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

5,626 篇 会议
90 篇 期刊文献
10 册 图书

馆藏范围

5,726 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,768 篇 工学
- 2,326 篇 计算机科学与技术...
- 1,325 篇 软件工程
- 565 篇 信息与通信工程
- 466 篇 电气工程
- 200 篇 生物工程
- 175 篇 控制科学与工程
- 174 篇 生物医学工程（可授...
- 108 篇 机械工程
- 84 篇 交通运输工程
- 83 篇 化学工程与技术
- 81 篇 电子科学与技术（可...
- 79 篇 光学工程
- 70 篇 仪器科学与技术
- 65 篇 动力工程及工程热...
- 55 篇 土木工程
- 55 篇 安全科学与工程
- 52 篇 环境科学与工程（可...
898 篇 理学
- 477 篇 数学
- 235 篇 生物学
- 232 篇 物理学
- 191 篇 统计学（可授理学、...
- 119 篇 系统科学
- 67 篇 化学
588 篇 管理学
- 325 篇 图书情报与档案管...
- 306 篇 管理科学与工程(可...
- 163 篇 工商管理
290 篇 医学
- 244 篇 临床医学
- 144 篇 基础医学(可授医学...
- 80 篇 药学(可授医学、理...
76 篇 法学
- 71 篇 社会学
54 篇 经济学
45 篇 教育学
40 篇 农学
26 篇 文学
2 篇 军事学
1 篇 历史学
1 篇 艺术学

主题

1,599 篇 data models
534 篇 predictive model...
529 篇 training
498 篇 machine learning
461 篇 data mining
416 篇 big data
404 篇 computational mo...
343 篇 feature extracti...
333 篇 task analysis
326 篇 prediction algor...
267 篇 deep learning
255 篇 machine learning...
245 篇 classification a...
238 篇 analytical model...
191 篇 clustering algor...
190 篇 support vector m...
182 篇 neural networks
158 篇 natural language...
142 篇 training data
141 篇 mathematical mod...

机构

19 篇 sun yat sen univ...
19 篇 daffodil interna...
12 篇 univ chinese aca...
11 篇 tsinghua univers...
11 篇 university of ch...
11 篇 school of data a...
10 篇 carnegie mellon ...
9 篇 renmin univ chin...
9 篇 lviv polytechnic...
8 篇 shenzhen researc...
7 篇 shanghai jiao to...
7 篇 college of compu...
7 篇 university of el...
7 篇 school of comput...
7 篇 national univers...
7 篇 harbin institute...
7 篇 beijing key lab ...
7 篇 natl univ def te...
7 篇 renmin univ chin...
6 篇 university of sc...

作者

7 篇 li li
7 篇 wang wei
7 篇 xiao yanghua
6 篇 wen ji-rong
6 篇 cui bin
6 篇 zhao wayne xin
6 篇 ying liu
6 篇 syed akhter hoss...
5 篇 yang tong
5 篇 liu yang
5 篇 li zhang
5 篇 jia weijia
5 篇 chen liu
5 篇 yang yang
5 篇 xiao hongbo
5 篇 nguyen trong-the
5 篇 yu jie
5 篇 albert bifet
5 篇 wang bin
5 篇 carlos ordonez

语言

5,682 篇 英文
36 篇 其他
9 篇 中文
2 篇 俄文
1 篇 乌克兰文

检索条件"任意字段=2020 International Conference on Data Processing Algorithms and Models, ICDPAM 2020"

共 5726 条记录，以下是301-310 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：

Analysis of Optimum 3-Dimensional Array and Fast data Movement for Efficient Memory Computation in Convolutional Neural Network models 7th

Analysis of Optimum 3-Dimensional Array and Fast Data Moveme...

引用

7th international conference on Computer, Communication and Signal processing, ICCCSP 2023

作者： Selvaraj, Deepika Venkatesan, Arunachalam Novo, David Department of Micro and Nanoelectronics Vellore Institute of Technology Vellore India University of Montpellier LIRMM Montpellier France

ISBN: (纸本)9783031398100

CNN-based inference engine’s performance and efficiency always depend on the computational and dataflow-control complexity. Instead of considering a 2-dimensional (2D) feature array for processing, a 3D array of features/weights would improve the dataflow movement & memory computation. The optimum 8 × 8 × 32 3D-feature array size was chosen based on the factor of on-chip memory requirement, data reuse, and PE utilization. Using the optimum 8 × 8 × 32 feature array, seven different combinations of data-flow scheduling strategies were analyzed by varying row, column, and depth-wise parameters on the workload model using a MATLAB environment. From the analysis, strategy-V (depth-wise parallel & row/column-wise sequence) is found to be the best with a 4 × 8 processor array. Compared to the state-of-the-art processor strategy, strategy-V achieves the data transfer rate (off-chip to on-chip) and on-chip memory requirement of 3.3 times (higher) and 16 times (lesser) with a small overhead of processor cost. © IFIP international Federation for Information processing 2023.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

Nonnegative Block-Term Decomposition with the β-Divergence: Joint data Fusion and Blind Spectral Unmixing 48

Nonnegative Block-Term Decomposition with the β-Divergence:...

引用

48th IEEE international conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Prévost, C. Leplat, V. University of Lille Cnrs Centrale Lille Umr 9189 CRIStAL LilleF-59000 France Moscow Russia

ISBN: (纸本)9781728163277

We present a new method for solving simultaneously hyperspectral super-resolution and spectral unmixing of the unknown super-resolution image. Our method relies on three key elements: (1) the nonnegative decomposition in rank-(Lr, Lr, 1) block-terms, (2) joint tensor factorization with multiplicative updates, and (3) the formulation of a family of optimization problems with β-divergences objective functions. We come up with a family of simple, robust and efficient algorithms, adaptable to various noise statistics. Experiments show that our approach competes favorably with state-of-the-art methods for solving both problems at hand for various noise statistics. © 2023 IEEE.

关键词： blind spectral unmixing blockterm decomposition hyperspectral super-resolution Nonnegative tensor factorization β-divergence

来源：评论

学校读者我要写书评

暂无评论

ChouBERT: Pre-training French Language Model for Crowdsensing with Tweets in Phytosanitary Context 16th

ChouBERT: Pre-training French Language Model for Crowdsensin...

引用

16th international conference on Research Challenges in Information Sciences (RCIS)

作者： Jiang, Shufan Angarita, Rafael Cormier, Stephane Orensanz, Julien Rousseaux, Francis Inst Super Elect Paris LISITE Paris France Univ Reims CReSTIC Reims France Cap2020 Gradignan France

ISBN: (纸本)9783031057601;9783031057595

To fulfil the increasing need for food of the growing population and face climate change, modern technologies have been applied to improve different farming processes. One important application scenario is to detect and measure natural hazards using sensors and data analysis techniques. Crowdsensing is a sensing paradigm that empowers ordinary people to contribute with data their sensor-enhanced mobile devices gather or generate. In this paper, we propose to use Twitter as an open crowdsensing platform for acquiring farmers knowledge. We proved this concept by applying pre-trained language models to detect individual's observation from tweets for pest monitoring.

关键词： Transfer learning Crowd-sensing Plant health monitoring Twitter

来源：评论

学校读者我要写书评

暂无评论

DNN Real-Time Collaborative Inference Acceleration with Mobile Edge Computing

DNN Real-Time Collaborative Inference Acceleration with Mobi...

引用

IEEE international conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / international Joint conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Yang, Run Li, Yan He, Hui Zhang, Weizhe Harbin Inst Technol Sch Cyberspace Sci Harbin 150001 Peoples R China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

The collaborative inference approach splits the Deep Neural Networks (DNNs) model into two parts. It runs collaboratively on the end device and cloud server to minimize inference latency and protect data privacy, especially in the 5G era. The scheme of DNN model partitioning depends on the network bandwidth size. However, in the context of dynamic mobile networks, resource-constrained devices cannot efficiently execute complex model partitioning algorithms to obtain optimal partitioning in real-time. In this paper, to overcome this challenge, we first formulate the model partitioning problem as a Min-cut problem to seek the optimal partition. Second, we propose a Collaborative Inference method based on model Compression named CIC. CIC enhances the efficiency of the execution of model partitioning algorithms on resource-constrained end devices by reducing the algorithm's complexity. CIC generates a splitting model based on the inherent characteristics of the DNN model and the platform resources. The splitting models are independent of the network environment, generated offline, and constantly used in the current environment. CIC has excellent compressibility, and even DNN models with hundreds of layers can be rapidly partitioned on resource-constrained devices. Experimental results show that our method is significantly more effective than existing solutions, speeding up model partitioning decision time by up to 100x, reducing inference latency by up to 2.6x, and increasing throughput by up to 3.3x in the best case.

关键词： Collaborative inference edge computing DNN model partitioning inference acceleration data privacy

来源：评论

学校读者我要写书评

暂无评论

Saudi Stock Market Prediction Using Machine Learning and Deep Learning

Saudi Stock Market Prediction Using Machine Learning and Dee...

引用

Computing and Information Technology (ICCIT-1441), 2020 international conference on

作者： Raid Mohsen Alhazmi Computer Science University of Tabouk Tabouk KSA

ISBN: (数字)9798350353839

ISBN: (纸本)9798350353846

The research seeks to apply a particular approach to predicting a company's adjusted closing price in hopes of making an advancement in forecasting of the stock price. This research is significant due to its advantages to individuals, corporations, and governments. Approximating a stock's volatility is challenging for traders, and accurate predictions can help investors reduce portfolio risks. Stock prices do not behave in the linear manner. Thus, we suggest the application of artificial intelligence techniques, namely multilayer perceptron (MLP) and long short-term memory (LSTM), to model the changes in Saudi Stock Exchange (Tadawul) index. This research aims at predicting the future of energy, telecommunication, financial, and industrial sectors of the stock exchange. The data was collected from Tadawul for the years 2018–2020 concerning these sectors. The AI algorithms aimed to predict the forthcoming benchmarks for the stock market sectors. The proposed models were tested against actual input data and simulation results, which produced extremely accurate results, demonstrating the effectiveness of the models. In addition, the correlation coefficient (R) of the MLP and LSTM models in predicting the values of Tadawul's four sectors integrated around 0.9950, signifying an exceptional correlation between forecasted and actual results. The forecasts were evaluated using four diverse trials, and between all the algorithms employed, LSTM produced the model's most precise predictions and best-fitting capacity.

关键词： Deep learning Sentiment analysis Analytical models Accuracy Predictive models Prediction algorithms data models Stock markets Forecasting Long short term memory

来源：评论

学校读者我要写书评

暂无评论

data-driven and Physics-informed Muscle Model Surrogates for Cardiac Cycle Simulations 10

Data-driven and Physics-informed Muscle Model Surrogates for...

引用

10th international conference on Electrical, Electronic and Computing Engineering, IcETRAN 2023

作者： Milicevic, Bogdan Ivanovic, Milos Stojanovic, Boban Milosevic, Miljan Simic, Vladimir Kojic, Milos Filipovic, Nenad University of Kragujevac Faculty of Engineering Sestre Janjic 6 Kragujevac3400 Serbia Prvoslava Stojanovica 6 Kragujevac34000 Serbia University of Kragujevac Faculty of Science Radoja Domanovica 12 Kragujevac3400 Serbia Belgrade Metropolitan University Tadeusa Koscuska 63 Belgrade11000 Serbia Institute for Information Technologies University of Kragujevac Jovana Cvijica BB Kragujevac34000 Serbia The Methodist Hospital Research Institute The Department of Nanomedicine HoustonTX77030 United States The Serbian Academy of Sciences and Arts Kneza Mihaila 35 Belgrade11000 Serbia Prvoslava Stojanovica 6 Kragujevac34000 Serbia

ISBN: (纸本)9798350307115

Health professionals can utilize biomechanical simulations of left ventricle to assess different possible situations and hypothetical scenarios. Understanding of the molecular mechanisms behind muscle contraction has resulted in the development of Huxley-like muscle models. Unlike Hill-type muscle models, Huxley-type muscle models can be used to simulate non-uniform and unstable contractions. However, Huxley models demand considerably more computational resources than Hill models, which limits their practical use in large-scale simulations. To address this, we have developed a data-driven and physics-informed surrogate models that mimic the Huxley muscle model, while requiring significantly less processing power. We collected data from various numerical simulations and trained deep neural networks to replace Huxley's muscle model. data-driven surrogate model was an order of magnitude faster than the original model, while being quite accurate. Our surrogate models were integrated into a finite element solver and used to simulate a complete cardiac cycle, which would be much harder to do with original Huxley's model. © 2023 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Natural Language processing in Healthcare: Intelligent System for Extracting Insights from Clinical Text data

Natural Language Processing in Healthcare: Intelligent Syste...

引用

2023 international conference on Evolutionary algorithms and Soft Computing Techniques, EASCT 2023

作者： Rashmi, C. Srinivas, Dava Prabu, S. Santosh Kumar, P.N. Siddiqua, Ayesha Malla Reddy Engineering College for Women It Department Hyderabad India Jyothishmathi Institute of Technology & Science Department of Computer Science and Engineeing Karimnagar India Mahendra Institute of Technology Department of Ece Namakkal India Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350313413

The World Health Organization identified COVID-19 to be a new pandemic in March 2020. This fatal virus spread over the world, affecting many different countries. Massive volumes of useful data were provided by social media platforms like Twitter on the outbreak to help evaluate health-related decision-making. To predict disease occurrence and issue early warnings, thus implement that user's attitudes be evaluated through the use of efficient deep learning. The gathered tweets were pre-processed and divided into three categories like neutral, positive, and negative. In the second step, various features were extracted from the articles using a number of popular techniques to capture feature dataset, including TF-IDF, FastText, and Glove. The implemented TFIDF has combination of semantic features (Glove and FAsText) to accurately describe posts and enhance the classification process utilizing the deep learning method. The implemented TF-IDF-CNN method's performance is evaluated using Twitter dataset. Implemented method achieved better performance than the existing intrusion detection methods including NLP-BiLSTM, TF-IDF, SVM and CF and the metrics are 96% of accuracy, 0.89 of f-measure, 0.93 of precision, and 0.90 of recall. © 2023 IEEE.

关键词： COVID-19 Deep learning Feature extraction Sentiment analysis Twitter

来源：评论

学校读者我要写书评

暂无评论

Mention Flags (MF): Constraining Transformer-based Text Generators 59

Mention Flags (MF): Constraining Transformer-based Text Gene...

引用

Joint conference of 59th Annual Meeting of the Association-for-Computational-Linguistics (ACL) / 11th international Joint conference on Natural Language processing (IJCNLP) / 6th Workshop on Representation Learning for NLP (RepL4NLP)

作者： Wang, Yufei Wood, Ian D. Wan, Stephen Dras, Mark Johnson, Mark Macquarie Univ Sydney NSW Australia CSIRO Data61 Sydney NSW Australia Oracle Corp Oracle Digital Assistant Santa Clara CA USA

ISBN: (纸本)9781954085527

This paper focuses on Seq2Seq (S2S) constrained text generation where the text generator is constrained to mention specific words, which are inputs to the encoder, in the generated outputs. Pre-trained S2S models such as T5 or a Copy Mechanism can be trained to copy the surface tokens from encoders to decoders, but they cannot guarantee constraint satisfaction. Constrained decoding algorithms always produce hypotheses satisfying all constraints. However, they are computationally expensive and can lower the generated text quality. In this paper, we propose Mention Flags (MF), which trace whether lexical constraints are satisfied in the generated outputs of an S2S decoder. The MF models are trained to generate tokens until all constraints are satisfied, guaranteeing high constraint satisfaction. Our experiments on the Common Sense Generation task (CommonGen) (Lin et al., 2020), End2end data-to-Text task (E2ENLG) (Dusek et al., 2020) and Novel Object Captioning task (nocaps) (Agrawal et al., 2019) show that the MF models maintain higher constraint satisfaction and text quality than the baseline models and other constrained text generation algorithms, achieving state-of-the-art performance on all three tasks. These results are achieved with a much lower run-time than constrained decoding algorithms. We also show that the MF models work well in the low-resource setting.(1)

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning on Long-Tailed data via Adversarial Feature Augmentation 48

Personalized Federated Learning on Long-Tailed Data via Adve...

引用

48th IEEE international conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Lu, Yang Qian, Pinxin Huang, Gang Wang, Hanzi Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City Xiamen China Zhejiang Lab Hangzhou China

ISBN: (纸本)9781728163277

Personalized Federated Learning (PFL) aims to learn personalized models for each client based on the knowledge across all clients in a privacy-preserving manner. Existing PFL methods generally assume that the underlying global data across all clients are uniformly distributed without considering the long-tail distribution. The joint problem of data heterogeneity and long-tail distribution in the FL environment is more challenging and severely affects the performance of personalized models. In this paper, we propose a PFL method called Federated Learning with Adversarial Feature Aug-mentation (FedAFA) to address this joint problem in PFL. FedAFA optimizes the personalized model for each client by producing a balanced feature set to enhance the local minority classes. The local minority class features are generated by transferring the knowledge from the local majority class features extracted by the global model in an adversarial example learning manner. The experimental results on benchmarks under different settings of data heterogeneity and long-tail distribution demonstrate that FedAFA significantly improves the personalized performance of each client compared with the state-of-the-art PFL algorithm. The code is available at https://***/pxqian/FedAFA. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Behavioral data Categorization for Transformers-based models in Digital Health

Behavioral Data Categorization for Transformers-based Models...

引用

4th IEEE-EMBS international conference on Wearable and Implantable Body Sensor Networks (BSN) / 18th IEEE-EMBS international conference on Biomedical and Health Informatics (BHI)

作者： Siebra, Clauirton Matias, Igor Wac, Katarzyna Univ Geneva Qual Life Technol Lab Geneva Switzerland

ISBN: (数字)9781665487917

ISBN: (纸本)9781665487917

Transformers are recent deep learning (DL) models used to capture the dependence between parts of sequential data. While their potential was already demonstrated in the natural language processing (NLP) domain, emerging research shows transformers can also be an adequate modeling approach to relate longitudinal multi-featured continuous behavioral data to future health outcomes. As transformers-based predictions are based on a domain lexicon, the use of categories, commonly used in specialized areas to cluster values, is the likely way to compose lexica. However, the number of categories may influence the transformer prediction accuracy, mainly when the categorization process creates imbalanced datasets, or the search space is very restricted to generate optimal feasible solutions. This paper analyzes the relationship between models' accuracy and the sparsity of behavioral data categories that compose the lexicon. This analysis relies on a case example that uses mQoL-Transformer to model the influence of physical activity behavior on sleep health. Results show that the number of categories shall be treated as a further transformer's hyperparameter, which can balance the literature-based categorization and optimization aspects. Thus, DL processes could also obtain similar accuracies compared to traditional approaches, such as long short-term memory, when used to process short behavioral data sequences.

关键词： deep learning transformers human behavior recommendations behavior informatics digital biomarkers

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 << < 27 28 29 30 31 32 33 34 35 36 > >>

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：