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

1,585 篇 会议
83 册 图书
16 篇 期刊文献

馆藏范围

1,684 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,044 篇 工学
- 874 篇 计算机科学与技术...
- 469 篇 软件工程
- 224 篇 信息与通信工程
- 185 篇 电气工程
- 101 篇 生物工程
- 98 篇 生物医学工程（可授...
- 84 篇 控制科学与工程
- 62 篇 光学工程
- 36 篇 电子科学与技术（可...
- 35 篇 机械工程
- 25 篇 仪器科学与技术
- 24 篇 化学工程与技术
- 21 篇 建筑学
- 21 篇 土木工程
- 20 篇 材料科学与工程（可...
- 20 篇 安全科学与工程
- 19 篇 交通运输工程
352 篇 理学
- 173 篇 数学
- 115 篇 生物学
- 88 篇 物理学
- 52 篇 统计学（可授理学、...
- 36 篇 系统科学
- 22 篇 化学
176 篇 管理学
- 92 篇 图书情报与档案管...
- 89 篇 管理科学与工程(可...
- 45 篇 工商管理
113 篇 医学
- 91 篇 临床医学
- 61 篇 基础医学(可授医学...
- 34 篇 药学(可授医学、理...
33 篇 法学
- 26 篇 社会学
17 篇 教育学
12 篇 经济学
8 篇 农学
3 篇 军事学
3 篇 艺术学
2 篇 文学

主题

237 篇 pattern recognit...
79 篇 cloud computing
74 篇 artificial intel...
71 篇 training
57 篇 feature extracti...
55 篇 neural networks
52 篇 machine learning
49 篇 deep learning
40 篇 computer archite...
36 篇 data mining
34 篇 computer imaging...
33 篇 pattern matching
33 篇 computer vision
32 篇 semantics
29 篇 image segmentati...
28 篇 computational mo...
28 篇 image recognitio...
28 篇 image processing...
27 篇 information syst...
26 篇 edge computing

机构

15 篇 school of comput...
15 篇 university of ch...
9 篇 school of comput...
8 篇 inria nancy gran...
8 篇 national center ...
8 篇 icube université...
8 篇 fujian key labor...
8 篇 erasmus mc - uni...
8 篇 tencent jarvis l...
8 篇 university of ba...
7 篇 college of intel...
6 篇 univ chinese aca...
6 篇 institute of ima...
6 篇 department of co...
6 篇 the 54th researc...
6 篇 school of artifi...
6 篇 dipartimento di ...
6 篇 dipartimento di ...
6 篇 computational sc...
6 篇 institute of com...

作者

13 篇 tan chew lim
12 篇 wang da-han
11 篇 yang jie
8 篇 stéphane cotin
8 篇 yefeng zheng
8 篇 chew lim tan
8 篇 philippe c. catt...
8 篇 marleen de bruij...
8 篇 stefanie speidel
8 篇 caroline essert
8 篇 nicolas padoy
7 篇 maier andreas
7 篇 yang yang
7 篇 hancock edwin r.
7 篇 rita cucchiara
7 篇 alberto del bimb...
6 篇 hugo jair escala...
6 篇 tao mei
6 篇 lu shijian
6 篇 marco bertini

语言

1,664 篇 英文
18 篇 其他
3 篇 中文

检索条件"任意字段=2021 10th International Conference on Computing and Pattern Recognition"

共 1684 条记录，以下是961-970 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：

Real-Time Surface EMG pattern recognition for Shoulder Motions Based on Support Vector Machine 2020

Real-Time Surface EMG Pattern Recognition for Shoulder Motio...

引用

Proceedings of the 2020 9th international conference on computing and pattern recognition

作者： Yang Zhou Chaoyang Chen Mark Cheng Sreten Franovic Stephanie Muh Stephen Lemos Wayne State University Detroit MI USA Department of Biomedical Engineering Wayne State University Detroit Michigan USA Wayne State University Detroit Michigan USA Department of Orthopaedic Surgery Henry Ford Health System Detroit Michigan USA Orthopedic Surgery and Sports Medicine DMC Detroit MI USA

ISBN: (纸本)9781450387835

Surface electromyography (sEMG) signals contain humans' motion intentions and can be used for intuitive control of prostheses or exoskeleton. Although recent research proposes several pattern recognition methods based on sEMG and reported high accuracy, the real-time applications are still limited due to the relatively low accuracy and long time consumption. In this paper, we propose a real-time shoulder motion pattern recognition model based on surface electromyography (sEMG). the Delsys Trigno wireless EMG system with customized LabVIEW program is applied to acquire surface EMG generated by shoulder-related muscles during different shoulder motions. Surface EMG features were extracted and used to create motion recognition. Support Vector Machine (SVM) model was selected and trained for real-time motion recognition. Motion recognition results were given every 135 milliseconds. In order to evaluate the model, an experiment with four shoulder related motions was set up and conducted on five subjects. the experiment result shows that the average accuracy can reach 87.6% in offline training and 85.3% in real-time validation.

关键词： Shoulder motion recognition real-time support vector machine surface electromyography

来源：评论

学校读者我要写书评

暂无评论

Earliest-Arrival Route: A Global Optimized Communication for Networked Control Systems 8th

Earliest-Arrival Route: A Global Optimized Communication for...

引用

8th EAI international conference on Advancement of Science and Technology, ICAST 2020

作者： Rajan, M. Sundar Arunkumar, J.R. Anusuya, R. Mesfin, Abraham Faculty of Electrical and Computer Engineering Arbaminch University Arba Minch Ethiopia Faculty of Computing and Software Engineering Arbaminch University Arba Minch Ethiopia

ISBN: (纸本)9783030806200

As per the present switched system theorem, data package-drop ratio decides the strength of NCSs. through the focal point principle to offer small data package-drop ratio for dispersed NCS under parameter transmission environment, the communication improvement issue is described from universal transmission aspect. Initially, system stimulated break is illustrated function associated with time can be calculated using auto-regressive-moving-average (ARMA) pattern, and the upcoming break is forecasted by the obtained break samples. Subsequently, the widespread referred shortest route of time dependent network(SPTDN) algorithm is described and enhanced by means of introducing waiting-time previous to data packages are dispatched to subsequent unit in a route, in order to get quickly coming time than SPTDN. Subsequently, the concept of earliest-arrival time (EAT) is suggested to calculate the excellence of transmission route, the connected EAT algorithm is intended to look for upcoming EAT and the equivalent route since universal system vigorously. Advantage from the active EAT route, data packages reach at target as early as feasible, it reduces data package-drop ratio. therefore, EAT route make sure the steadiness of shared NCSs from the opinion of worldwide system. At last, the experiment demonstrates the strength and efficiency of the suggested method. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Perceptually Constrained Fast Adversarial Audio Attacks

Perceptually Constrained Fast Adversarial Audio Attacks

引用

international conference on Machine Learning and Applications (ICMLA)

作者： Jason Henry Mehmet Ergezer Marko Orescanin Naval Postgraduate School Monterey CA School of Computing and Data Science Wentworth Institute of Technology Boston MA

ISBN: (纸本)9781665443388

Audio adversarial attacks on deep learning models are of great interest given the commercial success and proliferation of these technologies. these types of attacks have been successfully demonstrated, however, artifacts introduced in the adversarial audio are easily detectable by a human observer. In this work, an expansion of the fast audio adversarial perturbation framework is proposed that can produce an adversarial attack that is imperceptible to a human observer in near-real time using black-box attacks. this is achieved by proposing a perceptually motivated penalty function. We propose a perceptual fast audio adversarial perturbation generator (PFAPG) that employs a loudness constrained loss function, in lieu of a conventional L-2 norm, between the adversarial example and original audio signal. We compare the performance of PFAPG against the conventional constraint based on the MSE on three audio recognition datasets: speaker recognition, speech command, and the Ryerson audiovisual database of emotional speech and song. Our results indicate that, on average, PFAPG equipped with the loudness-constrained loss function yields a 11% higher success rate, while reducing the undesirable distortion artifacts in adversarial audio by 10% dB compared to the prevalent MSE constraints.

关键词： Training Measurement Psychoacoustics Perturbation methods Speech recognition Observers Distortion

来源：评论

学校读者我要写书评

暂无评论

Classical Equivalent Quantum Based pattern Matching Algorithms 10

Classical Equivalent Quantum Based Pattern Matching Algorith...

引用

10th international conference on computing, Communication and Networking Technologies (ICCCNT)

作者： Soni, Kapil Kumar Rasool, Akhtar Maulana Azad Natl Inst Technol Dept Comp Sci & Engn Bhopal MP India

ISBN: (纸本)9781538659069

the pattern matching problem is imperative in diversified field of computer science, and it finds occurrences of the pattern string(s) of any arbitrary length "M" in the large text string of length "N". Since past decades the solutions to a problem have been suggesting through efficient algorithms. Classical benchmark algorithms such as Knuth Morris Pratt and Boyer Moore locates such solution in O(N) time, equivalent quantum algorithms can utilize quantum computations which are inherently parallel and obtains computational speedup by providing the solution in O(root N) time. the quantum pattern matching algorithm uses Grover's search logic that finds an element existence in the large unstructured text data of "N" items in O(root N) time, instead classically it takes O(N) time. the article comprises of introductory pattern matching tactics, quantum basics, Grover's search method, quantum based pattern matching algorithms, their illustration followed by complexity analysis, and finally concludes with the possible algorithmic variations and relevant applications.

关键词： pattern Matching Quantum Bit (Qu-Bit) Quantum Computation Superposition Grover's Search

来源：评论

学校读者我要写书评

暂无评论

Wind Power pattern Prediction in time series measuremnt data for wind energy prediction modelling using LSTM-GA networks 10

Wind Power Pattern Prediction in time series measuremnt data...

引用

10th international conference on computing, Communication and Networking Technologies (ICCCNT)

作者： Vaitheeswaran, Sowmya Sevoor Ventrapragada, Varun Raj Vasavi Coll Engn Hyderabad 500031 Telengana India

ISBN: (纸本)9781538659069

Wind Power forecasts in the short and medium term time horizons are essential for overcoming variable energy productions caused by the changes in weather conditions and fluctuations in wind speed. Wind speed follows a time series pattern in time that can be exploited to forecast for power production. this paper uses a long short term (LSTM) neural network model to predict and validate wind power using time series measurements of an online available wind power measurements. Short term pattern prediction (for accuracy) and mid-term (for stability) are studied for wind power prediction. To increase the reliability of the model a genetic algorithm is used to optimize the window of time capture to alleviate problems of overfitting or an appropriate window size that does not lead to any loss of information. A root mean square error of 0.0957993 and 0.0929905 is obtained for the short term and medium predictions respectively

关键词： Long Short Term Neural Networks Genetic Algorithms Wind Power pattern Prediction

来源：评论

学校读者我要写书评

暂无评论

Automated Segmentation of Lateral Ventricle in MR Images Using Multi-scale Feature Fusion Convolutional Neural Network 25th

Automated Segmentation of Lateral Ventricle in MR Images Usi...

引用

25th international conference on pattern recognition Workshops, ICPR 2020

作者： Ye, Fei Wang, Zhiqiang Hu, Kai Zhu, Sheng Gao, Xieping Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan411105 China College of Medical Imaging and Inspection Xiangnan University Chenzhou423000 China

ISBN: (纸本)9783030687793

Studies have shown that the expansion of the lateral ventricle is closely related to many neurodegenerative diseases, so the segmentation of the lateral ventricle plays an important role in the diagnosis of related diseases. However, traditional segmentation methods are subjective, laborious, and time-consuming. Furthermore, due to the uneven magnetic field, irregular, small, and discontinuous shape of every single slice, the segmentation of the lateral ventricle is still a great challenge. In this paper, we propose an efficient and automatic lateral ventricle segmentation method in magnetic resonance (MR) images using a multi-scale feature fusion convolutional neural network (MFF-Net). First, we create a multi-center clinical dataset with a total of 117 patient MR scans. this dataset comes from two different hospitals and the images have different sampling intervals, different ages, and distinct image dimensions. Second, we present a new multi-scale feature fusion module (MSM) to capture different levels of feature information of lateral ventricles through various receptive fields. In particular, MSM can also extract the multi-scale lateral ventricle region feature information to solve the problem of insufficient feature extraction of small object regions with the deepening of network structure. Finally, extensive experiments have been conducted to evaluate the performance of the proposed MFF-Net. In addition, to verify the performance of the proposed method, we compare MFF-Net with seven state-of-the-art segmentation models. Both quantitative results and visual effects show that our MFF-Net outperforms other models and can achieve more accurate segmentation performance. the results also indicate that our model can be applied in clinical practice and is a feasible method for lateral ventricle segmentation. © 2021, Springer Nature Switzerland AG.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Pretraining Image Encoders without Reconstruction via Feature Prediction Loss

Pretraining Image Encoders without Reconstruction via Featur...

引用

international conference on pattern recognition

作者： Gustav Grund Pihlgren Fredrik Sandin Marcus Liwicki EISLAB Machine Learning Luleå University of Technology Luleå Sweden

this work investigates three methods for calculating loss for autoencoder-based pretraining of image encoders: the commonly used reconstruction loss, the more recently introduced deep perceptual similarity loss, and a feature prediction loss proposed here; the latter turning out to be the most efficient choice. Standard auto-encoder pretraining for deep learning tasks is done by comparing the input image and the reconstructed image. Recent work shows that predictions based on embeddings generated by image autoencoders can be improved by training with perceptual loss, i.e., by adding a loss network after the decoding step. So far the autoencoders trained with loss networks implemented an explicit comparison of the original and reconstructed images using the loss network. However, given such a loss network we show that there is no need for the time-consuming task of decoding the entire image. Instead, we propose to decode the features of the loss network, hence the name “feature prediction loss”. To evaluate this method we perform experiments on three standard publicly available datasets (LunarLander-v2, STL-10, and SVHN) and compare six different procedures for training image encoders (pixel-wise, perceptual similarity, and feature prediction losses; combined with two variations of image and feature encoding/decoding). the embedding-based prediction results show that encoders trained with feature prediction loss is as good or better than those trained with the other two losses. Additionally, the encoder is significantly faster to train using feature prediction loss in comparison to the other losses. the method implementation used in this work is available online.

关键词： Training Deep learning Turning Decoding pattern recognition Task analysis Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?

Is the Meta-Learning Idea Able to Improve the Generalization...

引用

international conference on pattern recognition

作者： Xiang Deng Zhongfei Mark Zhang State University of New York at Binghamton

ISBN: (纸本)9781728188089;9781728188096

Substantial efforts have been made on improving the generalization abilities of deep neural networks (DNNs) in order to obtain better performances without introducing more parameters. On the other hand, meta-learning approaches exhibit powerful generalization on new tasks in few-shot learning. Intuitively, few- shot learning is more challenging than the standard supervised learning as each target class only has a very few or no training samples. the natural question that arises is whether the meta-learning idea can be used for improving the generalization of DNNs on the standard supervised learning. In this paper, we propose a novel meta-learning based training procedure (MLTP) for DNNs and demonstrate that the meta-learning idea can indeed improve the generalization abilities of DNNs. MLTP simulates the meta-training process by considering a batch of training samples as a task. the key idea is that the gradient descent step for improving the current task performance should also improve a new task performance, which is ignored by the current standard procedure for training neural networks. MLTP also benefits from all the existing training techniques such as dropout, weight decay, and batch normalization. We evaluate MLTP by training a variety of small and large neural networks on three benchmark datasets, i.e., CIFAR-10, CIFAR-100, and Tiny ImageNet. the experimental results show a consistently improved generalization performance on all the DNNs with different sizes, which verifies the promise of MLTP and demonstrates that the meta-learning idea is indeed able to improve the generalization of DNNs on the standard supervised learning.

关键词： Training Supervised learning Neural networks Benchmark testing Linear programming pattern recognition Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Aesthetic Nostalgia Mediated Design for Long Distance Relationship 2021

Aesthetic Nostalgia Mediated Design for Long Distance Relati...

引用

10th international conference on Digital and Interactive Arts

作者： Xuqin Yu Masa Inakage Atsuro Ueki Graduate School of Media Design Keio University Japan

ISBN: (纸本)9781450384209

New technology and media platforms are emerging to support communications between Long Distance Relationships (LDRs). But few of them are aiming at a specific emotional expression such as nostalgic feelings. As Svetlana Boym says, nostalgic love can only survive in a Long-Distance Relationship [1]. Nostalgia is a common emotion we feel towards people we loved but living in distance. It has been shown to have benefits for relationship bonding and human well-being [2]. While most nostalgia designs are emphasized on retro style and memory-related uses, nostalgia's aesthetic meanings and reflective attributes are being ignored and lack theoretical *** someone who is absent is just like J. D. Salinger's description about love: "a touch and yet not a touch" [3]. the multi-layered emotion is hard to describe and harder to express over distance. Since nostalgic emotion is a perfect bridge for shortening psychological distance and establishing a real lasting, organic relationship bonding, we believe it is timely to create a new language to deliver this subtle *** this paper, we propose an LDR mediated design concept based on nostalgia theory, followed by two design cases: NostosMoon and NostosLamp. those design cases feature three factors: metaphorical nature-related content, slow and reserved way of interaction, and realized tangible output. We would like to open discussions on how factors that are seemly opposite with closeness actually enhance intimacy and strengthen bonding between LDR groups, thus influence the nostalgia mediated design.

关键词： 2021 YUXUQIN Aveiro Portugal © 2021 Association for computing Machinery. ACM ISBN 978-1-4503-8420-9/21/10…$15.00 https://***/10.1145/3483529.3483745 ATSURO UEKI. 2021. Aesthetic Nostalgia Mediated Design for Long Distance Relationship: In ARTECH 2021 Portugal October 13–15 MASA INAGAKE

来源：评论

学校读者我要写书评

暂无评论

A Model for Fostering Learning Interaction in Hybrid Classroom based on Constructivism theory

A Model for Fostering Learning Interaction in Hybrid Classro...

引用

IIAI international conference on Advanced Applied Informatics (IIAIAAI)

作者： Mohammad Nehal Hasnine Mahmoud Mohamed Hussien Ahmed Hiroshi Ueda Research Center for Computing and Multimedia Studies Hosei University Koganei Japan South Valley University Qena Egypt

ISBN: (纸本)9781665424219

In higher education, the pandemic has caused a dramatic disruption. Due to the disruption, educators are changing their conventional perspectives to reshape the teaching practices. Educators are now relying more on technologies for delivering lecture materials, interaction design, assessment, and engagement detections; and therefore, the conventional active learning models for learning interaction design became hard to implement, particularly in hybrid classrooms. this paper kept three key aspects of education: active learning, learning interaction, and hybrid classroom in the center spots; and explored the pedagogical changes that the higher educational institutions worldwide are experiencing. this article discusses the critical aspects of education under pandemic, including distance learning technologies, learning interaction, hybrid classroom, and learner-centric education. Based on the constructivism learning theory, a model called AL-TST (Active Learning-theory, Strategy, Technology) for increasing learning interaction and bridging the gaps between real space (i.e., in-class learning), virtual space (i.e., electronic learning), and hybridization space (i.e., hybrid learning) is proposed and discussed.

关键词： Electronic learning Pandemics Education Hybrid learning Informatics

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169页 << < 93 94 95 96 97 98 99 100 101 102 > >>

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：