检索结果-内蒙古大学图书馆

9th International Conference on machine Learning and Applications, ICMLA 2010

作者： Karnowski, Thomas P. Arel, Itamar Rose, Derek Image Science and Machine Vision Group Oak Ridge National Laboratory Oak Ridge TN 37831 United States Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN 37996 United States

ISBN: (纸本)9780769543000

Deep machine learning is an emerging framework for dealing with complex high-dimensionality data in a hierarchical fashion which draws some inspiration from biological sources. Despite the notable progress made in the field, there remains a need for an architecture that can represent temporal information with the same ease that spatial information is discovered. In this work, we present new results using a recently introduced deep learning architecture called Deep Spatio-Temporal Inference Network (DeSTIN). DeSTIN is a discriminative deep learning architecture that combines concepts from unsupervised learning for dynamic pattern representation together with Bayesian inference. In DeSTIN the spatiotemporal dependencies that exist within the observations are modeled inherently in an unguided manner. Each node models the inputs by means of clustering and simple dynamics modeling while it constructs a belief state over the distribution of sequences using Bayesian inference. We demonstrate that information from the different layers of this hierarchical system can be extracted and utilized for the purpose of pattern classification. Earlier simulation results indicated that the framework is highly promising, consequently in this work we expand DeSTIN to a popular problem, the MNIST data set of handwritten digits. The system as a preprocessor to a neural network achieves a recognition accuracy of 97.98% on this data set. We further show related experimental results pertaining to automatic cluster adaptation and termination. © 2010 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Flatten hierarchies for large-scale hierarchical text categorization

Flatten hierarchies for large-scale hierarchical text catego...

引用

International Conference on Digital Information Management

作者： Wang, Xiao-Lin Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781424475728

Hierarchies are very popular in organizing documents and web pages, hence automated hierarchical classification techniques are desired. However, the current dominant hierarchical approach of top-down method suffers accuracy decrease compared with flat classification approaches, because of error propagation and bottom nodes' data sparsity. In this paper we flatten hierarchies to relieve such accuracy decrease in top-down method, which aims to make hierarchies both effective enough to make large-scale classification tasks feasible, and simple enough to ensure high classification accuracy. We propose two flattening strategies based on these two causes of the accuracy decrease, and experimental results show that the flattening strategy designed for error propagation is more effective, which suggests that hierarchies with lots of branches at top layers can provide high classification accuracy. Besides, we analyze the computational complexity before and after flattening, which approximately agree with the experimental results. ©2010 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

A stochastic treatment of similarity

A stochastic treatment of similarity

引用

13th International Conference on Information Processing and Management of Uncertainty, IPMU 2010

作者： Ralescu, Anca Visa, Sofia Popovici, Stefana Machine Learning and Computational Intelligence Laboratory Computer Science Department University of Cincinnati ML 0030 Cincinnati OH 45221-0030 United States Department of Computer Science College of Wooster Wooster OH United States ATandT 2000 W ATT Center Drive Hoffman Estates IL 60196 United States

ISBN: (纸本)3642140483

This study investigates a robust measure of similarity applicable in many domains and across many dimensions of data. Given a distance or discrepancy measure on a domain, the similarity of two values in this domain is defined as the probability that any pair of values from that domain are more different (at a larger distance) than these two values are. We discuss the motivation for this approach, its properties, and the issues that arise from it. © 2010 Springer-Verlag Berlin Heidelberg.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Chinese keyword search over relational databases

Chinese keyword search over relational databases

引用

World Congress on Software Engineering

作者： Zhu, Liang Zhu, Yong Ma, Qin Key Laboratory of Machine Learning and Computational Intelligence School of Mathematics and Computer Science Hebei University Baoding Hebei 071002 China Department of Foreign Language Teaching and Research Hebei University Baoding Hebei 071002 China

ISBN: (纸本)9780769543031

Based on a knowledge base, we propose a new method to realize free-style Chinese keyword search over relational databases. Firstly, an index (also called knowledge base) is built by extracting related information of Chinese tuple words in a database, then query words and tuple words are matched quickly each other by with the index to obtain some of candidate answers for a given query. Secondly, we present a new ranking strategy to compute similarities between the query and the candidate answers, and refine the candidate answers by a matching algorithm proposed in this paper. Finally, we rank refined candidate answers to obtain top-N results. The experiments are conducted using a real dataset, and the experimental results show that our method is efficient and effective. © 2010 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Image and video descriptors

Image and video descriptors

引用

Workshops on Image Processing Theory, Tools and Applications, IPTA

作者： Abdenour Hadid Machine Vision Group Computer Science and Engineering Laboratory Department of Electrical and Information Engineering University of Oulu Finland

Feature (or descriptor) extraction from images and videos is a very crucial task in almost all computer vision systems. It consists of extracting characteristics describing important information in the images and videos. Different global (or holistic) methods such as Principal Component Analysis (PCA) have been widely studied and applied but lately local descriptors (such as LBP, SIFT and Gabor) have gained more attention due to their robustness to challenges such as pose and illumination changes. This tutorial gives an exhaustive overview of different image and video descriptors which can be found in literature with an emphasis on the most recent developments in the field. The tutorial will then focus on one or two state-of-the-art descriptors to demonstrate step by step how to successfully apply them to various computer vision problems such as biometrics, texture analysis, image and video retrieval, motion and activity analysis, human-computer interaction etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Torque Control Strategy with Charge Buffer for Parallel Hybrid Electric Vehicle

A Torque Control Strategy with Charge Buffer for Parallel Hy...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Xi Huang Ying Tan Xingui He Key Laboratory of Machine Perception and Intelligence Ministry of Education Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing China

As a new kind of vehicles with low fuel cost and low emission, hybrid electric vehicle (HEV) has been given more and more attention in recent years. The key technique in the HEV is the optimal control strategy for the best performance. This paper proposed a new torque control strategy with charge buffer (TCSCB) to control the two power sources of the HEV. The TCSCB is based on the control of engine torque which make the control strategy easily distribute the output power to the engine and motor. In this control strategy, the real time optimization based on the engine efficiency map increases engine efficiency observably. The charge buffer reduces the dramatic fluctuation of the engine torque to improve the fuel economy. The prediction engine torque based on the neural network improves the control performance by the future information greatly. The simulation results showed the TCSCB could reach a higher fuel economy and lower emission compared to the current control strategies. In order to optimize the control performances, the parameters in the TCSCB were also discussed in details.

关键词： Engines Torque Hybrid electric vehicles Thyristors Power capacitors Artificial neural networks System-on-a-chip

来源：评论

学校读者我要写书评

暂无评论

Providing SMS Notification with Less Interruption

Providing SMS Notification with Less Interruption

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Tiantian Gao Zhiqiang Yang Heng Wang Graphics Interaction Laboratory Key Laboratory of Machine Perception and Intelligence (MOE)Department of Computer Science Peking University Beijing China

SMS communication is gaining increasing popularity in people's daily life. Along with the growing number of times people sending and receiving SMSs every day, there are also increasing unwanted interruption to people when they are busy with their work or feel less receptive to unimportant messages. Unfortunately, current SMS systems are unable to present notifications according to user's states and willingness of being interrupted. In this work, we develop a SMS system that intelligently determines a good way to present notifications to the user at a suitable time. A decision module is made to analyze the message content, the relation between the sender and the user, and the user state when a new message comes. The results of the decision module are used to implement a nicer notification and to reduce interruptions to a user's ongoing tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extracting discriminative information from e-mail for spam detection inspired by Immune System

Extracting discriminative information from e-mail for spam d...

引用

Congress on Evolutionary Computation

作者： Yuanchun Zhu Ying Tan Key Laboratory of Machine Perception (Ministry of Education) and Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing China

Inspired from Biological Immune System, we propose a local concentration based feature extraction (LC) approach for anti-spam. A general anti-spam model is built to incorporate the LC approach with term selection methods and classifiers. In the LC model, each message is divided into areas by a sliding window. At each area, a two-dimensional feature is constructed by calculating the concentrations of spam and legitimate email. Then all the features of each area are combined together as a whole feature vector. Several experiments are conducted on four benchmark corpora, by using 10-fold cross-validation. It is shown that the LC approach can extract the effective position correlated information from messages. Compared to the prevalent Bag-of-Words approach, the LC has better performance in terms of both accuracy and F 1 measure. Most significantly, the LC approach can reduce feature dimensionality greatly and has much faster speed.

关键词： Feature extraction Electronic mail Accuracy Pathogens Training Construction industry Libraries

来源：评论

学校读者我要写书评

暂无评论

Development of the human cancer microRNA network

引用

Silence 2010年第1期1卷 1-14页

作者： Bandyopadhyay, Sanghamitra Mitra, Ramkrishna Maulik, Ujjwal Zhang, Michael Q. Machine Intelligence Unit Indian Statistical Institute Kolkata India Department of Computer Science and Engineering Jadavpur University Kolkata India Watson School of Biological Sciences Cold Spring Harbor Laboratory Cold Spring Harbor NY 11724 United States MOE Key Laboratory of Bioinformatics and Bioinformatics Division TNLIST Tsinghua University Beijing 100084 China

Background: MicroRNAs are a class of small noncoding RNAs that are abnormally expressed in different cancer cells. Molecular signature of miRNAs in different malignancies suggests that these are not only actively involved in the pathogenesis of human cancer but also have a significant role in patients survival. The differential expression patterns of specific miRNAs in a specific cancer tissue type have been reported in hundreds of research articles. However limited attempt has been made to collate this multitude of information and obtain a global perspective of miRNA dysregulation in multiple cancer ***: In this article a cancer-miRNA network is developed by mining the literature of experimentally verified cancer-miRNA relationships. This network throws up several new and interesting biological insights which were not evident in individual experiments, but become evident when studied in the global perspective. From the network a number of cancer-miRNA modules have been identified based on a computational approach to mine associations between cancer types and miRNAs. The modules that are generated based on these association are found to have a number of common predicted target onco/tumor suppressor genes. This suggests a combinatorial effect of the module associated miRNAs on target gene regulation in selective cancer tissues or cell lines. Moreover, neighboring miRNAs (group of miRNAs that are located within 50 kb of genomic location) of these modules show similar dysregulation patterns suggesting common regulatory pathway. Besides this, neighboring miRNAs may also show a similar dysregulation patterns (differentially coexpressed) in the cancer tissues. In this study, we found that in 67% of the cancer types have at least two neighboring miRNAs showing downregulation which is statistically significant (P < 10^-7, Randomization test). A similar result is obtained for the neighboring miRNAs showing upregulation in specific cancer type. These resul

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applying deep-layered clustering to mammography image analytics

Applying deep-layered clustering to mammography image analyt...

引用

Annual ORNL Biomedical science & Engineering Conference (BSEC)

作者： Derek C. Rose Itamar Arel Thomas P. Karnowski Vincent C. Paquit Department of Electrical Engineering and Computer Science University of Tennessee Knoxville TN USA Oak Ridge National Laboratory Machine Vision Group Oak Ridge USA

ISBN: (纸本)9781424467136;9781424467143

This paper details a methodology and preliminary results for applying a hierarchy of clustering units to mammographic image data. The identification of patients with breast cancer through the detection of microcalcifications and masses is a demanding classification problem; minimal false negatives are desired while simultaneously avoiding false positives that cause unnecessary cost to patients and health institutions. This research examines a segmented look at mammograms for computer aided detection with the goal of reliably labeling regions of interest requiring the attention of a radiologist. Classification is achieved by employing the building blocks, namely unsupervised clustering, of a deep learning architecture in tandem with a standard feed-forward neural network. Early results show promise for creating a classification engine that handles high-dimensional data with minimum engineering of image features, with a per-image patch sensitivity of 0.96 and specificity of 0.99.

关键词： Mammography Image analysis Breast cancer Cancer detection Costs Image segmentation computer network reliability Labeling computer architecture Feedforward systems

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：