检索结果-内蒙古大学图书馆

International Conference on Tools with Artificial Intelligence

作者： Shuhua You Quan Liu Zongzhang Zhang Hui Wang Xiaofang Zhang School of Computer Science and Technology Soochow University Suzhou China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education

ISBN: (纸本)9781509001644

We consider a modular method to reinforcement learning that represents uncertainty of model parameters by maintaining probability distributions over them. The algorithm we call MBDP (model-based Bayesian dynamic programming) can be decomposed into two parallel types of inference: model learning and policy learning. During learning a model, we update posterior distributions of a model over observations after taking an action in each state. During learning a policy, we solve MDPs by dynamic programming with greedy approximation to make an agent choose behaviors which maximize return under the estimated model. Furthermore, we propose a principled method which utilizes the variance of Dirichlet distributions for determining when to learn and relearn the model. We demonstrate that MBDP can find near optimal policies with high probability by sufficient model learning and experimental results show that MBDP performs better compared with current state-of-the-art methods in reinforcement learning.

关键词： reinforcement learning Bayesian dynamic programming model learning policy learning Dirichlet distributions

来源：评论

学校读者我要写书评

暂无评论

Image de-nosing with morphological component analysis

引用

Journal of Information and Computational Science 2015年第5期12卷 1875-1882页

作者： Yang, Chengjia Li, Xiongfei Key Laboratory of Symbolic Computation and Knowledge Engineering for Ministry of Education Jilin University Changchun China Network Information Center Jilin Jianzhu University Changchun China

In this paper, we investigate the problem of image de-noising. Here, the theory of morphological component analysis is employed to separate the image to be de-noised into some layers with different morphological components. In this paper, images are decomposed into two parts: smooth and textural parts. As noise only exists in the textural parts, we utilize bilateral filter to smooth textural parts. Finally, the smooth parts and the filtered textual parts are combined to get the image free of noise. The algorithm is tested experimentally, and the results show that it is superior to other state-of-art algorithms. Copyright © 2015 Binary Information Press.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

PCNN based Otsu multi-threshold segmentation algorithm for noised images

引用

Journal of Computational Information Systems 2015年第21期11卷 7791-7798页

作者： Zhou, Fanghao Li, Xiongfei Zhang, Xiaoli Key Laboratory of Symbolic Computation and Knowledge Engineering for Ministry of Education Jilin University Changchun China College of Computer Science and Technology Jilin University Changchun China

In this paper, a new image segmentation algorithm based on Otsu thresholding. One of attractive feature of this algorithm is its ability of processing noised images. The framework contains three steps: the image to be segmented is first denoised using PCNN (Pulse Coupled Neural Network);then find the optimal thresholds by maximizing the between-class variance;finally, the image can be segmented with the assistance of thresholds. We compared the proposed algorithm with other traditional ones on denoised images. The experimental results also justify the superiority of the proposed segmentation algorithm subjectively and objectively. Copyright © 2015 Binary Information Press.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Detect epistasis based on optimization of artificial neural network architecture and parameters

引用

ICIC Express Letters 2015年第5期9卷 1499-1506页

作者： Zhou, Zhihui Liu, Guixia Su, Lingta Tian, Yuan College of Computer Science and Technology China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University No. 2699 Qianjin Avenue Changchun China

Epistasis or the interaction of single nucleotide polymorphisms (SNPs) at different loci plays a significant role on the mechanisms and pathogenesis of many common complex, multifactorial diseases and may be responsible for the “missing” heredity in genetic epidemiology. A certain complex network of epistatic interactions may contribute to the disease susceptibility. Epistasis detection is a computational and statistical challenge for the absence of prior knowledge of biological data, intensive computational burden and inappropriate statistical tests. Here we investigate the application of a standard artificial neural network (ANN) to detect epistasis for genome-wide association studies (GWAS) for the ability of ANN to model nonlinear data. The pattern-recognition strategy of ANN is utilized in the hope that genotypes of SNP markers will successfully distinguish between cases and controls in a way leading to the ANN being able to classify the SNPs correctly. Using simulated data under a wide range of settings, we show that the proposed ANN can well model gene-gene interactions with good predictive ability. The performance of ANN shows considerable promise and further improvements could usefully be designed towards reducing the computing speed and optimizing implementation of such networks. © 2015, ICIC International.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Selective and incremental fusion for fuzzy and uncertain data based on probabilistic graphical model

Selective and incremental fusion for fuzzy and uncertain dat...

引用

作者： Zhu, Yungang Liu, Dayou Li, Yong Wang, Xinhua College of Computer Science and Technology Jilin University No. 2699 Qianjin Street Changchun China State Key Laboratory of Applied Optics Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences Changchun Jilin China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China College of Mathematics Jilin University Changchun China

Active and dynamic fusion for fuzzy and uncertain data have key challenges such as high complexity and difficult to guarantee accuracy, etc. In order to resolve the challenging issues, in this article a selective and incremental data fusion approach based on probabilistic graphical model is proposed. General Bayesian networks are adopted to represent the relationship among the data and fusion result. It purposively selects the most informative and decision-relevant data for fusion based on Markov Blanket in probabilistic graphical model. Meanwhile we present a special incremental learning method for updating the fusion model to reflect the temporal changes of environment. Theoretical analysis and experimental results all demonstrate the proposed method has higher accuracy and lower time complexity than existing state-of-the-art methods. © 2015 - IOS Press and the authors. All rights reserved.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

Author Correction: Altered structural brain asymmetry in autism spectrum disorder in a study of 54 datasets

引用

Nature communications 2021年第1期12卷 7260页

作者： Merel C Postema Daan van Rooij Evdokia Anagnostou Celso Arango Guillaume Auzias Marlene Behrmann Geraldo Busatto Filho Sara Calderoni Rosa Calvo Eileen Daly Christine Deruelle Adriana Di Martino Ilan Dinstein Fabio Luis S Duran Sarah Durston Christine Ecker Stefan Ehrlich Damien Fair Jennifer Fedor Xin Feng Jackie Fitzgerald Dorothea L Floris Christine M Freitag Louise Gallagher David C Glahn Ilaria Gori Shlomi Haar Liesbeth Hoekstra Neda Jahanshad Maria Jalbrzikowski Joost Janssen Joseph A King Xiang Zhen Kong Luisa Lazaro Jason P Lerch Beatriz Luna Mauricio M Martinho Jane McGrath Sarah E Medland Filippo Muratori Clodagh M Murphy Declan G M Murphy Kirsten O'Hearn Bob Oranje Mara Parellada Olga Puig Alessandra Retico Pedro Rosa Katya Rubia Devon Shook Margot J Taylor Michela Tosetti Gregory L Wallace Fengfeng Zhou Paul M Thompson Simon E Fisher Jan K Buitelaar Clyde Francks Department of Language & Genetics Max Planck Institute for Psycholinguistics Nijmegen The Netherlands. Department of Cognitive Neuroscience Donders Institute for Brain Cognition and Behaviour Donders Centre for Cognitive Neuroimaging Radboud University Medical Centre Nijmegen The Netherlands. Bloorview Research Institute Holland Bloorview Kids Rehabilitation Hospital and Department of Pediatrics University of Toronto Toronto ON USA. Child and Adolescent Psychiatry Department Gregorio Marañón General University Hospital School of Medicine Universidad Complutense IiSGM CIBERSAM Madrid Spain. Institut de Neurosciences de la Timone UMR 7289 Aix Marseille Université CNRS Marseille France. Department of Psychology Carnegie Mellon University Pittsburgh PA USA. Laboratory of Psychiatric Neuroimaging (LIM-21) Departamento e Instituto de Psiquiatria Hospital das Clinicas HCFMUSP Faculdade de Medicina Universidade de Sao Paulo Sao Paulo SP Brazil. IRCCS Stella Maris Foundation viale del Tirreno 331 56128 Pisa Italy. Department of Clinical and Experimental Medicine University of Pisa Pisa Italy. Department of Child and Adolescent Psychiatry and Psychology Hospital Clinic Psychiatry Unit Department of Medicine 2017SGR881 University of Barcelona IDIBAPS CIBERSAM Barcelona Spain. Department of Forensic and Neurodevelopmental Sciences Institute of Psychiatry Psychology & Neuroscience King's College London London UK. Institute for Pediatric Neuroscience NYU Child Study Center New York NY USA. Department of Psychology Ben-Gurion University of the Negev Beer Sheva Israel. Brain Center Rudolf Magnus Department of Psychiatry University Medical Center Utrecht Utrecht The Netherlands. Department of Child and Adolescent Psychiatry Psychosomatics and Psychotherapy University Hospital Goethe University Frankfurt am Main Frankfurt Germany. Imaging Genetics Center Mark and Mary Stevens Neuroimaging and Informatics Institute Keck School of Medicine of USC University o

来源：评论

学校读者我要写书评

暂无评论

Metallogenic prediction based on GIS through automatic database building and extraction of regional gravity and magnetic structure

Metallogenic prediction based on GIS through automatic datab...

引用

International Conference on Electronics, InformationTechnology and Intellectualization, EITI 2014

作者： Ye, S.S. Wang, S.C. Ye, Y.X. Zhao, G.X. Teng, F. Institute of Mineral Resources Prediction with Synthetic Information Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China National Engineering Research Center of Geophysics Exploration Instruments Changchun Jilin University Changchun China Tianjin Institute of Geology and Mineral Resources Tianjin China

ISBN: (纸本)9781138027411

The application of intelligent geophysical interpreting, technology of mapping and database building based on GIS have been discussed under the guidance of the theory and the method of the mineral resources prediction of synthetic information in this paper. The automatic extraction of regional gravity and magnetic structures to build databases has been realized. With the prediction of the iron mine as a case, the whole process of the application of synthetic information in minerals’ prediction of GIS technology has been stated. Through the realization of the data process of regional gravity and magnetic data, and of line-ring structure extraction, geophysical spatial information and map databases have been automatically built. Through a combination of geological and geophysical interpretation, the spatial information and map databases of geophysical ore-finding (iron mine) have been built. Through model units, an ore-finding model of comprehensive information has been built. Through geological units, geophysical-geological spatial information and map databases of synthetic information of predictive models have been built. According to the requirement of different mathematical models for mineral prediction of synthetic information for the data models, the spatial information in the synthetic information databases of predictive models has been extracted, and the geological variables have been converted, and then converted mutually into a digital geological multivariate statistical variable matrix. Different statistic prediction models of the multivariate statistical methods have been established to complete the whole process of metallogenic prediction by the computer. © 2015 Taylor & Francis Group, London.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Survey of active learning for networked data

Survey of active learning for networked data

引用

2015 4th National Conference on Electrical,Electronics and Computer engineering(NCEECE 2015)

作者： Xinlei Wang Bo Yang Jing Huang The College of Computer Science and Technology Jilin University The College of Computer Science and Technology Key laboratory of Symbolic Computation and knowledge EngineeringJilin University

ISBN: (纸本)9781510819085

Classification in networked data is a popular research of complex network. Because of the large scale of networked data and the shortage of training data, active learning, which is an effective classification method for sparse data in machine learning, is often applied to networked data classification problems. Introduced in this paper are classification methods based on active learning for networked data classification problems with basic concepts and algorithms. Finally, according to the existing research, some problems for the future developing and research of networked data classification issues is presented.

关键词： Active Learning Networked Data Classification Machine Learning

来源：评论

学校读者我要写书评

暂无评论

A fast rigid registration algorithm for medical images

引用

Journal of Fiber Bioengineering and Informatics 2014年第3期7卷 409-418页

作者： Feng, Yuncong Li, Xiongfei Zhang, Xiaoli Ding, Tienan Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China Department of Computer Science and Technology Changchun China

Image registration is a vital research branch in medical image processing and analysis. In this paper, we proposed a new framework for rigid medical image registration. It can also be regarded as a pre-processing of non-rigid image registration algorithms. The interest of the algorithm lies in its simplicity and high e±ciency. In the registration algorithm, we firstly segmented the reference image and °oat image into two parts: tissue parts and background parts. Then the centers of the two images were located through performing distance transform on the two segmented tissue images. Finally, we detected the longest radius of the two tissue regions, by which we determined the rotating angle. We tested the registration algorithm on dozens of medical images, and the experimental results show us that the algorithm is competent for medical image registration.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Simplifying Calculation of Graph Similarity Through Matrices

Simplifying Calculation of Graph Similarity Through Matrices

引用

The 9th International Conference on Computer and computing Technologies in Agriculture (CCTA 2015)

作者： Xu Wang Jihong Ouyang Guifen Chen College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University College of Information Technology Jilin Agricultural University

ISBN: (纸本)9783319483535

A method to simplify the calculation in the process of measuring graph similarity is proposed, where lots of redundant operations are avoided in order to quickly obtain the initial tickets matrixIn this proposal, the element value of the initial tickets matrix is assigned to 1 when it is positive in corresponding position of the paths matrix at the first timeThe proposed method calculates the initial tickets matrix value based on the positive value in the paths matrix in a forward and backward wayAn example is provided to illustrate that the method is feasible and effective.

关键词： Graph similarity measure Paths and tickets Adjacency matrix Forward and backward Simplifying calculation

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：