Multiobjective Optimization on a Budget of 250 Evaluations View Full Text


Ontology type: schema:Chapter      Open Access: True


Chapter Info

DATE

2005

AUTHORS

Joshua Knowles , Evan J. Hughes

ABSTRACT

In engineering and other ‘real-world’ applications, multiobjective optimization problems must frequently be tackled on a tight evaluation budget — tens or hundreds of function evaluations, rather than thousands. In this paper, we investigate two algorithms that use advanced initialization and search strategies to operate better under these conditions. The first algorithm, Bin_MSOPS, uses a binary search tree to divide up the decision space, and tries to sample from the largest empty regions near ‘fit’ solutions. The second algorithm, ParEGO, begins with solutions in a latin hypercube and updates a Gaussian processes surrogate model of the search landscape after every function evaluation, which it uses to estimate the solution of largest expected improvement. The two algorithms are tested using a benchmark suite of nine functions of two and three objectives — on a budget of only 250 function evaluations each, in total. Results indicate that the two algorithms search the space in very different ways and this can be used to understand performance differences. Both algorithms perform well but ParEGO comes out on top in seven of the nine test cases after 100 function evaluations, and on six after the first 250 evaluations. More... »

PAGES

176-190

References to SciGraph publications

  • 1996. On the performance assessment and comparison of stochastic multiobjective optimizers in PARALLEL PROBLEM SOLVING FROM NATURE — PPSN IV
  • 2002-10-04. Bayesian Optimization Algorithms for Multi-objective Optimization in PARALLEL PROBLEM SOLVING FROM NATURE — PPSN VII
  • 1998-12. Efficient Global Optimization of Expensive Black-Box Functions in JOURNAL OF GLOBAL OPTIMIZATION
  • 2005. Scalable Test Problems for Evolutionary Multiobjective Optimization in EVOLUTIONARY MULTIOBJECTIVE OPTIMIZATION
  • 2003. Multi-objective Binary Search Optimisation in EVOLUTIONARY MULTI-CRITERION OPTIMIZATION
  • 2002-10-04. Self-organizing Maps for Pareto Optimization of Airfoils in PARALLEL PROBLEM SOLVING FROM NATURE — PPSN VII
  • 1983-10. An interactive weighted Tchebycheff procedure for multiple objective programming in MATHEMATICAL PROGRAMMING
  • 2004. On Test Functions for Evolutionary Multi-objective Optimization in PARALLEL PROBLEM SOLVING FROM NATURE - PPSN VIII
  • 2003. Is Fitness Inheritance Useful for Real-World Applications? in EVOLUTIONARY MULTI-CRITERION OPTIMIZATION
  • Book

    TITLE

    Evolutionary Multi-Criterion Optimization

    ISBN

    978-3-540-24983-2
    978-3-540-31880-4

    Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1007/978-3-540-31880-4_13

    DOI

    http://dx.doi.org/10.1007/978-3-540-31880-4_13

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1006831024


    Indexing Status Check whether this publication has been indexed by Scopus and Web Of Science using the SN Indexing Status Tool
    Incoming Citations Browse incoming citations for this publication using opencitations.net

    JSON-LD is the canonical representation for SciGraph data.

    TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

    [
      {
        "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
        "about": [
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0102", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Applied Mathematics", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/01", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Mathematical Sciences", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "University of Manchester", 
              "id": "https://www.grid.ac/institutes/grid.5379.8", 
              "name": [
                "School of Chemistry, University of Manchester, PO Box 88, Faraday Building, Sackville Street, M60 1QD, Manchester, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Knowles", 
            "givenName": "Joshua", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Cranfield University", 
              "id": "https://www.grid.ac/institutes/grid.12026.37", 
              "name": [
                "Cranfield University, SN6 8LA, Shrivenham, Swindon, UK"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Hughes", 
            "givenName": "Evan J.", 
            "id": "sg:person.013547430723.21", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013547430723.21"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-540-30217-9_80", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000957882", 
              "https://doi.org/10.1007/978-3-540-30217-9_80"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/978-3-540-30217-9_80", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1000957882", 
              "https://doi.org/10.1007/978-3-540-30217-9_80"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-36970-8_3", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1005119556", 
              "https://doi.org/10.1007/3-540-36970-8_3"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1023/a:1008306431147", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1009040383", 
              "https://doi.org/10.1023/a:1008306431147"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45712-7_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010472546", 
              "https://doi.org/10.1007/3-540-45712-7_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45712-7_29", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1010472546", 
              "https://doi.org/10.1007/3-540-45712-7_29"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1162/106365601750190406", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1014679884"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-36970-8_8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1017034348", 
              "https://doi.org/10.1007/3-540-36970-8_8"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02591870", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019166567", 
              "https://doi.org/10.1007/bf02591870"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/bf02591870", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1019166567", 
              "https://doi.org/10.1007/bf02591870"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/s0955-2219(01)00289-8", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1023205308"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-61723-x_1022", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1024732816", 
              "https://doi.org/10.1007/3-540-61723-x_1022"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/1-84628-137-7_6", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1028475054", 
              "https://doi.org/10.1007/1-84628-137-7_6"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1145/298151.298382", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1036821240"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45712-7_12", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037946614", 
              "https://doi.org/10.1007/3-540-45712-7_12"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1007/3-540-45712-7_12", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1037946614", 
              "https://doi.org/10.1007/3-540-45712-7_12"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1016/0032-9592(94)00036-0", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1048758757"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ac034669a", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1054995215"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1021/ac034669a", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1054995215"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tevc.2002.800884", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061604548"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tevc.2003.810758", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061604587"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/tevc.2005.851274", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1061604686"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1214/ss/1177012413", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1064409909"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "https://doi.org/10.1109/cec.2003.1299427", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1095471252"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2005", 
        "datePublishedReg": "2005-01-01", 
        "description": "In engineering and other \u2018real-world\u2019 applications, multiobjective optimization problems must frequently be tackled on a tight evaluation budget \u2014 tens or hundreds of function evaluations, rather than thousands. In this paper, we investigate two algorithms that use advanced initialization and search strategies to operate better under these conditions. The first algorithm, Bin_MSOPS, uses a binary search tree to divide up the decision space, and tries to sample from the largest empty regions near \u2018fit\u2019 solutions. The second algorithm, ParEGO, begins with solutions in a latin hypercube and updates a Gaussian processes surrogate model of the search landscape after every function evaluation, which it uses to estimate the solution of largest expected improvement. The two algorithms are tested using a benchmark suite of nine functions of two and three objectives \u2014 on a budget of only 250 function evaluations each, in total. Results indicate that the two algorithms search the space in very different ways and this can be used to understand performance differences. Both algorithms perform well but ParEGO comes out on top in seven of the nine test cases after 100 function evaluations, and on six after the first 250 evaluations.", 
        "editor": [
          {
            "familyName": "Coello Coello", 
            "givenName": "Carlos A.", 
            "type": "Person"
          }, 
          {
            "familyName": "Hern\u00e1ndez Aguirre", 
            "givenName": "Arturo", 
            "type": "Person"
          }, 
          {
            "familyName": "Zitzler", 
            "givenName": "Eckart", 
            "type": "Person"
          }
        ], 
        "genre": "chapter", 
        "id": "sg:pub.10.1007/978-3-540-31880-4_13", 
        "inLanguage": [
          "en"
        ], 
        "isAccessibleForFree": true, 
        "isPartOf": {
          "isbn": [
            "978-3-540-24983-2", 
            "978-3-540-31880-4"
          ], 
          "name": "Evolutionary Multi-Criterion Optimization", 
          "type": "Book"
        }, 
        "name": "Multiobjective Optimization on a Budget of 250 Evaluations", 
        "pagination": "176-190", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1006831024"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1007/978-3-540-31880-4_13"
            ]
          }, 
          {
            "name": "readcube_id", 
            "type": "PropertyValue", 
            "value": [
              "208a022c68629486f0c1e1e69c4a4ab6a580823168120fd37939ff7dbf42b00c"
            ]
          }
        ], 
        "publisher": {
          "location": "Berlin, Heidelberg", 
          "name": "Springer Berlin Heidelberg", 
          "type": "Organisation"
        }, 
        "sameAs": [
          "https://doi.org/10.1007/978-3-540-31880-4_13", 
          "https://app.dimensions.ai/details/publication/pub.1006831024"
        ], 
        "sdDataset": "chapters", 
        "sdDatePublished": "2019-04-16T08:03", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-uberresearch-data-dimensions-target-20181106-alternative/cleanup/v134/2549eaecd7973599484d7c17b260dba0a4ecb94b/merge/v9/a6c9fde33151104705d4d7ff012ea9563521a3ce/jats-lookup/v90/0000000359_0000000359/records_29204_00000000.jsonl", 
        "type": "Chapter", 
        "url": "https://link.springer.com/10.1007%2F978-3-540-31880-4_13"
      }
    ]
     

    Download the RDF metadata as:  json-ld nt turtle xml License info

    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular format for linked data which is fully compatible with JSON.

    curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-31880-4_13'

    N-Triples is a line-based linked data format ideal for batch operations.

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-31880-4_13'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-31880-4_13'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1007/978-3-540-31880-4_13'


     

    This table displays all metadata directly associated to this object as RDF triples.

    150 TRIPLES      23 PREDICATES      46 URIs      20 LITERALS      8 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1007/978-3-540-31880-4_13 schema:about anzsrc-for:01
    2 anzsrc-for:0102
    3 schema:author N18e7c26ebbad4d1e829c535cb7673810
    4 schema:citation sg:pub.10.1007/1-84628-137-7_6
    5 sg:pub.10.1007/3-540-36970-8_3
    6 sg:pub.10.1007/3-540-36970-8_8
    7 sg:pub.10.1007/3-540-45712-7_12
    8 sg:pub.10.1007/3-540-45712-7_29
    9 sg:pub.10.1007/3-540-61723-x_1022
    10 sg:pub.10.1007/978-3-540-30217-9_80
    11 sg:pub.10.1007/bf02591870
    12 sg:pub.10.1023/a:1008306431147
    13 https://doi.org/10.1016/0032-9592(94)00036-0
    14 https://doi.org/10.1016/s0955-2219(01)00289-8
    15 https://doi.org/10.1021/ac034669a
    16 https://doi.org/10.1109/cec.2003.1299427
    17 https://doi.org/10.1109/tevc.2002.800884
    18 https://doi.org/10.1109/tevc.2003.810758
    19 https://doi.org/10.1109/tevc.2005.851274
    20 https://doi.org/10.1145/298151.298382
    21 https://doi.org/10.1162/106365601750190406
    22 https://doi.org/10.1214/ss/1177012413
    23 schema:datePublished 2005
    24 schema:datePublishedReg 2005-01-01
    25 schema:description In engineering and other ‘real-world’ applications, multiobjective optimization problems must frequently be tackled on a tight evaluation budget — tens or hundreds of function evaluations, rather than thousands. In this paper, we investigate two algorithms that use advanced initialization and search strategies to operate better under these conditions. The first algorithm, Bin_MSOPS, uses a binary search tree to divide up the decision space, and tries to sample from the largest empty regions near ‘fit’ solutions. The second algorithm, ParEGO, begins with solutions in a latin hypercube and updates a Gaussian processes surrogate model of the search landscape after every function evaluation, which it uses to estimate the solution of largest expected improvement. The two algorithms are tested using a benchmark suite of nine functions of two and three objectives — on a budget of only 250 function evaluations each, in total. Results indicate that the two algorithms search the space in very different ways and this can be used to understand performance differences. Both algorithms perform well but ParEGO comes out on top in seven of the nine test cases after 100 function evaluations, and on six after the first 250 evaluations.
    26 schema:editor Ndf28a59c1fea4a02b950e2dadaa1a598
    27 schema:genre chapter
    28 schema:inLanguage en
    29 schema:isAccessibleForFree true
    30 schema:isPartOf N5d17a04d3e154bcda09943bc7737ad01
    31 schema:name Multiobjective Optimization on a Budget of 250 Evaluations
    32 schema:pagination 176-190
    33 schema:productId N6b3b3eec9096444eb812fe77a46ffa6a
    34 N954ca177ac124b1ca6e6cc6bdc9c73b9
    35 N965a39e5da534408ae0fd77e111f1069
    36 schema:publisher N6564c4b3528a4fc092484e824e0b1fb6
    37 schema:sameAs https://app.dimensions.ai/details/publication/pub.1006831024
    38 https://doi.org/10.1007/978-3-540-31880-4_13
    39 schema:sdDatePublished 2019-04-16T08:03
    40 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    41 schema:sdPublisher Ne0993ca06d3642d083ddd70d7551b8ad
    42 schema:url https://link.springer.com/10.1007%2F978-3-540-31880-4_13
    43 sgo:license sg:explorer/license/
    44 sgo:sdDataset chapters
    45 rdf:type schema:Chapter
    46 N04bdada522464ef9a4a66d4f2d69c815 schema:affiliation https://www.grid.ac/institutes/grid.5379.8
    47 schema:familyName Knowles
    48 schema:givenName Joshua
    49 rdf:type schema:Person
    50 N06bdd915e8f94bb89555da3520280717 rdf:first N31f4028d1ad94726a127e7aa132fafec
    51 rdf:rest Nc46d198c543d4b819eccd24716c9a245
    52 N18e7c26ebbad4d1e829c535cb7673810 rdf:first N04bdada522464ef9a4a66d4f2d69c815
    53 rdf:rest N674879a479e54f609e817870ffd56cb6
    54 N1c0695fc682d4aaf835cb00afab97937 schema:familyName Zitzler
    55 schema:givenName Eckart
    56 rdf:type schema:Person
    57 N31f4028d1ad94726a127e7aa132fafec schema:familyName Hernández Aguirre
    58 schema:givenName Arturo
    59 rdf:type schema:Person
    60 N5d17a04d3e154bcda09943bc7737ad01 schema:isbn 978-3-540-24983-2
    61 978-3-540-31880-4
    62 schema:name Evolutionary Multi-Criterion Optimization
    63 rdf:type schema:Book
    64 N6564c4b3528a4fc092484e824e0b1fb6 schema:location Berlin, Heidelberg
    65 schema:name Springer Berlin Heidelberg
    66 rdf:type schema:Organisation
    67 N674879a479e54f609e817870ffd56cb6 rdf:first sg:person.013547430723.21
    68 rdf:rest rdf:nil
    69 N6b3b3eec9096444eb812fe77a46ffa6a schema:name dimensions_id
    70 schema:value pub.1006831024
    71 rdf:type schema:PropertyValue
    72 N954ca177ac124b1ca6e6cc6bdc9c73b9 schema:name doi
    73 schema:value 10.1007/978-3-540-31880-4_13
    74 rdf:type schema:PropertyValue
    75 N965a39e5da534408ae0fd77e111f1069 schema:name readcube_id
    76 schema:value 208a022c68629486f0c1e1e69c4a4ab6a580823168120fd37939ff7dbf42b00c
    77 rdf:type schema:PropertyValue
    78 Nc46d198c543d4b819eccd24716c9a245 rdf:first N1c0695fc682d4aaf835cb00afab97937
    79 rdf:rest rdf:nil
    80 Nd69f5791f0044f18b19e04d95c9600e1 schema:familyName Coello Coello
    81 schema:givenName Carlos A.
    82 rdf:type schema:Person
    83 Ndf28a59c1fea4a02b950e2dadaa1a598 rdf:first Nd69f5791f0044f18b19e04d95c9600e1
    84 rdf:rest N06bdd915e8f94bb89555da3520280717
    85 Ne0993ca06d3642d083ddd70d7551b8ad schema:name Springer Nature - SN SciGraph project
    86 rdf:type schema:Organization
    87 anzsrc-for:01 schema:inDefinedTermSet anzsrc-for:
    88 schema:name Mathematical Sciences
    89 rdf:type schema:DefinedTerm
    90 anzsrc-for:0102 schema:inDefinedTermSet anzsrc-for:
    91 schema:name Applied Mathematics
    92 rdf:type schema:DefinedTerm
    93 sg:person.013547430723.21 schema:affiliation https://www.grid.ac/institutes/grid.12026.37
    94 schema:familyName Hughes
    95 schema:givenName Evan J.
    96 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.013547430723.21
    97 rdf:type schema:Person
    98 sg:pub.10.1007/1-84628-137-7_6 schema:sameAs https://app.dimensions.ai/details/publication/pub.1028475054
    99 https://doi.org/10.1007/1-84628-137-7_6
    100 rdf:type schema:CreativeWork
    101 sg:pub.10.1007/3-540-36970-8_3 schema:sameAs https://app.dimensions.ai/details/publication/pub.1005119556
    102 https://doi.org/10.1007/3-540-36970-8_3
    103 rdf:type schema:CreativeWork
    104 sg:pub.10.1007/3-540-36970-8_8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017034348
    105 https://doi.org/10.1007/3-540-36970-8_8
    106 rdf:type schema:CreativeWork
    107 sg:pub.10.1007/3-540-45712-7_12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1037946614
    108 https://doi.org/10.1007/3-540-45712-7_12
    109 rdf:type schema:CreativeWork
    110 sg:pub.10.1007/3-540-45712-7_29 schema:sameAs https://app.dimensions.ai/details/publication/pub.1010472546
    111 https://doi.org/10.1007/3-540-45712-7_29
    112 rdf:type schema:CreativeWork
    113 sg:pub.10.1007/3-540-61723-x_1022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1024732816
    114 https://doi.org/10.1007/3-540-61723-x_1022
    115 rdf:type schema:CreativeWork
    116 sg:pub.10.1007/978-3-540-30217-9_80 schema:sameAs https://app.dimensions.ai/details/publication/pub.1000957882
    117 https://doi.org/10.1007/978-3-540-30217-9_80
    118 rdf:type schema:CreativeWork
    119 sg:pub.10.1007/bf02591870 schema:sameAs https://app.dimensions.ai/details/publication/pub.1019166567
    120 https://doi.org/10.1007/bf02591870
    121 rdf:type schema:CreativeWork
    122 sg:pub.10.1023/a:1008306431147 schema:sameAs https://app.dimensions.ai/details/publication/pub.1009040383
    123 https://doi.org/10.1023/a:1008306431147
    124 rdf:type schema:CreativeWork
    125 https://doi.org/10.1016/0032-9592(94)00036-0 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048758757
    126 rdf:type schema:CreativeWork
    127 https://doi.org/10.1016/s0955-2219(01)00289-8 schema:sameAs https://app.dimensions.ai/details/publication/pub.1023205308
    128 rdf:type schema:CreativeWork
    129 https://doi.org/10.1021/ac034669a schema:sameAs https://app.dimensions.ai/details/publication/pub.1054995215
    130 rdf:type schema:CreativeWork
    131 https://doi.org/10.1109/cec.2003.1299427 schema:sameAs https://app.dimensions.ai/details/publication/pub.1095471252
    132 rdf:type schema:CreativeWork
    133 https://doi.org/10.1109/tevc.2002.800884 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061604548
    134 rdf:type schema:CreativeWork
    135 https://doi.org/10.1109/tevc.2003.810758 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061604587
    136 rdf:type schema:CreativeWork
    137 https://doi.org/10.1109/tevc.2005.851274 schema:sameAs https://app.dimensions.ai/details/publication/pub.1061604686
    138 rdf:type schema:CreativeWork
    139 https://doi.org/10.1145/298151.298382 schema:sameAs https://app.dimensions.ai/details/publication/pub.1036821240
    140 rdf:type schema:CreativeWork
    141 https://doi.org/10.1162/106365601750190406 schema:sameAs https://app.dimensions.ai/details/publication/pub.1014679884
    142 rdf:type schema:CreativeWork
    143 https://doi.org/10.1214/ss/1177012413 schema:sameAs https://app.dimensions.ai/details/publication/pub.1064409909
    144 rdf:type schema:CreativeWork
    145 https://www.grid.ac/institutes/grid.12026.37 schema:alternateName Cranfield University
    146 schema:name Cranfield University, SN6 8LA, Shrivenham, Swindon, UK
    147 rdf:type schema:Organization
    148 https://www.grid.ac/institutes/grid.5379.8 schema:alternateName University of Manchester
    149 schema:name School of Chemistry, University of Manchester, PO Box 88, Faraday Building, Sackville Street, M60 1QD, Manchester, UK
    150 rdf:type schema:Organization
     




    Preview window. Press ESC to close (or click here)


    ...