@Article{          ponce-de-leon.ea2016-data-based,
    author       = {{Ponce de Le{\'{o}}n}, Pedro J. and I{\~{n}}esta,
                   Jos{\'{e}} M. and Calvo-Zaragoza, Jorge and Rizo, David},
    year         = {2016},
    title        = {Data-based melody generation through multi-objective
                   evolutionary computation},
    abstract     = {Genetic-based composition algorithms are able to explore
                   an immense space of possibilities, but the main difficulty
                   has always been the implementation of the selection
                   process. In this work, sets of melodies are utilized for
                   training a machine learning approach to compute fitness,
                   based on different metrics. The fitness of a candidate is
                   provided by combining the metrics, but their values can
                   range through different orders of magnitude and evolve in
                   different ways, which makes it hard to combine these
                   criteria. In order to solve this problem, a
                   multi-objective fitness approach is proposed, in which the
                   best individuals are those in the Pareto front of the
                   multi-dimensional fitness space. Melodic trees are also
                   proposed as a data structure for chromosomic
                   representation of melodies and genetic operators are
                   adapted to them. Some experiments have been carried out
                   using a graphical interface prototype that allows one to
                   explore the creative capabilities of the proposed system.
                   An Online Supplement is provided and can be accessed at
                   http://dx.doi.org/10.1080/17459737.2016.1188171, where the
                   reader can find some technical details, information about
                   the data used, generated melodies, and additional
                   information about the developed prototype and its
                   performance.},
    doi          = {10.1080/17459737.2016.1188171},
    issn         = {17459745},
    journal      = {Journal of Mathematics and Music},
    keywords     = {algorithmic composition,composition,evolutionary
                   algorithms,machine learning,melody,multi-objective
                   optimization,tree representation},
    mendeley-tags= {algorithmic composition},
    number       = {2},
    pages        = {173--192},
    url          = {https://doi.org/10.1080/17459737.2016.1188171},
    volume       = {10}
}

{"_id":"aaQh3FhkY8caMn9ig","bibbaseid":"poncedelen-iesta-calvozaragoza-rizo-databasedmelodygenerationthroughmultiobjectiveevolutionarycomputation-2016","authorIDs":[],"author_short":["Ponce de León, P. J.","Iñesta, J. M.","Calvo-Zaragoza, J.","Rizo, D."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Ponce de León"],"firstnames":["Pedro","J."],"suffixes":[]},{"propositions":[],"lastnames":["Iñesta"],"firstnames":["José","M."],"suffixes":[]},{"propositions":[],"lastnames":["Calvo-Zaragoza"],"firstnames":["Jorge"],"suffixes":[]},{"propositions":[],"lastnames":["Rizo"],"firstnames":["David"],"suffixes":[]}],"year":"2016","title":"Data-based melody generation through multi-objective evolutionary computation","abstract":"Genetic-based composition algorithms are able to explore an immense space of possibilities, but the main difficulty has always been the implementation of the selection process. In this work, sets of melodies are utilized for training a machine learning approach to compute fitness, based on different metrics. The fitness of a candidate is provided by combining the metrics, but their values can range through different orders of magnitude and evolve in different ways, which makes it hard to combine these criteria. In order to solve this problem, a multi-objective fitness approach is proposed, in which the best individuals are those in the Pareto front of the multi-dimensional fitness space. Melodic trees are also proposed as a data structure for chromosomic representation of melodies and genetic operators are adapted to them. Some experiments have been carried out using a graphical interface prototype that allows one to explore the creative capabilities of the proposed system. An Online Supplement is provided and can be accessed at http://dx.doi.org/10.1080/17459737.2016.1188171, where the reader can find some technical details, information about the data used, generated melodies, and additional information about the developed prototype and its performance.","doi":"10.1080/17459737.2016.1188171","issn":"17459745","journal":"Journal of Mathematics and Music","keywords":"algorithmic composition,composition,evolutionary algorithms,machine learning,melody,multi-objective optimization,tree representation","mendeley-tags":"algorithmic composition","number":"2","pages":"173–192","url":"https://doi.org/10.1080/17459737.2016.1188171","volume":"10","bibtex":"@Article{ ponce-de-leon.ea2016-data-based,\n author = {{Ponce de Le{\\'{o}}n}, Pedro J. and I{\\~{n}}esta,\n Jos{\\'{e}} M. and Calvo-Zaragoza, Jorge and Rizo, David},\n year = {2016},\n title = {Data-based melody generation through multi-objective\n evolutionary computation},\n abstract = {Genetic-based composition algorithms are able to explore\n an immense space of possibilities, but the main difficulty\n has always been the implementation of the selection\n process. In this work, sets of melodies are utilized for\n training a machine learning approach to compute fitness,\n based on different metrics. The fitness of a candidate is\n provided by combining the metrics, but their values can\n range through different orders of magnitude and evolve in\n different ways, which makes it hard to combine these\n criteria. In order to solve this problem, a\n multi-objective fitness approach is proposed, in which the\n best individuals are those in the Pareto front of the\n multi-dimensional fitness space. Melodic trees are also\n proposed as a data structure for chromosomic\n representation of melodies and genetic operators are\n adapted to them. Some experiments have been carried out\n using a graphical interface prototype that allows one to\n explore the creative capabilities of the proposed system.\n An Online Supplement is provided and can be accessed at\n http://dx.doi.org/10.1080/17459737.2016.1188171, where the\n reader can find some technical details, information about\n the data used, generated melodies, and additional\n information about the developed prototype and its\n performance.},\n doi = {10.1080/17459737.2016.1188171},\n issn = {17459745},\n journal = {Journal of Mathematics and Music},\n keywords = {algorithmic composition,composition,evolutionary\n algorithms,machine learning,melody,multi-objective\n optimization,tree representation},\n mendeley-tags= {algorithmic composition},\n number = {2},\n pages = {173--192},\n url = {https://doi.org/10.1080/17459737.2016.1188171},\n volume = {10}\n}\n\n","author_short":["Ponce de León, P. J.","Iñesta, J. M.","Calvo-Zaragoza, J.","Rizo, D."],"key":"ponce-de-leon.ea2016-data-based","id":"ponce-de-leon.ea2016-data-based","bibbaseid":"poncedelen-iesta-calvozaragoza-rizo-databasedmelodygenerationthroughmultiobjectiveevolutionarycomputation-2016","role":"author","urls":{"Paper":"https://doi.org/10.1080/17459737.2016.1188171"},"keyword":["algorithmic composition","composition","evolutionary algorithms","machine learning","melody","multi-objective optimization","tree representation"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://hmb.sampaio.me/bibliografia.bib.txt","creationDate":"2020-08-18T11:41:16.942Z","downloads":0,"keywords":["algorithmic composition","composition","evolutionary algorithms","machine learning","melody","multi-objective optimization","tree representation"],"search_terms":["data","based","melody","generation","through","multi","objective","evolutionary","computation","ponce de león","iñesta","calvo-zaragoza","rizo"],"title":"Data-based melody generation through multi-objective evolutionary computation","year":2016,"dataSources":["n6MFY2CscQLDpJ7nT","RFLDZw5KyJdadDXDm"]}