检索结果-内蒙古大学图书馆

16th international conference on Advanced Data Mining and Applications, ADMA 2020

ISBN: (纸本)9783030653897

The proceedings contain 49 papers. The special focus in this conference is on Advanced Data Mining and Applications. The topics include: FabricGene: A Higher-Level Feature Representation of Fabric patterns for Nationality Classification;low-Light Image Enhancement with Color Transfer Based on Local Statistical Feature;role-Aware Enhanced Matching Network for Multi-turn Response Selection in Customer Service Chatbots;SS-AOE: Subspace Based Classification Framework for Avoiding Over-Confidence Errors;influence Maximization Based Active Learning in Noisy Setting;DGRL: Text Classification with Deep Graph Residual Learning;Densely Connected Bidirectional LSTM with Max-Pooling of CNN Network for Text Classification;a Context-Aware computing Method of Sentence Similarity Based on Frame Semantics;preface;subspace-Weighted Consensus Clustering for High-Dimensional Data;learning the Concept Embeddings of Ontology;ATextCNN Model: A New Multi-classification Method for Police Situation;hierarchical and Pairwise Document Embedding for Plagiarism Detection;evolutionary Strategy for Graph Embedding;D2NE: Deep Dynamic Network Embedding;elaborating the Bayesian Priors in Unsupervised Graph Embedding via Graph Concepts;tuser3: A Profile Matching Based Algorithm Across Three Heterogeneous Social Networks;encrypted Traffic Classification Using Graph Convolutional Networks;Representing EHRs with Temporal Tree and Sequential pattern Mining for Similarity computing;research of Medical Aided Diagnosis System Based on Temporal Knowledge Graph;NOV-RSI: A Novel Optimization Algorithm for Mining Rare Significance Itemsets;TOP-R Keyword-Aware Community Search;online Community Identification over Heterogeneous Attributed Directed Graphs;MPB: Multi-Peak Binarization for Pupil Detection;rice Leaf Diseases recognition Using Convolutional Neural Networks;STCNet: Spatial-Temporal Convolution Network for Traffic Speed Prediction;Discriminative Features Generation for Mortality Prediction in ICU;motion

关键词：

来源：评论

学校读者我要写书评

暂无评论

G-GANISR: Gradual generative adversarial network for image super resolution

引用

NEUROcomputing 2019年 366卷 140-153页

作者： Shamsolmoali, Pourya Zareapoor, Masoumeh Wang, Ruili Jain, Deepak Kumar Yang, Jie Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China Tokyo Univ Technol Dept Comp Sci Tokyo Japan Massey Univ Inst Nat & Math Sci Auckland New Zealand Chinese Acad Sci Inst Automat Beijing Peoples R China

Adversarial methods have demonsterated to be signifiant at generating realistic images. However, these approaches have a challenging training process which partially attributed to the performance of discriminator. In this paper, we proposed an efficient super-resolution model based on generative adversarial network (GAN), to effectively generate reprehensive information and improve the test quality of the real-world images. To overcome the current issues, we designed the discriminator of our model based on the Least Square Loss function. The proposed network is organized by a gradual learning process from simple to advanced, which means from the small upsampling factors to the large upsampling factor that helps to improve the overall stability of the training. In particular, to control the model parameters and mitigate the training difficulties, dense residual learning strategy is adopted. Indeed, the key idea of proposed methodology is (i) fully exploit all the image details without losing information by gradually increases the task of discriminator, where the output of each layer is gradually improved in the next layer. In this way the model efficiently generates a super-resolution image even up to high scaling factors (e.g. x 8). (ii) The model is stable during the learning process, as we use least square loss instead of cross-entropy. In addition, the effects of different objective function on training stability are compared. To evaluate the model we conducted two sets of experiments, by using the proposed gradual GAN and the regular GAN to demonstrate the efficiency and stability of the proposed model for both quantitative and qualitative benchmarks. (C) 2019 Published by Elsevier B.

关键词： Image super-resolution Loss functions GAN CNN Gradual learning

来源：评论

学校读者我要写书评

暂无评论

Face recognition with Kernel Principal Component Analysis and Support Vector Machine 1

Face Recognition with Kernel Principal Component Analysis an...

引用

1st international conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Liliana, Dewi Yanti Setiawan, I. Made Agus State Polytech Jakarta Dept Informat & Comp Depok Indonesia Udayana Univ Denpasar Indonesia Univ Pittsburgh Pittsburgh PA 15260 USA

ISBN: (纸本)9781728129303

Machine learning and pattern recognition recently become a hot topic in computing world. This is due to the fast-growing of resources as well as techniques that make it easier to solve machine learning and pattern recognition problems. Problems that require machine learning solutions may be very simple for humans but actually can be very complex for machines to solve them. Face recognition is amongst those problems. Almost all human can easily recognize others without require specific knowledge to do it, different from machines which require its. This paper discussed face recognition task using machine learning strategies which involved Kernel Principal Component Analysis (KPCA) and Support Vector Machine (SVM) to identify person. KPCA extracted features from 2D image input and produced the important features of an image input. The extracted face features are recognized by SVM by classifying human face according to their stored identity in a database. SVM, which was basically a binary classifier worked by using one-against-one strategy to compare the face feature vector of a single test image to the stored face image in a face image database. Experiment results on grayscale images with size 92x112 pixels gave 96.25% of accuracy rate. Hence, KPCA and SVM for face recognition is a robust machine learning method.

关键词： face recognition kernel eigenface kernel PCA machine learning pattern recognition support vector machine

来源：评论

学校读者我要写书评

暂无评论

18th international conference on Intelligent Data Analysis, IDA 2020

18th International Conference on Intelligent Data Analysis, ...

引用

18th international conference on Intelligent Data Analysis, IDA 2020

ISBN: (纸本)9783030445836

The proceedings contain 45 papers. The special focus in this conference is on Intelligent Data Analysis. The topics include: computing Vertex-Vertex Dissimilarities Using Random Trees: Application to Clustering in Graphs;Evaluation of CNN Performance in Semantically Relevant Latent Spaces;Vouw: Geometric pattern Mining Using the MDL Principle;A Consensus Approach to Improve NMF Document Clustering;discriminative Bias for Learning Probabilistic Sentential Decision Diagrams;Widening for MDL-Based Retail Signature Discovery;addressing the Resolution Limit and the Field of View Limit in Community Mining;estimating Uncertainty in Deep Learning for Reporting Confidence: An Application on Cell Type Prediction in Testes Based on Proteomics;adversarial Attacks Hidden in Plain Sight;dual Sequential Variational Autoencoders for Fraud Detection;enriched Weisfeiler-Lehman Kernel for Improved Graph Clustering of Source Code;Overlapping Hierarchical Clustering (OHC);digital Footprints of international Migration on Twitter;percolation-Based Detection of Anomalous Subgraphs in Complex Networks;a Late-Fusion Approach to Community Detection in Attributed Networks;reconciling Predictions in the Regression Setting: An Application to Bus Travel Time Prediction;a Distribution Dependent and Independent Complexity Analysis of Manifold Regularization;actionable Subgroup Discovery and Urban Farm Optimization;AVATAR - Machine Learning Pipeline Evaluation Using Surrogate Model;detection of Derivative Discontinuities in Observational Data;a Principled Approach to Analyze Expressiveness and Accuracy of Graph Neural Networks;improving Prediction with Causal Probabilistic Variables;DO-U-Net for Segmentation and Counting: Applications to Satellite and Medical Images;enhanced Word Embeddings for Anorexia Nervosa Detection on Social Media;event recognition Based on Classification of Generated Image Captions;supervised Phrase-Boundary Embeddings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicate Clustering-Based Entity-Centered Graph pattern recognition for Query Extension on the LOD 12th

Predicate Clustering-Based Entity-Centered Graph Pattern Rec...

引用

12th international conference on Innovative Mobile and Internet Services in Ubiquitous computing (IMIS)

作者： Kim, Jongmo Kong, Junsik Park, Daeun Sohn, Mye Sungkyunkwan Univ Suwon South Korea

ISBN: (纸本)9783319935546;9783319935539

In this paper, we propose a method to reduce the difficulties of query caused by lack of information about graph patterns even though the graph pattern is one of the important characteristics of the LOD. To do so, we apply the clustering methodology to find the RDF predicates that have similar patterns. In addition, we identify representative graph patterns that imply its characteristics each cluster. The representative graph patterns are used to extend the users' query graphs. To show the difficulties of the query on the LOD, we developed an illustrative example. We propose the novel framework to support query extension using predicate clustering-based entity-centered graph patterns. Through the implementation of this framework, the user can easily query the LOD and at the same time collect appropriate query results.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Why is the Winner the Best?

引用

conference on Computer Vision and pattern recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

international benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

2nd international conference of Artificial Intelligence, Medical Engineering, Education, AIMEE 2018

2nd International Conference of Artificial Intelligence, Med...

引用

2nd international conference of Artificial Intelligence, Medical Engineering, Education, AIMEE 2018

ISBN: (纸本)9783030120818

The proceedings contain 70 papers. The special focus in this conference is on Artificial Intelligence, Medical Engineering, Education. The topics include: On Genetic Unitary Matrices and Quantum-Algorithmic Genetics;genetic Code Modelling from the Perspective of Quantum Informatics;focal Model in the pattern recognition Problem;experimental Detection of the Parallel Organization of Mental Calculations of a Person on the Basis of Two Algebras Having Different Associativity;determinant Optimization Method;analysis of Oscillator Ensemble with Dynamic Couplings;the Genetic Language: Natural Algorithms, Developmental patterns, and Instinctive Behavior;planck–Shannon Classifier: A Novel Method to Discriminate Between Sonified Raman Signals from Cancer and Healthy Cells;ECG Signal Spectral Analysis Approaches for High-Resolution Electrocardiography;intelligent System for Health Saving;A Life Ecosystem Management with DNA Base Complementarity;novel Approach to a Creation of Probe to Stop Bleeding from Esophageal Varicose Veins Based on Spiral-Compression Method;parallel Mechanisms in Layout of Human Musculoskeletal System;methods of Mutual Analysis of Random Oscillations in the Problems of Research of the Vertical Human Posture;verification of Mathematical Model for Bioimpedance Diagnostics of the Blood Flow in Cerebral Vessels;evaluation of Adhesive Bond Strength of Dental Fiber Posts by “Torque-Out” Test;image Segmentation Method Based on Statistical Parameters of Homogeneous Data Set;steganographic Protection Method Based on Huffman Tree;the Role of Hybrid Classifiers in Problems of Chest Roentgenogram Classification;patient-Specific Biomechanical Analysis in Computer Planning of Dentition Restoration with the Use of Dental Implants;a Viscoelastic Model of the Long-Term Orthodontic Tooth Movement.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Oscillator Based Energy Efficient computing Architecture for Smart Sensors 62

An Oscillator Based Energy Efficient Computing Architecture ...

引用

62nd IEEE international Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Zhang, Ting Lu, Ruikuan Haider, Mohammad Alexander, J. Iwan D. Massoud, Yehia Univ Alabama Birmingham UAB Sch Engn Birmingham AL 35294 USA Stevens Inst Technol Sch Syst & Enterprises Hoboken NJ 07030 USA

ISBN: (纸本)9781728127880

In the past decade, there is a fast-growing need for sensing technology applications. However, the implementation of sensing and proceeding creates a large burden on data processing. The idea for designing stable cluster state for coupled phase oscillator in pattern recognition is receiving significant attention. This paper gives an overview of an oscillator neural network (ONN) based hierarchical associative memory (AM) architecture using oscillator synchronization and stable cluster state for pattern recognition and how such architecture can be efficiently used in local processing units. The ONN based AM architecture can be easily achieved using CMOS technology on local hardware units. Unlike cloud computing system, our architecture provides an approach when it is under an offline mode which couldn't get responses from the web server. The proposed architecture can help perform sensing and data processing efficiently on the local device without connecting to the Internet.

关键词： ONN synchronization stable cluster state energy efficiency hierarchical AM pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Recognizing Hand-Woven Fabric pattern Designs Based on Deep Learning

Recognizing Hand-Woven Fabric Pattern Designs Based on Deep ...

引用

international conference on Computer, Communication and Computational Sciences (IC4S)

作者： Puarungroj, Wichai Boonsirisumpun, Narong Loei Rajabhat Univ Fac Sci & Technol Comp Sci Dept Loei 42000 Thailand

ISBN: (纸本)9789811368615;9789811368608

Hand-woven fabric pattern designs commonly represent the tradition and culture of local communities. pattern recognition methods can help classify these pattern designs without having to find an expert. The research aims at recognizing woven fabric pattern designs of traditional fabrics called Phasin in Loei province, Thailand based on deep learning methods. In recognizing pattern design, three deep learning models were experimented: Inception-v3, Inception-v4, and MobileNets. The research collected images of real silk fabrics containing 10 pattern designs. For each pattern, there were 180 images segmented and there were 1,800 images in total in the dataset. The data were trained and tested based on 10-fold cross-validation approach. The results of the test show that MobileNets outperforms Inception-v3 and Inception-v4. The test accuracy rates of pattern design recognition for MobileNets, Inception-v3, and Inception-v4 are 94.19, 92.08, and 91.81%, respectively. The future work will be done by carrying out more data training to increase performance, obtaining more pattern designs, and developing an application based on a high-performance model.

关键词： pattern recognition Deep learning Convolutional neural network Weaving pattern Loei Phasin Fabric pattern design

来源：评论

学校读者我要写书评

暂无评论

Diving deep in Deep Convolutional Neural Network

Diving deep in Deep Convolutional Neural Network

引用

international conference on Advances in computing, Communication Control and Networking (ICACCCN)

作者： Divya Arora Mehak Garg Megha Gupta Guru Gobind Singh Indraprastha University Delhi India

ISBN: (数字)9781728183374

ISBN: (纸本)9781728183381

Artificial Neural networks have been proved most efficient in Deep Learning mainly because of large number of datasets it can handle. The most widely used is the Convolutional Neural Network (CNN). It has been proved useful for computer vision, pattern recognition and Natural Language Processing (NLP). CNN is so vastly used, as, unlike traditional Neural Nets, it reduces number of parameters and focus more on domain specific features. There are various CNN architectures proposed, such as LeNet, AlexNet, GoogleNet. In this paper, we talk about structure of CNN and all the models of CNN which are proposed till date.

关键词： Deep learning Error analysis Learning (artificial intelligence) Tools Natural language processing pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：