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

7,748 篇 会议
98 篇 期刊文献
55 册 图书

馆藏范围

7,901 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,793 篇 工学
- 2,017 篇 计算机科学与技术...
- 1,391 篇 软件工程
- 654 篇 控制科学与工程
- 502 篇 信息与通信工程
- 497 篇 电气工程
- 252 篇 机械工程
- 206 篇 仪器科学与技术
- 186 篇 电子科学与技术（可...
- 136 篇 生物医学工程（可授...
- 121 篇 生物工程
- 91 篇 光学工程
- 79 篇 网络空间安全
- 78 篇 动力工程及工程热...
- 67 篇 化学工程与技术
- 64 篇 力学（可授工学、理...
- 53 篇 材料科学与工程（可...
- 51 篇 交通运输工程
1,051 篇 理学
- 680 篇 数学
- 288 篇 统计学（可授理学、...
- 220 篇 物理学
- 178 篇 系统科学
- 147 篇 生物学
- 79 篇 化学
671 篇 管理学
- 549 篇 管理科学与工程(可...
- 199 篇 工商管理
- 161 篇 图书情报与档案管...
128 篇 医学
- 99 篇 临床医学
- 80 篇 基础医学(可授医学...
68 篇 法学
- 67 篇 社会学
49 篇 经济学
- 48 篇 应用经济学
33 篇 教育学
20 篇 农学
19 篇 军事学
10 篇 文学
2 篇 艺术学

主题

1,885 篇 computational mo...
1,021 篇 measurement
440 篇 computer archite...
423 篇 neural networks
409 篇 predictive model...
348 篇 computer science
293 篇 accuracy
285 篇 biological syste...
258 篇 analytical model...
239 篇 noise measuremen...
224 篇 computer simulat...
221 篇 real-time system...
217 篇 training
216 篇 brain modeling
215 篇 mathematical mod...
211 篇 feature extracti...
187 篇 power system mod...
181 篇 neurons
178 篇 data models
175 篇 control systems

机构

20 篇 school of comput...
17 篇 department of el...
15 篇 school of electr...
14 篇 budapest univ te...
13 篇 chitkara univers...
13 篇 school of comput...
12 篇 department of co...
11 篇 department of co...
10 篇 college of compu...
10 篇 college of compu...
9 篇 tsinghua univers...
8 篇 department of el...
8 篇 department of co...
7 篇 school of comput...
7 篇 graphic era deem...
7 篇 school of comput...
7 篇 school of comput...
7 篇 peng cheng labor...
7 篇 school of contro...
6 篇 college of compu...

作者

11 篇 towsley don
10 篇 varró dániel
9 篇 wei wang
8 篇 liu alex x.
8 篇 anon
7 篇 liu yang
7 篇 wei li
7 篇 wang jia
6 篇 li zhang
6 篇 byung-ju yi
6 篇 reiner r. dumke
6 篇 yang liu
5 篇 deepak banerjee
5 篇 chunyan miao
5 篇 li li
5 篇 t.m. khoshgoftaa...
5 篇 rizzi antonello
5 篇 j.c. principe
5 篇 sakorn mekruksav...
5 篇 bergmann gábor

语言

7,792 篇 英文
84 篇 其他
26 篇 中文
5 篇 俄文

检索条件"任意字段=Joint International Conference on Measurement and Modeling of Computer Systems"

共 7901 条记录，以下是731-740 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：

GRU in Anomaly Detection for IoT: A Comparative Study

GRU in Anomaly Detection for IoT: A Comparative Study

引用

IEEE Students' conference on Electrical, Electronics and computer Science (SCEECS)

作者： V Sivakumar Aenugu Harshith Reddy Allam Nehal Varma School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology (VIT) Vellore India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

In this paper, we present a comparative analysis of Gated Recurrent Unit (GRU) models against other deep learning architectures, particularly focusing on anomaly detection and failure prediction within IoT-based industrial systems. GRU’s simplified structure, which accelerates training and reduces memory usage, makes it well-suited for real-time applications in IoT, outperforming its Long Short-Term Memory (LSTM) counterparts in many cases. However, its limitations in handling long-term dependencies, noisy data, and larger datasets can impede performance in more complex scenarios. Several studies have explored hybrid models that combine GRU with architectures like Transformers and CNNs to improve accuracy, especially in environments with irregular and noisy data. This paper discusses the computational efficiency of GRU and its application in edge computing while addressing its weaknesses through hybrid approaches. By leveraging insights from recent literature and projects, we evaluate GRU’s effectiveness in IoT applications and propose a hybrid GRU-Transformer model to enhance anomaly detection capabilities.

关键词： Training Computational modeling Predictive models Transformers Real-time systems Noise measurement Anomaly detection Long short term memory Industrial Internet of Things Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Research on E-Commerce Image Recognition Search Engine Optimization System Based on computer Artificial Intelligence

Research on E-Commerce Image Recognition Search Engine Optim...

引用

Image Processing and computer Applications (ICIPCA), IEEE international conference on

作者： Daocai Wang Chongqing Electronic Information College Chongqing China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

This paper proposes an electronic commerce system based on Java platform. The main content of the platform is to obtain the user's interest characteristics, build the model and calculate the similarity. This paper generates a preliminary proposal template and set thresholds during data processing. The vector space modeling method is used to classify different types of goods. By using the joint optimal convolutional neural network based on SoftMax Loss and Triplet Loss, a ternal embedded tag structure is constructed to realize similarity detection at each level. Using WebLogic technology and J2EE architecture to achieve all business logic and load balance. The JSP/Servlet web program has been loaded into the web container. An entity Beans is deployed in the EJB container. The results show that this method can not only achieve better classification performance, but also improve the image retrieval accuracy of different levels of label structures on fine-grained data sets. This is of great significance in the recommendation of related products in e-commerce.

关键词： Java Image recognition Search methods Containers Search engines Vectors Electronic commerce Proposals Optimization Recommender systems

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Cyber Security Proactive Threat Detection and Response systems

AI-Enhanced Cyber Security Proactive Threat Detection and Re...

引用

Sentiment Analysis and Deep Learning (ICSADL), international conference on

作者： Venkata Sai Swaroop Reddy Nallapareddy Siva Koteswara Rao Katta Department of Software Engineering Sony Interactive Entertainment Austin Department of Mechanical Engineering KIETW India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The introduction of AI-Enhanced Cyber Threat Detection, which aids in improving organizational security through sophisticated algorithms, has caused a paradigm change in cybersecurity. The proactive posture of AI-driven detection systems that autonomously sift through massive data sets to identify patterns suggestive of cyber intrusions and attacks is explored in this research study. These tools relieve human analysts of routine tasks like threat identification and incident response, freeing them to focus on more strategic matters like making decisions and developing mitigation measures. Artificial intelligence (AI) based detection also makes monitoring network activities easier in real-time, increasing operational efficiency and decreasing dwell time. Another approach to accomplishing this in cybersecurity is combining different technologies, including threat intelligence platforms, with AI or SOAR systems. Further research and improved collaboration are needed to strengthen AI-enabled cyber threat identification in the face of obstacles like adversarial attacks and ethical concerns. Given the prevalence of modern e-crimes, this paper stresses the need for joint defence strategies and proactive cybersecurity measures to safeguard digital assets.

关键词： Explainable AI Organizations Telecommunication traffic Threat assessment Real-time systems Time factors Artificial intelligence computer security Stress Stress measurement

来源：评论

学校读者我要写书评

暂无评论

FA-LiteSeg: A Fully-Attention Enhanced Real-Time Semantic Segmentation Model

FA-LiteSeg: A Fully-Attention Enhanced Real-Time Semantic Se...

引用

IEEE international conference on Power, Intelligent Computing and systems (ICPICS)

作者： Qice Zhang Central South University Changsha Hunan China

ISBN: (数字)9798350374315

ISBN: (纸本)9798350374322

With the rapid development of computer vision technology, real-time semantic segmentation plays an increasingly important role in many fields. PP-LiteSeg is a real-time semantic segmentation model which is lightweight with encoding-decoding framework and shows excellent performance. However, it exhibits limitations in feature extraction, a critical component for high-performance segmentation. For this purpose, we proposes a Fully-Attention Enhanced Real-Time Semantic Segmentation model (FA-LiteSeg), designed to bolster real-time semantic segmentation capabilities. Specifically, our approach integrates a novel Fully Attention Block within the encoder, facilitating more precise feature extraction and enhancing the model's detail recognition and edge delineation. Experiments on the Cityscapes and Cam Vid datasets demonstrate that our proposed FA-LiteSeg achieves a 1.13% and 0.21% increase in mean Intersection over Union (mIoU) scores over PP-LiteSeg, respectively. Notably, FA-LiteSeg markedly outperforms its predecessor in scenarios featuring intricate backgrounds and diminutive objects, showcasing superior detail capture and edge segmentation. Extensive experiments corroborate FA-LiteSeg's superiority in semantic segmentation, particularly in complex and challenging environments.

关键词： measurement computer vision Accuracy Semantic segmentation Computational modeling Image edge detection Semantics Refining Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Understanding power variation and its implications on performance optimization on the Cori supercomputer 12

Understanding power variation and its implications on perfor...

引用

12th international Workshop on Performance modeling, Benchmarking and Simulation of High Performance computer systems held as part of the 33rd ACM/IEEE international conference for High Performance Computing, Networking, Storage and Analysis

作者： Bhalachandra, Sridutt Austin, Brian Wright, Nicholas J. Lawrence Berkeley Natl Lab Berkeley CA 94720 USA

ISBN: (纸本)9781665411189

Power is increasingly becoming a limiting factor in supercomputing. The performance and scale of future high-performance computing systems will be determined by how efficiently they manage their power budgets. Therefore any amount of unused power is forsaken performance. Regardless of the processors chosen for a future system, it will be necessary to understand power variation and its implications on performance optimization. In this paper, we identify and quantify the factors that affect the power consumption of the NERSC Cori supercomputer at different levels of the system hierarchy. Our study presents node-level power-performance trade-offs for fundamental computational patterns. We show that I/O activity and load imbalance are common causes of job-level power variation among jobs in Cori's production workload. We quantitatively attribute system-level power variation to three sources and find that 86% of the variation is due to temporal variation in application behavior over the duration of a job. Furthermore, our analysis reveals that under typical workload conditions, the Cori system's power budget could accommodate up to 60% more nodes.

关键词： Schedules Power measurement Power demand Heuristic algorithms Computational modeling Production Supercomputers

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph Augmentation for Recommendation System

Dynamic Graph Augmentation for Recommendation System

引用

international conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Xiang Zongyi School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

With the explosive growth of online information, recommender systems play a key role to alleviate such information overload. There is a lot graph information in the recommender system and graph neural network (GNN) has superiority in graph represent learning, GNN have become the new state-of-the-art approach of recommender system recently. However, unlike the graphs used in the GNN research field, the user-item bipartite graphs extracted from recommender systems often contain abnormal connection information, also known as false-positive edges. These edges will cause GNN to learn different interest users with similar embedding. At the same time, the user-item bipartite graph also lacks some potential edges for some practical reasons. In order to solve the question mentioned above. We propose a Dynamic Graph Augmentation model based on Teacher-Student framework. Through the pre-trained teacher model, the student model is guided to make flexible changes to the structure of the graph. Then the student model feedback what it has learned to the teacher model, and the teacher model fine-tunes itself to accommodate the student model. This work outperformed the baseline model on MovieLens-100k dataset.

关键词： Heuristic algorithms Computational modeling Noise Information processing Media Graph neural networks Explosives Bipartite graph Noise measurement Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Extraction of c- F os Protein Regions from Mouse Brain Slice Images using Multi-channelization, 1 x 1 Convolution and U -Net

Extraction of c- F os Protein Regions from Mouse Brain Slice...

引用

international Symposium on Soft Computing and Intelligent systems (SCIS)

作者： Ziyue Wang Hibiki Okamura Shijie Luo Yu Hayashi Hotaka Takizawa Master's Program in Computer Science University of Tsukuba Tsukuba Japan Ph.D. Program in Humanics International Institute for Integrative Sleep Medicine University of Tsukuba Tsukuba Japan International Institute for Integrative Sleep Medicine University of Tsukuba Tsukuba Japan Institute of Systems and Information Engineering Academic Computing & Communications Center University of Tsukuba Tsukuba Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

This study proposed a novel extraction method of c-Fos protein regions in DAB(3,3‘-diaminobenzidine)-stained mouse brain slice images using the U-Net model combined with the multi-channelization and $1\times 1$ convolution techniques. Our U-Net m odel, called $1\times 1$ conv U-Net, was applied to three DAB- strainedmouse slice images whose resolutions were $1000\mathrm{x}1000$ pixels. The experimental results demonstrated that the $1\times 1$ conv U-Net outperformed the conventional U-Net.

关键词： Proteins Visualization Image resolution Image analysis Convolution Feature extraction Brain modeling Biology Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Proceedings of the 21st international conference on Business Process Management , BPM 2023

Proceedings of the 21st International Conference on Business...

引用

Proceedings of the 21st international conference on Business Process Management , BPM 2023

ISBN: (纸本)9783031416194

The proceedings contain 27 papers. The special focus in this conference is on Business Process Management. The topics include: Inferring Missing Entity Identifiers from Context Using Event Knowledge Graphs;process Channels: A New Layer for Process Enactment Based on Blockchain State Channels;action-Evolution Petri Nets: A Framework for modeling and Solving Dynamic Task Assignment Problems;context-Based Activity Label-Splitting;verifying Resource Compliance Requirements from Natural Language Text over Event Logs;from Text to Performance measurement: Automatically Computing Process Performance Using Textual Descriptions and Event Logs;agent Miner: An Algorithm for Discovering Agent systems from Event Data;interactive Multi-interest Process Pattern Discovery;Increasing RPA Adoption: An Experiment on Countermeasures for Status Quo Bias;can I Trust My Simulation Model? Measuring the Quality of Business Process Simulation Models;stochastic-Aware Comparative Process Mining in Healthcare;on the Cognitive Effects of Abstraction and Fragmentation in Modularized Process Models;not Here, But There: Human Resource Allocation Patterns;a Novel Multi-perspective Trace Clustering Technique for IoT-Enhanced Processes: A Case Study in Smart Manufacturing;the Impact of Process Complexity on Process Performance: A Study Using Event Log Data;Deviation from Standards and Performance in Knowledge-Intensive Processes: Evidence from the Process of Selling Customized IT Solutions;benevolent Business Processes - Design Guidelines Beyond Transactional Value;PEM4PPM: A Cognitive Perspective on the Process of Process Mining;event Abstraction for Partial Order Patterns;incremental Discovery of Process Models Using Trace Fragments;approximating Multi-perspective Trace Alignment Using Trace Encodings;POWL: Partially Ordered Workflow Language;polynomial-Time Conformance Checking for Process Trees;investigating the Influence of Data-Aware Process States on Activity Probabilities in Simulation Models:

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection on Gas Pipeline Operational Data Using Classic Seasonal Decomposition and Level Shift Anomaly Detection Architecture

Anomaly Detection on Gas Pipeline Operational Data Using Cla...

引用

Advancement in Data Science, E-learning and Information systems (ICADEIS), international conference on

作者： Akmal Muzakki Bakir Aditya Firman Ihsan Widi Astuti School of Computing Telkom University Bandung Indonesia

ISBN: (数字)9798331513320

ISBN: (纸本)9798331513337

Gas pipeline infrastructure is critical to energy distribution, but its operational existence is often threatened by anomalies such as leaks, malfunctions, and system disruptions. Early detection of these anomalies is critical to prevent safety hazards, operational inefficiencies, and economic losses. This paper proposes an anomaly detection framework using Classic Seasonal Decomposition and Level Shift Anomaly Detection methods for frequency selection and labeling processes, as well as LSTM and VAE-GAN algorithms for anomaly detection. The dataset consists of time-series sensor measurements, including pressure, temperature, energy flow rate, and gas composition. Classic Seasonal Decomposition isolates trend, seasonal, and residual components, enhancing periodic anomaly detection. Meanwhile, Level Shift Anomaly Detection identifies abrupt changes in data levels that signal critical events. LSTM leverages temporal dependencies to detect anomalies with high accuracy in data with strong sequential patterns, while VAE-GAN is effective in modeling complex data distributions and capturing anomalies in datasets with less obvious patterns. Experimental results demonstrate the effectiveness of the proposed approach, with model performance evaluated using F1-Score for each LSTM and VAE-GAN model. The proposed framework shows great potential for peering into real-time monitoring systems, improving operational efficiency, supporting data-driven decision making, and significantly reducing the risk of system failure.

关键词： Temperature measurement Computational modeling Pipelines Decision making computer architecture Market research Data models Real-time systems Anomaly detection Long short term memory

来源：评论

学校读者我要写书评

暂无评论

m2Vib: 2D Vibration measurement Using a Single mmWave Radar

m2Vib: 2D Vibration Measurement Using a Single mmWave Radar

引用

international conference on Parallel and Distributed systems (ICPADS)

作者： Haolin Wang Wei Xu Zezhao Li Yanni Yang Zhijian Huang School of Computer Science and Technology Shandong University Qingdao China National Key Laboratory of Science and Technology on Information System Security China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Two-dimensional vibration measurement is essential for monitoring structure and machine health, especially providing more information than those 1D solutions. However, most existing 2D vibration monitoring methods require multi-dimension sensors, which can be costly for large-scale deployment. In this paper, we propose $m^measurement$ Vib, the first work that can realize accurate 2D vibration measurement using a single mmWave radar. Our system is achieved by creating a virtual radar with non-line-of-sight (NLoS) signals from a nearby reflector (e.g., wall) to offer the 2nd-dimension vibration observations. We further establish a geometric model to unveil the relationship between 2D vibration displacement and mmWave signal. Such an idea still encounters challenges from significantly attenuated NLoS signals and low-resolution geometric parameters from the commercial mmWave radar. Thus, we design a new retroreflector to enhance NLoS signals and advanced signal processing methods to obtain fine-grained geometric parameters. Extensive experimental results show that we can achieve sub-mm level 2D vibration measurement with an average vibration displacement error of 62.2 um and frequency error of 0.01 Hz in the X-axis and Y-axis.

关键词： Vibrations Radar measurements Geometric modeling Radar Displacement measurement Vibration measurement Signal processing Frequency measurement Millimeter wave communication Monitoring

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 << < 70 71 72 73 74 75 76 77 78 79 > >>

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：