检索结果-内蒙古大学图书馆

2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, ACM-BCB 2011

作者： Mathew, George Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University Philadelphia PA United States

ISBN: (纸本)9781450307963

We model transactions as exchange of graphs and propose constraint graphs as transaction filters for attribute-based transformations in clinical settings. An informal representation and working of constraint graphs is presented. A workbench was developed using a real world EMR system to demonstrate the concept. Results of our experiments using constraint graphs are consistent with published benchmark results. Copyright © 2011 ACM.

关键词： Medical informatics

来源：评论

学校读者我要写书评

暂无评论

Learning-based automatic breast tumor detection and segmentation in ultrasound images

Learning-based automatic breast tumor detection and segmenta...

引用

IEEE International Symposium on biomedical Imaging

作者： Peng Jiang Jingliang Peng Guoquan Zhang Erkang Cheng Vasileios Megalooikonomou Haibin Ling School of Computer Science and Technology Shandong Provincial Key Laboratory of Software Engineering P.R.China Department of Ultrasound Shandong Provincial Hospital Affiliated to Shandong University P.R. China Center for Data Analytics & Biomedical Informatics Temple University Philadelphia PA USA

ISBN: (纸本)9781457718571

Ultrasound (US) images have been widely used in the diagnosis of breast cancer in particular. While experienced doctors may locate the tumor regions in a US image manually, it is highly desirable to develop algorithms that automatically detect the tumor regions in order to assist medical diagnosis. In this paper, we propose a novel algorithm for automatic detection of breast tumors in US images. We formulate the tumor detection as a two step learning problem: tumor localization by bounding box and exact boundary delineation. Specifically, the proposed method uses an AdaBoost classifier on Harr-like features to detect a preliminary set of tumor regions. The preliminarily detected tumor regions are further screened with a support vector machine using quantized intensity features. Finally, the random walk segmentation algorithm is performed on the US image to retrieve the boundary of each detected tumor region. The proposed method has been evaluated on a data set containing 112 breast US images, including histologically confirmed 80 diseased ones and 32 normal ones. The data set contains one image from each patient and the patients are from 31 to 75 years old. Experiments demonstrate that the proposed algorithm can automatically detect breast tumors, with their locations and boundary shapes retrieved with high accuracy.

关键词： Image segmentation Support vector machines Breast tumors Ultrasonic imaging Feature extraction Accuracy

来源：评论

学校读者我要写书评

暂无评论

Imputation of missing links and attributes in longitudinal social surveys

Imputation of missing links and attributes in longitudinal s...

引用

11th IEEE International Conference on data Mining Workshops, ICDMW 2011

作者： Ouzienko, Vladimir Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University Philadelphia PA 19122 United States

ISBN: (纸本)9780769544090

We propose a unified approach for imputation of the links and attributes in longitudinal social surveys which accounts for changing network topology and interdependence between the actor's links and attributes. The previous studies on the treatment of non-respondents in longitudinal social networks were mostly concerned with imputation of the missing links only or imputation effects on the networks statistics. For this study we conduct a set of experiments on synthetic and real life datasets with 20%-60% of nodes missing under four mechanisms. The obtained results were better than when using alternative methods which suggest that our method can be used as a viable imputation tool. © 2011 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Extracting STRIPS representations of actions and events

Extracting STRIPS representations of actions and events

引用

8th International Conference on Recent Advances in Natural Language Processing, RANLP 2011

作者： Sil, Avirup Yates, Alexander Center for Data Analytics and Biomedical Informatics Temple University Broad St. and Montgomery Ave. Philadelphia PA 19122 United States

Knowledge about how the world changes over time is a vital component of commonsense knowledge for Artificial Intelligence (AI) and natural language understanding. Actions and events are fundamental components to any knowledge about changes in the state of the world: the states before and after an event differ in regular and predictable ways. We describe a novel system that tackles the problem of extracting knowledge from text about how actions and events change the world over time. We leverage standard language-processing tools, like semantic role labelers and coreference resolvers, as well as large-corpus statistics like pointwise mutual information, to identify STRIPS representations of actions and events, a type of representation commonly used in AI planning systems. In experiments on Web text, our extractor's Area under the Curve (AUC) improves by more than 31% over the closest system from the literature for identifying the preconditions and add effects of actions. In addition, we also extract significant aspects of STRIPS representations that are missing from previous work, including delete effects and arguments.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Identifying pair-wise gene functional similarity by multiplex gene expression maps and supervised learning 11

Identifying pair-wise gene functional similarity by multiple...

引用

2011 ACM Conference on Bioinformatics, Computational Biology and Biomedicine, ACM-BCB 2011

作者： An, Li Smith, Desmond J. Ling, Haibin Megalooikonomou, Vasileios Obradovic, Zoran Data Engineering Laboratory Center for Data Analytics and Biomedical Informatics Temple University 1805 N. Broad St. Philadelphia PA 19122 United States Department of Molecular and Medical Pharmacology David Geffen School of Medicine UCLA Los Angeles CA 90095 United States Center for Data Analytics and Biomedical Informatics Temple University 305 Wachman Hall 1805 N. Broad St. Philadelphia PA 19122 United States Center for Data Analytics and Biomedical Informatics Temple University 303 Wachman Hall 1805 N. Broad St. Philadelphia PA 19122 United States

ISBN: (纸本)9781450307963

Research has been done to explore the relationships between the Gene Ontology-based similarity and gene expression profiles in the mammalian brain. However, little attention has been paid to the location information of a gene's expressions. Gene expression maps, which contain spatial information regarding the expression of genes in mice's brain, are obtained by combining voxelation and microarrays. Based on the hypothesis that genes with similar gene expression maps may have similar gene functions, we propose an approach to identify pair-wise gene functional similarities by gene expression maps. By considering pairs of genes from an original dataset as samples whose features are extracted from expression maps and labels are the functional similarities of pairs of genes, we explore the relationship between similarities of gene maps and gene functions. We restrict the dataset to genes that are associated with previously detected functional expression profiles to strengthen the relationship. We use AdaBoost, coupled with our proposed weak classifier, to analyze the dataset and predict the functional similarities. The experimental results show that with the increasing similarities of gene expression maps, the functional similarities are increased too. The boosting analysis can predict the functional similarities between genes to a certain degree. The weights of the features in the model indicate which features are significant for this prediction. These findings can potentially assist the biologists by providing helpful clues in predicting gene functions. Copyright © 2011 ACM.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

A decoupled exponential random graph model for prediction of structure and attributes in temporal social networks

引用

Statistical Analysis and data Mining 2011年第5期4卷 470-486页

作者： Ouzienko, Vladimir Guo, Yuhong Obradovic, Zoran Center for Data Analytics and Biomedical Informatics Temple University Philadelphia PA 19122 United States

The analysis of social networks often assumes time invariant scenario, while in practice actor attributes and links in such networks often evolve over time and are inextricably dependent on each other. In this article, we propose a new method to predict actor attributes and links in temporal networks. Our approach takes into account the attributes corresponding to the participating actors together with topological and structural changes of the network over time. This is achieved by building two conditional predictors to jointly infer links and actor attributes. The proposed prediction method was significantly more accurate than alternatives when evaluated on synthetic data sets and two well-studied real-life temporal social networks. In addition, the new algorithm is computationally more efficient than a related alternative scaling up linearly with the number of temporal observations and quadratically with the number of actors considered. © 2011 Wiley Periodicals, Inc.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Intrinsic Disorder in Putative Protein Sequences

Intrinsic Disorder in Putative Protein Sequences

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Uros Midic Zoran Obradovic Center of Data Analytics and Biomedical Informatics Temple University Philadelphia PA USA

Intrinsically disordered proteins perform a variety of crucial biological functions despite lacking stable tertiary structure under physiological conditions in vitro. State-of-the-art sequence-based predictors of intrinsic disorder are achieving per-residue accuracies over 80%. In a genome-wide study we observed big difference in predicted disorder content between confirmed and putative human proteins, and suspected that this is due to large errors introduced by gene-finding algorithms for putative sequence annotation. To test this hypothesis we trained a predictor to discriminate sequences of real proteins from synthetic sequences that mimic errors of gene finding algorithms. Its application to putative human protein sequences shows that they contain a substantial fraction of incorrectly assigned regions. These regions are predicted to have higher levels of disorder content than correctly assigned regions. Our finding provides first evidence that current practice of predicting disorder content in putative sequences should be reconsidered, as such estimates are biased.

关键词： Proteins Amino acids Accuracy Humans Genomics Protein engineering Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Learning-based vessel segmentation in mammographic images

Learning-based vessel segmentation in mammographic images

引用

2011 1st IEEE International Conference on Healthcare informatics, Imaging and Systems Biology, HISB 2011

作者： Cheng, Erkang McLaughlin, Shawn Megalooikonomou, Vasileios Bakic, Predrag R. Maidment, Andrew D.A. Ling, Haibin Center for Data Analytics and Biomedical Informatics Computer and Information Science Department Temple University Philadelphia PA United States Temple University Philadelphia PA United States Department of Radiology University of Pennsylvania Philadelphia PA United States

ISBN: (纸本)9780769544076

In this paper we propose using a learning-based method for vessel segmentation in mammographic images. To capture the large variation in vessel patterns not only across subjects, but also within a subject, we create a feature pool containing local, Gabor and Haar features extracted from mammographic images generating a feature space of very high dimension. We also employ a huge number of training samples, which essentially contains the pixels in the training images. To deal with the very high dimensional feature space and the huge number of training samples, we apply a forest with boosting trees for vessel segmentation. Specifically, we use the standard AdaBoost algorithm for each tree in the forest. The randomness is encoded, when training each AdaBoost tree, using randomly sampled training set (pixels) and randomly selected features from the whole feature pool. The proposed method is tested using a real dataset with 20 anonymous mammographic images. The effectiveness of the proposed features and classifiers is demonstrated in the experiments where we compare different approaches and feature combinations. In the paper, we also present full analysis of different types of features. © 2011 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Preservative License Plate De-identification for Privacy Protection

Preservative License Plate De-identification for Privacy Pro...

引用

International Conference on Document Analysis and Recognition

作者： Liang Du Haibin Ling Center for Data Analytics & Biomedical Informatics Department of Computer & Information Science Temple University Philadelphia PA USA

Advances in imaging devices and web technologies have brought dramatic improvements in collecting, storing, and sharing images. The leakage of privacy information in the process becomes an important issue that has started drawing attention from both academia and industry. In this work, we study the problem of privacy preserving with focus on license plate number protecting in imagery. Specifically, we present a novel method for de-identifying license plate images with the least degradation in image visual quality for privacy protection. Unlike previous de-identification methods that pay little attention to the image quality preservation, our method, named inhomogeneous principal component blur (IPCB), adaptively blurs different pixels of a license plate by taking into account the prior distribution of sensitive information. We tested the proposed method on a public dataset in comparison with several popular de-identification methods. The evaluation shows that our method successfully de-identified the privacy information with the least damage of image quality when compared with several other solutions.

关键词： Licenses Privacy Image quality Degradation data privacy Nonhomogeneous media Visualization

来源：评论

学校读者我要写书评

暂无评论

Visual tracking based on log-Euclidean Riemannian sparse representation

Visual tracking based on log-Euclidean Riemannian sparse rep...

引用

7th International Symposium on Visual Computing, ISVC 2011

作者： Wu, Yi Ling, Haibin Blasch, Erik Bai, Li Chen, Genshe Center for Data Analytics and Biomedical Informatics Computer and Information Science Department Temple University Philadelphia PA United States Air Force Research Lab. SNAA OH United States Electrical and Computer Engineering Department Temple University Philadelphia PA United States

ISBN: (纸本)9783642240270

Recently, sparse representation has been utilized in many computer vision tasks and adapted for visual tracking. Sparsity-based visual tracking is formulated as searching candidates with minimal reconstruction errors from a template subspace with sparsity constraints in the approximation coefficients. However, an intensity template is easily corrupted by noise and not robust for target tracking under a dynamic environment. The recently proposed covariance region descriptor has been proven robust and versatile for a modest computational cost. Further, the covariance matrix enables efficient fusion of different types of features, where the spatial and statistical properties as well as their correlation are characterized, and its dimension is small. Although the covariance matrix lies on Riemannian manifolds, its log-transformation can be measured on a Euclidean subspace. Based on the covariance region descriptor and using the sparse representation, we propose a novel tracking approach on the Log-Euclidean Riemannian subspace. Specifically, the target region is characterized by a covariance matrix which is then log-transformed from the Riemannian manifold to the Euclidean subspace. After that, the target tracking problem is integrated under a sparse approximation framework, where the sparsity is achieved by solving an 1- regularization problem. Then the candidate with the smallest approximation is taken as the tracked target. For target propagation, we use the Bayesian state inference framework, which propagates sample distributions over time using the particle filter algorithm. To evaluate our method, we have collected several video sequences and the experimental results show that our tracker can achieve robustly and reliably target tracking. © 2011 Springer-Verlag.

关键词： Target tracking

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：