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

644 篇 会议
185 册 图书
8 篇 期刊文献
1 篇 学位论文

馆藏范围

838 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

479 篇 工学
- 450 篇 计算机科学与技术...
- 188 篇 软件工程
- 42 篇 电气工程
- 39 篇 信息与通信工程
- 21 篇 控制科学与工程
- 19 篇 生物医学工程（可授...
- 12 篇 生物工程
- 11 篇 机械工程
- 8 篇 仪器科学与技术
- 6 篇 材料科学与工程（可...
- 6 篇 电子科学与技术（可...
- 6 篇 交通运输工程
- 5 篇 土木工程
- 5 篇 航空宇航科学与技...
- 4 篇 光学工程
188 篇 理学
- 117 篇 数学
- 62 篇 物理学
- 34 篇 统计学（可授理学、...
- 24 篇 系统科学
- 15 篇 生物学
107 篇 管理学
- 59 篇 管理科学与工程(可...
- 52 篇 图书情报与档案管...
- 23 篇 工商管理
22 篇 医学
- 18 篇 临床医学
- 15 篇 基础医学(可授医学...
- 7 篇 公共卫生与预防医...
- 6 篇 药学(可授医学、理...
5 篇 法学
- 5 篇 社会学
5 篇 教育学
- 5 篇 教育学
4 篇 经济学
- 3 篇 应用经济学
3 篇 农学
1 篇 文学

主题

328 篇 data mining
150 篇 data mining and ...
121 篇 artificial intel...
69 篇 information syst...
63 篇 knowledge discov...
63 篇 information stor...
51 篇 database managem...
51 篇 pattern recognit...
43 篇 computer communi...
41 篇 databases
37 篇 computer applica...
36 篇 set theory
33 篇 machine learning
33 篇 data structures ...
31 篇 rough sets
29 篇 rough set theory
24 篇 theory of comput...
24 篇 fuzzy systems
24 篇 data analysis
23 篇 computer science

机构

11 篇 institute of aut...
9 篇 institute of cyb...
9 篇 school of automa...
8 篇 school of electr...
8 篇 chinese academy ...
7 篇 school of automa...
7 篇 zhejiang univers...
7 篇 tongji universit...
7 篇 unsw sydney
6 篇 guangdong univer...
6 篇 shimane med univ...
6 篇 lovely professio...
6 篇 central south un...
5 篇 indian institute...
5 篇 indian institute...
5 篇 indian statistic...
5 篇 university of in...
5 篇 san jose state u...
5 篇 kobe university ...
5 篇 university of so...

作者

15 篇 zheng-guang wu
15 篇 hongyi li
15 篇 chaojie li
15 篇 biao luo
15 篇 long cheng
8 篇 tsumoto s
6 篇 sonali agarwal
6 篇 kanubhai k. pate...
6 篇 ngoc thanh nguye...
6 篇 atul patel
6 篇 zhang yq
5 篇 seiichi ozawa
5 篇 ashish ghosh
5 篇 lin ty
5 篇 mohammad tanveer
5 篇 asif ekbal
5 篇 wang gy
5 篇 adam jatowt
5 篇 faloutsos christ...
5 篇 leung carson k.

语言

830 篇 英文
7 篇 中文
1 篇 法文
1 篇 其他

检索条件"任意字段=Conference on Data Mining and Knowledge Discovery - Theory, Tools, and Technology II"

共 838 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：

Flexi-clique: Exploring Flexible and Sub-linear Clique Structures 24

Flexi-clique: Exploring Flexible and Sub-linear Clique Struc...

引用

33rd ACM International conference on Information and knowledge Management (CIKM)

作者： Kim, Song Kim, Junghoon Yoon, Susik Kim, Jungeun Ulsan Natl Inst Sci & Technol Ulsan South Korea Korea Univ Seoul South Korea Inha Univ Incheon South Korea

ISBN: (纸本)9798400704369

Identifying cohesive subgraphs within networks is a fundamental problem in graph theory, relevant to various domains. The traditional clique problem, which finds fully connected subgraphs, often faces limitations due to its strict connectivity requirements. This paper introduces a novel degree-based relaxation model called Flexi-clique, where the degree constraint is adjusted sub-linearly based on the subgraph size. We establish that the maximum Flexi-clique problem is NP-hard and propose an efficient and effective peeling algorithm to address it. Our extensive experimental evaluation of real-world datasets demonstrates the effectiveness and efficiency of our approach in discovering large, cohesive subgraphs in networks.

关键词： graph mining cohesive subgraph discovery

来源：评论

学校读者我要写书评

暂无评论

Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations 23

Pyramid Graph Neural Network: A Graph Sampling and Filtering...

引用

29th ACM SIGKDD conference on knowledge discovery and data mining (KDD)

作者： Geng, Haoyu Chen, Chao He, Yixuan Zeng, Gang Han, Zhaobing Chai, Hua Yan, Junchi Shanghai Jiao Tong Univ Shanghai Peoples R China Univ Oxford Oxford England Didi Chuxing Beijing Peoples R China Shanghai Jiao Tong Univ Dept CSE Shanghai Peoples R China Shanghai Jiao Tong Univ MoE Key Lab AI Shanghai Peoples R China

ISBN: (纸本)9798400701030

Spectral methods for graph neural networks (GNNs) have achieved great success. Despite their success, many works have shown that existing approaches are mainly focused on low-frequency information which may not be pertinent to the task at hand. Recent efforts have been made to design new graph filters for wider frequency profiles, but it remains an open problem how to learn multi-scale disentangled node embeddings in the graph Fourier domain. In this paper, we propose a graph (signal) sampling and filtering framework, entitled Pyramid Graph Neural Network (PyGNN), which follows the Downsampling-Filtering-Upsampling-Decoding scheme. To be specific, we develop the.. -bandlimited downsampling approach to split input graph into subgraphs for the reduction of high-frequency components, then perform spectral graph filters on subgraphs to achieve node embeddings with different frequency bands, and propose the Laplacian smoothing-based upsampling approach to extrapolate the node embedding on subgraphs to the full set of vertices on the original graph. In the end, we add the frequency-aware gated units to decode node embeddings of different frequencies for the downstream tasks. Results on both homophilic and heterophilic graph datasets show that our proposed PyGNN model can outperform many state-of-the-art baselines for node classification.

关键词： Graph Neural Networks Spectral Graph theory Graph Algorithms

来源：评论

学校读者我要写书评

暂无评论

Advanced Graph Convolutional Networks for Semantic Relationship mining in Large-Scale Ontologies 2

Advanced Graph Convolutional Networks for Semantic Relations...

引用

2nd IEEE International conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Anuradha, R. Swathi, B. Kumar, Rakesh Nagpal, Amandeep Kalra, Ravi Abdulaali, Hayder Saadoon Institute of Aeronautical Engineering Dundigal Hyderabad India New Horizon College of Engineering Department of Information Science Engineering Bangalore India Applications Gla University Department of Computer Engineering Mathura India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park Ii Uttar Pradesh Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar Iraq

ISBN: (纸本)9798350384277

This research introduces novel methodologies in graph convolutional networks (GCNs) to enhance semantic relationship mining within large-scale ontologies. Traditional approaches to understanding and extracting meaningful patterns from ontological structures often struggle with the complexity and scale of data. The proposed framework leverages advanced GCNs, incorporating a series of innovative mechanisms designed to optimize performance, accuracy, and scalability. Firstly, an enhanced graph convolutional layer is introduced, specifically tailored to capture the nuanced hierarchical and relational data typical of extensive ontological datasets. This layer employs a multidimensional feature extraction technique, significantly improving the depth and quality of semantic relationship identification. Secondly, the paper presents a unique embedding algorithm that efficiently maps semantic and relational data into a lower-dimensional space, facilitating faster computation while retaining critical information. To address the challenges of scalability, a distributed processing architecture is also proposed, enabling the handling of ontologies at an unprecedented scale. Empirical evaluations demonstrate the superiority of the approach in terms of precision, recall, and computational efficiency compared to existing methods. This research contributes to the field by providing a robust tool for experts and practitioners involved in knowledge discovery, data mining, and semantic web technologies, paving the way for more intelligent and efficient ontology management. © 2024 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robustness of Prototype with Attentive Information Guided Alignment in Few-Shot Classification 27th

Enhancing Robustness of Prototype with Attentive Information...

引用

27th Pacific-Asia conference on knowledge discovery and data mining (PAKDD)

作者： Kim, Tae-Hyung Nam, Woo-Jeoung Lee, Seong-Whan Korea Univ Dept Artificial Intelligence Seoul South Korea Kyungpook Natl Univ Sch Comp Sci & Engn Daegu South Korea

ISBN: (纸本)9783031333736;9783031333743

In this paper, we carefully revisit the issues of conventional few-shot learning: i) gaps in highlighted features between objects in support and query samples, and ii) losing the explicit local properties due to global pooled features. Motivated by them, we propose a novel method to enhance robustness in few-shot learning by aligning prototypes with abundantly informed ones. As a way of providing more information, we smoothly augment the support image by carefully manipulating the discriminative part corresponding to the highest attention score to consistently represent the object without distorting the original information. In addition, we leverage word embeddings of each class label to provide abundant feature information, serving as the basis for closing gaps between prototypes of different branches. The two parallel branches of explicit attention modules independently refine support prototypes and information-rich prototypes. Then, the support prototypes are aligned with superior prototypes to mimic rich knowledge of attention-based smooth augmentation and word embeddings. We transfer the imitated knowledge to queries in a task-adaptive manner and cross-adapt the queries and prototypes to generate crucial features for metric-based few-shot learning. Extensive experiments demonstrate that our method consistently outperforms existing methods on four benchmark datasets.

关键词： Few-shot classification data augmentation Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Driven Blockchain for Enhanced Drug discovery and Development in Pharmaceutical Research

Machine Learning-Driven Blockchain for Enhanced Drug Discove...

引用

2024 OPJU International technology conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Asha, V. Anjimoon, Shaik Verma, Meenu Rani Singla, Atul Khan, Irfan Alkhafaji, Mohammed Ayad New Horizon College of Engineering Department of Computer Applications Bangalore India Institute of Aeronautical Engineering Hyderabad Dundigal India GyanGanga Institute of Technology and Sciences DoCSBS M.P Jabalpur India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India National University of Science and Technology College of Technical Engineering Dhi Qar64001 Iraq

ISBN: (纸本)9798350373783

Machine learning (ML) and blockchain technologies have made huge steps forward in the pharmacy business by being used in the process of creating and discovering new medicines. Both breakthroughs were made possible by using both tools together. With the help of a blockchain design powered by machine learning, the study's main goal is to come up with a new way to make drug research more effective and efficient. This method makes it possible to make molecules with a wide range of structure features that have the right pharmacological qualities. You can also make these molecules, improve the plans of clinical trials, and guess how drugs will interact with their targets. Technologies like generative adversarial networks, reinforcement learning methods, and deep learning algorithms have made it possible for these things to be used. If blockchain technology is used throughout the whole process of making medicines, it improves global openness, traceability, and data security. This is because it makes sure that managing data is safe. The tests show that the suggested method works better than the others when it comes to the process of finding and developing new drugs. This is better because the creation process is more precise, accurate, and efficient. © 2024 IEEE.

关键词： Drug discovery

来源：评论

学校读者我要写书评

暂无评论

Enhancing Federated Learning Robustness Using data-Agnostic Model Pruning 27th

Enhancing Federated Learning Robustness Using Data-Agnostic ...

引用

27th Pacific-Asia conference on knowledge discovery and data mining (PAKDD)

作者： Meng, Mark Huasong Teo, Sin G. Bai, Guangdong Wang, Kailong Dong, Jin Song ASTAR Inst Infocomm Res I2R Singapore Singapore Univ Queensland Brisbane Qld Australia Huazhong Univ Sci & Technol Wuhan Peoples R China Natl Univ Singapore Singapore Singapore

ISBN: (纸本)9783031333767;9783031333774

Federated learning enables multiple data owners with a common objective to participate in a machine learning task without sharing their raw data. At each round, clients train local models with their own data and then upload the model parameters to update the global model. This multi-agent form of machine learning has been shown prone to adversarial manipulation by recent studies. Byzantine attackers impersonated as benign clients can stealthily interrupt or destroy the learning process. In this paper, we propose FLAP, a post-aggregation model pruning technique to enhance the Byzantine robustness of federated learning by effectively disabling the malicious and dormant components in the learned neural network models. Our technique is data-agnostic, without requiring clients to submit their dataset or training output, well aligned with the data locality of federated learning. FLAP is performed by the server right after the aggregation, which renders it compatible with an arbitrary aggregation algorithm and existing defensive techniques. Our empirical study demonstrates the effectiveness of FLAP under various settings. It reduces the error rate by up to 10.2% against the state-of-the-art adversarial models. Moreover, FLAP also manages to increase the average accuracy by up to 22.1% against different adversarial settings, mitigating the adversarial impacts while preserving learning fidelity.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Modern Theoretical tools for Designing Information Retrieval System 22

Modern Theoretical Tools for Designing Information Retrieval...

引用

28th ACM SIGKDD conference on knowledge discovery and data mining (KKD)

作者： Xu, Da Ruan, Chuanwei Walmart Labs Sunnyvale CA 94086 USA Instacart San Francisco CA USA

ISBN: (纸本)9781450393850

In the past decade, deep learning has significantly reshaped the landscape of information retrieval (IR). The community has recently begun to notice the potential dangers of overusing less-understood mechanisms and over-simplified assumptions to learn patterns and make decisions. In particular, there is growing concerns on the interpretation, reliability, social impact, and long-term utility of real-world IR systems. Therefore, it has become a pressing issue to bring the IR community comprehensive and systematic tools to understand empirical domain solutions and motivate principled design ideas. We focus on the three pillar stones of modern IR systems: pattern recognition with deep learning, causal inference analysis, and online decision making (with bandits and reinforcement learning). Our objectives are as follows. For pattern recognition, we introduce theoretical tools that address the expressivity, optimization, generalization, and model diagnostic for widespread domain practices, including models from unsupervised, (semi-)supervised, meta-learning, and online learning. For causal inference analysis, we emphasize both learning from observational studies and optimizing online experiment design, leveraging the recent theoretical advancements from various domains. Finally, for online decision making (with bandits and reinforcement learning), we aim to resolve both the conceptual and practical learning, evaluation and deployment challenges by introducing powerful tools from robust optimization and optimal control. Our tutorial is inclusive: we not only cover a broad range of heating topics, more importantly, we substantiate our discussion with the production examples at Walmart and Instacart such that audiences with different backgrounds can learn to leverage the tools as instructed. Our tutorial can serve as a guideline for practitioners seeking justifications and principled design ideas, a playbook for researchers landing their innovations on IR productions, and a

关键词： Information Retrieval theory

来源：评论

学校读者我要写书评

暂无评论

DSG: An End-to-End Document Structure Generator 23

DSG: An End-to-End Document Structure Generator

引用

23rd IEEE International conference on data mining, ICDM 2023

作者： Rausch, Johannes Rashiti, Gentiana Gusev, Maxim Zhang, Ce Feuerriegel, Stefan Eth Zurich Department of Computer Science Switzerland Lmu Munich Munich Center for Machine Learning Germany

ISBN: (纸本)9798350307887

Information in industry, research, and the public sector is widely stored as rendered documents (e.g., PDF files, scans). Hence, to enable downstream tasks, systems are needed that map rendered documents onto a structured hierarchical format. However, existing systems for this task are limited by heuristics and are not end-to-end trainable. In this work, we introduce the Document Structure Generator (DSG), a novel system for document parsing that is fully end-to-end trainable. DSG combines a deep neural network for parsing (i) entities in documents (e.g., figures, text blocks, headers, etc.) and (ii) relations that capture the sequence and nested structure between entities. Unlike existing systems that rely on heuristics, our DSG is trained end-to-end, making it effective and flexible for real-world applications. We further contribute a new, large-scale dataset called E-Periodica comprising real-world magazines with complex document structures for evaluation. Our results demonstrate that our DSG outperforms commercial OCR tools and, on top of that, achieves state-of-the-art performance. To the best of our knowledge, our DSG system is the first end-to-end trainable system for hierarchical document parsing. © 2023 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

How Pandemic Affected the Adoption of e-Health Systems 23

How Pandemic Affected the Adoption of e-Health Systems

引用

27th International database Engineered Applications Symposium, IDEAS 2023

作者： Napolitano, Enea Vincenzo Fioretto, Simona Masciari, Elio Anniciello, Arianna DIETI University of Naples Federico II Naples Italy

ISBN: (纸本)9798400707445

The COVID-19 pandemic has dramatically transformed healthcare systems globally, therefore improving health information technology sector. From the moment that pandemic has broken out, the use of information and communication technologies (ICT) has become absolutely necessary for the continuation of healthcare services. Furthermore, data digitization has enabled the extraction of meaningful insights through big data analytics. E-Health, encompassing a wide range of ICTs used in healthcare, has become a critical component in addressing the challenges posed by the pandemic. The main goal of this paper is to examine the impact of COVID-19 on health information technology and explores the rapid growth of e-Health and big data-driven innovation in healthcare processes. Through the analysis of the major tools, techniques, and innovative processes that have emerged in response to the pandemic, this paper has the aim of highlight their potential to improve system efficiency and enhance citizen health. We explore the current state of e-Health and big data in healthcare and discuss the future implications of these technologies for the sector. Our analysis underscores the need for continued investments in health information technology and highlights the role of policymakers, healthcare providers, and researchers in fostering innovation and driving positive change in the sector. © 2023 ACM.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Limit of Detection in Network dataset Quality Assessment with PerQoDA 1

引用

European conference on Machine Learning and Principles and Practice of knowledge discovery in databases (ECML PKDD)

作者： Wasielewska, Katarzyna Soukup, Dominik Cejka, Tomas Camacho, Jose Univ Granada Signal Theory Networking & Commun Dept Granada Spain Czech Tech Univ Fac Informat Technol Prague Czech Republic CESNET Ale Prague Czech Republic

ISBN: (数字)9783031236334

ISBN: (纸本)9783031236327;9783031236334

Machine learning is recognised as a relevant approach to detect attacks and other anomalies in network traffic. However, there are still no suitable network datasets that would enable effective detection. On the other hand, the preparation of a network dataset is not easy due to privacy reasons but also due to the lack of tools for assessing their quality. In a previous paper, we proposed a new method for data quality assessment based on permutation testing. This paper presents a parallel study on the limits of detection of such an approach. We focus on the problem of network flow classification and use well-known machine learning techniques. The experiments were performed using publicly available network datasets.

关键词： dataset quality assessment Permutation testing Network dataset Network security Attack detection Machine learning Classification

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84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：