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

756 篇 会议
3 册 图书
2 篇 期刊文献

馆藏范围

761 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

655 篇 工学
- 535 篇 计算机科学与技术...
- 465 篇 软件工程
- 247 篇 信息与通信工程
- 147 篇 生物工程
- 114 篇 光学工程
- 93 篇 电气工程
- 92 篇 控制科学与工程
- 91 篇 电子科学与技术（可...
- 76 篇 生物医学工程（可授...
- 54 篇 化学工程与技术
- 39 篇 机械工程
- 34 篇 仪器科学与技术
- 34 篇 材料科学与工程（可...
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 25 篇 交通运输工程
- 24 篇 土木工程
439 篇 理学
- 204 篇 数学
- 159 篇 物理学
- 152 篇 生物学
- 71 篇 统计学（可授理学、...
- 66 篇 化学
- 34 篇 系统科学
199 篇 管理学
- 123 篇 图书情报与档案管...
- 98 篇 管理科学与工程(可...
- 39 篇 工商管理
52 篇 医学
- 49 篇 基础医学(可授医学...
- 49 篇 临床医学
- 36 篇 药学(可授医学、理...
28 篇 法学
- 25 篇 社会学
15 篇 经济学
15 篇 农学
14 篇 教育学
2 篇 军事学

主题

23 篇 deep learning
19 篇 machine learning
16 篇 support vector m...
15 篇 feature extracti...
14 篇 computer vision
11 篇 convolution
11 篇 natural language...
11 篇 sentiment analys...
10 篇 internet of thin...
10 篇 object detection
10 篇 big data
10 篇 semantics
10 篇 convolutional ne...
9 篇 natural language...
7 篇 signal processin...
7 篇 visualization
6 篇 signal detection
6 篇 deep neural netw...
6 篇 graphics process...
6 篇 neural networks

机构

7 篇 key laboratory o...
7 篇 school of inform...
6 篇 school of comput...
6 篇 xinjiang key lab...
6 篇 school of inform...
6 篇 xinjiang key lab...
6 篇 key laboratory o...
4 篇 nss college of e...
4 篇 school of comput...
4 篇 college of infor...
4 篇 school of contro...
3 篇 school of comput...
3 篇 department of co...
3 篇 college of compu...
3 篇 college of intel...
3 篇 guangdong polyte...
3 篇 school of comput...
3 篇 school of comput...
3 篇 academy for engi...
2 篇 hefei university...

作者

10 篇 hamdulla askar
6 篇 ablimit mijit
5 篇 gao yanxia
5 篇 liu yiwen
4 篇 shi yuanquan
4 篇 xiao jianhua
3 篇 faisal rehman
3 篇 wang chao
3 篇 xiao hongbo
3 篇 sharif hanan
3 篇 peng xiaoning
3 篇 rehman faisal
3 篇 chen xi
3 篇 mala c.
3 篇 shi zhen-gang
3 篇 li chao
3 篇 jiang huiming
3 篇 yuan jing
3 篇 li jing
3 篇 zhao qian

语言

753 篇 英文
8 篇 其他

检索条件"任意字段=2022 3rd International Conference on Signal Processing and Computer Science, SPCS 2022"

共 761 条记录，以下是681-690 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：

A Rapid Image Semantic Segment Method Based on Deeplab V3+ 3rd

A Rapid Image Semantic Segment Method Based on Deeplab V3+

引用

3rd international conference on Artificial Intelligence, 2022

作者： Zhang, Hailong Luo, Hanwu Li, Wenzhen Qin, Ruofeng Wuhan NARI Limited Liability Company State Grid Electric Power Research Institute Wuhan China East Inner Mongolia Electric Power Co. Ltd. Erdos China

ISBN: (纸本)9789811694226

As one of research directions in the fields of image processing and computer vision, image semantic segmentation classifies images by pixel for semantic comprehension. Due to the lack of a general theory of segmentation, conventional image semantic segmentation algorithms are mostly on the strength of specific image models, so a variety of methods develope with their respective range for using and relative merits. What’s more, it’s a pity that most of them can only use the underlying features to generate simple segmentation results of foreground and background. Since the breakthrough in deep learning at the ImageNet competition in 2012, convolutional neural networks have taken every field of computer vision by storm. Image semantic segmentation has broken through the limits of traditional methods rapidly after the integration of deep learning. After making use of convolutional neural networks, its accuracy for segmentation has been improved effectively so that image semantic segmentation at present can further meet the requirements of segmentation technology in different application scenarios. In recent years, it has developed rapidly and gradually become a research hotspot. This paper mainly studies the image semantic segmentation methods about Deeplab series based on deep learning and raises a lightweight model for semantic segmentation based on Deeplab v3+. Regarding MobileNet as backbone to extract features, it makes use of atrous spatial pyramid pooing to gain global multi-scale features. Then the decoder structure concatenates multi-scale features and low-level features to enhance the expression for spatial features and improve its performance. After sufficient experiments on PASCAL VOC using the fast semantic segmentation model, the result reveals that it obtains a good balance between accuracy and speed. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Sleep Apnea detecting based on ECG and EEG signals using Discrete Wavelet Transform and Artificial Neural Network

Sleep Apnea detecting based on ECG and EEG signals using Dis...

引用

The 3rd international conference on Distributed Sensing and Intelligent Systems (ICDSIS 2022)

作者： A. A. Hammal T. Bonney W. A. Nassan K. Obaideen Electrical and Computer Engineering Aleppo University Syria Department of Computer Engineering University of Sharjah Sharjah United Arab Emirates Sustainable Energy and Power Systems Research Centre RISE University of Sharjah Sharjah United Arab Emirates

Sleep apnea is a severe sleep disorder that happens when breathing stops and starts during slumber. If it goes untreated, it can cause serious health problems. In recent years, Sleep Apnea (SA) has been diagnosed using either Electrocardiogram (ECG) signals that refer the heart health or Electroencephalogram (EEG) signals that refer to brain health. This research aims to build an Artificial Neural Network (ANN) classification model to determine sleep disorders using ECG and EEG signals. Features Delta sub-band waves are extracted and processed using a multilayer perceptron (MLP) with two different topologies; hidden layers are the same. The results show that using ECG and EEG signals to classify sleep apnea achieves high accuracy of 99.97% compared to other recent related work. We anticipate our assay to be a starting point for reliable wearable diagnostic devices to control equipment that can help patients with sleep apnea avoid respiratory distress episodes.

关键词： discrete wavelet transforms diseases electrocardiography electroencephalography medical disorders medical signal processing multilayer perceptrons pneumodynamics signal classification sleep

来源：评论

学校读者我要写书评

暂无评论

Design and Demonstrate an Attack Strategy to Control a Vehicle’s computer by Targeting Its Electrical Network 3rd

Design and Demonstrate an Attack Strategy to Control a Vehic...

引用

3rd international conference on Electronic Engineering and Renewable Energy, ICEERE 2022

作者： Karrouchi, Mohammed Messaoudi, Abdelhafid Kassmi, Kamal Nasri, Ismail Atmane, Ilias Blaacha, Jalal Electrical Engineering and Maintenance Laboratory High School of Technology Mohammed First University BP. 473 Oujda Morocco Energy Embedded Systems and Information Processing Laboratory National School of Applied Sciences Mohammed First University Oujda Morocco Department of Physics Faculty of Science Mohammed First University Oujda Morocco

ISBN: (纸本)9789811962226

The functionality of most modern automobiles is controlled by electronic control units (ECUs) that interact with one another via the CAN communication protocol (controller area network), as defined by the ISO 11898 standard, which is one of the fundamental features of most modern cars. This physical bus provides excellent data transfer quality by providing wide propagation reaching all areas of a vehicle in a short amount of time. However, because of the absence of secrecy and ease of access (physical or remote), this protocol does not place a high value on security, which causes the CAN bus control system to be vulnerable. Due to this weakness, it is possible to control the car from the outside and place the vehicle's passengers in jeopardy. The objective of this paper is to describe the existing vulnerability of the security system against attacks, and also a demonstration of a hacking technique used to manage the dashboard of a 2014 DACIA Dokker automobile using the automotive network. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

A Quantitative Assessment of Emerging Trends in IoT Botnet Attacks

A Quantitative Assessment of Emerging Trends in IoT Botnet A...

引用

Innovations in computer science & Software Engineering (ICONICS), international conference on

作者： Muhammad Hassan Nasir Muhammad Mubashir Khan Junaid Arshad Department of Computer Science & IT NED University of Engineering & Technology Karachi Pakistan School of Computing and Digital Technology Birmingham City University United Kingdom

In recent years, the world has witnessed a great increase in IoT Botnet attacks. Since these IoT devices are heterogeneous and typically resource-constrained with less processing and memory resources available to employ an efficient security mechanism. Moreover, the attack vectors and malicious adversaries have become advanced both in terms of complexity and diversity. This implies an effective mechanism to efficiently identify and prevent IoT Botnet attacks. This study aims to present a methodological quantitative assessment of the research conducted in the area of IoT Botnets from the year 2015 to 2022. Typically, the ISI Web of science (WoS) along with VOSviewer (a software tool for constructing and visualizing bibliometric networks) are used to conduct the overall bibliometric assessment. Our assessment shows that the research in this area encompasses multiple domains with the USA leading in terms of research publication with English as the leading language. This bibliometric assessment provides an in-depth quantitative analysis based on the 9 research questions formulated during our research. This consequently helps the research community to collaborate with other researchers, institutions and funding agencies to make further progress in this area.

关键词： Visualization Systematics Statistical analysis Botnet Bibliometrics Market research Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Designing neuromorphic architectures: towards an ultra low power AI

Designing neuromorphic architectures: towards an ultra low p...

引用

international conference on Embedded & Distributed Systems (EDiS)

作者： Pierre Boulet Laboratory CRIStAL University of Lille France

ISBN: (数字)9798350397543

ISBN: (纸本)9798350397550

In the “bio-inspired information processing” project of the IRCICA interdisciplinary institute, we tackle the scientific challenges of the emerging neuromorphic architectures. These computer architectures mimic the brain by handling the information as spike trains and by processing this information with spiking neural networks. They have a strong potential for ultra low power artificial intelligence. Based on our last 10 years of research, we will present the state-of-the-art of these architectures, the applications we focus on, and the scientific hot topics.

关键词： computer architecture Low-power electronics computer science Professional societies Parallel processing Neuromorphic engineering Nanoelectronics

来源：评论

学校读者我要写书评

暂无评论

LSTM-based Pedestrian Trajectory Prediction Model under the General Direction Mechanism: DIR-LSTM 3

LSTM-based Pedestrian Trajectory Prediction Model under the ...

引用

3rd international conference on Electronic InformationTechnology and Smart Agriculture, ICEITSA 2023

作者： Luo, Junyuan Fu, Qiongfang Xiao, Jianhua Xiao, Hongbo Liao, Jiyong School of Computer Science and Engineering Huaihua University Hunan Huaihua China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing Application in Hunan Province Universities Hunan Huaihua China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (纸本)9798400716775

Accurate prediction of future traffic flow trends is essential to solve urban transportation problems. However, traffic flow prediction faces great challenges due to the multimodal nature of pedestrian behavior and the complexity of the traffic environment. Although a large number of studies have been conducted to investigate these issues in depth, there are still some limitations. In order to address these challenges more effectively, we propose a pedestrian trajectory prediction model based on long-short-term memory networks (LSTMs): the DIR-LSTM. The model introduces an innovative generalized direction mechanism and a self-attention mechanism, which captures pedestrian movement patterns more comprehensively and accurately by predicting overall directional movements first and then gradually subdividing them into individual directions of movement. The DIR-LSTM is designed to address the challenges posed by the diversity of pedestrian behaviors and the complexity of urban environments. To validate the state-of-the-art of the model, we conducted experiments using the publicly available ETH [10] and UCY [9] datasets. The experiments demonstrate that DIR-LSTM performs better in terms of accuracy compared to other models, providing a more reliable prediction tool for future urban traffic management. © 2023 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Generating Recommendations for Various Problems Using Data Mining and Machine Learning Algorithms 3rd

Generating Recommendations for Various Problems Using Data M...

引用

3rd international conference on Communication, Computing and Electronics Systems, ICCCES 2021

作者： Lobo, L.M.R.J. Birbal, Kale Manoj Department of Computer Science & Engineering Walchand Institute of Technology Solapur India

ISBN: (纸本)9789811688614

The system available today which generates recommendations is supported by the user’s information collected within the past. It does not include intention at a specific time. The utilization of data mining and machine learning algorithms offers real-time recommendations employing a fitness function and models that estimate the suitability of recommended lists. The utilization of a social network provides user-generated content during a much more convenient scenario. It also uses a user experience. Recommendation systems play an outsized role in providing quality to those. In this paper, we present how recommendations are often produced using data processing and machine learning algorithms. Three systems with varied applications are addressed during this paper. First, a recommendation is used for better crop cultivation using certain parameters of concern with the assistance of association rule mining and genetic algorithms. Second, a way to recommend videos for advertisements from those available with titles, descriptions, and hashtags as extracted features is presented. These use machine learning-associated multi-label classification algorithm. Finally, an anti-vice recommendation system that uses neural networks to get recommendations is brought forward. Altogether the three cases, it is observed that the accuracy and efficiency of recommendations are upgraded. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Organ Risk Prediction Using Deep Learning and Neural Networks 1

引用

3rd international conference on Sustainable Advanced Computing, ICSAC 2021

作者： Bafna, Simran Shankar, Achyut Nehra, Vanshika Thakur, Sanjeev Mala, Shuchi Department of Computer Science Amity School of Engineering and Technology Amity University Noida India

ISBN: (数字)9789811690129

ISBN: (纸本)9789811690112

Parkinson’s disease is a chronic degenerative condition caused predominantly by a deficiency of dopamine in the brain. Due to a long latency before the first dopamine damage, PD is mostly not diagnosed at its early stage. The precise and successful diagnosis have been, therefore, a major challenge. To resolve the precise diagnosis of the problem of the disease, we proposed a non-invasive prediction method based on convolutional neural network prognostic modelling for specific and effective Parkinson’s disease diagnosis by diagnosing the organs at risk at different stages and also its severity. Deep learning-based approaches have recently shown promise for the tasks of medical image processing and disease detection. The proposed deep learning-based approach first extracted features from the clinical data and then merged them to predict organs at risk at various stages. Our findings show that the addition of imaging data to non-imaging clinical data in patients with PD is helpful in predicting outcomes. The suggested approach that combines clinical evidence from both imaging and non-imaging shows great promise for outcome prediction in patients with PD. This paper provides a systematic analysis of the prediction of Parkinson’s disease with an accuracy rate of overall 90.93%. This paper also presents the review of findings obtained in the literature by numerous studies to predict Parkinson’s diseases. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Spectrum Sensing and Resource Allocation in WSN-IoT Smart Applications 3rd

Reinforcement Learning Based Spectrum Sensing and Resource A...

引用

3rd international conference on computer Vision, High Performance Computing, Smart Devices, and Networks, CHSN 2022

作者： Raghava Deepthi, J.V.N. Khan, Ajoy Kumar Acharjee, Tapodhir Department of Computer Science and Engineering Assam University Assam Silchar788011 India Department of Computer Engineering Mizoram University Aizawl India

ISBN: (纸本)9789819966899

There is a tremendous demand for resources due to the different emerging IoT applications that must be fulfilled. The large-scale resource-constrained IoT ecosystem needs a novel and robust technique to manage resources. An optimal resource provisioning in IoT ecosystem has to handle the mapping of requestresource and is hard to achieve as the IoT requests and resources are dynamic and heterogeneous. Therefore, artificial intelligence (AI) has a vital role in the IoT network. As changes are dynamic, global optimization cannot be achieved due to classifiers of the wireless signals and high interference. In this research, spectrum selection is integrated with spectrum access by the use of reinforcement learning with stochastic-based reward measures for efficient resource allocation in WSN-IoT applications. Here, state–action–reward–state–action approach with the Gittins index named SARSA-GI is involved. The role of the state–action–reward– state–action model is developed with an energy-efficient approach for optimizing the channel. Next, the Gittins index is designed to reduce the delay and enhance the accuracy of spectrum access. The simulation results are compared with two state-of-the-art methods which achieve 91.4% of reliability, 88.4% of transmission probability, 93.4% of throughput, 66.8% of collision performance, and 57.2% of signal-to-interference noise ratio. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Invading Deep Neural Information Management Systems by Adaptive Multi-Gradient Based Method

Invading Deep Neural Information Management Systems by Adapt...

引用

computer science and Management Technology (ICCSMT), international conference on

作者： Pian Wang Yatie Xiao Jingyu Jiang Management School Guangdong Innovative Technical College Dongguan China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

The applications of deep learning have been widely employed in many specific domains (e.g., computer vision and language processing). The research on the security and privacy of deep neural networks (DNNs) has drawn much attention related to adversarial attacks and defense on DNNs. To provide a simple yet effective adversarial learning resource for building adversarial security, we formulate imperceptible adversarial perturbations in an adaptive multi-gradient learning manner, which calls a few adaptive operators on gradient-based terms. First, the proposed work searches for the input gradient based on the source representation in deep neural models. Then, fusing three adaptive gradient-based mechanisms to form the perturbed terms, which improves the capability of the generated samples to search the decision boundaries between original and adversarial domains directly. We compare the proposed work to other gradient-based adversarial attack methods in fooling convolutional neural networks in the field of computer vision. Experimental results reveal that adversarial examples generated by the introduced approach show surpassing effectiveness in fooling deep neural networks. It manifests fewer pixel changes in generated adversarial examples both on and norm constraints with specific attack strategies, respectively.

关键词：

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77页 << < 65 66 67 68 69 70 71 72 73 74 > >>

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：