@conference {17442, title = {TreeVersity: Comparing tree structures by topology and node{\textquoteright}s attributes differences}, booktitle = {2011 IEEE Conference on Visual Analytics Science and Technology (VAST)}, year = {2011}, month = {2011/10/23/28}, pages = {275 - 276}, publisher = {IEEE}, organization = {IEEE}, abstract = {It is common to classify data in hierarchies, they provide a comprehensible way of understanding big amounts of data. From budgets to organizational charts or even the stock market, trees are everywhere and people find them easy to use. However when analysts need to compare two versions of the same tree structure, or two related taxonomies, the task is not so easy. Much work has been done on this topic, but almost all of it has been restricted to either compare the trees by topology, or by the node attribute values. With this project we are proposing TreeVersity, a framework for comparing tree structures, both by structural changes and by differences in the node attributes. This paper is based on our previous work on comparing traffic agencies using LifeFlow [1, 2] and on a first prototype of TreeVersity.}, keywords = {Computer science, data classification, Data visualization, Educational institutions, hierarchy, Image color analysis, LifeFlow, node attributes differences, Pattern classification, structural changes, Topology, topology attributes differences, traffic agencies, tree structures comparison, trees (mathematics), TreeVersity, Vegetation, Visualization}, isbn = {978-1-4673-0015-5}, doi = {10.1109/VAST.2011.6102471}, author = {Gomez,J.A.G. and Buck-Coleman,A. and Plaisant, Catherine and Shneiderman, Ben} } @conference {16278, title = {MetaPhyler: Taxonomic profiling for metagenomic sequences}, booktitle = {2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)}, year = {2010}, month = {2010/12/18/21}, pages = {95 - 100}, publisher = {IEEE}, organization = {IEEE}, abstract = {A major goal of metagenomics is to characterize the microbial diversity of an environment. The most popular approach relies on 16S rRNA sequencing, however this approach can generate biased estimates due to differences in the copy number of the 16S rRNA gene between even closely related organisms, and due to PCR artifacts. The taxonomic composition can also be determined from whole-metagenome sequencing data by matching individual sequences against a database of reference genes. One major limitation of prior methods used for this purpose is the use of a universal classification threshold for all genes at all taxonomic levels. We propose that better classification results can be obtained by tuning the taxonomic classifier to each matching length, reference gene, and taxonomic level. We present a novel taxonomic profiler MetaPhyler, which uses marker genes as a taxonomic reference. Results on simulated datasets demonstrate that MetaPhyler outperforms other tools commonly used in this context (CARMA, Megan and PhymmBL). We also present interesting results obtained by applying MetaPhyler to a real metagenomic dataset.}, keywords = {Bioinformatics, CARMA comparison, Databases, Genomics, Linear regression, marker genes, matching length, Megan comparison, metagenomic sequences, metagenomics, MetaPhyler, microbial diversity, microorganisms, molecular biophysics, molecular configurations, Pattern classification, pattern matching, phylogenetic classification, Phylogeny, PhymmBL comparison, reference gene database, Sensitivity, sequence matching, taxonomic classifier, taxonomic level, taxonomic profiling, whole metagenome sequencing data}, isbn = {978-1-4244-8306-8}, doi = {10.1109/BIBM.2010.5706544}, author = {Liu,Bo and Gibbons,T. and Ghodsi,M. and Pop, Mihai} } @article {16656, title = {Feature discovery and classification of Doppler umbilical artery blood flow velocity waveforms}, journal = {Computers in Biology and Medicine}, volume = {26}, year = {1996}, month = {1996/11//}, pages = {451 - 462}, abstract = {Doppler umbilical artery blood flow velocity waveform measurements are used in perinatal surveillance for the evaluation of fetal condition. There is an ongoing debate on the predictive value of Doppler measurements concerning the critical effect of the selection of parameters for the interpretation of Doppler waveforms. In this paper, we describe how neural network methods can be used both to discover relevant classification features and subsequently to classify Doppler umbilical artery blood flow velocity waveforms. Results obtained from 199 normal and high risk patients{\textquoteright} umbilical artery waveforms highlighted a classification concordance varying from 90 to 98\% accuracy.}, keywords = {Doppler umbilical artery blood flow velocity waveforms, Feature extraction, IMAGE PROCESSING, Pattern classification}, isbn = {0010-4825}, doi = {10.1016/S0010-4825(96)00018-2}, url = {http://www.sciencedirect.com/science/article/pii/S0010482596000182}, author = {Baykal,Nazife and Reogia,James A. and Yalabik,Nese and Erkmen,Aydan and Beksac,M.Sinan} }