocation problems are prone to early convergence and local optima. To address these issues, this study proposes four strategies to enhance global search capability and population diversity: (1) multi-population strategy to increase diversity;(2) t-distribution mutation to disturb optimal individuals, improving early global search and late-stage local optimization, thereby accelerating convergence;(3) hybrid operation to introduce diversity and prevent local convergence;and (4) replacement strategy to maintain population diversity and exploration ability. Taking the optimal configuration of a wind-solar-diesel-storage microgrid as an example, experimental results show that the multi-population collaborative GWO algorithm reduces annual costs by 3,720 RMB, 10,470 RMB, and 57,350 RMB compared to traditional GWO, PSO, and DE algorithms, respectively. these results demonstrate the superiority of the proposed algorithm in microgrid optimization, highlighting its advantages in enhancing global optimization capabilities and reducing operational costs. © 2024 IEEE.

关键词： Distributed energy

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 << < 58 59 60 61 62 63 64 65 66 67 > >>

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：