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

2,959 篇 会议
39 篇 期刊文献
7 册 图书

馆藏范围

3,005 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,760 篇 工学
- 1,407 篇 计算机科学与技术...
- 684 篇 软件工程
- 490 篇 电气工程
- 397 篇 信息与通信工程
- 203 篇 控制科学与工程
- 130 篇 生物工程
- 79 篇 电子科学与技术（可...
- 65 篇 生物医学工程（可授...
- 59 篇 机械工程
- 54 篇 仪器科学与技术
- 49 篇 光学工程
- 34 篇 网络空间安全
- 30 篇 动力工程及工程热...
- 24 篇 材料科学与工程（可...
- 24 篇 安全科学与工程
- 22 篇 化学工程与技术
- 20 篇 测绘科学与技术
- 19 篇 石油与天然气工程
517 篇 理学
- 226 篇 物理学
- 190 篇 数学
- 143 篇 生物学
- 58 篇 统计学（可授理学、...
- 40 篇 系统科学
- 27 篇 化学
203 篇 管理学
- 135 篇 管理科学与工程(可...
- 81 篇 图书情报与档案管...
- 31 篇 工商管理
135 篇 医学
- 112 篇 临床医学
- 38 篇 基础医学(可授医学...
37 篇 法学
- 20 篇 社会学
18 篇 文学
14 篇 农学
10 篇 教育学
9 篇 经济学
2 篇 军事学

主题

590 篇 neural networks
173 篇 training
168 篇 artificial neura...
165 篇 deep learning
135 篇 computational mo...
124 篇 feature extracti...
115 篇 neural network
114 篇 convolutional ne...
88 篇 machine learning
87 篇 neurons
86 篇 parallel process...
79 篇 deep neural netw...
74 篇 computer archite...
73 篇 distributed comp...
65 篇 signal processin...
62 篇 distributed proc...
62 篇 accuracy
60 篇 recurrent neural...
55 篇 data models
50 篇 convolutional ne...

机构

11 篇 institute of inf...
9 篇 school of cyber ...
8 篇 univ chinese aca...
8 篇 natl univ def te...
7 篇 college of compu...
7 篇 carnegie mellon ...
7 篇 national laborat...
7 篇 beijing universi...
7 篇 natl univ def te...
6 篇 shanghai jiao to...
6 篇 the islamic univ...
6 篇 department of co...
5 篇 science and tech...
5 篇 ibm tj watson re...
5 篇 school of inform...
5 篇 king saud univer...
5 篇 shandong normal ...
5 篇 kaust thuwal
5 篇 university of ch...
5 篇 natl univ def te...

作者

8 篇 li dongsheng
8 篇 dou yong
8 篇 jie liu
6 篇 richtarik peter
6 篇 ribeiro alejandr...
6 篇 liu jie
6 篇 niu xin
6 篇 yong dou
6 篇 shulian yang
6 篇 zhang wei
5 篇 ryabinin max
5 篇 segarra santiago
5 篇 lai zhiquan
5 篇 ding bo
5 篇 qiao peng
5 篇 xu jiren
5 篇 kokkinos yiannis
5 篇 peng yuxing
5 篇 wang huaimin
5 篇 li aiping

语言

2,925 篇 英文
72 篇 其他
8 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Neural Network and Distributed Processing"

共 3005 条记录，以下是981-990 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：

Optimizing Resource Allocation for Secure Communication in IoT Ecosystems

Optimizing Resource Allocation for Secure Communication in I...

引用

distributed Systems, Computer networks and Cybersecurity (ICDSCNC), International conference on

作者： Suresh Bysani Venkata Naga Arnav Kotiyal Suruchi Singh K. B. V. Brahma Rao Abhijit Mitra Natrayan L Eightfold.ai Ex - Cohesity California USA Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Science and Engineering UIET Chhatrapati Shahu Ji Maharaj University Kanpur India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation India Symbiosis Centre for Advanced Legal Studies and Research (SCALSAR) Symbiosis Law School Symbiosis International (Deemed University) Pune India Department of Mechanical Engineering Saveetha School of Engineering SIMATS India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

The proliferation of social media has made sites like Twitter a treasure trove of information for diagnosing mental health problems like depression. By examining trends in user-generated material, this research presents a machine learning system with the goal of identifying Twitter profiles exhibiting symptoms of sadness. We made sure to include tweets from a wide range of demographics in our dataset by collecting them from both people who reported having depression and a control group. Text, facial expressions, and interaction patterns were all subjected to feature extraction analysis. We used sentiment analysis and natural language processing (NLP) techniques to identify depressive symptoms in language and emotions. A number of ML models were trained and assessed for accuracy, precision, and recall; these models included neural networks, Random Forests, and Support Vector Machines (SVMs). Our approach outperforms baseline algorithms in identifying depressed symptoms, according to the data. Providing a scalable method for early diagnosis of depression, this research adds to the continuing efforts in digital psychiatry. It could aid in prompt intervention and support for affected patients. Responsible use of technology in mental health monitoring requires further discussion of privacy implications and ethical considerations when implementing such models. Several indicators were used to objectively analyze the performance of the machine learning models. With 89% accuracy, 86% precision, and 88% recall, the neural network model was the top performer. Additionally, the Random Forest model performed admirably, achieving 85% accuracy, 83% precision, and 84% recall. A recall of 81%, precision of 80%, and accuracy of 82% were all rather respectable for the SVM model.

关键词： Support vector machines Sentiment analysis Accuracy Social networking (online) Biological system modeling neural networks Blogs Mental health Depression Internet of Things

来源：评论

学校读者我要写书评

暂无评论

HCPipe: Hidden Computation Pipeline Model Parallelism for Large-scale DCNN Model Training

HCPipe: Hidden Computation Pipeline Model Parallelism for La...

引用

International conference on Computer Engineering and Applications (ICCEA)

作者： Bin Liu Yongyao Ma Zhonghao Zhang Zeyu Ji Guoqiang Hu Yijie Chen College of Information Engineering Northwest A&F University Yangling China Network and Educational Technology Center Northwest A&F University Yangling China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

The complexity of Deep Convolutional neural networks (DCNNs) with big datasets significantly prolongs the time of model training. Pipeline Model Parallelism (PMP) is a commonly used method in distributed training for shortening model time. However, traditional PMP methods struggle to maximize hidden computational, resulting in significant idle time. This paper introduces an innovative method, HCPipe, which employs a hidden computation method to overlap computation times further, effectively reducing idle time in pipeline training. The effectiveness of this method is firstly theoretically demonstrated. Subsequently, a model partitioning method based on dynamic programming is designed, aimed at rapidly dividing the model. To evaluate the performance of HCPipe, using the ImageNet dataset extensive experiments were conducted with ResNet and VGG models on a 4-GPU server. The experimental results indicate that the proposed HCPipe achieves significant performance improvements. Compared to GPipe, DAPPLE, and GEMS, the average throughput for the VGG series is increased by 13.3%, 4.6%, and 128%, respectively, while the average throughput for the ResNet series is increased by 27.8%, 14.4%, and 157%, respectively.

关键词： Training Computational modeling Pipelines Graphics processing units Parallel processing Throughput Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

splitDyn: Federated Split neural network for distributed Edge AI Applications

splitDyn: Federated Split Neural Network for Distributed Edg...

引用

IEEE International conference on Big Data

作者： Tran Anh Khoa Do-Van Nguyen Minh-Son Dao Koji Zettsu Big Data Integration Research Center National Institute of Information and Communications Technology Tokyo Japan

ISBN: (纸本)9781665480468

Split learning (SL) is a popular distributed machine learning (ML) method used to enable ML. It divides a neural network based model into subnetworks. Then, it separately trains the subnetworks on distributed parties (e.g., client and server). In distributed ML, data are generated and collected on the client-side. In contrast, the collected data are processed using an application deployed on the server side. However, when applied in practice using Internet of things systems and clients, numerous obstacles occur because of limited configuration and resources. Dividing neural networks in the SL is the biggest problem and an open question in numerous studies. This study introduces splitDyn, which is a new dynamic SL solution to solve the aforementioned problems. This method provides a solution for eliminating their inherent drawbacks. The main idea is to apply a Round-Robin schedule to select the client for the training process. Then, the next idea is to use the Hungarian optimization algorithm to assign a layer to a client and enhance the accuracy. The proposed method reasonably achieved better accuracy and reduced processing time than the other learning models. Furthermore, it applies the incident datasets to predict the incident event and in edge computing for edge artificial intelligence (AI) applications.

关键词： Training Temperature distribution Schedules neural networks Big Data Prediction algorithms Servers

来源：评论

学校读者我要写书评

暂无评论

Safety prediction of deep foundation pit based on neural network and entropy fuzzy evaluation 2

Safety prediction of deep foundation pit based on neural net...

引用

2020 2nd International Academic Exchange conference on Science and Technology Innovation, IAECST 2020

作者： Xie, Xiudong Pan, Caizhen College of Civil Engineering Fuzhou University Fuzhou Fujian China

The monitoring data can effectively reflect the safety status of the project during the construction of deep foundation pit, and the risks existing in the project can be discovered in time and the development trend can be reasonably predicted through the processing and analysis of the existing monitoring data. In this paper, a deep foundation pit in compound soil area of a coastal city was taken as an example, the BP neural network was taken to predict the monitoring data in the next stage, the entropy method was utilized to determine the weight of the evaluation index according to the predicted value, and the fuzzy comprehensive evaluation method was used to quantitatively describe the future safety status, so as to formulate targeted countermeasures and improve the construction safety. © The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (http://***/licenses/by/4.0/).

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Indian Currency Recognition:A Lightweight Transfer Learning Approach for Visually Impaired

Indian Currency Recognition:A Lightweight Transfer Learning ...

引用

International conference on Parallel distributed and Grid Computing (PDGC)

作者： Poonam Saini Ankit Goyal Bishwash Pokhrel Jaspreet Singh Neetish Kumar Dept. of Computer Science and Engg. Punjab Engineering College Chandigarh India

ISBN: (纸本)9781665454025

The knowledge of artificial intelligence, especially, machine learning has been widely used to handle various real-world applications and related societal challenges. One of the crucial issues faced by visually impaired people is to correctly recognize paper currency and its denomination easily. The paper proposes a convolutional neural network-based currency recognition system applied to the Indian Currency. The basic features include data pre-processing to filter out the old currency notes and incorrect labels, followed by a pre-trained model selection. The proposed model is trained using transfer learning, and afterward, a custom layer is added to recognize currency notes. Further, a fully connected customized neural network architecture has been designed. The model undergoes fine tuning of essential hyperparameters. The proposed model classifies Indian banknotes with more reliable accuracy (99.5%), which is even flexible to different image orientations (flipped, folded, out of frame, etc.) as well as empty backgrounds for a real-time application.

关键词： Training Face recognition Transfer learning neural networks Computer architecture Real-time systems Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

WholeGraph: A Fast Graph neural network Training Framework with Multi-GPU distributed Shared Memory Architecture

WholeGraph: A Fast Graph Neural Network Training Framework w...

引用

Supercomputing conference

作者： Dongxu Yang Junhong Liu Jiaxing Qi Junjie Lai NVIDIA Beijing China

ISBN: (纸本)9781665454452

Graph neural networks (GNNs) are prevalent to deal with graph-structured datasets, encoding graph data into low dimensional vectors. In this paper, we present a fast training graph neural network framework, i.e., WholeGraph, based on a multi-GPU distributed shared memory architecture. Whole-Graph consists of partitioning the graph and corresponding node or edge features to multi-GPUs, eliminating the bottleneck of communication between CPU and GPUs during the training process. And the communication between different GPUs is implemented by GPUDirect Peer-to-Peer (P2P) memory access technology. Furthermore, WholeGraph provides several optimized computing operators. Our evaluations show that on large-scale graphs WholeGraph outperforms state-of-the-art GNN frameworks, such as Deep Graph Library (DGL) and Pytorch Geometric (PyG). The speedups of WholeGraph are up to $57.32\mathrm{x}$ and $242.98\mathrm{x}$ compared with DGL and PyG on a single machine multi-GPU node, respectively. The ratio of GPU utilization can sustain above 95% during GNN training process.

关键词： Training Computational modeling High performance computing Memory architecture Graphics processing units distributed databases Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on energy consumption prediction of public buildings based on improved support vector machine

Research on energy consumption prediction of public building...

引用

Chinese Control and Decision conference, CCDC

作者： Liyao Yang Hongyan Ma Yingda Zhang Shengyan Li School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China School of Electrical and Information Engineering Institute of Distributed Energy Storage Safety Big Data Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

An improved support vector machine model for energy consumption prediction is proposed to achieve efficient energy saving in buildings. In this paper, firstly, a gray correlation analysis model is used to measure the correlation between temperature, humidity, sunlight and other factors and building energy consumption. Secondly, the sparrow search algorithm (SSA) is introduced to optimize the penalty coefficient c and kernel function parameter g of the support vector machine, and then the SSA-SVM energy consumption prediction model is established. Finally, the experimental results are analyzed by comparing with the data derived from the support vector machine prediction (SVM) model and BP neural network energy consumption prediction. The experimental results show that compared with SVM and BP neural network, the prediction results of SSA-SVM model perform better in error index, indicating that the energy consumption prediction of SSA-SVM model has higher prediction accuracy; the maximum relative error of SSA-SVM prediction model is 0.0514, and the maximum relative errors of the other two models are greater than 0.55, indicating that SSA-SVM model has a higher degree of reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

19th IEEE International Symposium on Parallel and distributed processing with Applications, 11th IEEE International conference on Big Data and Cloud Computing, 14th IEEE International conference on Social Computing and networking and 11th IEEE International conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021

19th IEEE International Symposium on Parallel and Distribute...

引用

19th IEEE International Symposium on Parallel and distributed processing with Applications, 11th IEEE International conference on Big Data and Cloud Computing, 14th IEEE International conference on Social Computing and networking and 11th IEEE International conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021

ISBN: (纸本)9781665435741

The proceedings contain 222 papers. The topics discussed include: DRL-deploy: adaptive service function chains deployment with deep reinforcement learning;accuracy vs. efficiency: achieving both through hardware-aware quantization and reconfigurable architecture with mixed precision;cmss: collaborative modeling of safety and security requirements for network protocols;FGPA: fine-grained pipelined acceleration for depthwise separable CNN in resource constraint scenarios;Dyacon: JointCloud dynamic access control model of data security based on verifiable credentials;understanding the runtime overheads of deep learning inference on edge devices;and alleviating imbalance in synchronous distributed training of deep neural networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Web Application Firewall System through Convolutional neural network and Deep Learning

Design of Web Application Firewall System through Convolutio...

引用

Computers, Information processing and Advanced Education (CIPAE), 2020 International conference on

作者： Shihao Wang Ruiheng Liu Xu Guo Gaoda Wei School of Software Zhengzhou University Zhengzhou China

ISBN: (纸本)9781665468138

Attacks against web applications emerge in endlessly, and protecting the security of web applications is an important part of the current cyberspace security. This paper constructs one cloud web application firewall system based on deep learning. The system architecture adopts a multi-server distributed architecture. Taking into account the real-time nature of web requests and the user's sense of user experience, through the use of a high-performance server framework Openers and high-efficiency volumes. The convolutional neural network improves the operating efficiency of the system while ensuring the recognition rate. At the same time, the system implemented in this paper also saves server request information in the database to further provide targeted data sets for artificial intelligence training.

关键词： Deep learning Training Firewalls (computing) Systems architecture Learning (artificial intelligence) User experience Real-time systems

来源：评论

学校读者我要写书评

暂无评论

PMC-CNN: Trajectory Prediction Method Fusing Pedestrian Motion Features

PMC-CNN: Trajectory Prediction Method Fusing Pedestrian Moti...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Xiling Cao Yan Li Hong Liu School of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan China Inspur (Shandong) Computer Technology Co Ltd. Jinan China

ISBN: (数字)9798350356670

ISBN: (纸本)9798350356687

Predicting how pedestrians will move is a valuable and challenging task. It can be applied to various domains, such as crowd evacuation and autonomous driving. However, in practice, scene information and pedestrian interaction make it difficult to accurately predict pedestrian trajectories. Therefore, more effective processing of information affecting pedestrian trajectories is particularly important. Extraction of pedestrian motion features is insufficient in current research in this area. To address this problem, a neural network trajectory prediction method, PMC-CNN, is proposed. This method incorporates pedestrian motion features and stores the heterogeneous information required for prediction within a knowledge graph. Furthermore, it combines this information with the proposed IN-EX pedestrian motion model, resulting in an improvement in prediction accuracy. In addition, this research applies the prediction framework to a crowd evacuation scenario to improve the efficiency of crowd evacuation. This verifies the effectiveness and practicality of our proposed model.

关键词： Pedestrians Accuracy Urban planning neural networks Safety management Knowledge graphs Predictive models Feature extraction Real-time systems Trajectory

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301页 << < 95 96 97 98 99 100 101 102 103 104 > >>

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：