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

6,793 篇 会议
630 册 图书
130 篇 期刊文献

馆藏范围

7,552 篇 电子文献
2 种 纸本馆藏

日期分布

学科分类号

3,899 篇 工学
- 3,090 篇 计算机科学与技术...
- 1,403 篇 软件工程
- 794 篇 电气工程
- 679 篇 信息与通信工程
- 503 篇 控制科学与工程
- 299 篇 生物工程
- 281 篇 生物医学工程（可授...
- 265 篇 机械工程
- 191 篇 光学工程
- 163 篇 电子科学与技术（可...
- 145 篇 仪器科学与技术
- 140 篇 化学工程与技术
- 59 篇 安全科学与工程
- 45 篇 材料科学与工程（可...
- 36 篇 交通运输工程
1,222 篇 理学
- 673 篇 数学
- 356 篇 物理学
- 334 篇 生物学
- 198 篇 统计学（可授理学、...
- 147 篇 化学
- 105 篇 系统科学
553 篇 管理学
- 314 篇 管理科学与工程(可...
- 255 篇 图书情报与档案管...
- 59 篇 工商管理
274 篇 医学
- 230 篇 临床医学
- 109 篇 基础医学(可授医学...
- 75 篇 药学(可授医学、理...
66 篇 法学
- 62 篇 社会学
51 篇 艺术学
- 49 篇 设计学（可授艺术学...
42 篇 农学
- 39 篇 作物学
21 篇 教育学
19 篇 文学
18 篇 经济学
5 篇 军事学

主题

3,150 篇 pattern recognit...
535 篇 feature extracti...
429 篇 artificial intel...
385 篇 neural networks
295 篇 data mining
278 篇 machine learning
234 篇 face recognition
224 篇 pattern matching
215 篇 support vector m...
203 篇 image segmentati...
194 篇 pattern classifi...
193 篇 computer imaging...
183 篇 computer science
182 篇 local binary pat...
168 篇 computational mo...
159 篇 computer vision
147 篇 humans
146 篇 testing
142 篇 accuracy
141 篇 training

机构

40 篇 school of comput...
38 篇 national laborat...
25 篇 institute of ima...
24 篇 center for resea...
24 篇 computer vision ...
22 篇 institute of ima...
22 篇 university of ch...
21 篇 department of co...
20 篇 indian statistic...
19 篇 national laborat...
19 篇 institute of com...
16 篇 tongji universit...
16 篇 chinese academy ...
15 篇 institute for pa...
14 篇 national center ...
14 篇 chinese acad sci...
14 篇 częstochowa univ...
13 篇 agh university o...
13 篇 school of electr...
12 篇 indian stat inst...

作者

35 篇 yang jie
31 篇 de-shuang huang
25 篇 tieniu tan
23 篇 umapada pal
19 篇 ryszard tadeusie...
19 篇 liang wang
18 篇 ajith abraham
17 篇 marcin korytkows...
17 篇 lu hanqing
17 篇 jacek m. zurada
17 篇 leszek rutkowski
16 篇 jie yang
16 篇 zhenan sun
16 篇 shamsuddin siti ...
16 篇 pal umapada
15 篇 wang da-han
15 篇 chew lim tan
15 篇 rafał scherer
14 篇 xu changsheng
14 篇 lotfi a. zadeh

语言

7,403 篇 英文
84 篇 其他
77 篇 中文

检索条件"任意字段=International Conference on Soft Computing and Pattern Recognition"

共 7554 条记录，以下是241-250 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 novel hardware-efficient liquid state machine of non-simultaneous CA-based neurons for spatio-temporal pattern recognition

A novel hardware-efficient liquid state machine of non-simul...

引用

international Joint conference on Neural Networks (IJCNN)

作者： Takeda, Kentaro Torikai, Hiroyuki Kagawa Univ Fac Engn & Design Takamatsu Kagawa Japan Hosei Univ Fac Sci & Engn Tokyo Japan

ISBN: (纸本)9781665488679

In this paper, a novel liquid state machine (LSM) comprising neurons whose nonlinear dynamics are described by a non-simultaneous cellular automaton (CA) is proposed. The proposed LSM is applied to a supervised classification task. It is shown that the proposed LSM can recognize spatiotemporal spike patterns with high accuracy. Furthermore, the non-simultaneous CA-based neuron is implemented on a field programmable gate array (FPGA), and an experiment validates its spiking function. It is then shown that the non-simultaneous CA-based neuron occupies fewer FPGA resources compared with typical conventional neuron models, such as the Izhikevich, leaky integrate-and-fire, quadratic integrate-and-fire, and Morris-Lecar neurons.

关键词： Reservoir computing (RC) liquid state machine (LSM) spiking neural network (SNN) cellular automaton (CA) field programmable gate array (FPGA)

来源：评论

学校读者我要写书评

暂无评论

Classifying Me softly: A Novel Graph Neural Network Based on Features soft-Alignment

Classifying Me Softly: A Novel Graph Neural Network Based on...

引用

joint IAPR international Workshop on Structural and Syntactic pattern recognition (SSPR) / Statistical Techniques in pattern recognition (SPR)

作者： Bicciato, Alessandro Cosmo, Luca Minello, Giorgia Rossi, Luca Torsello, Andrea Ca Foscari Univ Venice Venice Italy IESE Business Sch Barcelona Spain Queen Mary Univ London London England

ISBN: (纸本)9783031230271;9783031230288

Graph neural networks are increasingly becoming the framework of choice for graph-based machine learning. In this paper we propose a new graph neural network architecture based on the soft-alignment of the graph node features against sets of learned points. In each layer of the network the input node features are transformed by computing their similarity with respect to a set of learned features. The similarity information is then propagated to other nodes in the network, effectively creating a message passing-like mechanism where each node of the graph individually learns what is the optimal message to pass to its neighbours. We perform an ablation study to evaluate the performance of the network under different choices of its hyper-parameters. Finally, we test our model on standard graph-classification benchmarks and we find that it outperforms widely used alternative approaches, including both graph kernels and graph neural networks.

关键词： Graph neural network Deep learning

来源：评论

学校读者我要写书评

暂无评论

Cell-like SNP System with Several Types of Spikes and Generation of Basic Picture Languages

Cell-like SNP System with Several Types of Spikes and Genera...

引用

international conference on Computer Vision and Internet of Things 2023, ICCVIoT 2023

作者： Ceon, Y. Preethi Christinal, A. Hepzibah Jebasingh, S. Chandy, D. Abraham Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9781839539848

A basic picture language consists of basic pictures (patterns) described using strings over finite alphabets and generated using the Chomsky form of grammars. Spiking Neural P Systems (SN P Systems) is a nature inspired computing in which the transformation of collections of elements occurs through the absorption of an existing elements within a membrane -like structure and concurrently producing a new multiset of alphabets. It was found to compute string language and functions. pattern recognition and image processing are practical applications stemming from the scientific exploration of picture languages and the grammatical structures used to generate them. In this paper, we compare the family of basic picture languages generated by regular, linear, and context free grammars with the family of languages generated by cell-like spiking neural P system with several types of Spikes. © The Institution of Engineering & Technology 2023.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Fermatean Fuzzy Type a Three-Way Correlation Coefficients 4th

Fermatean Fuzzy Type a Three-Way Correlation Coefficients

引用

international conference on Mathematics and its Applications in Science and Engineering (ICMASE)

作者： Kirisci, Murat Istanbul Univ Cerrahpasa Istanbul Turkiye

ISBN: (纸本)9783031492204;9783031492181;9783031492174

In challenging decision-making circumstances, tools like aggregation operators and information measures are routinely used. Using correlation coefficient (KK)'s estimate of the amount of reliance between two sets is another way to decide whichchoice isbetter. Thereareafewmethods forfiguring outtheKKofFermatean fuzzy sets (FFSs). These previous methodologies, which are specified between leftbracket0comma1rightbracket.[0, 1], simply evaluate the strength of the link between FFSs. This study, using the notions of variance and covariance, respectively, provides a three-way method for computing the KKs between FFSs. The strength of the association between the considered FFSs is demonstrated by this novel approach, which is defined inside the interval leftbracketnegative1comma1rightbracket.[-1, 1] similar to standard statistics, and it identifies whether the FFSs are positivelyornegativelyassociated. Thepotentialofinaccuracyowingtoinformation leakage is reasonably mitigated by the suggested technique's inclusion of the three traditional FFSs parameters. To demonstrate the new technique's usefulness as an accurate information measure, several theoretical results will be used to validate it. The advantages of the new methods over comparable methods will be demonstrated using a few numerical examples. With the help of the novel approach, several decision-making issues involving pattern recognition and diagnostic medicine will be handled. Multi-attribute decision-making issues can be resolved using the threeway technique for determining the correlation coefficient between FFSs.

关键词： Correlation coefficient Fermatean fuzzy set Medical decision-making pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Ambient Intelligence Ecosystem for Elderly pattern Detection and Care Using Social Robots 17

Ambient Intelligence Ecosystem for Elderly Pattern Detection...

引用

IEEE Congress on Cybermatics: 17th IEEE international conference on Internet of Things, iThings 2024, 20th IEEE international conference on Green computing and Communications, GreenCom 2024, 17th IEEE international conference on Cyber, Physical and Social computing, CPSCom 2024, 10th IEEE international conference on Smart Data, SmartData 2024

作者： Gómez-Ramos, Raúl Duque-Domingo, Jaime Zalama, Eduardo Gómez-García-Bermejo, Jaime ITAP-DISA University of Valladolid Cartif Technological Center Valladolid Spain University of Valladolid ITAP-DISA Valladolid Spain

ISBN: (纸本)9798350351637

This article presents an ambient intelligence system to provide support and security to residents living alone, particularly in supervised domiciles. It confronts the challenges arising from the burgeoning elderly population in Europe, many of whom opt for independent living. The system combines non-intrusive sensors, a social robot, and algorithms geared towards activity monitoring and anomaly detection. Central to its functionality is the monitoring of activities, employing a hierarchical Hidden Markov Model (HMM)-based Human Activity recognition (HAR) system. This system adeptly discerns the Activities of Daily Living (ADLs) performed by users, enabling swift interventions or alerts in instances of emergencies. Furthermore, anomalies such as prolonged periods of inactivity or nocturnal wanderings are promptly identified, triggering requisite responses to ensure user safety and well-being. A key component is the cognitive system, which establishes rules for actions predicated on data gleaned from the HAR module and anomaly detection. This enables interactions with the social robot and interventions within the environment. Validation and performance evaluation in real-world scenarios underscore the system's efficacy, with high precision, recall, and F1Score metrics reported for the HAR module. © 2024 IEEE.

关键词： Ambient intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on Denoising Algorithm of Orthopedic CT Image Based on Wavelet soft Threshold Filtering

Research on Denoising Algorithm of Orthopedic CT Image Based...

引用

2023 international conference on Networking, Informatics and computing, ICNETIC 2023

作者： Liu, Haoyu Nanchang University Queen Mary School Medical College Nanchang330006 China Queen Mary University of London School of Biological and Chemical Science Biological Science LondonE1 4NS United Kingdom

ISBN: (纸本)9798350313314

Influenced by relevant conditions, digital images are easily disturbed by external noise in the process of generation, transmission and compression, which makes the image edges and texture details blurred, which is not conducive to the recognition and reading of image information. As far as orthopedic CT images are concerned, when the attenuation coefficients of diseased tissues are very close to those of normal tissues, the existence of noise will reduce the signal-to-noise ratio of the images, which will directly lead to some feature details of the images being submerged in the image noise and unrecognizable. The research on denoising algorithm of orthopedic CT image based on wavelet soft threshold filtering is carried out. In this paper, an improved method based on extreme median filtering and wavelet soft threshold denoising algorithm is proposed to remove the mixed impulse noise and Gaussian white noise in the image. Firstly, the image with mixed noise is filtered by the improved median filtering algorithm based on extreme value, and the impulse noise is removed, so that the image with only Gaussian noise is obtained. The wavelet coefficients obtained are quantized by the improved threshold to obtain the estimated wavelet coefficients. The estimated wavelet coefficients are inversely transformed to reconstruct the image, and the denoised image is obtained. The research shows that wavelet soft threshold filtering has the best denoising effect, MSE, EPI and expert evaluation values are 1.2358, 0.9276 and 88 respectively. This method can protect the edge information and improve the visual effect while effectively denoising, which shows that this method also has high denoising ability. © 2023 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Factors that Influence Reliability of Biometric Identification for On-Scene Smart Healthcare Applications 3

Factors that Influence Reliability of Biometric Identificati...

引用

3rd international conference on computing and Machine Intelligence (ICMI)

作者： Hong, Guanyue Fong, A. C. M. Western Michigan Univ Dept Comp Sci Kalamazoo MI 49008 USA

ISBN: (纸本)9798350372977;9798350372984

In a medical emergency situation, such as a traffic accident, effective and efficient identification of patients can improve the chances of survival for critically injured patients. In some cases, the patients may be unconscious when paramedics arrive at the scene. Timely and successful identification of patient in varying states of injury and/or consciousness can provide the attending paramedics with vital information about the patients' medical records, thereby allowing them to provide the patients with the most appropriate life-saving on-scene medical interventions. Major improvements in miniaturized biometric hardware, low-power telecommunication devices, efficient biometric identification platforms, and energy-efficient artificial intelligent-enhanced data processing techniques all contribute towards the next generation of smart on-scene patient identification, even for paramedics attending at emergency sites in remote locations. This paper focuses specifically on fingerprint acquisition and processing, as fingerprints are among the most popular biometrics used for identification. In addition to fingerprint identification for patients, it is also useful for quick and effective identification of medical personnel for access to resources like ambulances. Specifically, the purpose of this research is to investigate factors that can enhance the reliability of such identification systems in practical scenarios involving some form of telecommunications backbone, which are typically much more unforgiving than comparable laboratory settings.

关键词： Biometric identification fingerprint identification pattern recognition mission-critical applications smart healthcare smart cities prognostics telehealth telecommunications in harsh operating environments

来源：评论

学校读者我要写书评

暂无评论

Bento Packaging Activity recognition with Convolutional LSTM Using Autocorrelation Function and Majority Vote 1

引用

3rd international conference on Activity and Behavior computing (ABC)

作者： Fujii, Atsuhiro Yoshida, Kazuki Shirai, Kiichi Murao, Kazuya Ritsumeikan Univ Grad Sch Informat Sci & Engn 1-1-1 Nojihigashi Kusatsu Shiga 5258577 Japan

ISBN: (数字)9789811903618

ISBN: (纸本)9789811903618;9789811903601

This paper reports Bento Packaging Activity recognition Challenge by team "RitsBen" held in the international conference on Activity and Behavior computing (ABC 2021). Our approach used an autocorrelation function in the preprocessing to isolate the data since the dataset was given with repetitive activity. We then use a model that implements convolutional layers and LSTM. The final decision is made by majority vote using sigmoid predictions output from all body parts. The loss is calculated using BCEWithLogitsLoss for each body part. The evaluation results showed that average accuracy of 0.123 was achieved among subjects 1, 2, and 3 in leave-one-subject-out manner. However, we did not achieve high accuracy as the possibility that the extraction of repetitive actions was not correct.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

DenseGAP: Graph-Structured Dense Correspondence Learning with Anchor Points 26

DenseGAP: Graph-Structured Dense Correspondence Learning wit...

引用

26th international conference on pattern recognition / 8th international Workshop on Image Mining - Theory and Applications (IMTA)

作者： Kuang, Zhengfei Li, Jiaman He, Mingming Wang, Tong Zhao, Yajie Univ Southern Calif Los Angeles CA USA USC Inst Creat Technol Los Angeles CA USA Stanford Univ Stanford CA USA

ISBN: (数字)9781665490627

ISBN: (纸本)9781665490627

Establishing dense correspondence between two images is a fundamental computer vision problem, which is typically tackled by matching local feature descriptors. However, without global awareness, such local features are often insufficient for disambiguating similar regions. And computing the pairwise feature correlation across images is both computation-expensive and memory-intensive. To make the local features aware of the global context and improve their matching accuracy, we introduce DenseGAP, a new solution for efficient Dense correspondence learning with a Graph-structured neural network conditioned on Anchor Points. Specifically, we first propose a graph structure that utilizes anchor points to provide sparse but reliable prior on inter- and intra-image context and propagates them to all image points via directed edges. We also design a graph-structured network to broadcast multi-level contexts via light-weighted message-passing layers and generate high-resolution feature maps at low memory cost. Finally, based on the predicted feature maps, we introduce a coarse-to-fine framework for accurate correspondence prediction using cycle consistency. Our feature descriptors capture both local and global information, thus enabling a continuous feature field for querying arbitrary points at high resolution. Through comprehensive ablative experiments and evaluations on large-scale indoor and outdoor datasets, we demonstrate that our method advances the state-of-the-art of correspondence learning on most benchmarks.

关键词： Computer vision Costs Correlation Image edge detection Neural networks Estimation pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Innovative Deep Learning Techniques for Solving Complex Computer Vision Challenges and Enhancing pattern recognition Accuracy

Innovative Deep Learning Techniques for Solving Complex Comp...

引用

2024 international conference on Distributed Systems, Computer Networks and Cybersecurity, ICDSCNC 2024

作者： Jayachitra, T. Sathya, S. Ramesh, P.S. Jothikumar, R. Gouri, M.S. Hussain, Mohammed Waheeduddin Sharda University Department of Electrical Electronics and Communication Engineering Greater Noida India Grt Institute of Engineering and Technology Department of Artificial Intelligence and Data Science Tiruttani India Vellore Institute of Technology Department of Smart Computing Vellore India Shadan College of Engineering and Technology Department of Computer Science and Engineering Hyderabad India Baselios Mathews - Ii College of Engineering Department of Computer Science and Engineering Sasthamcotta Kollam India Shadan College of Engineering and Technology Department of Information Technology Peerancheru Hyderabad India

ISBN: (纸本)9798350375442

The proposed work provides an in-depth analysis of DL techniques to enhance pattern recognition accuracy in difficult computer vision applications. This background explains the present status of the problems in the area and motivates the development of a complex framework that blends innovative neural network topologies, state-of-the-art optimization approaches, and inventive data augmentation strategies. Among the methods are CNNs enhanced with residual blocks and attention mechanisms, which are implemented using the TensorFlow deep learning framework. The results demonstrate significant improvements over baseline models on a number of measures. Using the CIFAR-10 dataset, the proposed system achieves an impressive 92.5% accuracy and 92.1% F1-score for classification tasks. With an IoU of 78.2% and a mAP of 81.4% in object identification tasks, the system shows its robustness in accurately localizing and recognizing things within photos. These findings have practical ramifications for industries needing accurate visual identification, such autonomous driving and medical imaging, in addition to advancing theoretical knowledge. The efficacy of the architecture highlights its potential to serve as a benchmark for next deep learning studies and applications. © 2024 IEEE.

关键词： Stochastic systems

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 << < 21 22 23 24 25 26 27 28 29 30 > >>

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：