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

4,600 篇 期刊文献
4,148 篇 会议
41 册 图书

馆藏范围

8,789 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

5,559 篇 工学
- 4,189 篇 计算机科学与技术...
- 3,533 篇 软件工程
- 1,181 篇 信息与通信工程
- 762 篇 生物工程
- 698 篇 电气工程
- 663 篇 控制科学与工程
- 530 篇 生物医学工程（可授...
- 489 篇 光学工程
- 453 篇 电子科学与技术（可...
- 279 篇 机械工程
- 246 篇 化学工程与技术
- 203 篇 安全科学与工程
- 196 篇 网络空间安全
- 194 篇 交通运输工程
- 179 篇 仪器科学与技术
- 176 篇 动力工程及工程热...
3,329 篇 理学
- 1,760 篇 数学
- 906 篇 物理学
- 866 篇 生物学
- 644 篇 统计学（可授理学、...
- 291 篇 化学
- 284 篇 系统科学
1,593 篇 管理学
- 918 篇 管理科学与工程(可...
- 748 篇 图书情报与档案管...
- 471 篇 工商管理
526 篇 医学
- 464 篇 临床医学
- 402 篇 基础医学(可授医学...
- 238 篇 公共卫生与预防医...
- 221 篇 药学(可授医学、理...
283 篇 法学
- 239 篇 社会学
163 篇 经济学
110 篇 教育学
105 篇 农学
20 篇 文学
12 篇 军事学
7 篇 艺术学
1 篇 历史学

主题

275 篇 accuracy
265 篇 deep learning
227 篇 machine learning
225 篇 feature extracti...
218 篇 training
184 篇 computational mo...
179 篇 semantics
160 篇 predictive model...
145 篇 data models
132 篇 real-time system...
119 篇 federated learni...
111 篇 optimization
105 篇 reinforcement le...
105 篇 convolutional ne...
104 篇 graph neural net...
93 篇 internet of thin...
90 篇 image segmentati...
88 篇 neural networks
86 篇 contrastive lear...
85 篇 visualization

机构

550 篇 college of compu...
175 篇 university of ch...
129 篇 nanyang technolo...
102 篇 national enginee...
101 篇 college of compu...
99 篇 beijing advanced...
97 篇 school of data a...
85 篇 school of comput...
81 篇 cas key lab of n...
71 篇 shandong provinc...
70 篇 school of comput...
66 篇 national enginee...
63 篇 department of co...
61 篇 cas key laborato...
50 篇 school of comput...
50 篇 college of intel...
47 篇 college of compu...
46 篇 shandong enginee...
44 篇 school of comput...
41 篇 school of comput...

作者

260 篇 niyato dusit
158 篇 cheng xueqi
70 篇 hai jin
63 篇 guo jiafeng
52 篇 tao dacheng
51 篇 sun geng
44 篇 shen huawei
43 篇 jin hai
37 篇 zheng wei-shi
35 篇 peng hao
35 篇 xiaofei liao
32 篇 liu yang
31 篇 jin xiaolong
28 篇 shen linlin
27 篇 e. j. siskind
27 篇 r. bellazzini
25 篇 p. spinelli
25 篇 chen chen
25 篇 li jianxin
24 篇 j. b. thayer

语言

7,553 篇 英文
1,190 篇 其他
70 篇 中文
2 篇 斯洛文尼亚文

检索条件"机构=Computing and Data Science"

共 8789 条记录，以下是641-650 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：

Adaptive Decision Boundary for Few-Shot Class-Incremental Learning 39

Adaptive Decision Boundary for Few-Shot Class-Incremental Le...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Linhao Tan, Yongzhang Yang, Siyuan Cheng, Hao Dong, Yongfeng Yang, Liang School of Artificial Intelligence and Data Science Hebei University of Technology China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Few-Shot Class-Incremental Learning (FSCIL) aims to continuously learn new classes from a limited set of training samples without forgetting knowledge of previously learned classes. Conventional FSCIL methods typically build a robust feature extractor during the base training session with abundant training samples and subsequently freeze this extractor, only fine-tuning the classifier in subsequent incremental phases. However, current strategies primarily focus on preventing catastrophic forgetting, considering only the relationship between novel and base classes, without paying attention to the specific decision spaces of each class. To address this challenge, we propose a plug-and-play Adaptive Decision Boundary Strategy (ADBS), which is compatible with most FSCIL methods. Specifically, we assign a specific decision boundary to each class and adaptively adjust these boundaries during training to optimally refine the decision spaces for the classes in each session. Furthermore, to amplify the distinctiveness between classes, we employ a novel inter-class constraint loss that optimizes the decision boundaries and prototypes for each class. Extensive experiments on three benchmarks, namely CIFAR100, miniImageNet, and CUB200, demonstrate that incorporating our ADBS method with existing FSCIL techniques significantly improves performance, achieving overall state-of-the-art results. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mitigating Over-Unlearning in Machine Unlearning with Synthetic data Augmentation 24th

Mitigating Over-Unlearning in Machine Unlearning with Synt...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Baohai Qu, Youyang Gao, Longxiang Li, Conggai Li, Lin Smith, David Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Data61 Commonwealth Science and Industry Research Organization CanberraVIC Australia College of Business and Law Royal Melbourne Institute of Technology MelbourneVIC Australia

ISBN: (纸本)9789819615445

In machine learning, data privacy and security has become an increasingly growing concern. The introduction of machine unlearning offers the ability to address this issue through the removal of personal and sensitive data from trained models to comply with laws, regulations, and user privacy requirements. However, despite the significant benefits of this technique, performing unlearning operations is only sometimes smooth in practice. When we attempt to remove specific data, the model may over-adjust, resulting in its performance on unlearned data. This phenomenon not only reduces the accuracy of the model on known data but also affects its ability to generalize new data, thus weakening the model’s overall performance. Therefore, in this paper, we analyze the phenomenon of over-unlearning;firstly, we explore how to mitigate the effects of over-unlearning by generating synthetic data to fill in the forgotten parts, using data synthesis-based techniques. Secondly, we combine the data synthesis-based compensation strategy with model fine-tuning to further improve the model’s adaptability and generalization capability by further training the model to accommodate synthetic data. Through comprehensive experimentation, we verify the effectiveness of the proposed data synthesis-based compensation strategy. The experimental results show that the data synthesis-based compensation strategy can effectively mitigate the effects of the over-unlearning phenomenon, as well as maintaining the stability and accuracy of the model after removing specific data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

Fire Detection System using Deep Learning Techniques 4

Fire Detection System using Deep Learning Techniques

引用

4th International Conference on Inventive Research in computing Applications, ICIRCA 2022

作者： Srividhya, S. Sindhu, S. Sornalakshmi, K. Hemavathi, D. Rajaram, V. School of Computing Srm Institute of Science and Technology Data Science and Business Systems Chennai India School of Computing Srm Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

An image-based fire detection system is designed using an image dataset to train the model, and further, any image capturing device will be used for later prediction purposes. The training and prediction are done using deep learning techniques. Convolution Neural Network is used for implementation. As another fire identification innovation, picture fire location has as of late assumed a pivotal part in diminishing property misfortune and harm during a fire by disturbing clients at a beginning phase through early fire discovery. Picture fire location depends on an algorithmic investigation of pictures. Nonetheless, there is a lower precision, postponed recognition, and much calculation in like manner identification calculations, including physically and machine naturally separating picture highlights. The model is designed to alert the user via SMS and email along with a captured image of fire when a fire occurs. The proposed system in development aims at providing a detection system that can alert a user instantly at the time of a hazardous fire. The aim is to create an accurate model that does not result in false alerts. The model is trained using accurate image datasets to differentiate between a fire and a non-fire scenario. Existing models used the RGB-HIS colour space for their model. Particularly, it is used to obtain pre-detected areas rather than the traditional motion differential method. The centroid variety of candidates is used to measure the flame colour dispersions in subsequent frames. Multi-expert systems have the following;dispersion of colour and centroid movement are entrenched to classify fire based on testing various clips acquired by a surveillance camera in private confinement. © 2022 IEEE.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Evolution of the Participation of Women in University Computer science Studies in Spain and in Europe 53

Evolution of the Participation of Women in University Comput...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Nebot, Àngela Mugica, Francisco Soft Computing Research Group Intelligent Data Science and Artificial Intelligence Research Center Universitat Politécnica de Catalunya Barcelona Spain

ISBN: (纸本)9798350336429

This paper presents a comprehensive examination of the current state of underrepresentation of women in computer science (CS) degrees in Spain. It offers an overview of the situation across autonomous communities in Spain, highlighting the evolving trends within the country, regional variations, and the distinctions between public and private universities. The research employs descriptive statistical methods to analyze data obtained from the Spanish Ministry of Universities, Eurostat, as well as recent literature reviews. Furthermore, the study contextualizes the evolution of female enrollments in Spain by comparing it with data from other European countries. The primary objective is to gain a thorough understanding of the broader Spanish landscape and suggest future research directions aimed at reducing the gender gap in CS studies. © 2023 IEEE.

关键词： computer science degree descriptive statistical methods gender imbalance

来源：评论

学校读者我要写书评

暂无评论

Emotional Analysis Based on LSTM-CNN Hybrid Neural Network Model 8

Emotional Analysis Based on LSTM-CNN Hybrid Neural Network M...

引用

8th IEEE International Conference on Software Engineering and Computer Systems, ICSECS 2023

作者： Wu, You Al-Daweri, Muataz Salam Kumar, Venkata Durga School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia University of Nizwa College of Economics Mangement & Information System Nizwa Oman

ISBN: (纸本)9798350310931

In the realm of natural language processing (NLP), text classification is an important task. Current techniques for text classification tasks still need development, however, because of the complex abstraction of text semantic information and the considerable impact of context. This research synthesizes the strengths of the Bidirectional Long Short-Term Memory (Bi-LSTM) and the Convolutional Neural Network (CNN) models of neural networks. The LSTM-CNN hybrid model is a combination of the two models: the LSTM-generated text feature vector is then extracted using the CNN structure. The Bi-LSTM can retain long text sequences while taking into account the importance of the whole text, and it can subsequently use the organizational principles of the CNN to extract local text features. The research's experiment compares the effectiveness of the LSTM-CNN, the Bi-LSTM, and the Random Forest (RF) in a sentiment analysis project based on the ternary classification (Neutral, Positive, and Negative) of the metaverse, which can be described as a virtual reality space where individuals can interact with a computer-generated environment and other users in real-time, related topics. From what can be gathered from this research experiments, the LSTM-CNN outperforms other models when it comes to boosting text classification accuracy and achieving lower loss. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

SCTAP: Supporting Scenario-Centric Trigger-Action Programming based on Software-Defined Physical Environments 23

SCTAP: Supporting Scenario-Centric Trigger-Action Programmin...

引用

2023 World Wide Web Conference, WWW 2023

作者： Sun, Bingkun Shen, Liwei Peng, Xin Wang, Ziming Fudan University China School of Computer Science Shanghai Key Laboratory of Data Science Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China

ISBN: (纸本)9781450394161

The physical world we live in is accelerating digitalization with the vigorous development of Internet of Things (IoT). Following this trend, Web of Things (WoT) further enables fast and efficient creation of various applications that perceive and act on the physical world using standard Web technologies. A popular way for creating WoT applications is Trigger-Action Programming (TAP), which allows users to orchestrate the capabilities of IoT devices in the form of "if trigger, then action". However, existing TAP approaches don't support scenario-centric WoT applications which involve abstract modeling of physical environments and complex spatio-temporal dependencies between events and actions. In this paper, we propose an approach called SCTAP which supports Scenario-Centric Trigger-Action Programming based on software-defined physical environments. SCTAP defines a structured and conceptual representation for physical environments, which provides the required programming abstractions for WoT applications. Based on the representation, SCTAP defines a grammar for specifying scenario-centric WoT applications with spatio-temporal dependencies. Furthermore, we design a service-based architecture for SCTAP which supports the integration of device access, event perception, environment representation, and rule execution in a loosely-coupled and extensible way. We implement SCTAP as a WoT infrastructure and evaluate it with two case studies including a smart laboratory and a smart coffee house. The results confirm the usability, feasibility and efficiency of SCTAP and its implementation. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A NOVEL RULE-BASED OVERSAMPLING APPROACH FOR IMBALANCED data CLASSIFICATION 37

A NOVEL RULE-BASED OVERSAMPLING APPROACH FOR IMBALANCED DATA...

引用

37th Annual European Simulation and Modelling Conference, ESM 2023

作者： Zhang, Xiao Paz, Iván Nebot, Àngela Soft Computing Research Group Intelligent Data Science and Artificial Intelligence Research Center Universitat Politècnica de Catalunya Barcelona Spain

ISBN: (纸本)9789492859280

When confronted with imbalanced datasets, traditional classifiers frequently struggle to correctly categorize samples from the minority class, adversely impacting the overall predictive performance of machine learning models. Current oversampling techniques generally focus on data interpolation through neighbor selection, often neglecting to uncover underlying data structures and relationships. This study introduces a novel application for RuLer, an algorithm originally developed for identifying sound patterns in the artistic domain of live coding. When adapted for data oversampling (as Ad-RuLer), the algorithm shows significant promise in addressing the challenges associated with imbalanced class distribution. We undertake a thorough comparative evaluation of Ad-RuLer against established oversampling algorithms such as SMOTE, ADASYN, Tomek-links, Borderline-SMOTE, and KmeansSMOTE. The evaluation employs various classifiers including logistic regression, random forest, and XGBoost, and is conducted over six real-world biomedical datasets with varying degrees of imbalance. © 2023 ESM. All Rights Reserved.

关键词： Classification data synthesis Imbalanced data Oversampling Rule-based approach

来源：评论

学校读者我要写书评

暂无评论

R2V-PPI: Enhancing Prediction of Protein-Protein Interactions Using Word2Vec Embeddings and Deep Neural Networks 4

R2V-PPI: Enhancing Prediction of Protein-Protein Interaction...

引用

4th International Conference on Advances in Electrical, computing, Communication and Sustainable Technologies, ICAECT 2024

作者： Oviya, I.R. Sravya N, Shanmukha Raja, Kalpana Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science Engineering Chennai601103 India Yale University Section for Biomedical Informatics and Data Science School of Medicine New HavenCT United States

ISBN: (纸本)9798350343670

Proteins play a crucial role in living organisms, and understanding protein-protein interactions is vital for comprehending their functions and aiding drug discovery. In recent years, advanced deep learning models have been developed to predict protein-protein interactions from sequences. However, these large-scale approaches often suffer from deficiencies, resulting in both false positive and false negative predictions. Traditional encoding methods struggle to effectively represent the semantic meaning of individual residues in protein sequences and their impact on neighbouring residues. To overcome these deficiencies, we propose a novel method named R2V-PPI (Residue-to-Vector embeddings based Protein-Protein Interaction Framework) that effectively represents protein sequences and predicts protein-protein interactions. Inspired by Word2Vec, R2V-PPI learns informative representations of individual amino acid residues, capturing the context and relationships between them in raw protein sequences. These representations provide valuable input features for a downstream deep learning model. Our methodology offers a robust and versatile approach for predicting protein-protein interactions, especially when structural information is limited or unavailable. Evaluation on the S. cerevisiae dataset demonstrates that R2V-PPI outperforms existing state-of-the-art machine learning models. © 2024 IEEE.

关键词： Deep Learning Machine Learning Protein Feature Encoding Protein Protein interaction Protein sequence

来源：评论

学校读者我要写书评

暂无评论

Air Pollutant Prediction Using Shallow Architecture Machine Learning Algorithms 8th

Air Pollutant Prediction Using Shallow Architecture Machine ...

引用

8th World Conference on Smart Trends in Systems Security and Sustainability, WorldS4 2024

作者： Olaifa, Moses Malele, Vusumuzi Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria South Africa Unit of Data Science and Computing Vaal Campus North-West University Vanderbijlpark South Africa

ISBN: (纸本)9789819786947

Over the past few decades, mortality rates associated with air quality pollution have risen in numerous countries around the globe. This pollution stems from different factors such as meteorological conditions, human activities from urban industrialization, vehicular emission, and so on. Air pollution constituents such as NO2, CO, SO, and coarse and fine particulate matter for different locations have been analyzed to learn both correlation and inter-dependency for long and short terms. However, many of these studies overlook datasets collected using low-cost tools and equipment. Most of the time, datasets of this nature are marred with inconsistencies and gaps at irregular intervals. This may render the air pollutant data unsuitable. In order to test the suitability of machine learning algorithms on such dataset, this study conducts a time-series forecast analysis using the prophet algorithm. Two additional models including linear regressor and random forest regressor are trained and tested on the same dataset and a comparative analysis of the three models is performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Compound Selection of Anti-cancer Drugs Based on Multi-Objective Optimization

Intelligent Compound Selection of Anti-cancer Drugs Based on...

引用

2023 International Conference on Intelligent Supercomputing and BioPharma, ISBP 2023

作者： Liu, Xiaoyan Xu, Zhiwei Liu, Guangwen Liu, Limin Inner Mongolia University of Technology College of Data Science and Application Hohhot China Chinese Academy of Sciences Institute of Computing Technology Beijing China

ISBN: (纸本)9798350397789

In the compound selection process of anti-cancer drugs, safety properties such as drug activity and pharmacokinetics need to be considered simultaneously. To construct a more complete and precise drug screening mechanism, this paper proposed an intelligent compound selection method for anti-cancer drugs based on multi-objective optimization. The proposed model is executed in the MapReduce environment. Quantitatively analyze the biological activity of the compound, and qualitatively analyze the properties of pharmacokinetics and safety properties (Absorption, Distribution, Metabolism, Excretion, and Toxicity) to build a multi-objective optimization model. Guided by Pareto optimization theory, the set of non-inferior solution values was determined, and the compound combination that satisfies the optimization goal was found by genetic optimization. On this basis, a Monte Carlo hypothesis test was used to determine the equipped range of the compounds. Finally, an example of the compound selection of anti-breast cancer drugs is given, and the experimental evaluation proves that the algorithm can screen compounds limitedly, which provides a basis for anti-cancer drug synthesis. © 2023 IEEE.

关键词： Multiobjective optimization

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 << < 61 62 63 64 65 66 67 68 69 70 > >>

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：