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

8,426 篇 会议
50 篇 期刊文献
29 册 图书

馆藏范围

8,505 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,428 篇 工学
- 3,380 篇 计算机科学与技术...
- 2,254 篇 软件工程
- 1,104 篇 信息与通信工程
- 824 篇 控制科学与工程
- 773 篇 电气工程
- 357 篇 生物工程
- 336 篇 电子科学与技术（可...
- 257 篇 机械工程
- 250 篇 动力工程及工程热...
- 195 篇 生物医学工程（可授...
- 190 篇 网络空间安全
- 178 篇 仪器科学与技术
- 148 篇 交通运输工程
- 140 篇 安全科学与工程
- 139 篇 光学工程
- 115 篇 化学工程与技术
2,207 篇 理学
- 1,656 篇 数学
- 392 篇 生物学
- 368 篇 统计学（可授理学、...
- 332 篇 物理学
- 305 篇 系统科学
- 118 篇 化学
1,108 篇 管理学
- 803 篇 管理科学与工程(可...
- 367 篇 图书情报与档案管...
- 332 篇 工商管理
177 篇 医学
- 152 篇 临床医学
- 146 篇 基础医学(可授医学...
146 篇 法学
- 121 篇 社会学
132 篇 文学
- 128 篇 新闻传播学
113 篇 经济学
- 111 篇 应用经济学
56 篇 教育学
43 篇 农学
16 篇 军事学
9 篇 艺术学

主题

1,132 篇 convergence
444 篇 cloud computing
411 篇 optimization
342 篇 computational mo...
293 篇 genetic algorith...
230 篇 information tech...
200 篇 algorithm design...
196 篇 particle swarm o...
195 篇 neural networks
182 篇 resource managem...
178 篇 servers
175 篇 training
170 篇 internet of thin...
162 篇 computer archite...
143 篇 mobile computing
142 篇 real-time system...
141 篇 wireless sensor ...
137 篇 educational inst...
136 篇 costs
129 篇 deep learning

机构

37 篇 university of ch...
28 篇 state key labora...
25 篇 college of compu...
25 篇 chitkara univers...
22 篇 amrita vishwa vi...
18 篇 beijing key labo...
17 篇 school of comput...
15 篇 university of sc...
15 篇 shenyang institu...
15 篇 college of compu...
15 篇 school of inform...
14 篇 school of comput...
14 篇 department of co...
14 篇 college of infor...
13 篇 faculty of infor...
13 篇 college of compu...
13 篇 national univers...
13 篇 institute of com...
12 篇 communication un...
12 篇 state key labora...

作者

40 篇 jeong jongpil
24 篇 kim dong-seong
20 篇 lee jae-min
19 篇 yang yang
14 篇 wang hui
14 篇 pan jeng-shyang
13 篇 wang lei
12 篇 zhiwei ye
12 篇 dong-seong kim
11 篇 sampedro gabriel...
11 篇 peeta basa pati
11 篇 younghan kim
11 篇 jongpil jeong
10 篇 jongwon kim
10 篇 rajagopal shinu ...
10 篇 lee jae min
9 篇 jie yang
9 篇 li li
9 篇 liu yang
9 篇 jae-min lee

语言

8,331 篇 英文
147 篇 其他
38 篇 中文
1 篇 法文

检索条件"任意字段=International Conference on Computing and Convergence Technology"

共 8505 条记录，以下是11-20 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：

An approach for early prediction of multi-disease using ML techniques 2nd

An approach for early prediction of multi-disease using ML t...

引用

2nd international conference on Next-Generation computing and Information Systems, ICNGCIS 2023

作者： Malagar, Vani Sharma, Mekhla Upadhyay, Navin Mani Model Institute of Engineering and Technology J&K Jammu India

ISBN: (纸本)9781032738659

Leveraging the explosion of medical data including patient histories, electronic health records & medical imaging, the integration of machine learning techniques with healthcare for multi-disease prediction has experienced tremendous growth. Several algorithms have already been proposed by many researchers but they cannot fit for all the solutions at once. So, this research paper uses Machine Learning (ML) techniques to investigate the complexity involved in multi-disease prognosis in the context of convergence. It explores three well-knows ML- algorithms (Decision Tree, Random Forest classifier and Gradient Boosting) to investigate and compare the best way to identify and diagnose the prediction problems. Further a detailed comparison with existing algorithms shows a better result from 70%–77%. The accuracy of used algorithm has shown 78.57% for Decision Tree, 77.92% for Random classifier and for Gradient Boosting 95.38%. Similarly, the F1-score is also improved up to 3%. The paper also redefines several machine learning algorithms used by several researchers to solve the prediction problem, by emphasizing the importance of gradient boosting as a successful strategy. This work also validates the used models based on a statistical analysis "ANOVA and Chi-square". © 2025 The Author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Delay-Optimized Task Scheduling Based on Deep Reinforcement Learning in computing Power Networks 3rd

Delay-Optimized Task Scheduling Based on Deep Reinforcement ...

引用

3rd international conference on Machine Learning, Cloud computing and Intelligent Mining, MLCCIM 2024

作者： Tang, Qinqin Xu, Deyun Xie, Renchao Feng, Li Chen, Tianjiao Huang, Tao Beijing University of Posts and Telecommunications Beijing China China Mobile Research Institute Beijing China

ISBN: (纸本)9789819624676

With the rapid advancement of information and communication technology, there arises an increasing demand for heightened computing capabilities to facilitate a myriad of intelligent services. The computing power network (CPN) amalgamates an array of resources including cloud and edge devices to enable collaborative sensing, routing, and scheduling. This integration significantly amplifies the utilization of computing network resources while concurrently augmenting service quality. In the realm of multi-node distributed joint computing within CPNs conventional scheduling methodologies frequently neglect the interplay between computing and the network, resulting in suboptimal task scheduling. To address this issue, this study proposes a delay-optimized task scheduling mechanism based on deep reinforcement learning. Simulation results demonstrate that this framework achieves faster convergence speed, particularly under dual-depth networks, outperforming other algorithms in reducing system delays, energy and enhancing scheduling efficiency. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： computing power

来源：评论

学校读者我要写书评

暂无评论

Research on optimization techniques for thread-level parallelism implementation targeting the GCC compiler 5

Research on optimization techniques for thread-level paralle...

引用

5th international conference on Signal Processing and Computer Science, SPCS 2024

作者： Chen, Mengyao Yan, Pengyan Han, Lin Li, Haoran Wang, Cuixia Zhenzhou University Zhengzhou450001 China Zhongyuan University of Technology Zhengzhou450001 China

ISBN: (数字)9781510686731

ISBN: (纸本)9781510686724

The automatic OpenMP implementation in the current GCC compiler adopts the fork-join model, where frequent creation and convergence of thread groups result in significant management control overhead. This paper studies methods to reduce thread group creation and convergence to improve the efficiency of automatic OpenMP programs. A universal optimization method for merging parallel regions is proposed in this paper to address the fork-join model. Through variable attribute modifications, handling of serial statements, and synchronization operation optimization, adjacent continuous parallel regions are merged into a larger parallel region to reduce parameter passing within the parallel region and lower the overhead caused by the creation and destruction of parallel regions. This work is implemented based on the GCC 10.3.0 compiler and experimentally validated using the NPB 3.4-OMP test suite, achieving an average overall performance improvement of 20%. The experimental results demonstrate the effectiveness and generality of the method proposed in this paper. This method can effectively enhance the runtime efficiency of OpenMP programs, serve as a reference for optimizing the implementation of OpenMP programs, and provide support for thread dynamic merging techniques in AI compilation. © 2025 SPIE.

关键词： Program compilers

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Stage Identification Using Machine Learning 11th

Breast Cancer Stage Identification Using Machine Learning

引用

11th EAI international conference on Advancement of Science and technology, ICAST 2023

作者： Arega, Birtukan Shegaw Mengsitu, Tesfahunegn Minwuyelet Faculty of Computing Bahir Dar Institute of Technology Bahir Dar University Bahir Dar Ethiopia Department of Information Convergence Engineering Pusan National University Busan Korea Republic of

ISBN: (纸本)9783031641503

This paper presents a machine learning model for determining the stages of breast cancer. The model normalizes images, eliminates noise, and removes artifacts through preprocessing, segmentation, and classification. Patching is used to extract the region of interest (ROI), while multi-thresholding is used for segmentation. The suggested models, including CNN-KNN, VGGNet-16, CNN-naïve Bayes, and CNN-SVM, were tested on a dataset of images from the CBIS-DDSM database. Experiments were conducted using full mammogram images and segmented ROI images, resulting in accuracies of 39%, 85%, 86%, and 91%, respectively. The CNN-SVM model achieved a 6% increase in classification accuracy compared to the state-of-the-art VGGNet-16 model. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Latency and Communication in Federated Edge computing with LAFEO and Gradient Compression for Real-Time Edge Analytics 6

Optimizing Latency and Communication in Federated Edge Compu...

引用

6th international conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Namratha, P. Chaganti, Koushik Reddy Elicherla, Sivananda Lahari Reddy Guddati, Surekha Swarna, Akarapu Thiramal Reddy, P. Department of CSE GATES Institute of Technology and Science Anantapur India Dept. of Computer and Information Systems University of the Cumberlands KY United States Dept of CSE Dayananda Sagar University Bangalore India Dept of CSE Vidya Jyothi Institute of Technology Hyderabad India

ISBN: (纸本)9798331522667

The increasing need for real-time data analytics in edge computing is furthered by the latency pressures from computational and communication bottlenecks, thus demanding novel solutions. Fundamental approaches to federated learning and distributed machine learning do not accommodate changes in dynamic latency conditions very well, thereby being inefficient in terms of synchronization, communication overhead, and delay in task execution. This paper presents a holistic framework consisting of three innovative approaches to solve these problems: Latency-Aware Federated Edge-Aware Optimization (LAFEO), Latency-Driven Gradient Compression with Adaptive Sparsity (LAGCAS), and Predictive Latency Compensation with Dynamic Replication (PLCDR). The LAFEO framework consists of a double-layer optimization framework, combining latency-weighted scheduling with reinforcement learning to dynamically adapt the synchronization frequencies. This results in 25-30% end-to-end latency reduction with an accuracy deviation that is capped at 2% centralized models. LAGCAS reduces communication overhead by applying adaptive gradient scarification methods, bringing compressions of gradients under real-time accuracy thresholds: it reduces 40% communication volume and accelerates convergence by 20%. PLCDR uses predictive modelling to predict latency bottlenecks and dynamically replicates critical computations across the edge nodes. It hence offers 15-25% decrease in the completion time of tasks and up to 30% enhancement in the resilience of system sets. The existing methods will be addressed with the key limitations due to the introduction of latency-aware mechanisms that adapt to real-time edge conditions along with high accuracy and efficiency. Simulation results have shown marked scalability improvements, latency reductions, and resilience;in its positioning, this work's effort is a transformative advancement in the latency-sensitive edge computing process. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Research on the allocation of kiwifruit yield tasks in planting areas based on improved local search algorithm 24

Research on the allocation of kiwifruit yield tasks in plant...

引用

2024 international conference on Artificial Intelligence of Things and computing, AITC 2024

作者： Huang, Zhen Xi'an Mingde Institute of Technology Shaanxi Xi'an China

ISBN: (纸本)9798400709869

In the process of assigning kiwifruit production tasks, due to the large planting area of kiwifruit, it takes a long time to allocate suitable planting intervals for kiwifruit trees, resulting in an increase in algorithm execution time and cost. Therefore, it is proposed to further improve the local search algorithm based on the improved local search algorithm for kiwifruit yield task allocation, combined with the global search ability of the sparrow search algorithm and the introduction of variable helix factors and dimension wise lens learning strategies. The simulation results show that the improved local search algorithm has a faster convergence speed, and the curve has converged after 500 iterations. When the kiwifruit yield task is less than 30 tons, H is set to 2, and when the kiwifruit yield task is greater than 40 tons, H is set to 4. When the yield task is less than or equal to 40 tons, planting area 3 can meet the optimal planting interval. When the yield is greater than or equal to 50 tons, planting area 4 meets the requirements. Therefore, using an improved local search algorithm to allocate intervals between kiwifruit trees has good allocation performance, and can allocate kiwifruit trees reasonably based on different yield tasks and planting area. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Local search (optimization)

来源：评论

学校读者我要写书评

暂无评论

Emotional Contribution to Parkinson's Disease Diagnosis using Machine Learning for EEG Dataset Generation 6

Emotional Contribution to Parkinson's Disease Diagnosis usin...

引用

6th international conference on Mobile computing and Sustainable Informatics, ICMCSI 2025

作者： Arockiya Selvi, S. Kamalakannan, T. Department of Computer science VEL’S Institute of Science Technology and Advanced Studies Tamil Nadu Chennai India

ISBN: (纸本)9798331522667

Emotion is the root cause of nearly all harmful illnesses in humans. Emotion affects blood pressure, heart rate, kidney function, and a few disorders of the nervous system. Parkinson's disease, which causes impairment of movement, is one of the brain disorders. This issue is caused by a reduction in dopamine release in the cortex of the brain. Dopamine production deviations have been related to essential hypertension. Dopamine has a crucial role in anxiety modulation in multiple regions of the brain. Patients with Parkinson's disease frequently indicate that acute stress worsens their motor symptoms, especially gait freezing, dyskinesia, and tremors and the emotions play a substantial role in Parkinson's disease. This study focuses on the Classification Learner algorithms and the Electro Encephalogram (EEG) dataset, both of which covered the diagnostic range of PD development. The classifiers were evaluated using key performance indicators such as error rate, accuracy, sensitivity, specificity, and precision. The findings illustrate the convergence of emotional analysis, machine learning (ML), and neuroscience in improving diagnostic capabilities by demonstrating how a combination of EEG datasets with KNN algorithms offers a reliable and accurate approach for early Parkinson's disease identification. © 2025 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Web Security with Lightweight, Minimal Vulnerability Detection

Revolutionizing Web Security with Lightweight, Minimal Vulne...

引用

2025 international conference on computing for Sustainability and Intelligent Future, COMP-SIF 2025

作者： Shankitha, M.G. Basavaraj, G.N. Mohan, B.A. Bms Institute of Technology & Management Department of Ise Bengaluru India

ISBN: (数字)9798331538538

ISBN: (纸本)9798331538538

Web vulnerability scanners have an important function of defining security vulnerabilities and possible penetrations in web applications. Old style scanners are usually more complicated with procedures and require many resources from a system which makes them rather inconvenient for developers and small businesses. This paper describes a new web vulnerability scanner that is designed to be extremely lightweight and easy to use while meeting the need for vulnerability detection. As a result of the application of minimalistic design and automation, the proposed scanner mainly targets fundamental features, including identification of well-known types of vulnerabilities, including SQL injections, cross-site scripting (XSS), and insecure headers. A modular design is used, and that means the scanner is built for flexibility and can adapt to different web environments. Performance evaluations show that this simplified approach has further accuracy and similar level of convergence as current methods while gaining considerable advantages in terms of setup time and computational burden. This work alleges to fill the gap between usability and security;giving users background information on how to incorporate effective vulnerability assessment into their developmental life cycle. © 2025 IEEE.

关键词： Performance evaluation Cross-site scripting Organizations SQL injection Forgery Security Usability Sustainable development Faces Payloads

来源：评论

学校读者我要写书评

暂无评论

Prediction of discharge in compound channel with converging and diverging floodplain using different machine learning approach 12th

Prediction of discharge in compound channel with converging ...

引用

12th international conference on Fluvial Hydraulics, River Flow 2024

作者： Sandilya, S.S. Das, B.S. Khuntia, J.R. Devi, K. Department of Civil Engineering National Institute of Technology Patna India Department of Civil Engineering Chaitanya Bharathi Institute of Technology Hyderabad India

ISBN: (纸本)9781032757216

The discharge estimation in rivers is crucial in implementing flood manage ment techniques and essential flood defense and drainage systems. During non-monsoon season, water flows only in the main channel. However, during a flood, the watercourse over flows its banks and submerges the surrounding lands known as floodplains, which results in devastating consequences and loss of livelihood. The river comprises of a main channel and floodplains, collectively called a compound channel. Estimation of discharge in non-prismatic compound channels is a tedious task, where the floodplain converges or diverges along the length of flow. Nunumerical methods available for computing the discharge are usually com plex, as they require solving a system of complex nonlinear equations. While traditional methods often produce poor results with significant errors. Therefore, various soft computing techniques are becoming popular now-a-days in the field of water resources engineering to solve these complex non-linear problems. In this study, soft computing models XgBoost, PSO- XgBoost, and RPSO- XgBoost have been developed to predict discharge in non prismatic compound open channels. The study considers nine non-dimensional parameters such as bed slope, relative flow depth, relative longitudinal distance, hydraulic radius ratio, angle of convergence or divergence, flow aspect ratio, relative friction factor, and area ratio as influencing parameters. A gamma test is performed to find the optimal combination of input variables. The developed XgBoost, PSO-XgBoost, and RPSO-XgBoost models have produced excellent agreement with the results. All models have a mean absolute percentage error (MAPE) of less than 2% and a coefficient of determination (R2) value of more than 0.95. © 2025 The Author(s).

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Enhanced Economic Load Dispatch Using a Novel Optimization Approach: A Cost Minimization Perspective 5

Enhanced Economic Load Dispatch Using a Novel Optimization A...

引用

5th IEEE international conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Raaj, V. B. Thurai Srinivas, Chodagam Kumar, A. V. Pavan Rao, A.Venkata Subba Sindhuja, V. Navya, C.Venkata Madanapalle Institute of Technology & Science Department of Eee Andhra Pradesh India

ISBN: (纸本)9798350356236

This paper proposes an advanced African Vulture Optimization (AVO) algorithm integrated with Gaussian Process Regression (GPR) for the economic load dispatch (ELD) problem in power systems. The proposed method aims to enhance the ELD's efficiency by minimizing operational costs while maintaining power system constraints. The AVO algorithm optimizes the power generation across various units, and the GPR model is incorporated to improve convergence and accuracy in capturing the cost function's nonlinearity. The IEEE 30-bus system is used as a test case, examining three distinct load demand scenarios to evaluate the algorithm's robustness under varied conditions. Additionally, three different population sizes are applied to investigate the effects on algorithmic performance, specifically focusing on convergence rate and solution quality. Results demonstrate that the AVO-GPR method effectively reduces computational costs while achieving feasible and optimal power dispatch, outperforming traditional methods in terms of both accuracy and computational efficiency. This study contributes to the development of reliable and adaptive optimization techniques in economic load dispatch, supporting the operational efficiency of modern power systems. © 2025 IEEE.

关键词： Cost functions

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 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：