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

2,236 篇 会议
13 册 图书
5 篇 期刊文献

馆藏范围

2,254 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,606 篇 工学
- 1,382 篇 计算机科学与技术...
- 966 篇 软件工程
- 321 篇 控制科学与工程
- 241 篇 信息与通信工程
- 218 篇 电气工程
- 177 篇 生物工程
- 129 篇 生物医学工程（可授...
- 91 篇 机械工程
- 76 篇 交通运输工程
- 57 篇 光学工程
- 50 篇 电子科学与技术（可...
- 43 篇 化学工程与技术
- 42 篇 安全科学与工程
- 35 篇 仪器科学与技术
- 32 篇 土木工程
466 篇 理学
- 237 篇 数学
- 182 篇 生物学
- 101 篇 统计学（可授理学、...
- 81 篇 物理学
- 47 篇 系统科学
- 41 篇 化学
434 篇 管理学
- 287 篇 管理科学与工程(可...
- 162 篇 图书情报与档案管...
- 79 篇 工商管理
170 篇 医学
- 163 篇 临床医学
- 81 篇 基础医学(可授医学...
- 54 篇 药学(可授医学、理...
- 34 篇 公共卫生与预防医...
76 篇 教育学
- 74 篇 教育学
49 篇 法学
- 44 篇 社会学
30 篇 经济学
18 篇 农学
2 篇 军事学

主题

173 篇 machine learning
160 篇 deep learning
135 篇 training
100 篇 data models
78 篇 feature extracti...
76 篇 accuracy
70 篇 data mining
67 篇 neural networks
66 篇 predictive model...
61 篇 reinforcement le...
57 篇 computational mo...
52 篇 support vector m...
46 篇 real-time system...
42 篇 machine learning...
39 篇 training data
39 篇 artificial intel...
36 篇 visualization
35 篇 learning systems
35 篇 adaptation model...
31 篇 big data

机构

18 篇 kazan natl res t...
12 篇 king mongkuts un...
10 篇 institute of inf...
9 篇 school of cyber ...
7 篇 chitkara univers...
7 篇 college of compu...
6 篇 king mongkuts un...
6 篇 department of co...
6 篇 the key laborato...
5 篇 chinese acad sci...
5 篇 department of co...
5 篇 department of co...
4 篇 peng cheng lab
4 篇 univ chinese aca...
4 篇 department of ci...
4 篇 school of electr...
4 篇 department of el...
4 篇 school of inform...
4 篇 univ chinese aca...
4 篇 school of comput...

作者

7 篇 yang qiang
7 篇 piriyasurawong p...
6 篇 ouya samuel
6 篇 akatimagool soms...
5 篇 mendy gervais
5 篇 cortez paulo
5 篇 kraysman natalia...
4 篇 peng shaoliang
4 篇 liu sheng
4 篇 you linlin
4 篇 li han
4 篇 barabanova svetl...
4 篇 wang wei
4 篇 huang kaiqi
4 篇 lei baiying
4 篇 wang jinyan
4 篇 khatsrinova olga...
4 篇 shen dinggang
4 篇 li wei
4 篇 li qianmu

语言

2,155 篇 英文
93 篇 其他
27 篇 中文
1 篇 葡萄牙文

检索条件"任意字段=22nd International Conference on Intelligent Data Engineering and Automated Learning"

共 2254 条记录，以下是431-440 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 Label Sound Classification using Deep learning Models

Multi Label Sound Classification using Deep Learning Models

引用

international conference on Software engineering Research, Management and Applications (SERA)

作者： Tasnim Akter Onisha Jongyeop Kim Jongho Seol dept. Information Technology Georgia Southern University Statesboro GA dept. Information Technology Middle Georgia State University Macon GA

ISBN: (数字)9798350391343

ISBN: (纸本)9798350391350

Accurate and automated sound classification enables a strong groundwork for diverse advanced deep learning applications within the audio and music domain. This study focuses on the application of Convolutional Neural Networks (CNN) and combined LSTM (Long Short-Term Memory) and GRU (Gated Recurrent unit) models for instrument classification from audio signals, contributing to intelligent audio processing systems. Our proposed model exclusively utilizes the Mel-frequency cepstral coefficients (MFCCs) extraction from the audio data for preprocessing. A large and complex dataset, including Nineteen instrument classes are used for training and evaluation. These experimental results demonstrate promising performance, with our proposed CNN architecture achieving an impressive accuracy of 97%, and the LSTM-GRU model achieves a lower accuracy of 80%, compared to the CNN model on the multi-label sound classification task for instruments classes, but its ability to model temporal dependencies add valuable insights into the dynamics of instrument audio sequences. These findings provide valuable insights for researchers and practitioners in audio signal processing and machine learning.

关键词： Deep learning Training Accuracy Instruments Music Computer architecture Logic gates

来源：评论

学校读者我要写书评

暂无评论

Know Your Enemy: Identifying and Adapting to Adversarial Attacks in Deep Reinforcement learning 22

Know Your Enemy: Identifying and Adapting to Adversarial Att...

引用

22nd international conference on Autonomous Agents and Multiagent Systems, AAMAS 2023

作者： Curley, Seán Caulfield Mason, Karl Mannion, Patrick University of Galway Ireland

It has been shown that an agent can be trained with an adversarial policy which achieves high degrees of success against a state-of-the-art DRL victim despite taking unintuitive actions. This prompts the question: is this adversarial behaviour detectable through the observations of the victim alone? In competitive simulation environments, we find that widely used classification methods such as random forests are only able to achieve a maximum of ≈ 71% test set accuracy when classifying an agent for a single timestep. However, when the classifier inputs are treated as time-series data, test set classification accuracy is increased significantly to ≈ 98%. This is true for both classification of episodes as a whole, and for "live" classification at each timestep in an episode. These classifications can then be used to "react" to incoming attacks and increase the overall win rate against Adversarial opponents by approximately 17%. Classification of the victim's own internal activations in response to the adversary is shown to achieve similarly impressive accuracy while also offering advantages like increased transferability to other domains. © 2023 international Foundation for Autonomous Agents and Multiagent Systems (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

DDoS Detection Approach Based on Continual learning in the SDN Environment 22nd

DDoS Detection Approach Based on Continual Learning in the S...

引用

22nd international conference on Hybrid intelligent Systems, HIS 2022 and the 18th international conference on Information Assurance and Security, IAS 2022

作者： Chetouane, Ameni Karoui, Kamel RIADI Laboratory ENSI University of Manouba Manouba Tunisia National Institute of Applied Sciences and Technology University of Carthage Carthage Tunisia

ISBN: (纸本)9783031274084

Software Defined Networking (SDN) is a technology that has the capacity to revolutionize the way we develop and operate network infrastructure. It separates control and data functions and can be programmed directly using a high-level programming language. However, given the existing and growing security risks, this technology introduces a new security burden into the network architecture. Intruders have more access to the network and can develop various attacks in the SDN environment. In addition, modern cyber threats are developing faster than ever. Distributed Denial of Service (DDoS) attacks are the major security risk in the SDN architecture. They attempt to interfere with network services by consuming all available bandwidth and other network resources. In order to provide a network with countermeasures against attacks, an Intrusion Detection System (IDS) must be continually evolved and integrated into the SDN architecture. In this paper, we focus on Continual learning (CL) for DDoS detection in the context of SDN. We propose a method of continually enriching datasets in order to have a better prediction model. This is done without interrupting the normal operation of the DDoS detection system. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

In-Car Violence Detection Based on the Audio Signal 22nd

In-Car Violence Detection Based on the Audio Signal

引用

22nd international conference on intelligent data engineering and automated learning

作者： Santos, Flavio Duraes, Dalila Hammerschmidt, Niklas Marcondes, Francisco S. Lange, Sascha Machado, Jose Novais, Paulo Univ Minho Algorithm Ctr Braga Portugal Bosch Car Multimedia Braga Portugal

ISBN: (纸本)9783030916077;9783030916084

When it is intended to detect violence in the car, audio, speech processing, music, and ambient sound are some of the main points of this problem since it is necessary to find the similarities and differences between these domains. The recent increase in interest in deep learning has allowed practical applications in many areas of signal processing, often surpassing traditional signal processing on a large scale. This paper presents a comparative study of state-of-the-art deep learning architectures applied for inside car violence detection based only on the audio signal. The methodology proposed for audio signal representation was Mel-spectrogram, after an in-depth review of the literature. We build an In-Car video dataset in the experiments and apply four different deep learning architectures to solve the classification problem. The results have shown that the ResNet-18 model presents the best accuracy results on the test set.

关键词： Audio violence detection Audio action recognition Deep learning Interior vehicle

来源：评论

学校读者我要写书评

暂无评论

Enhancing Gas Leak Detection with IoT Technology: An Innovative Approach 2

Enhancing Gas Leak Detection with IoT Technology: An Innovat...

引用

2nd international conference on Machine learning and data engineering, ICMLDE 2023

作者： Babu, Tina Nair, Rekha R. Kishore, S. Vineeth, M. Department of Computer Science and Engineering Alliance University Bengaluru India Department of Computer Applications Nitte Institute of Professional Education Nitte University Mangalore India Buisness Intelligent Consultant Zellis HR Infopark Ernakulam India

The presence of a natural gas leak within a household carries the potential for fires and poses a risk of natural gas poisoning. Similar to how we approach other hazardous energy sources such as electricity and gasoline, it is crucial to exercise caution when dealing with natural gas exposure. To prevent potential hazards and dangerous situation, identified a smart gas detection system for rapid and accurate detection of gas leaks. The proposed gas leakage detection system combines advanced sensor technology, real-time monitoring, and automated alert mechanisms to ensure timely identification and response to gas leaks. The MQ2 sensor helps in detection of gas leakage. The MQ2 sensor possesses the capability to detect a wide range of gases, including methane, propane, carbon monoxide, and hydrogen. This versatility makes it an invaluable tool in ensuring safety and protecting against potential hazards and early identification of gas leaks. The collected data is analyzed using sophisticated algorithms to distinguish between normal background gas levels and potential leaks. NodeMCU, equipped with its Wi-Fi capabilities, functions as the central control unit of the system. The NodeMCU gathers real-time data from the gas sensors, constantly monitoring gas levels. It processes this data and sends it to the cloud or a central server using its internet connection. The system's ability to monitor in real-time ensures that any gas leaks detected are quickly reported to the relevant personnel or authorities through automated alerts. The fast notification system allows for quick actions, reducing the risks of accidents, saving lives, preventing property damage, and mitigating harm to the environment. © 2024 Elsevier B.V.. All rights reserved.

关键词： Gas detectors

来源：评论

学校读者我要写书评

暂无评论

Design of Attitude Simulation Control Platform for UAV Teaching 22

Design of Attitude Simulation Control Platform for UAV Teach...

引用

22nd IEEE international conference on Industrial Informatics, IndIN 2024

作者： Jiao, Yongkang Han, Xiao Huang, Doudou Li, Lei Naval Aeronautical University Yantai China The equipment Support Group of the Naval Armament Department Beijing China Unit 92781 Sanya China School of Electrical Engineering and Automation Hefei University of Technology Hefei China

ISBN: (纸本)9798331527471

Amid China's push for new infrastructure and intelligent manufacturing, the ndRC has advocated for the integration of technologies like the Internet, big data, and artificial intelligence to drive the modernization of traditional manufacturing. National policies also strongly back the development of research facilities in universities, particularly in promoting smart education initiatives. In recent years, UAVs have seen widespread adoption across various fields due to their ease of operation and stable performance. This paper explores the development of UAV flight control and navigation experiment platforms in universities, with a focus on teaching platforms for navigation, guidance, and control. In view of the need for fast and efficient verification of scientific research theories, high-quality experimental platforms are particularly important. The UAV flight control system platform installs the UAV through the swing table, and the inertia element is installed on the main rotating surface of the three-axis turntable. In this paper, the attitude Angle change of the UAV is simulated by controlling the precise rotation of the turntable. The turntable drives the inertial measurement unit to rotate. The flight control computer obtains data to solve the current heading, pitch and roll Angle of the UAV, and the rudder quantity of the steering gear, and transmits it to the corresponding actuator. The flight control computer transmits the current rudder quantity to the model as the control quantity input, and transmits the attitude and position information to the supreme position computer for displaying the current flight status in real time and saving and analyzing the data. © 2024 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

MaxEVA: Maximizing the Efficiency of Matrix Multiplication on Versal AI Engine

MaxEVA: Maximizing the Efficiency of Matrix Multiplication o...

引用

22nd international conference on Field Programmable Technology (ICFPT)

作者： Taka, Endri Arora, Aman Wu, Kai-Chiang Marculescu, Diana Univ Texas Austin Austin TX 78712 USA Arizona State Univ Tempe AZ 85287 USA Natl Yang Ming Chiao Tung Univ Taipei Taiwan

ISBN: (纸本)9798350359114

The increasing computational and memory requirements of Deep learning (DL) workloads has led to outstanding innovations in hardware architectures. An archetype of such architectures is the novel Versal AI Engine (AIE) by AMD/Xilinx. The AIE comprises multiple programmable processors optimized for vector-based algorithms. An AIE array consisting of 400 processor cores, operating at 1.25 GHz is able to deliver a peak throughput of 8 TFLOPs for 32-bit floating-point (fp32), and 128 TOPs for 8-bit integer (int8) precision. In this work, we propose MaxEVA: a novel framework to efficiently map Matrix Multiplication (MatMul) workloads on Versal AIE devices. Our framework maximizes the performance and energy efficiency of MatMul applications by efficiently exploiting features of the AIE architecture and resolving performance bottlenecks from multiple angles. When demonstrating on the VC1902 device of the VCK190 board, MaxEVA accomplishes up to 5.44 TFLOPs and 77.01 TOPs throughput for fp32 and int8 precisions, respectively. In terms of energy efficiency, MaxEVA attains up to 124.16 GFLOPs/W for fp32, and 1.16 TOPs/W for int8. Our proposed method substantially outperforms the state-of-the-art approach by exhibiting up to 2.19x throughput gain and 20.4% higher energy efficiency. The MaxEVA framework provides notable insights to fill the knowledge gap in effectively designing MatMulbased DL workloads on the new Versal AIE devices.

关键词： Versal AI Engine FPGA Matrix Multiplication Hardware Acceleration System-on-Chip Deep learning

来源：评论

学校读者我要写书评

暂无评论

intelligent Irrigation System for Agriculture using IoT and Machine learning 2

Intelligent Irrigation System for Agriculture using IoT and ...

引用

2nd international conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2022

作者： Gujar, Kumud A. Jagtap, Santosh Shri Jjt University Department of Computer Science India Prof. Ramkrishna More College Pune India

ISBN: (纸本)9781665437899

Agriculture plays vital role in development of social and economic condition of the all countries in the world. Water is the source of life and also a precious source for agriculture. Emerging trends in agriculture aims at ensuring more productivity, less damage to the land and helpful for the concept of Sustainable Agriculture (12). Crop productivity is mainly dependent on soil moisture level, less moisture result in loss of yield and plants dying. Excess water causes water wastage and root diseases. To maximize crop production the adequate water quantity at right time is required. In the proposed study IoT and Machine learning based automated irrigation system developed. The system is divided in to three stages, first is circuit building and sensors installation, the second stage is of reading sensor data and check the present soil moisture level and in third stage motor ON and OFF decisions is taken by considering the crop type. On server the sensor data is get stored, system gives real time data from the sensors. IoT (Internet of Thing) helps to implement Wireless Sensor Network and Machine learning can manage optimum water utilization for precious farming by analyzing available data. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Research on A Classification Algorithm of the Power System Related Objects Based on YOLOv4 22

Research on A Classification Algorithm of the Power System R...

引用

22nd IEEE/ACIS international conference on Computer and Information Science, ICIS 2022

作者： Tang, Guida Zheng, Gang Southwest Minzu University School of Computer Science and Engineering Chengdu China Chengdu Companiontek Technology Company Limited Chengdu China

ISBN: (数字)9781665494632

ISBN: (纸本)9781665494632

Recently, drones have been widely used in the power system. However, interpreting the image data of drones through the traditional human-based method is time-consuming, labor-intensive, and inefficient. Thus, in this paper, an innovative method based on deep learning for identification and classification of objects related to power system is proposed, which has achieved the satisfied result. Experiment in this paper shows that the data collected from drones could be processed easily and automatically, besides, the proposed algorithm greatly improves the work efficiency of drone inspections and saves inspection time. Therefore, people can extract and identify building signs effectively with the proposed method in this paper. © 2022 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Smart Waste Collecting Robot Integration With IoT and Machine learning 2

Smart Waste Collecting Robot Integration With IoT and Machin...

引用

2nd international conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Srinivasan, S. Jambulingam, Umamagewaran Purushothaman, K.E. Jegan Amarnath, J. Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chengalpattu India College of Computer Science King Khalid University Saudi Arabia Department of Computer Science and Engineering Kammavari Sangham Institute of Technology Karnataka Bangalore India

ISBN: (纸本)9798350305418

Non-biodegradable waste collecting from a wide area is a time-consuming process. The study aims to create an intelligent robot that can independently collect waste utilizing innovative technology. The study uses the Internet of Things (IoT) to connect and manage the various robot parts. A Raspberry Pi organizes many functions as the system's central processing unit. Real-time visual data, essential for waste detection and identification, is captured by a camera module. Ultrasonic sensors identify obstacles and measure distances so the robot can navigate its environment. The sensor helps the robot avoid collisions and navigate the predetermined space effectively. The robot's robotic arm, which enables it to pick up and collect waste materials physically, is one of its primary features. The Raspberry Pi controls the arm, allowing for accurate and synchronized motions for waste collection. They use machine learning methods to facilitate waste identification and categorization, especially a CNN model. To reliably identify various forms of waste, the CNN model is trained using a collection of waste images. These technologies may be combined to enable the automated waste-collected robot to function independently while effectively locating and collecting rubbish. By seamlessly integrating IoT, machine learning, and robots, this solution helps to save human labor and enhance waste management procedures. © 2023 IEEE.

关键词： Convolutional Neural Network (CNN) Environmental sustainability Image processing Internet of Things (IoT) Waste Collecting Robot

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226页 << < 40 41 42 43 44 45 46 47 48 49 > >>

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：