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

9,485 篇 会议
1,076 册 图书

馆藏范围

10,561 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

9,153 篇 工学
- 8,699 篇 计算机科学与技术...
- 4,037 篇 信息与通信工程
- 1,156 篇 机械工程
- 725 篇 软件工程
- 531 篇 电气工程
- 228 篇 农业工程
- 147 篇 控制科学与工程
- 116 篇 环境科学与工程（可...
- 81 篇 城乡规划学
- 44 篇 生物医学工程（可授...
- 34 篇 安全科学与工程
- 25 篇 测绘科学与技术
- 25 篇 生物工程
- 18 篇 电子科学与技术（可...
- 17 篇 土木工程
1,977 篇 管理学
- 1,925 篇 管理科学与工程(可...
- 116 篇 工商管理
- 57 篇 图书情报与档案管...
542 篇 农学
- 538 篇 作物学
364 篇 理学
- 155 篇 科学技术史(分学科...
- 143 篇 数学
- 35 篇 生物学
- 17 篇 大气科学
- 16 篇 地理学
174 篇 教育学
- 174 篇 教育学
165 篇 法学
- 147 篇 社会学
- 16 篇 政治学
82 篇 文学
- 81 篇 新闻传播学
52 篇 经济学
- 41 篇 理论经济学
16 篇 医学
- 16 篇 基础医学(可授医学...
1 篇 军事学
1 篇 艺术学

主题

282 篇 artificial intel...
275 篇 computer communi...
253 篇 industry 4.0
233 篇 information syst...
182 篇 machine learning
130 篇 simulation
125 篇 computer applica...
113 篇 computers and so...
108 篇 collaborative ne...
98 篇 knowledge manage...
95 篇 sustainability
86 篇 theory of comput...
84 篇 software enginee...
83 篇 internet of thin...
81 篇 deep learning
79 篇 software enginee...
77 篇 circular economy
77 篇 optimization
74 篇 management of co...
71 篇 digitalization

机构

62 篇 china agr univ c...
45 篇 univ paulista sa...
40 篇 norwegian univ s...
38 篇 natl engn res ct...
30 篇 tecnol monterrey...
29 篇 university of am...
27 篇 zf friedrichshaf...
27 篇 beijing res ctr ...
26 篇 univ hong kong c...
26 篇 politecn milan d...
24 篇 university of pi...
24 篇 univ bergamo ber...
23 篇 univ cape town c...
23 篇 politecn milan d...
23 篇 tecnol monterrey...
23 篇 chalmers univ te...
21 篇 democritus unive...
20 篇 china agr univ c...
20 篇 univ oslo oslo
20 篇 nova university ...

作者

63 篇 luis m. camarinh...
55 篇 taisch marco
47 篇 camarinha-matos ...
41 篇 chow kam-pui
41 篇 ilias maglogiann...
39 篇 wuest thorsten
38 篇 afsarmanesh hami...
38 篇 powell daryl
38 篇 stich volker
36 篇 nielsen kjeld
35 篇 gaiardelli paolo
33 篇 tzovaras dimitri...
32 篇 kiritsis dimitri...
32 篇 chochliouros ioa...
30 篇 hamideh afsarman...
29 篇 strandhagen jan ...
29 篇 schuh guenther
27 篇 rabelo ricardo j...
27 篇 alfnes erlend
26 篇 dolgui alexandre

语言

10,514 篇 英文
47 篇 中文

检索条件"丛书名=IFIP Advances in Information and Communication Technology 461"

共 10561 条记录，以下是161-170 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：

Leveraging Task-Specific VAEs for Efficient Exemplar Generation in HAR 7th

Leveraging Task-Specific VAEs for Efficient Exemplar Generat...

引用

7th ifip WG 5.5 International Cross-Domain Conference on Internet of Things

作者： Kann, Bonpagna Castellanos-Paez, Sandra Rombourg, Romain Lalanda, Philippe Univ Grenoble Alpes CNRS Grenoble INP LIG F-38000 Grenoble France Cambodia Acad Digital Technol Inst Digital Res & Innovat Phnom Penh 121002 Cambodia Univ Grenoble Alpes CNRS Grenoble INP G2Elab F-38000 Grenoble France

ISBN: (纸本)9783031819025;9783031819001;9783031818998

The emerging technologies of smartphones and wearable devices have transformed Human Activity Recognition (HAR), offering a rich source of sensor data for building an automated system to recognize people's daily activities. The sensor-based HAR data also enables Machine Learning (ML) algorithms to classify various activities, indicating a new era of intelligent systems for health monitoring and diagnostics. However, integrating ML into these systems faces the challenge of catastrophic forgetting, where models lose proficiency in previously learned activities when introduced to new ones by users. Continual Learning (CL) has emerged as a solution, enabling models to learn continuously from evolving data streams while reducing forgetting of past knowledge. Within CL methodologies, the use of generative models, such as Variational Autoencoders (VAEs), for example, has drawn significant interest for their capacity to generate synthetic data. This reduces storage demands by creating on-demand samples. However, the application of VAEs with a CL classifier has been limited to low-dimensional data or fine-grained features, leaving a gap in harnessing raw, high-dimensional sensor data for the HAR model. Our research aims to bridge this gap by constructing VAEs with a filtering mechanism for direct training with raw sensor data from the HAR dataset, enhancing CL models' capability in class-incremental learning scenario. We demonstrate that VAE with a boundary box sampling and filtering process significantly outperforms both traditional and hybrid exemplar CL methods, offering a more balanced and diverse training set that enhances the knowledge acquisition of the model. Our findings also emphasize the importance of sampling strategies in the latent space of VAEs to maximize data diversity, crucial for recognizing the variability in human activities for better representation of each activity in each CL task.

关键词： Continual Learning HAR Replay Methods VAE

来源：评论

学校读者我要写书评

暂无评论

Dynamic Truth: Immutable Humans, AI and Innovation 24th

Dynamic Truth: Immutable Humans, AI and Innovation

引用

24th International TRIZ Future Conference

作者： Mann, Darrell Systemat Innovat Network Plymouth Devon England

ISBN: (纸本)9783031759253;9783031759239;9783031759222

The continuing survival of Society depends on the existence of Truth. Innovation depends on Truth. The mismatch between AI technology, our Stone-Age brains and our Dark-Age institutions jeopardises the ability to identify Truth. It has become possible for small numbers of 'bad actors' to corrupt truth and create highly non-linear harm. At the same time, Truth is also dynamic. Facts have a half-life. Metaphorical truths, in the form of the 'meaning of life' work of artists, are also constantly evolving. The purpose of the paper is to examine how Society defines and uses dynamic Truth, and from there to conceptualise and demonstrate AI system algorithms capable of establishing context-appropriate, harm-eliminating, actionable 'truth'. The primary purpose of such AI solutions will be to increase the success rate of innovation attempts. The secondary, albeit bigger, purpose is to try to mitigate the enormous risks that a failure to determine truth in a timely manner poses to Society at large.

关键词： TRIZ Contradiction Humanocracy Complexity Reality Discontinuity First-Principles Half-Life

来源：评论

学校读者我要写书评

暂无评论

Efficient Implementation of Authenticated Encryption on 16-bit MSP430 Microcontrollers 7th

Efficient Implementation of Authenticated Encryption on 16-b...

引用

7th ifip WG 5.5 International Cross-Domain Conference on Internet of Things

作者： Franck, Christian Grossschaedl, Johann Univ Luxembourg DCS & SnT 6 Ave FonteAve Fonte L-4364 Luxembourg Luxembourg

ISBN: (纸本)9783031819025;9783031819001;9783031818998

Algorithms for Authenticated Encryption with Associated Data (AEAD) extend the normal functionality of authenticated encryption schemes by the ability to process data that is only authenticated but not encrypted. Such algorithms have attracted much interest in the past few years, especially the question of how they can be designed and implemented efficiently to perform well in resource-constrained devices like miniature sensor nodes or RFID tags. In this paper, we analyze the performance of the lightweight AEAD schemes ELEPHANT v2, GRAIN-128AEADV2, ISAP v2.0, PHOTON-BEETLE, and ROMULUS v1.3 on the MSP430 family of 16-bit ultra-low-power microcontrollers. All five have in common that they offer large security margins and made it into the last round of the Lightweight Cryptography (LWC) standardization project of the U.S. National Institute of Standards and technology. We describe how these AEAD algorithms can be implemented efficiently in software and introduce Assembly-level optimization techniques for the underlying primitives, which include three permutations, one tweakable block cipher, and one stream cipher. Furthermore, we present numerous detailed benchmarking results (i.e., execution time and code size) for the primitives as well as for the full AEAD algorithms for different lengths of plaintext and associated data. Our benchmarks clearly show that all five AEAD algorithms are much more efficient (up to almost two orders of magnitude) on MSP430 than indicated by results in the literature.

关键词： Lightweight cryptography AEAD algorithm Permutation Block cipher MSP430 architecture

来源：评论

学校读者我要写书评

暂无评论

Employing Clustering Techniques and Association Rules for Client Segmentation and Attribute Dependency Mining in the Domain of Car Insurance 24th

Employing Clustering Techniques and Association Rules for Cl...

引用

24th International TRIZ Future Conference

作者： Mitrea, Delia Mitrea, Paulina Barna, Erik Tech Univ Cluj Napoca Dept Comp Sci Cluj Napoca Romania Life Hard SRL Cluj Napoca Romania

ISBN: (纸本)9783031759253;9783031759239;9783031759222

Segmenting clients according to common characteristics and determining the needs for each group is an important objective in the domain of car insurance. We perform segmentation through specific methods, comparing multiple clustering techniques, considering both classical and deep learning algorithms. Regarding the classical methods, clustering techniques appropriate for both numerical and categorical data were adopted, such as k-means clustering, X-means clustering, respectively k-prototype clustering. Regarding the deep-learning techniques, a stacked denoising autoencoder, followed by conventional clustering techniques, was experimented, the performance being compared with that achieved after the individual application of the classical techniques. After employing the clustering methods, the relevant attributes that separate among clusters were determined, the dependencies between the policy insurance type and other attributes being also analyzed through graphical representations and association rules. The experiments were performed considering the data extracted from a relational database specific for car insurance, containing 1000 instances for the main tables.

关键词： client segmentation clustering (grouping) methods relevant features deep learning techniques association rules car insurance

来源：评论

学校读者我要写书评

暂无评论

Hardware Trojan Key-Corruption Detection with Automated Neural Architecture Search 7th

Hardware Trojan Key-Corruption Detection with Automated Neur...

引用

7th ifip WG 5.5 International Cross-Domain Conference on Internet of Things

作者： Mezzarapa, Franco Goodrich, Jenna Robins, Andey Borowczak, Mike Univ Cent Florida Orlando FL 32816 USA

ISBN: (纸本)9783031819025;9783031819001;9783031818998

This work presents a model hardware trojan which intermittently is capable of corrupting an encryption operation occurring on a device. It asks whether this trojan can be detected via power-based, side-channel attacks only instrumenting the encryption itself, not the control flow of the trojan itself. By applying Automated Machine Learning techniques to search neural architecture, a classification of corrupted encryption operations is able to completely identify whether the operation corresponded with a corrupted operation or not. Through a number of experiments, we demonstrate this fact holds regardless of variable or constant plaintext, rotating encryption keys, or even with different corrupted keys.

关键词： Side Channels Hardware Trojan Power Analysis Deep Neural Network

来源：评论

学校读者我要写书评

暂无评论

Honeypot-Based Data Collection for Dark Web Investigations Using the Tor Network 20th

Honeypot-Based Data Collection for Dark Web Investigations U...

引用

20th ifip WG 11.9 International Conference on Digital Forensics

作者： Singh, Krishan Pal Pilli, Emmanuel Laxmi, Vijay Malaviya Natl Inst Technol Jaipur Rajasthan India

ISBN: (纸本)9783031710278;9783031710254;9783031710247

The Dark Web presents a challenging and complex environment where cyber criminals conduct illicit activities with high degrees of anonymity and privacy. This chapter describes a honeypot-based data collection approach for Dark Web browsing that incorporates honeypots on three isolated virtual machines, including production honeypots, an onion-website-based research honeypot (Honey Onion) offering illegal services and a log server that collects and securely stores the honeypot logs. Experiments conducted over 14 days collected more than 250 requests on the Honey Onion service and in excess of 28,000 chat records from the Dark Web forum. The log server also monitored Honey Onion traffic, providing details such as packet types, timestamps, network data, and HTTP requests. The data collection results provide valuable insights into Dark Web activities, including malicious, benign and uncategorized activities. The data analysis identified common user categories such as malicious actors, researchers and security professionals, and uncategorized actors. The experimental results demonstrate that honeypot-based data collection can advance DarkWeb investigations as well as enable the development of effective cyber security strategies and efforts to combat cyber crime in the Dark Web.

关键词： Dark Web Investigations Data Collection The Onion Router Honey Onion Service Production Honeypot Research Honeypot

来源：评论

学校读者我要写书评

暂无评论

Challenges in Inventive Design Problem Solving with Generative AI: Interactive Problem Definition, Multi-directional Prompting, and Concept Development 24th

Challenges in Inventive Design Problem Solving with Generati...

引用

24th International TRIZ Future Conference

作者： Livotov, Pavel Mas'udah Offenburg Univ Appl Sci Badstr 24 D-77652 Offenburg Germany

ISBN: (纸本)9783031759215;9783031759192;9783031759185

This paper explores the application of generative AI for systematic and inventive problem-solving in engineering design. Utilizing a multi-directional prompting approach, the study investigates the ability of AI chatbots to generate and evaluate innovative concepts based on numerous elementary solution principles. The research involved two sets of experiments with graduate and undergraduate students solving seven engineering design problems. The findings indicate that while generative AI can quickly generate a large number of ideas, it often over-estimates the feasibility and usefulness of its solutions and tends to create overly complex designs. Comparisons of AI evaluations with those conducted by human participants revealed significant differences, highlighting the need for human oversight to ensure practical and contextually relevant outcomes. The experiments also revealed performance differences among various AI models, confirming a bias in self-assessment. Despite these challenges, integrating generative AI with multi-directional prompting using elementary inventive principles, primarily based on TRIZ methodology, proved effective in fostering innovative solutions. The study highlights the potential of simultaneously applying different AI models alongside human expertise to leverage the strengths of both large language models and human technical creativity.

关键词： Generative AI Autonomous Innovation Inventive Design Prompt Engineering Engineering Creativity

来源：评论

学校读者我要写书评

暂无评论

Using Microposture Features and Optical Flows for Deepfake Detection 20th

Using Microposture Features and Optical Flows for Deepfake D...

引用

20th ifip WG 11.9 International Conference on Digital Forensics

作者： Chen, Kai Ma, Duohe Zhang, Zhenchao Tang, Zhimin Wang, Liming Jiang, Junye Chinese Acad Sci Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

ISBN: (纸本)9783031710278;9783031710254;9783031710247

The proliferation of deepfake videos underscores the need to develop reliable detection methods to mitigate their negative consequences. Several deepfake video detection methods achieve satisfactory performance. However, the methods often focus on specific facial features and overlook the noise introduced during feature extraction. This chapter describes a deepfake video detection method that focuses on five key facial features and their changes in video frames and uses optical flows to fine-tune facial landmark points to reduce landmark errors. An efficient model is employed to compute optical flows in frame sequences and refine the actual and predicted landmark points. This facilitates the accurate identification of facial landmark points, including anomalous landmark points. Two recurrent neural networks are employed to capture temporal relationships between landmark points and their movement patterns. The proposed deepfake video detection method achieves high performance on raw and compressed videos.

关键词： Deepfake Video Detection Facial Landmark Extraction Optical Flow Recurrent Neural Network

来源：评论

学校读者我要写书评

暂无评论

Graph-Based Classification of IoT Malware Families Enhanced by Fuzzy Hashing 7th

Graph-Based Classification of IoT Malware Families Enhanced ...

引用

7th ifip WG 5.5 International Cross-Domain Conference on Internet of Things

作者： Mahmoudyar, Nastaran Ghorbani, Ali A. Lashkari, Arash Habibi Univ New Brunswick Fredericton NB Canada

ISBN: (纸本)9783031819025;9783031819001;9783031818998

The proliferation of Internet of Things (IoT) devices has led to an increase in IoT malware, posing a significant cybersecurity threat. Detecting and mitigating this threat is challenging due to the diverse CPU architectures in IoT malware families and the limited resources of IoT devices. Specialized detection methods are needed to identify malware across different platforms, while lightweight mechanisms are required to minimize resource strain. This paper introduces a novel graph-based framework, Aggregated Weighted Graph of Hashes (AWGH), to tackle the CPU diversity challenge. The framework leverages Function Call Graphs (FCGs) and fuzzy hashing to capture the structural and code characteristics of IoT malware. By utilizing static analysis techniques, the framework can efficiently group new malware samples and identify similarities with existing families, even in the case of unknown malware to mitigate potential risks before they cause significant damage. FCGs are generated using IDA Pro [1], and fuzzy hashes are calculated using ssdeep [2]. The framework is implemented in Python and evaluated using a dataset from VirusTotal [3] through 10-fold cross-validation. The experimental results demonstrate the effectiveness of the proposed framework in accurately classifying the IoT malware into IoT malware families across various CPU architectures (MIPS, ARM, i386, PowerPC, and AMD64).

关键词： IoT Malware Family Function Call Graph Fuzzy Hashing Graph-based Malware Classification

来源：评论

学校读者我要写书评

暂无评论

Programmable and Scalable Bit-Sliced VLSI Architecture for Decision Tree-Based Machine Learning Edge Inference 7th

Programmable and Scalable Bit-Sliced VLSI Architecture for D...

引用

7th ifip WG 5.5 International Cross-Domain Conference on Internet of Things

作者： Somesula, Raaga Sai Sivakumar, Sibi Rajagopal Katkoori, Srinivas Univ S Florida Tampa FL 33620 USA

ISBN: (纸本)9783031819025;9783031819001;9783031818998

As the volume and diversity of Internet of Things (IoT) data continues to grow, traditional cloud-based processing methods face significant challenges, including latency, bandwidth constraints, and privacy concerns. Our research focuses on employing decision trees (DTs) [1] as an intelligent filtering mechanism on the edge. We propose a novel programmable and scalable custom ASIC architecture designed for decision tree based Machine Learning (ML) inference. Each bit-slice incorporates two 8-bit SISO input registers connected to an 8-bit comparator for data processing, the output of the comparator drives the select line of Mux, which selects the respective true and false paths. Each bit-slice can be programmed into either a leaf node or a regular node. A leaf node stores classification labels. A regular node compares a feature value with a weight value to decide between true and false paths. Given a DT model, the decision tree can be pre-programmed to store the model weights in respective tree nodes. In the inference phase, feature values are sequentially fed into the DT nodes. After the feature values are loaded the DT tree performs an inference with the classification value generated in the root node. We have implemented and validated the architecture at the layout level using Cadence Virtuoso in 0.5 mu m CMOS technology node. A 5-level DT occupies roughly 90mm(2) area with 22.58 mW of power consumption at a maximum clock speed of 12.8 MHz.

关键词： Decision Tree Edge-AI IoT ASIC VLSI

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 << < 13 14 15 16 17 18 19 20 21 22 > >>

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：