Using artificial neurons in evidence based trust computation

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Uittreksel

This paper proposes an alternative approach for evidence based trust computation where the relationship between evidence and trust is learned using an artificial neuron, making it possible to automatically adapt trust computation to different use cases. Computational trust aims to quantify trust based on ever increasing evidence on observations. In the literature a trust value is seen as a posterior subjective probability, computed using Bayesian inference on evidence, a prior and a weight of the prior. This provides a fixed mapping between evidence and trust, which may not be suitable for every case study, e.g. when positive and negative evidences are not equally important. The proposed solution is also a first step towards our future work to replace complex and case-specific trust fusion operators proposed in the literature with a generic case-independent artificial neural network solution. Our experiments on example cases of coin toss prediction and occupancy detection show that for sufficiently large data sets, i.e. given sufficient evidence based on a history of observations, the proposed learning approach yields comparable results and in some cases beats the existing approach.

TaalEngels
TitelProceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018
Plaats van productiePiscataway
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's1879-1884
Aantal pagina's6
ISBN van geprinte versie9781538643877
DOI's
StatusGepubliceerd - 5 sep 2018
Evenement17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018 - New York, Verenigde Staten van Amerika
Duur: 31 jul 20183 aug 2018

Congres

Congres17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018
LandVerenigde Staten van Amerika
StadNew York
Periode31/07/183/08/18

Vingerafdruk

Neurons
Fusion reactions
Neural networks
Experiments
Evidence-based
Neuron

Trefwoorden

    Citeer dit

    Guven, C., Holenderski, M., Ozcelebi, T., & Lukkien, J. (2018). Using artificial neurons in evidence based trust computation. In Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018 (blz. 1879-1884). [8456153] Piscataway: Institute of Electrical and Electronics Engineers. DOI: 10.1109/TrustCom/BigDataSE.2018.00285
    Guven, Cicek ; Holenderski, Mike ; Ozcelebi, Tanir ; Lukkien, Johan. / Using artificial neurons in evidence based trust computation. Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018. Piscataway : Institute of Electrical and Electronics Engineers, 2018. blz. 1879-1884
    @inproceedings{cb429bd9a1d642b889ea29a3823eec29,
    title = "Using artificial neurons in evidence based trust computation",
    abstract = "This paper proposes an alternative approach for evidence based trust computation where the relationship between evidence and trust is learned using an artificial neuron, making it possible to automatically adapt trust computation to different use cases. Computational trust aims to quantify trust based on ever increasing evidence on observations. In the literature a trust value is seen as a posterior subjective probability, computed using Bayesian inference on evidence, a prior and a weight of the prior. This provides a fixed mapping between evidence and trust, which may not be suitable for every case study, e.g. when positive and negative evidences are not equally important. The proposed solution is also a first step towards our future work to replace complex and case-specific trust fusion operators proposed in the literature with a generic case-independent artificial neural network solution. Our experiments on example cases of coin toss prediction and occupancy detection show that for sufficiently large data sets, i.e. given sufficient evidence based on a history of observations, the proposed learning approach yields comparable results and in some cases beats the existing approach.",
    keywords = "artificial neuron, computational trust, machine learning",
    author = "Cicek Guven and Mike Holenderski and Tanir Ozcelebi and Johan Lukkien",
    year = "2018",
    month = "9",
    day = "5",
    doi = "10.1109/TrustCom/BigDataSE.2018.00285",
    language = "English",
    isbn = "9781538643877",
    pages = "1879--1884",
    booktitle = "Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018",
    publisher = "Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Guven, C, Holenderski, M, Ozcelebi, T & Lukkien, J 2018, Using artificial neurons in evidence based trust computation. in Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018., 8456153, Institute of Electrical and Electronics Engineers, Piscataway, blz. 1879-1884, New York, Verenigde Staten van Amerika, 31/07/18. DOI: 10.1109/TrustCom/BigDataSE.2018.00285

    Using artificial neurons in evidence based trust computation. / Guven, Cicek; Holenderski, Mike; Ozcelebi, Tanir; Lukkien, Johan.

    Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018. Piscataway : Institute of Electrical and Electronics Engineers, 2018. blz. 1879-1884 8456153.

    Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

    TY - GEN

    T1 - Using artificial neurons in evidence based trust computation

    AU - Guven,Cicek

    AU - Holenderski,Mike

    AU - Ozcelebi,Tanir

    AU - Lukkien,Johan

    PY - 2018/9/5

    Y1 - 2018/9/5

    N2 - This paper proposes an alternative approach for evidence based trust computation where the relationship between evidence and trust is learned using an artificial neuron, making it possible to automatically adapt trust computation to different use cases. Computational trust aims to quantify trust based on ever increasing evidence on observations. In the literature a trust value is seen as a posterior subjective probability, computed using Bayesian inference on evidence, a prior and a weight of the prior. This provides a fixed mapping between evidence and trust, which may not be suitable for every case study, e.g. when positive and negative evidences are not equally important. The proposed solution is also a first step towards our future work to replace complex and case-specific trust fusion operators proposed in the literature with a generic case-independent artificial neural network solution. Our experiments on example cases of coin toss prediction and occupancy detection show that for sufficiently large data sets, i.e. given sufficient evidence based on a history of observations, the proposed learning approach yields comparable results and in some cases beats the existing approach.

    AB - This paper proposes an alternative approach for evidence based trust computation where the relationship between evidence and trust is learned using an artificial neuron, making it possible to automatically adapt trust computation to different use cases. Computational trust aims to quantify trust based on ever increasing evidence on observations. In the literature a trust value is seen as a posterior subjective probability, computed using Bayesian inference on evidence, a prior and a weight of the prior. This provides a fixed mapping between evidence and trust, which may not be suitable for every case study, e.g. when positive and negative evidences are not equally important. The proposed solution is also a first step towards our future work to replace complex and case-specific trust fusion operators proposed in the literature with a generic case-independent artificial neural network solution. Our experiments on example cases of coin toss prediction and occupancy detection show that for sufficiently large data sets, i.e. given sufficient evidence based on a history of observations, the proposed learning approach yields comparable results and in some cases beats the existing approach.

    KW - artificial neuron

    KW - computational trust

    KW - machine learning

    UR - http://www.scopus.com/inward/record.url?scp=85054094924&partnerID=8YFLogxK

    U2 - 10.1109/TrustCom/BigDataSE.2018.00285

    DO - 10.1109/TrustCom/BigDataSE.2018.00285

    M3 - Conference contribution

    SN - 9781538643877

    SP - 1879

    EP - 1884

    BT - Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018

    PB - Institute of Electrical and Electronics Engineers

    CY - Piscataway

    ER -

    Guven C, Holenderski M, Ozcelebi T, Lukkien J. Using artificial neurons in evidence based trust computation. In Proceedings - 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications and 12th IEEE International Conference on Big Data Science and Engineering, Trustcom/BigDataSE 2018. Piscataway: Institute of Electrical and Electronics Engineers. 2018. blz. 1879-1884. 8456153. Beschikbaar vanaf, DOI: 10.1109/TrustCom/BigDataSE.2018.00285