| fullrecord |
[{"key": "dc.contributor.author", "value": "Kalmbach, Antoine", "language": null, "element": "contributor", "qualifier": "author", "schema": "dc"}, {"key": "dc.date.accessioned", "value": "2014-08-18T11:00:39Z", "language": "", "element": "date", "qualifier": "accessioned", "schema": "dc"}, {"key": "dc.date.available", "value": "2014-08-18T11:00:39Z", "language": "", "element": "date", "qualifier": "available", "schema": "dc"}, {"key": "dc.date.issued", "value": "2014", "language": null, "element": "date", "qualifier": "issued", "schema": "dc"}, {"key": "dc.identifier.other", "value": "oai:jykdok.linneanet.fi:1444344", "language": null, "element": "identifier", "qualifier": "other", "schema": "dc"}, {"key": "dc.identifier.uri", "value": "https://jyx.jyu.fi/handle/123456789/44048", "language": "", "element": "identifier", "qualifier": "uri", "schema": "dc"}, {"key": "dc.description.abstract", "value": "T\u00e4m\u00e4 pro gradu -ty\u00f6 tutkii automaattisen p\u00e4\u00e4ttelyn\r\nhy\u00f6dynt\u00e4mist\u00e4 reitinoptimointiongelmien ratkaisemisessa. Reitinoptimointiongelma\r\non kombinatorinen optimointiongelma, jonka ratkaiseminen edellytt\u00e4\u00e4 nk. ratkaisuj\u00e4rjestelm\u00e4n\r\nluontia. Ratkaisuj\u00e4rjestelm\u00e4 toimii ratkaisupalveluna, johon sy\u00f6tet\u00e4\u00e4n\r\nongelman tiedot ja j\u00e4rjestelm\u00e4 tuottaa ongelmasta optimoidun version.\r\n\r\nT\u00e4m\u00e4 toimintaketju alkaa ongelman tietojen tulkitsemisella. T\u00e4ss\u00e4 ty\u00f6ss\u00e4 esitell\u00e4\u00e4n\r\nmenetelm\u00e4 t\u00e4m\u00e4n askeleen nopeuttamiseksi. Koneoppimisella luodaan j\u00e4rjestelm\u00e4,\r\njolle opetetaan esimerkkej\u00e4 n\u00e4ytt\u00e4en milt\u00e4 reitinoptimointiongelman data n\u00e4ytt\u00e4\u00e4.\r\nMenetelm\u00e4 on kaksiosainen: datasta etsit\u00e4\u00e4n rakenne sis\u00e4isten viittauksien ymm\u00e4rt\u00e4miseksi\r\nja kun datan rakenne on tulkittu, yhdistet\u00e4\u00e4n datassa l\u00f6ytyv\u00e4 tieto\r\nvastaamaan varsinaisen optimointiongelman tietoja.\r\n\r\nAiemmin t\u00e4m\u00e4 askel on sis\u00e4lt\u00e4nyt paljon k\u00e4sity\u00f6t\u00e4. Lis\u00e4ksi optimointiymp\u00e4rist\u00f6t\r\novat edellytt\u00e4neet, ett\u00e4 optimointiongelmat sy\u00f6tet\u00e4\u00e4n ratkaisijoihin tietyss\u00e4 ja vain\r\ntietyss\u00e4 muodossa. Datan muuntaminen t\u00e4h\u00e4n muotoon on vaivalloista. Siksi t\u00e4ss\u00e4\r\ngradussa esitell\u00e4\u00e4n tapa, joka automaatiota k\u00e4ytt\u00e4en s\u00e4\u00e4st\u00e4\u00e4 aikaa ja vaivaa operaatiotutkijalta.\r\n\r\nT\u00e4m\u00e4n ratkaisemiseksi gradussa tutkitaan kalustop\u00e4\u00e4ttely\u00e4 koneoppimista k\u00e4ytt\u00e4en.\r\nKalustop\u00e4\u00e4ttely koostuu liitosp\u00e4\u00e4ttelyst\u00e4 ja attribuuttiluokittelusta. Liitosp\u00e4\u00e4ttely\r\nanalysoi hajautetussa muodossa olevan datan, esimerkiksi useassa Excel R\r\ntai CSVtiedostossa\r\nsijaitsevan datan, keskin\u00e4iset viitteet ja muodostaa n\u00e4ist\u00e4 rakenteen.\r\nRakenteen muodostamisen j\u00e4lkeen datasta l\u00f6ydet\u00e4\u00e4n se tarvittava tieto, jota optimointiin\r\nedellytet\u00e4\u00e4n\u2014esimerkiksi datasta tarvitaan kalustoon kuuluvien autojen\r\nkapasiteetit, jotta ajoneuvot voidaan j\u00e4rjestell\u00e4 oikein optimoinnissa.\r\n\r\nRatkaisu koostuu pitk\u00e4lti menetelm\u00e4st\u00e4, jossa algoritmia opetetaan n\u00e4ytt\u00e4m\u00e4ll\u00e4 esimerkkej\u00e4\r\nsiit\u00e4, miten liitosp\u00e4\u00e4ttelyss\u00e4 liitokset muodostuvat ja milt\u00e4 kohdeattribuutit\r\nn\u00e4ytt\u00e4v\u00e4t attribuuttiluokittelussa. Toisin sanoen, algoritmi opetetaan ymm\u00e4rt\u00e4m\u00e4\u00e4n\r\nmiten datan sis\u00e4iset viitteet toimivat ja miten n\u00e4m\u00e4 kuvautuvat reaalimaailmaan eli\r\nlopputulokseen.\r\n\r\nEsitelty ratkaisu on toteutettu erilaisin koneoppimisen menetelmin. T\u00e4ss\u00e4 ty\u00f6ss\u00e4\r\nk\u00e4ymme l\u00e4pi ratkaisun ymm\u00e4rt\u00e4m\u00e4isen vaadittavan teorian sek\u00e4 testaamme kalustonp\u00e4\u00e4ttely\u00e4\r\nkonseptina l\u00e4pikotaisesti. Tutkimme ensisijaisesti sit\u00e4, miten automaattisella\r\ndatan k\u00e4sittelyll\u00e4 voidaan helpottaa vaativien optimointiongelmien ratkaisemista\r\nja miten sellainen j\u00e4rjestelm\u00e4 toteutetaan.", "language": "fi", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.abstract", "value": "This thesis studies the use of automated reasoning in speeding up the\r\nprocess of converting vehicle routing problem data into data that is understood by\r\na system that optimises them. The vehicle routing problem is a combinatorial optimisation\r\nproblem, and we call the optimising system a solver for short. In this thesis,\r\nwe consider a solver a program that functions using the software-as-a-service\r\nparadigm: problem descriptions are entered into the system, and the solver produces\r\nan optimised version of the problem.\r\n\r\nTraditionally, solvers require the problem descriptions to be in a particular data format.\r\nSuch data usually exists in other formats, and a great effort must be put in\r\nconverting them to the accepted format. This is usually done manually by operations\r\nresearchers, and such conversion can be onerous and time-consuming. In light\r\nof this, we study the use of machine learning in creating a system that can understand\r\na variety of input data formats and convert the source data into one target\r\nformat, letting operations researchers shift their focus away from demanding data\r\nprocessing tasks.\r\n\r\nTo this end, we implement such a framework, titled fleet inference, using machine\r\nlearning. The former finds links between data files, usually column oriented CSV or\r\nExcel files, and the latter pairs source data entities into target entities.\r\n\r\nThis thesis implements fleet inference using two separate modules\u2014join inference\r\nand attribute classification. The framework consists of an automated classifier that\r\nis shown how optimisation problem data is structured, after this training the classifier\r\ncan be used to understand structure in an otherwise seemingly unstructured\r\ndata set. After a structure in these files has been obtained, we try to match data in\r\nthem to data a vehicle routing problem solver needs\u2014e.g., the capacities of vehicles\r\navailable in the problem.\r\n\r\nThis system was implemented using a variety of classification techniques, and we\r\npresent careful evaluations and introduce readers to the concepts of classification\r\nand data integration, all the while showing the apparent benefits of what automated\r\nreasoning can produce when faced with onerous data processing scenarios.", "language": "en", "element": "description", "qualifier": "abstract", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted using Plone Publishing form by Antoine Kalmbach (anhekalm) on 2014-08-18 11:00:39.336286. Form: Pro gradu -lomake (https://kirjasto.jyu.fi/julkaisut/julkaisulomakkeet/pro-gradu-lomake). JyX data: [jyx_publishing-allowed (fi) =True]", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Submitted by jyx lomake-julkaisija (jyx-julkaisija@noreply.fi) on 2014-08-18T11:00:39Z\r\nNo. of bitstreams: 2\r\nURN:NBN:fi:jyu-201408182374.pdf: 869385 bytes, checksum: 9a6c482c805040d1419fd8c0a5253b74 (MD5)\r\nlicense.html: 4837 bytes, checksum: 5398f125a70aeb9349287bcddfa9cc39 (MD5)", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.description.provenance", "value": "Made available in DSpace on 2014-08-18T11:00:39Z (GMT). No. of bitstreams: 2\r\nURN:NBN:fi:jyu-201408182374.pdf: 869385 bytes, checksum: 9a6c482c805040d1419fd8c0a5253b74 (MD5)\r\nlicense.html: 4837 bytes, checksum: 5398f125a70aeb9349287bcddfa9cc39 (MD5)\r\n Previous issue date: 2014", "language": "en", "element": "description", "qualifier": "provenance", "schema": "dc"}, {"key": "dc.format.extent", "value": "1 verkkoaineisto.", "language": null, "element": "format", "qualifier": "extent", "schema": "dc"}, {"key": "dc.format.mimetype", "value": "application/pdf", "language": null, "element": "format", "qualifier": "mimetype", "schema": "dc"}, {"key": "dc.language.iso", "value": "eng", "language": null, "element": "language", "qualifier": "iso", "schema": "dc"}, {"key": "dc.rights", "value": "In Copyright", "language": "en", "element": "rights", "qualifier": null, "schema": "dc"}, {"key": "dc.subject.other", "value": "fleet inference", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "join inference", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "data integration", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "machine learning", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "vehicle routing problem", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "data exchange", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "attribute classification", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.subject.other", "value": "operations research", "language": "", "element": "subject", "qualifier": "other", "schema": "dc"}, {"key": "dc.title", "value": "Fleet inference : importing vehicle routing problems using machine learning", "language": null, "element": "title", "qualifier": null, "schema": "dc"}, {"key": "dc.type", "value": "master thesis", "language": null, "element": "type", "qualifier": null, "schema": "dc"}, {"key": "dc.identifier.urn", "value": "URN:NBN:fi:jyu-201408182374", "language": null, "element": "identifier", "qualifier": "urn", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Pro gradu -tutkielma", "language": "fi", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.type.ontasot", "value": "Master\u2019s thesis", "language": "en", "element": "type", "qualifier": "ontasot", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Informaatioteknologian tiedekunta", "language": "fi", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.faculty", "value": "Faculty of Information Technology", "language": "en", "element": "contributor", "qualifier": "faculty", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Tietotekniikan laitos", "language": "fi", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.department", "value": "Department of Mathematical Information Technology", "language": "en", "element": "contributor", "qualifier": "department", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "University of Jyv\u00e4skyl\u00e4", "language": "en", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.contributor.organization", "value": "Jyv\u00e4skyl\u00e4n yliopisto", "language": "fi", "element": "contributor", "qualifier": "organization", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Tietotekniikka", "language": "fi", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.subject.discipline", "value": "Mathematical Information Technology", "language": "en", "element": "subject", "qualifier": "discipline", "schema": "dc"}, {"key": "dc.date.updated", "value": "2014-08-18T11:00:40Z", "language": "", "element": "date", "qualifier": "updated", "schema": "dc"}, {"key": "dc.type.coar", "value": "http://purl.org/coar/resource_type/c_bdcc", "language": null, "element": "type", "qualifier": "coar", "schema": "dc"}, {"key": "dc.rights.accesslevel", "value": "openAccess", "language": null, "element": "rights", "qualifier": "accesslevel", "schema": "dc"}, {"key": "dc.type.publication", "value": "masterThesis", "language": null, "element": "type", "qualifier": "publication", "schema": "dc"}, {"key": "dc.subject.oppiainekoodi", "value": "602", "language": null, "element": "subject", "qualifier": "oppiainekoodi", "schema": "dc"}, {"key": "dc.subject.yso", "value": "koneoppiminen", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.subject.yso", "value": "tiedonsiirto", "language": null, "element": "subject", "qualifier": "yso", "schema": "dc"}, {"key": "dc.format.content", "value": "fulltext", "language": null, "element": "format", "qualifier": "content", "schema": "dc"}, {"key": "dc.rights.url", "value": "https://rightsstatements.org/page/InC/1.0/", "language": null, "element": "rights", "qualifier": "url", "schema": "dc"}, {"key": "dc.type.okm", "value": "G2", "language": null, "element": "type", "qualifier": "okm", "schema": "dc"}]
|