Newspaper article-based agent control in smart city simulations View Full Text


Ontology type: schema:ScholarlyArticle      Open Access: True


Article Info

DATE

2020-11-03

AUTHORS

Euhee Kim, Sejun Jang, Shuyu Li, Yunsick Sung

ABSTRACT

The latest research on smart city technologies mainly focuses on utilizing cities’ resources to improve the quality of the lives of citizens. Diverse kinds of control signals from massive systems and devices such as adaptive traffic light systems in smart cities can be collected and utilized. Unfortunately, it is difficult to collect a massive dataset of control signals as doing so in the real-world requires significant effort and time. This paper proposes a deep generative model which integrates a long short-term memory model with generative adversarial network (LSTM-GAN) to generate agent control signals based on the words extracted from newspaper articles to solve the problem of collecting massive signals. The discriminatory network in the LSTM-GAN takes continuous word embedding vectors as inputs generated by a pre-trained Word2Vec model. The agent control signals of sequential actions are simultaneously predicted by the LSTM-GAN in real time. Specifically, to collect the training data of smart city simulations, the LSTM-GAN is trained based on the Corpus of Contemporary American English (COCA) newspaper dataset, which contains 5,317,731 sentences, for a total of 93,626,203 word tokens, from written texts. To verify the proposed method, agent control signals were generated and validated. In the training of the LSTM-GAN, the accuracy of the discriminator converged to 50%. In addition, the losses of the discriminator and the generator converged from 4527.04 and 4527.94 to 2.97 and 1.87, respectively. More... »

PAGES

44

References to SciGraph publications

  • 2018-08-24. A Combined CNN and LSTM Model for Arabic Sentiment Analysis in MACHINE LEARNING AND KNOWLEDGE EXTRACTION
  • 2020-03-17. A blockchain-based smart home gateway architecture for preventing data forgery in HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
  • 2019-08-01. CIoT-Net: a scalable cognitive IoT based smart city network architecture in HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
  • Identifiers

    URI

    http://scigraph.springernature.com/pub.10.1186/s13673-020-00252-8

    DOI

    http://dx.doi.org/10.1186/s13673-020-00252-8

    DIMENSIONS

    https://app.dimensions.ai/details/publication/pub.1132295174


    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/2008/08", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Information and Computing Sciences", 
            "type": "DefinedTerm"
          }, 
          {
            "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/0801", 
            "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
            "name": "Artificial Intelligence and Image Processing", 
            "type": "DefinedTerm"
          }
        ], 
        "author": [
          {
            "affiliation": {
              "alternateName": "Department of Computer Science and Engineering, Shinhan University, 11644, Kyunggi, Republic of Korea", 
              "id": "http://www.grid.ac/institutes/grid.496515.a", 
              "name": [
                "Department of Computer Science and Engineering, Shinhan University, 11644, Kyunggi, Republic of Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Kim", 
            "givenName": "Euhee", 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea", 
              "id": "http://www.grid.ac/institutes/grid.255168.d", 
              "name": [
                "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Jang", 
            "givenName": "Sejun", 
            "id": "sg:person.014250625353.94", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014250625353.94"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea", 
              "id": "http://www.grid.ac/institutes/grid.255168.d", 
              "name": [
                "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Li", 
            "givenName": "Shuyu", 
            "id": "sg:person.015046205753.32", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015046205753.32"
            ], 
            "type": "Person"
          }, 
          {
            "affiliation": {
              "alternateName": "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea", 
              "id": "http://www.grid.ac/institutes/grid.255168.d", 
              "name": [
                "Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea"
              ], 
              "type": "Organization"
            }, 
            "familyName": "Sung", 
            "givenName": "Yunsick", 
            "id": "sg:person.01231445370.36", 
            "sameAs": [
              "https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01231445370.36"
            ], 
            "type": "Person"
          }
        ], 
        "citation": [
          {
            "id": "sg:pub.10.1007/978-3-319-99740-7_12", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1106325998", 
              "https://doi.org/10.1007/978-3-319-99740-7_12"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13673-019-0190-9", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1120017099", 
              "https://doi.org/10.1186/s13673-019-0190-9"
            ], 
            "type": "CreativeWork"
          }, 
          {
            "id": "sg:pub.10.1186/s13673-020-0214-5", 
            "sameAs": [
              "https://app.dimensions.ai/details/publication/pub.1125694468", 
              "https://doi.org/10.1186/s13673-020-0214-5"
            ], 
            "type": "CreativeWork"
          }
        ], 
        "datePublished": "2020-11-03", 
        "datePublishedReg": "2020-11-03", 
        "description": "The latest research on smart city technologies mainly focuses on utilizing cities\u2019 resources to improve the quality of the lives of citizens. Diverse kinds of control signals from massive systems and devices such as adaptive traffic light systems in smart cities can be collected and utilized. Unfortunately, it is difficult to collect a massive dataset of control signals as doing so in the real-world requires significant effort and time. This paper proposes a deep generative model which integrates a long short-term memory model with generative adversarial network (LSTM-GAN) to generate agent control signals based on the words extracted from newspaper articles to solve the problem of collecting massive signals. The discriminatory network in the LSTM-GAN takes continuous word embedding vectors as inputs generated by a pre-trained Word2Vec model. The agent control signals of sequential actions are simultaneously predicted by the LSTM-GAN in real time. Specifically, to collect the training data of smart city simulations, the LSTM-GAN is trained based on the Corpus of Contemporary American English (COCA) newspaper dataset, which contains 5,317,731 sentences, for a total of 93,626,203 word tokens, from written texts. To verify the proposed method, agent control signals were generated and validated. In the training of the LSTM-GAN, the accuracy of the discriminator converged to 50%. In addition, the losses of the discriminator and the generator converged from 4527.04 and 4527.94 to 2.97 and 1.87, respectively.", 
        "genre": "article", 
        "id": "sg:pub.10.1186/s13673-020-00252-8", 
        "isAccessibleForFree": true, 
        "isPartOf": [
          {
            "id": "sg:journal.1136381", 
            "issn": [
              "2192-1962"
            ], 
            "name": "Human-centric Computing and Information Sciences", 
            "publisher": "Springer Nature", 
            "type": "Periodical"
          }, 
          {
            "issueNumber": "1", 
            "type": "PublicationIssue"
          }, 
          {
            "type": "PublicationVolume", 
            "volumeNumber": "10"
          }
        ], 
        "keywords": [
          "control signals", 
          "adaptive traffic light system", 
          "LSTM-GAN", 
          "city simulations", 
          "traffic light system", 
          "massive signals", 
          "light system", 
          "real time", 
          "simulations", 
          "signals", 
          "smart cities", 
          "smart city technologies", 
          "generator", 
          "significant efforts", 
          "city resources", 
          "devices", 
          "city technologies", 
          "long short-term memory (LSTM) model", 
          "short-term memory model", 
          "system", 
          "model", 
          "technology", 
          "generative adversarial network", 
          "network", 
          "accuracy", 
          "latest research", 
          "adversarial network", 
          "time", 
          "input", 
          "method", 
          "training data", 
          "agent control", 
          "kind", 
          "discriminator", 
          "problem", 
          "diverse kinds", 
          "addition", 
          "control", 
          "loss", 
          "resources", 
          "quality", 
          "vector", 
          "dataset", 
          "research", 
          "deep generative models", 
          "city", 
          "data", 
          "lives of citizens", 
          "efforts", 
          "life", 
          "article", 
          "massive datasets", 
          "generative model", 
          "memory model", 
          "massive systems", 
          "action", 
          "continuous words", 
          "words", 
          "training", 
          "tokens", 
          "word2vec model", 
          "total", 
          "pre-trained word2vec model", 
          "citizens", 
          "sequential action", 
          "word tokens", 
          "corpus", 
          "text", 
          "sentences", 
          "newspaper articles", 
          "paper"
        ], 
        "name": "Newspaper article-based agent control in smart city simulations", 
        "pagination": "44", 
        "productId": [
          {
            "name": "dimensions_id", 
            "type": "PropertyValue", 
            "value": [
              "pub.1132295174"
            ]
          }, 
          {
            "name": "doi", 
            "type": "PropertyValue", 
            "value": [
              "10.1186/s13673-020-00252-8"
            ]
          }
        ], 
        "sameAs": [
          "https://doi.org/10.1186/s13673-020-00252-8", 
          "https://app.dimensions.ai/details/publication/pub.1132295174"
        ], 
        "sdDataset": "articles", 
        "sdDatePublished": "2022-11-24T21:05", 
        "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
        "sdPublisher": {
          "name": "Springer Nature - SN SciGraph project", 
          "type": "Organization"
        }, 
        "sdSource": "s3://com-springernature-scigraph/baseset/20221124/entities/gbq_results/article/article_840.jsonl", 
        "type": "ScholarlyArticle", 
        "url": "https://doi.org/10.1186/s13673-020-00252-8"
      }
    ]
     

    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.10.1186/s13673-020-00252-8'

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

    curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/pub.10.1186/s13673-020-00252-8'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/pub.10.1186/s13673-020-00252-8'

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

    curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/pub.10.1186/s13673-020-00252-8'


     

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

    162 TRIPLES      21 PREDICATES      97 URIs      86 LITERALS      6 BLANK NODES

    Subject Predicate Object
    1 sg:pub.10.1186/s13673-020-00252-8 schema:about anzsrc-for:08
    2 anzsrc-for:0801
    3 schema:author N7d112b9ed4ad4604a46cf800ad9b555b
    4 schema:citation sg:pub.10.1007/978-3-319-99740-7_12
    5 sg:pub.10.1186/s13673-019-0190-9
    6 sg:pub.10.1186/s13673-020-0214-5
    7 schema:datePublished 2020-11-03
    8 schema:datePublishedReg 2020-11-03
    9 schema:description The latest research on smart city technologies mainly focuses on utilizing cities’ resources to improve the quality of the lives of citizens. Diverse kinds of control signals from massive systems and devices such as adaptive traffic light systems in smart cities can be collected and utilized. Unfortunately, it is difficult to collect a massive dataset of control signals as doing so in the real-world requires significant effort and time. This paper proposes a deep generative model which integrates a long short-term memory model with generative adversarial network (LSTM-GAN) to generate agent control signals based on the words extracted from newspaper articles to solve the problem of collecting massive signals. The discriminatory network in the LSTM-GAN takes continuous word embedding vectors as inputs generated by a pre-trained Word2Vec model. The agent control signals of sequential actions are simultaneously predicted by the LSTM-GAN in real time. Specifically, to collect the training data of smart city simulations, the LSTM-GAN is trained based on the Corpus of Contemporary American English (COCA) newspaper dataset, which contains 5,317,731 sentences, for a total of 93,626,203 word tokens, from written texts. To verify the proposed method, agent control signals were generated and validated. In the training of the LSTM-GAN, the accuracy of the discriminator converged to 50%. In addition, the losses of the discriminator and the generator converged from 4527.04 and 4527.94 to 2.97 and 1.87, respectively.
    10 schema:genre article
    11 schema:isAccessibleForFree true
    12 schema:isPartOf Nc6a40810c4224937873da97455a0bca9
    13 Nfd0db982f1504cc99ceb0e0e41710b82
    14 sg:journal.1136381
    15 schema:keywords LSTM-GAN
    16 accuracy
    17 action
    18 adaptive traffic light system
    19 addition
    20 adversarial network
    21 agent control
    22 article
    23 citizens
    24 city
    25 city resources
    26 city simulations
    27 city technologies
    28 continuous words
    29 control
    30 control signals
    31 corpus
    32 data
    33 dataset
    34 deep generative models
    35 devices
    36 discriminator
    37 diverse kinds
    38 efforts
    39 generative adversarial network
    40 generative model
    41 generator
    42 input
    43 kind
    44 latest research
    45 life
    46 light system
    47 lives of citizens
    48 long short-term memory (LSTM) model
    49 loss
    50 massive datasets
    51 massive signals
    52 massive systems
    53 memory model
    54 method
    55 model
    56 network
    57 newspaper articles
    58 paper
    59 pre-trained word2vec model
    60 problem
    61 quality
    62 real time
    63 research
    64 resources
    65 sentences
    66 sequential action
    67 short-term memory model
    68 signals
    69 significant efforts
    70 simulations
    71 smart cities
    72 smart city technologies
    73 system
    74 technology
    75 text
    76 time
    77 tokens
    78 total
    79 traffic light system
    80 training
    81 training data
    82 vector
    83 word tokens
    84 word2vec model
    85 words
    86 schema:name Newspaper article-based agent control in smart city simulations
    87 schema:pagination 44
    88 schema:productId N13bf54f948b5406aa25a17d573fef722
    89 N7221d4c666804994928e3931d04695b9
    90 schema:sameAs https://app.dimensions.ai/details/publication/pub.1132295174
    91 https://doi.org/10.1186/s13673-020-00252-8
    92 schema:sdDatePublished 2022-11-24T21:05
    93 schema:sdLicense https://scigraph.springernature.com/explorer/license/
    94 schema:sdPublisher Na158ce2b203f46e79ef16d551fa0d8ca
    95 schema:url https://doi.org/10.1186/s13673-020-00252-8
    96 sgo:license sg:explorer/license/
    97 sgo:sdDataset articles
    98 rdf:type schema:ScholarlyArticle
    99 N029fbdb54d7843c0b030b7e274663b1e rdf:first sg:person.01231445370.36
    100 rdf:rest rdf:nil
    101 N13bf54f948b5406aa25a17d573fef722 schema:name doi
    102 schema:value 10.1186/s13673-020-00252-8
    103 rdf:type schema:PropertyValue
    104 N26e4a49967254353900b6fdf80047697 rdf:first sg:person.015046205753.32
    105 rdf:rest N029fbdb54d7843c0b030b7e274663b1e
    106 N29639c7e08874c619a4a2c6327044cee rdf:first sg:person.014250625353.94
    107 rdf:rest N26e4a49967254353900b6fdf80047697
    108 N7221d4c666804994928e3931d04695b9 schema:name dimensions_id
    109 schema:value pub.1132295174
    110 rdf:type schema:PropertyValue
    111 N7d112b9ed4ad4604a46cf800ad9b555b rdf:first Nf8d92427e1994b539c4bd36fc0a821e2
    112 rdf:rest N29639c7e08874c619a4a2c6327044cee
    113 Na158ce2b203f46e79ef16d551fa0d8ca schema:name Springer Nature - SN SciGraph project
    114 rdf:type schema:Organization
    115 Nc6a40810c4224937873da97455a0bca9 schema:issueNumber 1
    116 rdf:type schema:PublicationIssue
    117 Nf8d92427e1994b539c4bd36fc0a821e2 schema:affiliation grid-institutes:grid.496515.a
    118 schema:familyName Kim
    119 schema:givenName Euhee
    120 rdf:type schema:Person
    121 Nfd0db982f1504cc99ceb0e0e41710b82 schema:volumeNumber 10
    122 rdf:type schema:PublicationVolume
    123 anzsrc-for:08 schema:inDefinedTermSet anzsrc-for:
    124 schema:name Information and Computing Sciences
    125 rdf:type schema:DefinedTerm
    126 anzsrc-for:0801 schema:inDefinedTermSet anzsrc-for:
    127 schema:name Artificial Intelligence and Image Processing
    128 rdf:type schema:DefinedTerm
    129 sg:journal.1136381 schema:issn 2192-1962
    130 schema:name Human-centric Computing and Information Sciences
    131 schema:publisher Springer Nature
    132 rdf:type schema:Periodical
    133 sg:person.01231445370.36 schema:affiliation grid-institutes:grid.255168.d
    134 schema:familyName Sung
    135 schema:givenName Yunsick
    136 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.01231445370.36
    137 rdf:type schema:Person
    138 sg:person.014250625353.94 schema:affiliation grid-institutes:grid.255168.d
    139 schema:familyName Jang
    140 schema:givenName Sejun
    141 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.014250625353.94
    142 rdf:type schema:Person
    143 sg:person.015046205753.32 schema:affiliation grid-institutes:grid.255168.d
    144 schema:familyName Li
    145 schema:givenName Shuyu
    146 schema:sameAs https://app.dimensions.ai/discover/publication?and_facet_researcher=ur.015046205753.32
    147 rdf:type schema:Person
    148 sg:pub.10.1007/978-3-319-99740-7_12 schema:sameAs https://app.dimensions.ai/details/publication/pub.1106325998
    149 https://doi.org/10.1007/978-3-319-99740-7_12
    150 rdf:type schema:CreativeWork
    151 sg:pub.10.1186/s13673-019-0190-9 schema:sameAs https://app.dimensions.ai/details/publication/pub.1120017099
    152 https://doi.org/10.1186/s13673-019-0190-9
    153 rdf:type schema:CreativeWork
    154 sg:pub.10.1186/s13673-020-0214-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1125694468
    155 https://doi.org/10.1186/s13673-020-0214-5
    156 rdf:type schema:CreativeWork
    157 grid-institutes:grid.255168.d schema:alternateName Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea
    158 schema:name Department of Multimedia Engineering, Dongguk University-Seoul, 04620, Seoul, Republic of Korea
    159 rdf:type schema:Organization
    160 grid-institutes:grid.496515.a schema:alternateName Department of Computer Science and Engineering, Shinhan University, 11644, Kyunggi, Republic of Korea
    161 schema:name Department of Computer Science and Engineering, Shinhan University, 11644, Kyunggi, Republic of Korea
    162 rdf:type schema:Organization
     




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


    ...