bib.bib

@Manual{trackr2020,
    title = {trackR: Simple Video Tracking Software},
    author = {Simon Garnier},
    year = {2020},
    url = {https://swarm-lab.github.io/trackR/},
    note = {https://github.com/swarm-lab/trackR}
}

@Manual{spectrum2020,
    title = {Spectrum: Fast Adaptive Spectral Clustering for Single and Multi-View Data},
    author = {Christopher R John and David Watson},
    year = {2020},
    note = {R package version 1.1},
    url = {https://CRAN.R-project.org/package=Spectrum},
}

@ARTICLE{John2020-jk,
  title    = "{Spectrum: fast density-aware spectral clustering for single and
              multi-omic data}",
  author   = "John, Christopher R and Watson, David and Barnes, Michael R and
              Pitzalis, Costantino and Lewis, Myles J",
  abstract = "MOTIVATION: Clustering patient omic data is integral to
              developing precision medicine because it allows the
              identification of disease subtypes. A current major challenge is
              the integration multi-omic data to identify a shared structure
              and reduce noise. Cluster analysis is also increasingly applied
              on single-omic data, for example, in single cell RNA-seq analysis
              for clustering the transcriptomes of individual cells. This
              technology has clinical implications. Our motivation was
              therefore to develop a flexible and effective spectral clustering
              tool for both single and multi-omic data. RESULTS: We present
              Spectrum, a new spectral clustering method for complex omic data.
              Spectrum uses a self-tuning density-aware kernel we developed
              that enhances the similarity between points that share common
              nearest neighbours. It uses a tensor product graph data
              integration and diffusion procedure to reduce noise and reveal
              underlying structures. Spectrum contains a new method for finding
              the optimal number of clusters (K) involving eigenvector
              distribution analysis. Spectrum can automatically find K for both
              Gaussian and non-Gaussian structures. We demonstrate across 21
              real expression datasets that Spectrum gives improved runtimes
              and better clustering results relative to other methods.
              AVAILABILITY AND IMPLEMENTATION: Spectrum is available as an R
              software package from CRAN
              https://cran.r-project.org/web/packages/Spectrum/index.html.
              SUPPLEMENTARY INFORMATION: Supplementary data are available at
              Bioinformatics online.",
  journal  = "Bioinformatics",
  volume   =  36,
  number   =  4,
  pages    = "1159--1166",
  month    =  feb,
  year     =  2020,
  url      = "http://dx.doi.org/10.1093/bioinformatics/btz704",
  file     = "All Papers/J/John et al. 2020 - Spectrum - fast density-aware spectral clustering for single and multi-omic data.pdf",
  language = "en",
  issn     = "1367-4803, 1367-4811",
  pmid     = "31501851",
  doi      = "10.1093/bioinformatics/btz704"
}


@INPROCEEDINGS{Yan2009-ok,
  title     = "{Fast approximate spectral clustering}",
  booktitle = "{Proceedings of the 15th ACM SIGKDD international conference on
               Knowledge discovery and data mining}",
  author    = "Yan, Donghui and Huang, Ling and Jordan, Michael I",
  abstract  = "Spectral clustering refers to a flexible class of clustering
               procedures that can produce high-quality clusterings on small
               data sets but which has limited applicability to large-scale
               problems due to its computational complexity of O(n3) in
               general, with n the number of data points. We extend the range
               of spectral clustering by developing a general framework for
               fast approximate spectral clustering in which a
               distortion-minimizing local transformation is first applied to
               the data. This framework is based on a theoretical analysis that
               provides a statistical characterization of the effect of local
               distortion on the mis-clustering rate. We develop two concrete
               instances of our general framework, one based on local k-means
               clustering (KASP) and one based on random projection trees
               (RASP). Extensive experiments show that these algorithms can
               achieve significant speedups with little degradation in
               clustering accuracy. Specifically, our algorithms outperform
               k-means by a large margin in terms of accuracy, and run several
               times faster than approximate spectral clustering based on the
               Nystrom method, with comparable accuracy and significantly
               smaller memory footprint. Remarkably, our algorithms make it
               possible for a single machine to spectral cluster data sets with
               a million observations within several minutes.",
  publisher = "Association for Computing Machinery",
  pages     = "907--916",
  series    = "KDD '09",
  month     =  jun,
  year      =  2009,
  url       = "https://doi.org/10.1145/1557019.1557118",
  file      = "All Papers/Y/Yan et al. 2009 - Fast approximate spectral clustering.pdf",
  address   = "New York, NY, USA",
  keywords  = "unsupervised learning, spectral clustering, data quantization",
  location  = "Paris, France",
  isbn      = "9781605584959",
  doi       = "10.1145/1557019.1557118"
}


@ARTICLE{Zelnik-Manor2004-vj,
  title   = "{Self-tuning spectral clustering}",
  author  = "Zelnik-Manor, Lihi and Perona, Pietro",
  journal = "Advances in neural information processing systems",
  volume  =  17,
  pages   = "1601--1608",
  year    =  2004,
  url     = "https://proceedings.neurips.cc/paper/2004/file/40173ea48d9567f1f393b20c855bb40b-Paper.pdf",
  file    = "All Papers/Z/Zelnik-Manor and Perona 2004 - Self-tuning spectral clustering.pdf",
  issn    = "1049-5258"
}


@Article{mixtools2009,
    title = {{mixtools}: An {R} Package for Analyzing Finite Mixture Models},
    author = {Tatiana Benaglia and Didier Chauveau and David R. Hunter and Derek Young},
    journal = {Journal of Statistical Software},
    year = {2009},
    volume = {32},
    number = {6},
    pages = {1--29},
    url = {http://www.jstatsoft.org/v32/i06/},
  }


@ARTICLE{rebmix2020,
  title     = "{Improved Initialization of the EM Algorithm for Mixture Model
               Parameter Estimation}",
  author    = "Pani{\'c}, Branislav and Klemenc, Jernej and Nagode, Marko",
  abstract  = "A commonly used tool for estimating the parameters of a mixture
               model is the Expectation--Maximization (EM) algorithm, which is
               an iterative procedure that can serve as a maximum-likelihood
               estimator. The EM algorithm has well-documented drawbacks, such
               as the need for good initial values and the possibility of being
               trapped in local optima. Nevertheless, because of its appealing
               properties, EM plays an important role in estimating the
               parameters of mixture models. To overcome these initialization
               problems with EM, in this paper, we propose the
               Rough-Enhanced-Bayes mixture estimation (REBMIX) algorithm as a
               more effective initialization algorithm. Three different
               strategies are derived for dealing with the unknown number of
               components in the mixture model. These strategies are thoroughly
               tested on artificial datasets, density--estimation datasets and
               image--segmentation problems and compared with state-of-the-art
               initialization methods for the EM. Our proposal shows promising
               results in terms of clustering and density-estimation
               performance as well as in terms of computational efficiency. All
               the improvements are implemented in the rebmix R package.",
  journal   = "Science in China, Series A: Mathematics",
  publisher = "Multidisciplinary Digital Publishing Institute",
  volume    =  8,
  number    =  3,
  pages     = "373",
  month     =  mar,
  year      =  2020,
  url       = "https://www.mdpi.com/2227-7390/8/3/373",
  file      = "All Papers/P/Panić et al. 2020 - Improved Initialization of the EM Algorithm for Mixture Model Parameter Estimation.pdf",
  language  = "en",
  doi       = "10.3390/math8030373"
}

@Manual{cluster2019,
    title = {cluster: Cluster Analysis Basics and Extensions},
    author = {Martin Maechler and Peter Rousseeuw and Anja Struyf and Mia Hubert and Kurt Hornik},
    year = {2019},
    note = {R package version 2.1.0 --- For new features, see the 'Changelog' file (in the package source)},
  }


@INPROCEEDINGS{Schubert2019-om,
  title     = "{Faster k-Medoids Clustering: Improving the PAM, CLARA, and
               CLARANS Algorithms}",
  booktitle = "{Similarity Search and Applications}",
  author    = "Schubert, Erich and Rousseeuw, Peter J",
  abstract  = "Clustering non-Euclidean data is difficult, and one of the most
               used algorithms besides hierarchical clustering is the popular
               algorithm Partitioning Around Medoids (PAM), also simply
               referred to as k-medoids.",
  publisher = "Springer International Publishing",
  pages     = "171--187",
  year      =  2019,
  url       = "http://dx.doi.org/10.1007/978-3-030-32047-8_16",
  file      = "All Papers/S/Schubert and Rousseeuw 2019 - Faster k-Medoids Clustering - Improving the PAM, CLARA, and CLARANS Algorithms.pdf",
  doi       = "10.1007/978-3-030-32047-8\_16"
}


@ARTICLE{Tabor2014-kd,
  title    = "{Cross-entropy clustering}",
  author   = "Tabor, J and Spurek, Przemyslaw",
  abstract = "We build a general and easily applicable clustering theory, which
              we call cross-entropy clustering (shortly CEC), which joins the
              advantages of classical k-means (easy implementation and speed)
              with those of EM (affine invariance and ability to adapt to
              clusters of desired shapes). Moreover, contrary to k-means and
              EM, CEC finds the optimal number of clusters by automatically
              removing groups which have negative information cost. Although
              CEC, like EM, can be built on an arbitrary family of densities,
              in the most important case of Gaussian CEC the division into
              clusters is affine invariant.",
  journal  = "Pattern recognition",
  volume   =  47,
  number   =  9,
  pages    = "3046--3059",
  month    =  sep,
  year     =  2014,
  url      = "http://www.sciencedirect.com/science/article/pii/S0031320314000764",
  file     = "All Papers/T/Tabor and Spurek 2014 - Cross-entropy clustering.pdf",
  keywords = "Clustering; Cross-entropy; Memory compression",
  issn     = "0031-3203",
  doi      = "10.1016/j.patcog.2014.03.006"
}


@Manual{cec2018,
    title = {CEC: Cross-Entropy Clustering},
    author = {Konrad Kamieniecki and Przemyslaw Spurek},
    year = {2018},
    note = {R package version 0.10.2},
    url = {https://CRAN.R-project.org/package=CEC},
  }