selectedpapers.bib


@INPROCEEDINGS{Wang+Makedon-Rstar-Hi:2004,
  ADDRESS = {New York, New York, USA},
  AUTHOR = {Wang, Yuhang and Makedon, Fillia and Chakrabarti, Amit},
  BOOKTITLE = {To appear in Proceedings of the 12th Annual ACM International Conference on Multimedia},
  TITLE = {R*-Histograms: Efficient Representation of Spatial Relations between Objects of Arbitrary Topology},
  YEAR = 2004,
  ABSTRACT = {Representation of relative spatial relations between objects is
                  often required in many multimedia database applications because
                  spatial relations between objects in an image convey important
                  information about the image. Quantitative representation of
                  spatial relations taking into account shape, size, orientation and
                  distance is often required. The \mbox{R-Histogram} is such a
                  quantitative representation of spatial relations between two
                  objects. However, this method only considers pixels on the object
                  boundary, assuming that the objects are homeomorphic to a 2-ball.
                  For objects with more complicated topology, we propose in this
                  paper the \mbox{R*-Histogram}, a new extension to the
                  \mbox{R-Histogram}. The \mbox{R*-Histogram} generalizes the
                  \mbox{R-Histogram} by taking into account all the pixels in the
                  objects. We also introduce an efficient $O(kN\/log N)$ time
                  algorithm to compute the \mbox{R*-Histogram}, which is
                  asymptotically faster than the original $O(N^{2})$ time algorithm
                  for the \mbox{R-Histogram} even when $k=O(n)$. Here, $N=n^{2}$
                  denotes the number of pixels in the processed $n\times n$ image
                  and $k$ is the number of different directions considered. The
                  effectiveness of the \mbox{R*-Histogram} is evaluated empirically
                  with a Query By Example (QBE) system on a database of 2000
                  synthetic images containing objects with complicated shape and
                  topology. Experiments have shown that the similarly search results
                  match human intuition very well.}
}


@INPROCEEDINGS{Wang+MakedonETAL-MiniMarkGenePhen:04,
  AUTHOR = {Yuhang Wang and Fillia Makedon and James Ford},
  TITLE = {Mining Marker Genes for Phenotype Classification using Microarray Gene Expression Data},
  BOOKTITLE = {In submission},
  YEAR = 2004
}


@ARTICLE{Wang+MakedonETAL-FastAlgoCompForc:04,
  AUTHOR = {Yuhang Wang and Fillia Makedon and Robert L. (Scot) Drysdale},
  TITLE = {Fast Algorithms to Compute the Force Histogram},
  JOURNAL = {In submission},
  YEAR = 2004
}


@INPROCEEDINGS{Wang+MakedonETAL-BipaGrapMatcFram:04,
  AUTHOR = {Yuhang Wang and Fillia Makedon and James Ford},
  TITLE = {A Bipartite Graph Matching Framework for Finding Correspondences between Structural Elements in Two Proteins},
  BOOKTITLE = {To appear in Proceedings of the 26th Annual International Conference of
                  the IEEE Engineering in Medicine and Biology Society},
  DATE = {September 1--5},
  YEAR = 2004,
  ABSTRACT = {A protein molecule consists one or more chains
                  of amino acid sequences that fold into a complex
                  three-dimensional structure. A protein's functions are often
                  determined by its 3D structure, and so comparing the similarity
                  of 3D structures between proteins is an important problem. To
                  accomplish such comparison, one must align two proteins properly
                  with rotation and translation in 3D space. Finding the
                  correspondences between structural elements in the two proteins
                  is the key step in many protein structure alignment algorithms.
                  In this paper, we introduce a new graph theoretic framework
                  based on bipartite graph matching for finding sufficiently good
                  correspondences. It is capable of providing both
                  sequence-dependent and sequence-independent correspondences. It
                  is a general framework for pair-wise matching of atoms, amino
                  acids residues or secondary structure elements.
                  },
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/embs04_alignment.pdf}
}


@INPROCEEDINGS{Wang+Makedon-ApplReliFeatFilt:04,
  ADDRESS = {Stanford, California},
  AUTHOR = {Yuhang Wang and Fillia Makedon},
  BOOKTITLE = {To appear in Proceedings of the 2004 IEEE Computational Systems Bioinformatics Conference},
  TITLE = {Application of Relief-F Feature Filtering Algorithm to Selecting Informative Genes
                  for Cancer Classification using Microarray Data (poster paper)},
  DATE = {August 16--19},
  YEAR = 2004,
  ABSTRACT = {Numerous recent studies have shown that microarray gene expression
                  data is useful for cancer classification. Classification based on
                  microarray data is very different from previous classification
                  problems in that the number of features (genes) greatly exceeds
                  the number of instances (tissue samples). It has been shown that
                  selecting a small set of informative genes can lead to improved
                  classification accuracy. It is thus important to first apply
                  feature selection methods prior to classification. In the machine
                  learning field, one of the most successful feature filtering
                  algorithms is the Relief-F algorithm. In this work, we
                  empirically evaluate its performance on three published cancer
                  classification data sets. We use the linear SVM and the k-NN
                  as classifiers in the experiments, and compare the performance of
                  Relief-F with other feature filtering methods, including
                  Information Gain, Gain Ratio, and $\chi^{2}$-statistic. Using the
                  leave-one-out cross validation, experimental results show that the
                  performance of Relief-F is comparable with other methods.
                  },
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/csb04_geneselection.pdf}
}


@INPROCEEDINGS{Wang+MakedonETAL-GeneFuzzSemaMeta:04,
  ADDRESS = {Tucson, Arizona},
  AUTHOR = {Yuhang Wang and Fillia Makedon and James Ford and Li Shen and Dina Goldin},
  BOOKTITLE = {Proceedings of the Fourth ACM/IEEE-CS Joint Conference on Digital Libraries},
  TITLE = {Generating Fuzzy Semantic Metadata describing Spatial Relations from Images using the {R}-Histogram},
  PAGES = {202--211},
  YEAR = 2004,
  ABSTRACT = {Automatic generation of semantic metadata
                      describing spatial relations is highly desirable for image
                      digital libraries. Relative spatial relations between objects
                      in an image convey important information about the image.
                      Because the perception of spatial relations is subjective, we
                      propose a novel framework for automatic metadata generation
                      based on fuzzy k-nn classification that generates fuzzy
                      semantic metadata describing spatial relations between objects
                      in an image. For each pair of objects of interest, the
                      corresponding R-histogram is computed and used as input for a
                      set of fuzzy k-nn classifiers. The R-histogram is a
                      quantitative representation of spatial relations between two
                      objects. The outputs of the classifiers are soft class labels
                      for each of the following eight spatial relations: 1) LEFT OF,
                      2) RIGHT OF, 3) ABOVE, 4) BELOW, 5) NEAR, 6) FAR, 7) INSIDE,
                      8) OUTSIDE. Because the classifier-training stage
                      involves annotating the training images manually, it is
                      desirable to use as few training images as possible. To
                      address this issue, we applied existing prototype selection
                      techniques and also devised two new extensions. We evaluated
                      the performance of different fuzzy k-nn algorithms and
                      prototype selection algorithms empirically on both synthetic
                      and real images. Preliminary experimental results show that
                      our system is able to obtain good annotation accuracy (92\%-98\%
                      on synthetic images and 82\%-93\% on real images) using only a
                      small training set (4-5 images).},
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/jcdl04_metadata.pdf}
}


@INPROCEEDINGS{Wang+Makedon-R-Hi:2003,
  ADDRESS = {Berkeley, California, USA},
  AUTHOR = {Wang, Yuhang and Makedon, Fillia},
  BOOKTITLE = {The 11th Annual ACM International Conference on Multimedia},
  TITLE = {R-Histogram: Quantitative Representation of SpatialRelations for
                  Similarity-Based Image Retrieval},
  PAGES = {323--326},
  YEAR = 2003,
  ABSTRACT = {Representation of relative spatial relations between objects is
                  required in many multimedia database applications. Quantitative
                  representation of spatial relations taking into account shape,
                  size, orientation and distance is often required. This cannot be
                  accomplished by assimilating an object to elementary entities
                  such as the centroid or the minimum bounding rectangle. Thus many
                  authors have proposed numerous representations based on the
                  notion of histograms of angles. However, they can only represent
                  directional relations, but not the topological spatial relations
                  ''inside'' and ''overlap.'' Moreover, distance information is not
                  explicitly taken into account. To address these issues, we
                  propose in this paper a new histogram representation called
                  R-Histogram that extends the histogram of angles by incorporating
                  both angles and labeled distances. Dissimilarity between images
                  is then defined by the distance between corresponding
                  R-Histograms. A prototype Query By Example (QBE) system using the
                  R-Histogram has been implemented. The effectiveness of our
                  algorithm is demonstrated with experiments on two databases of
                  2000 synthetic images.},
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/acmmm03_rhist.pdf}
}


@INPROCEEDINGS{Wang+SteinbergETAL-QuanEvol:2003,
  ADDRESS = {Montr\'eal, Qu\'ebec, Canada},
  AUTHOR = {Wang, Yuhang and Steinberg, Tilmann and Makedon, Fillia and
                  Wishart, Heather and Saykin, Andrew},
  BOOKTITLE = {The Sixth Annual International Conference on Medical Image
                  Computing and Computer-Assisted Intervention (MICCAI 2003)},
  TITLE = {Quantifying Evolving Processes in Multimodal {3D} Medical Images},
  YEAR = 2003,
  PAGES = {101--108},
  ABSTRACT = {Quantitative measurements of changes in evolving brain
                  pathology, such as multiple sclerosis lesions and brain tumors,
                  are important for clinicians to perform pertinent diagnoses and
                  to help in patient follow-up. Lesions or tumors can vary over
                  time in size, shape, location and composition because of natural
                  pathological processes or the effect of a drug treatment or
                  therapy. In the past, people have used as a quantitative
                  measurement the change in total or regional lesion/tumor volume.
                  In this paper we propose a new model to quantify changes in
                  evolving processes in multimodal 3D medical images. We believe
                  this model reflects changes in pathology more accurately because
                  it simultaneously takes into account information in multiple
                  imaging modalities and the location of lesion/tumor voxels. We
                  demonstrate the effectiveness of this model with experiments on
                  synthetic lesion data.},
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/miccai03_quantify.pdf}
}


@INPROCEEDINGS{Makedon+WangETAL-SystFram:2003,
  ADDRESS = {Capri Island, Italy},
  AUTHOR = {Makedon, Fillia and Wang, Yuhang and Steinberg, Tilmann and
                  Wishart, Heather and Saykin, Andrew and Ford, James and Ye, Song
                  and Shen, Li},
  BOOKTITLE = {Proceedings of First International IEEE EMBS Conference on
                  Neural Engineering},
  PAGES = {495--498},
  TITLE = {A System Framework for the Integration and Analysis of Multi-modal
                  Spatiotemporal Data Streams: A Case Study in {MS} Lesion Analysis},
  YEAR = 2003,
  ABSTRACT = {This paper describes the development of MS-Analyze, a system
                  framework to analyze and detect patterns in brain pathology of
                  multiple sclerosis (MS) as the disease progresses over time. We
                  are building the system to collect, analyze and integrate
                  disparate data extracted from observing the behavior of MS
                  lesions and surrounding pathology on magnetic resonance imaging
                  (MRI) over time. Multiple sclerosis (MS) is a brain disease that
                  affects over 250,000 people in the USA alone. Various MRI
                  sequences are used to monitor brain changes during the natural
                  progression of the disease, and as different drug treatments are
                  explored to slow the disease. The outcome is a set of disparate
                  data streams that need to be correlated efficiently to discover
                  patterns of MS pathology and plan treatment. However, MS data
                  analysis faces the same computational problems as many other
                  scientific domains with heterogeneous data streams: the need for
                  integration of and access to large amounts of data, beyond what
                  is normally available to any one given laboratory. MS-Analyze
                  addresses both of these challenges by combining data collection,
                  data fusion, data analysis, and secure data sharing. MS is a good
                  application to demonstrate the system because it offers rich data
                  that challenge the system development.},
  URL = {http://www.cs.dartmouth.edu/~wyh/papers/embs03_framework.pdf}
}


@INPROCEEDINGS{Steinberg+WangETAL-SpatMult:2003,
  ADDRESS = {Cambridge, Massachusetts, USA},
  AUTHOR = {Steinberg, Tilmann and Wang, Yuhang and Makedon, Fillia and Shen,
                  Li and Saykin, Andrew and Wishart, Heather},
  BOOKTITLE = {Proceedings of 15th International Conference on Scientific and
                  Statistical Database Management (SSDBM '03)},
  PAGES = {245--246},
  TITLE = {A Spatio-temporal Multi-modal Data Management and Analysis
                  Environment for Tracking {MS} Lesions},
  YEAR = 2003
}


@INPROCEEDINGS{Butler+FitchETAL-Distgoal:2002,
  AUTHOR = {Butler, Z. and Fitch, R. and Rus, D. and Wang, Yuhang},
  BOOKTITLE = {Proceedings of 2002 IEEE International Conference on Robotics
                  and Automation (ICRA '02)},
  PAGES = {110--116},
  TITLE = {Distributed Goal Recognition Algorithms for Modular Robots},
  VOLUME = 1,
  YEAR = 2002
}


This file has been generated by bibtex2html 1.61