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

60,463 篇 会议
2,738 篇 期刊文献
118 册 图书
12 篇 学位论文
1 件 标准
1 篇 专利
1 篇 科技报告

馆藏范围

63,333 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

32,695 篇 工学
- 26,901 篇 计算机科学与技术...
- 15,208 篇 软件工程
- 11,107 篇 信息与通信工程
- 5,597 篇 电气工程
- 3,642 篇 控制科学与工程
- 2,799 篇 电子科学与技术（可...
- 1,186 篇 动力工程及工程热...
- 1,063 篇 机械工程
- 895 篇 仪器科学与技术
- 874 篇 生物工程
- 666 篇 生物医学工程（可授...
- 493 篇 安全科学与工程
- 470 篇 光学工程
- 464 篇 交通运输工程
- 453 篇 网络空间安全
- 423 篇 建筑学
- 325 篇 材料科学与工程（可...
- 322 篇 土木工程
8,449 篇 理学
- 5,954 篇 数学
- 1,471 篇 统计学（可授理学、...
- 1,183 篇 系统科学
- 1,122 篇 物理学
- 1,040 篇 生物学
5,394 篇 管理学
- 3,931 篇 管理科学与工程(可...
- 1,960 篇 工商管理
- 1,708 篇 图书情报与档案管...
780 篇 法学
- 496 篇 社会学
612 篇 医学
- 464 篇 临床医学
- 398 篇 基础医学(可授医学...
575 篇 经济学
- 572 篇 应用经济学
202 篇 文学
187 篇 农学
160 篇 教育学
107 篇 军事学
18 篇 艺术学
2 篇 哲学

主题

7,054 篇 computer network...
4,661 篇 computer archite...
4,373 篇 computer science
4,157 篇 distributed comp...
3,697 篇 wireless sensor ...
2,958 篇 application soft...
2,777 篇 protocols
2,576 篇 computational mo...
2,300 篇 hardware
2,269 篇 neural networks
2,193 篇 bandwidth
2,152 篇 delay
2,145 篇 distributed comp...
2,040 篇 routing
1,849 篇 costs
1,610 篇 intelligent netw...
1,603 篇 resource managem...
1,509 篇 network topology
1,422 篇 control systems
1,401 篇 ip networks

机构

93 篇 school of comput...
66 篇 ibm thomas j. wa...
59 篇 department of co...
59 篇 department of co...
49 篇 school of comput...
45 篇 school of electr...
38 篇 department of sy...
36 篇 school of comput...
32 篇 college of compu...
32 篇 department of el...
29 篇 school of comput...
29 篇 department of el...
29 篇 department of el...
28 篇 department of el...
28 篇 ibm thomas j. wa...
27 篇 inria
27 篇 department of el...
27 篇 department of sy...
27 篇 department of co...
27 篇 shandong provinc...

作者

50 篇 m. takizawa
26 篇 kowalski dariusz...
26 篇 li li
26 篇 s.k. das
25 篇 santoro nicola
23 篇 k.g. shin
23 篇 kuhn fabian
23 篇 peleg david
23 篇 p.k. srimani
23 篇 yu wang
23 篇 duato j.
22 篇 dhabaleswar k. p...
22 篇 l.m. ni
22 篇 klaus wehrle
21 篇 sens pierre
21 篇 xiaodong lu
20 篇 jun wang
19 篇 guohong cao
19 篇 y. shibata
18 篇 torsten hoefler

语言

62,278 篇 英文
606 篇 其他
411 篇 中文
51 篇 葡萄牙文
7 篇 法文
4 篇 西班牙文
3 篇 德文
3 篇 日文
3 篇 俄文

检索条件"任意字段=International Symposium on Computer Networks and Distributed Systems"

共 63334 条记录，以下是4961-4970 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：

Multi-Scale Sampling Based MLP networks for Anomaly Detection in Multivariate Time Series

Multi-Scale Sampling Based MLP Networks for Anomaly Detectio...

引用

international Conference on Parallel and distributed systems (ICPADS)

作者： Haojie Li Hongzuo Xu Wei Peng Chiran Shen Xianwen Qiu College of Computer National University of Defense Technology Changsha China

Multivariate time series data are produced in various domains, including AIOps, space crafts, and healthcare. Identifying anomalies within them is significant to ensure the stability of target systems. Current anomaly detectors mainly focus on devising intricate network structures based on recurrent neural networks, Transformers, or graph neural networks to model the temporal and inter-variate dependencies of the input time series. Nevertheless, complex models often lead to computational burden in training and inferencing stage. Also, system operators have to understand the technical details of these complex models to fine-tune them or add new modules for different needs. This motivates us to consider an intriguing question: can we construct an anomaly detection model merely based on simple networks? In this paper, we propose FlightAD, a light but effective anomaly detection model using only multi-layer perceptron (MLP) networks. FlightAD applies MLP networks on top of a multi-scale sampling strategy, followed by an informationfusing mechanism to fuse the learned features. More specific, the multi-scale sampling strategy is used to extract abundant temporal patterns of time series, and the MLP blocks applied to it can simultaneously model the dependencies along the time axis and dependencies between different sampled sub-sequences (i.e., different variables). Finally, we wield an informationfusing module to fully integrate the learned multi-scale features. Extensive experiments on six real-world datasets show that our model outperforms seven state-of-the-art competitors on average by 2.1%-18.2% in F 1 score and 3.8%-38.9% in AUC-PR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Abnormal Behavior in Activities of Daily Life Using Novelty Detection 19th

Identification of Abnormal Behavior in Activities of Daily L...

引用

19th European-Alliance-for-Innovation (EAI) international Conference on Mobile and Ubiquitous systems - Computing, Networking and Services (MobiQuitous)

作者： Freitas, Mauricio Piai, Vinicius de Aquino Dazzi, Rudimar Teive, Raimundo Parreira, Wemerson Fernandes, Anita Pires, Ivan Miguel Quietinho Leithardt, Valderi Reis Univ Vale Itajai Artificial Intelligence Lab BR-88302901 Itajai Brazil Univ Beira Interior Inst Telecomunicacoes P-6200001 Covilha Portugal Inst Politecn Portalegre Res Ctr Endogenous Resources Valorizat VALORIZA P-7300555 Portalegre Portugal Univ Lusofona Humanidades & Tecnol COPELABS P-1749024 Lisbon Portugal Univ Vale Itajai Lab Embedded & Distributed Syst BR-88302901 Itajai Brazil

ISBN: (纸本)9783031347757;9783031347764

The world population is aging at a rapid pace. According to the WHO (World Health Organization), from 2015 to 2050, the proportion of elderly people will practically double, from 12 to 22%, representing 2.1 billion people. From the individual's point of view, aging brings a series of challenges, mainly related to health conditions. Although, seniors can experience opposing health profiles. With advancing age, cognitive functions tend to degrade, and conditions that affect the physical and mental health of the elderly are disabilities or deficiencies that affect Activities of Daily Living (ADL). The difficulty of carrying out these activities within the domestic context prevents the individual from living independently in their home. Abnormal behaviors in these activities may represent a decline in health status and the need for intervention by family members or caregivers. This work proposes the identification of anomalies in the ADL of the elderly in the domestic context through Machine Learning algorithms using the Novelty Detection method. The focus is on using available ADL data to create a baseline of behavior and using new data to classify them as normal or abnormal daily. The results obtained using the E-Health Monitoring database, using different Novelty Detection algorithms, have an accuracy of 91% and an F1-Score of 90%.

关键词： Novelty Detection Anomaly Detection Activities of Daily Living Machine Learning One-Class Support Vector Machine (OC-SVM) Local Outlier Factor (LOF)

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Wireless Water Quality Monitoring System

Design and Implementation of a Wireless Water Quality Monito...

引用

computer Technology and Information Science (ISCTIS), international symposium on

作者： Jiayue Zhao Zhijie Hu Shenrui Bing Xiaoyue Yang School of Information Engineering Xi’an Eurasia University Xi’an China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

With the development of technology and the economy, people's living standards have significantly improved. However, environmental pollution has become increasingly severe, especially water quality pollution, which is closely related to people's daily lives. The current water quality monitoring systems have drawbacks such as single monitoring indicators, mostly wired monitoring, and long monitoring cycles. Based on this, this study designs and implements a wireless water quality monitoring system that can monitor multiple water quality parameters in real-time and achieve remote data viewing and alarming through wireless communication. Firstly, the system collects data such as pH, oxidation-reduction potential (ORP), and temperature through sensors. Then, the collected data is processed by the STM32F103C8T6 microcontroller and transmitted to the gateway node via the LoRa module. Finally, the gateway node uploads the data to a cloud platform for remote viewing on an upper computer. Additionally, the upper computer can modify the threshold values in manual mode. When the relevant parameters exceed the set thresholds, the system will issue an alarm to promptly alert users to changes in water quality. The establishment of a real-time water quality monitoring system not only helps in promptly detecting abnormal water quality conditions but also provides strong data support for relevant departments, aiding them in formulating more scientific and targeted improvement measures.

关键词： Temperature sensors Temperature measurement Wireless communication Wireless sensor networks Microcontrollers Water quality Real-time systems Sensor systems Sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

Electronically Steerable Mobile Optical-Wireless Mesh-Network

Electronically Steerable Mobile Optical-Wireless Mesh-Networ...

引用

Annual IEEE systems Conference

作者： Suman Bhunia Yicheng Qian Mahmudur Khan Department of Computer Science and Software Engineering Miami University Oxford Ohio USA Department of Electrical & Computer Engineering and Computer Science York College of Pennsylvania USA

ISBN: (数字)9798350358803

ISBN: (纸本)9798350358810

Free Space Optical (FSO) Communication provides better communication coverage and higher data rate. However, FSO requires neighboring nodes to schedule their transceiver towards each other for communication, which makes multi-hop communication challenging. In this paper, we present an FSO mesh network system that enables data transfer among multiple nodes. Each node is equipped with a multi-transceiver FSO communication module and a low-bitrate long-range (LoRa) omnidirectional radio frequency (RF) communication module. Scheduling remains a significant challenge for wireless communication using highly directional transceivers such as FSO. Hence, we propose a distributed coordination and communication method that utilizes a supplementary omnidirectional LoRa channel for distributed coordination among the nodes in the mesh network. In the proposed scheme, a per-packet beam scheduling is proposed where the assisting low bandwidth omnidirectional channel helps the higher data rate directional channel to coordinate and face the line of sight. Our proposed method enables communication via both single-hop and multi-hop FSO links. We also present the implementation of a proof-of-concept prototype of an RF-FSO communication module comprising multiple FSO transceivers and a LoRa transceiver using commercial off-the-shelf devices (COTS). We demonstrate the effectiveness of our proposed FSO mesh network system through real test-bed experiments using the developed prototype.

关键词： Wireless communication Radio frequency Mesh networks Schedules Free-space optical communication Protocols Wireless mesh networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Probabilistic Packet Marking for AS Traceback

Efficient Probabilistic Packet Marking for AS Traceback

引用

2021 international symposium on networks, computers and Communications, ISNCC 2021

作者： Nur, Abdullah Yasin University Of New Orleans Department Of Computer Science New OrleansLA70148 United States

ISBN: (纸本)9780738113166

distributed Denial of Service (DDoS) attacks are among the most perilous attack types in the Internet. In addition to the significant harms for the victim site, intermediate Autonomous systems (AS) are also unintended victims in DDoS attacks. The main goal of a DDoS defense mechanism is to reduce the attack's effect as close as possible to their sources to prevent malicious traffic in the Internet. In this work, we proposed an AS traceback scheme to infer AS level forward paths from attacker sites to a victim site. We utilize the 16-bit IP ID field and 6-bit from the ToS field in the IPv4 protocol. In our method, only the ingress routers of ASes probabilistically mark the packet with their AS numbers. We propose an encoding technique to reduce the number of required packets significantly. The destination site can construct the path after receiving enough packets. Our results show that a victim site can construct the forward path from an attacker site after receiving 10.14 packets on the average. Compared to the other techniques, our approach requires fewer packets to construct the paths from attacker sites to a victim site. © 2021 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

HSDP: Accelerating Large-scale Model Training via Efficient Sharded Data Parallelism

HSDP: Accelerating Large-scale Model Training via Efficient ...

引用

international symposium on Parallel and distributed Processing with Applications, ISPA

作者： Yanqi Hao Zhiquan Lai Wei Wang Shengwei Li Weijie Liu Keshi Ge Dongsheng Li National Key Laboratory of Parallel and Distributed Computing(PDL) College of Computer National University of Defense Technology Changsha China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Large deep neural network (DNN) models have demonstrated exceptional performance across diverse downstream tasks. Sharded data parallelism (SDP) has been widely used to reduce the memory footprint of model states. In a DNN training cluster, a device usually has multiple inter-device links that connect to other devices, like NVLink and InfiniBand. However, existing SDP approaches employ a single link at any given time, encountering challenges in efficient training due to significant communication overheads. We observe that the inter-device links can work independently without affecting each other. To reduce the fatal communication overhead of distributed training of large DNNs, this paper introduces HSDP, an efficient SDP training approach that enables the simultaneous utilization of multiple inter-device links. HSDP partitions models in a novel fine-grained manner and orchestrates the communication processes of partitioned parameters while considering inter-device links. This design enables concurrent communication execution and reduces communication overhead. To further optimize the training performance of HSDP, we propose a HSDP planner. The HSDP planner first abstracts the model partition and execution of HSDP into a communication parallel strategy, and builds a cost model to estimate the performance of each strategy. We then formulate the strategy searching as an optimization problem and solve it with an off-the-shelf solver. Evaluations on representative DNN workloads demonstrate that HSDP achieves up to 1.30× speedup compared to the state-of-the-art SDP training approaches.

关键词： Training Performance evaluation Costs distributed databases Artificial neural networks Parallel processing Throughput Search problems Data models Optimization

来源：评论

学校读者我要写书评

暂无评论

A Digital Twin Framework for Edge Server Placement in Mobile Edge Computing 4

A Digital Twin Framework for Edge Server Placement in Mobile...

引用

4th international Informatics and Software Engineering Conference, IISEC 2023

作者： Bozkaya, Elif National Defence University Turkish Naval Academy Department of Computer Engineering Istanbul Turkey

ISBN: (纸本)9798350318036

Mobile edge computing is considered a key technology for upcoming 6G networks, which allows real-Time processing of large amounts of data at the network edge. Specifically, considering the strict requirements of new services and Internet of Things (IoT) applications in different domains, such as healthcare, transportation, smart city, smart grid and more, increased mobile data traffic can be handled with the benefits of this technology. As an enabler for these interesting applications for 6G, mobile edge computing deploys edge servers at the network edge, enabling the offloading of computation tasks to reduce processing latency. However, achieving cost-effective placement of edge servers presents a challenge in effectively distributing the workload among them while simultaneously minimizing overall system cost. To address this issue, we propose a digital twin framework, where digital twin technology is used to model virtual replicas of edge servers in the real world and simulate their behavior. Then, the proposed edge server placement framework can place the edge servers and balance the workload of the edge servers. The objective of the proposed strategy is to minimize the system cost in terms of processing time and access delay. The edge server placement is formulated as an optimization problem in mobile edge computing systems and a genetic-based algorithm is introduced to address this issue. Simulation results demonstrate the efficiency of our proposed digital twin framework achieving less system cost compared to other benchmark methods. © 2023 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based Speech Signal for COVID-19 Diagnostics 6

Artificial Intelligence-based Speech Signal for COVID-19 Dia...

引用

6th international Conference on Future networks and distributed systems, ICFNDS 2022

作者： Alfaidi, Aseel Alshahrani, Abdullah Aljohani, Maha Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Saudi Arabia Department of Software Engineering College of Computer Science and Engineering University of Jeddah Saudi Arabia

ISBN: (纸本)9781450399050

The speech signal has numerous features that represent the characteristics of a specific language and recognize emotions. It also contains information that can be used to identify the mental, psychological, and physical states of the speaker. Recently, the acoustic analysis of speech signals offers a practical, automated, and scalable method for medical diagnosis and monitoring symptoms of many diseases. In this paper, we explore the deep acoustic features from confirmed positive and negative cases of COVID-19 and compare the performance of the acoustic features and COVID-19 symptoms in terms of their ability to diagnose COVID-19. The proposed methodology consists of the pre-trained Visual Geometry Group (VGG-16) model based on Mel spectrogram images to extract deep audio features. In addition to the K-means algorithm that determines effective features, followed by a Genetic Algorithm-Support Vector Machine (GA-SVM) classifier to classify cases. The experimental findings indicate the proposed methodology's capability to classify COVID-19 and NOT COVID-19 from acoustic features compared to COVID-19 symptoms, achieving an accuracy of 97%. The experimental results show that the proposed method remarkably improves the accuracy of COVID-19 detection over the handcrafted features used in previous studies. © 2022 ACM.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

(POSTER) Towards Data Dissemination Policy Prediction for Constrained Environments Using Analytics

(POSTER) Towards Data Dissemination Policy Prediction for Co...

引用

international Conference on distributed Computing in Sensor systems (DCOSS)

作者： Loic Guegan Issam Raïs Otto Anshus Department of Computer Science UiT The Arctic University of Norway Tromso Norway

In Cyber-Physical systems (CPS) such as Wireless Sensors networks (WSN), disseminating data is crucial. Under energy constraints with limited communications capabilities, performing data dissemination is challenging. In such contexts, common data dissemination methods cannot be used. Nodes must rely on device-to-device communications policies to mitigate the impact of communications on the nodes energy consumption. However, depending on nodes configuration (up-times duration, wireless technology capabilities and energy consumption), choosing a suitable communication policy is challenging. This work exposes the problem statement for using analytic algorithms to predict the most suitable device-to-device communication policy, for a given node configuration, to match a given coverage and energy consumption target in a constrained environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of the impact of visual attacks on the characteristics of neural networks in image recognition 14

Analysis of the impact of visual attacks on the characterist...

引用

14th international symposium on Intelligent systems

作者： Andriyanov, N. A. Dementiev, V. E. Kargashin, Yu D. Financial Univ Govt Russian Federat Leningradsky AveH 49 Moscow 125993 Russia Ulyanovsk State Tech Univ Severny Venets StH 32 Ulyanovsk 432027 Russia JSC RPC Istok Vokzalnaya StH 2 Fryazino 141190 Moscow Region Russia

The article discusses various methods of visual attacks on neural networks such as the introducing of additive white Gaussian noise, pixel maximization and minimization of brightness, maximization and minimization of brightness in the area. For well-known datasets (MNIST, Kaggle dataset called as Dogs_vs_Cats), the dependence of the proportion of correct recognitions on the proportion of distorted images in the test sample is studied. networks such as VGG-16, Inception_v3, networks without training transfer are analyzed. The characteristics of the accuracy of such networks from the noise level in the image, from the size of the attack areas are obtained. The probabilities of belonging to a given class for various images in various attacks are analyzed. As a method for combating visual attacks, it is proposed to single out a new class during training: "poor image". By selecting valid images by dumping "bad images" by the neural network, accuracy is improved even in the case of a large volume of distorted images in the test sample. The accuracy of such a network is compared for N classes and for (N + 1) classes of images. Ways of further research and ideas of alternative methods of combating visual attacks on neural networks are formulated. (C) 2021 The Authors. Published by Elsevier B.V.

关键词： Convolutional neural networks pattern recognition visual attacks VGG-16 Inception_v3 image processing

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 << < 491 492 493 494 495 496 497 498 499 500 > >>

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：