{"corpus_id":199444133,"paper_sha":"3db6b70327b94c46c98ef863e2270a8f8cddbfdd","doi":"10.1007/s10115-019-01388-5","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2965423010,"dblp_id":"journals/kais/SchellingP20","acl_id":null,"title":"Dataset-Transformation: improving clustering by enhancing the structure with DipScaling and DipTransformation","year":2019,"publication_date":"2019-07-05","venue":"Knowledge and Information Systems","journal":{"name":"Knowledge and Information Systems","pages":"457 - 484","volume":"62"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle"],"pubmed_pub_types":null,"s2_fields_of_study":["Mathematics","Computer Science"],"reference_count":27,"citation_count":13,"influential_citation_count":0,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"A data set might have a well-defined structure, but this does not necessarily lead to good clustering results. If the structure is hidden in an unfavourable scaling, clustering will usually fail. The aim of this work is to present techniques—DipScaling and DipTransformation—which enhance the data set by rescaling and transforming its features and thus emphasizing and accentuating its structure. If the structure is sufficiently clear, clustering algorithms will perform far better. We refer to such techniques as “Dataset-Transformations” and try to provide a mathematical framework for them. To show that our algorithms work well, we have conducted extensive experiments on several real-world data sets, where we improve clustering not only for k-means, which is our main focus but also for other standard clustering approaches.","claims":[{"public_id":"cl_be98470366560c362c3f7200ce2754e9","status":"active","text":"A mathematical framework is provided for dataset-transformations.","confidence":0.86,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_be98470366560c362c3f7200ce2754e9"},{"public_id":"cl_dd9becb543464edcd8580659f1c4da8f","status":"active","text":"DipScaling and DipTransformation rescale and transform features to emphasize a data set's structure for clustering.","confidence":0.98,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_dd9becb543464edcd8580659f1c4da8f"},{"public_id":"cl_0a5c58eee5c8fe544d16f0b4a2bbde1d","status":"active","text":"Extensive experiments on several real-world data sets show improved clustering for k-means and other standard clustering approaches.","confidence":0.97,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_0a5c58eee5c8fe544d16f0b4a2bbde1d"},{"public_id":"cl_fc603f568696859cc9c0aa2e64f1070c","status":"active","text":"When the underlying structure becomes sufficiently clear, clustering algorithms perform far better.","confidence":0.91,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_fc603f568696859cc9c0aa2e64f1070c"}],"concepts":[{"public_id":"co_24b27112fe316f521a329760290c4a8d","status":"active","name":"DipTransformation","description":"A feature-transformation technique used to enhance a data set's structure for clustering.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_24b27112fe316f521a329760290c4a8d"},{"public_id":"co_273fc174a418a3386ed04b45359cb3a6","status":"active","name":"real-world data sets","description":"Empirical datasets drawn from practical applications and used for experimental evaluation.","types":["dataset"],"aliases":["real-world datasets"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_273fc174a418a3386ed04b45359cb3a6"},{"public_id":"co_336f61b914c0568c9cfdbe28bc8ba99d","status":"active","name":"clustering algorithms","description":"Algorithms that group data points into clusters based on similarity or structure.","types":["method"],"aliases":["clusterers"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_336f61b914c0568c9cfdbe28bc8ba99d"},{"public_id":"co_39f277fd550edaf38518da53a93caa7c","status":"active","name":"standard clustering approaches","description":"Common off-the-shelf clustering methods used for comparison or evaluation.","types":["method family"],"aliases":["standard clustering methods"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_39f277fd550edaf38518da53a93caa7c"},{"public_id":"co_424004291b72b440e7f9893ece9cfe7d","status":"active","name":"DipScaling","description":"A feature-rescaling technique used to modify a data set so its structure becomes more apparent for clustering.","types":["method"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_424004291b72b440e7f9893ece9cfe7d"},{"public_id":"co_59832a4bee3f71e8e139abc1e22c394e","status":"active","name":"k-means","description":"A standard centroid-based clustering algorithm used as a main evaluation target.","types":["algorithm"],"aliases":["k means","kmeans"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_59832a4bee3f71e8e139abc1e22c394e"},{"public_id":"co_8fbd52a31b62b61161b73b50fd7bc94d","status":"active","name":"data set structure","description":"The underlying organization or separability present in the data that affects clustering performance.","types":["property"],"aliases":["dataset structure"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_8fbd52a31b62b61161b73b50fd7bc94d"},{"public_id":"co_902cd2471653e6b8c0d4d5ad9dfe9ea2","status":"active","name":"Dataset-Transformations","description":"A class of techniques that alter data sets by rescaling or transforming features to make structure more visible to clustering algorithms.","types":["method family"],"aliases":["dataset transformations"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_902cd2471653e6b8c0d4d5ad9dfe9ea2"},{"public_id":"co_ce7fac294eea12bd102349f1ee6bb0cf","status":"active","name":"mathematical framework","description":"A formal mathematical formulation for describing and analyzing dataset-transformations.","types":["framework"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ce7fac294eea12bd102349f1ee6bb0cf"}],"external_ids":{"DOI":"10.1007/s10115-019-01388-5","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2965423010,"DBLP":"journals/kais/SchellingP20","ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/199444133","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":636759,"paper_uid":"762ea7e8-1c4a-4dad-86d0-6e7f6b9bc59f","canonical_identity":{"paper_id":636759,"paper_uid":"762ea7e8-1c4a-4dad-86d0-6e7f6b9bc59f","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/199444133"}