Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems

My-Linh Nguyen; Thao Phung; Duong-Hai Ly; Linh Truong

doi:10.1109/REW53955.2021.00034

Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems

My-Linh Nguyen, Thao Phung, Duong-Hai Ly, Linh Truong

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

3 Sitaatiot (Scopus)

106 Lataukset (Pure)

Abstrakti

End-to-end machine learning (ML) in Internet of Things (IoT) Cloud systems consists of multiple processes, covering data, model, and service engineering, and involves multiple stakeholders. Therefore, to be able to explain ML to relevant stakeholders, it is important to identify explainability requirements in a holistic manner. In this paper, we present our methodology to address explainability requirements for end-to-end ML in developing ML services to be deployed within IoT Cloud systems. We identify and classify explainability requirements engineering through (i) involvement of relevant stakeholders, (ii) end-to-end data, model, and service engineering processes, and (iii) multiple explainability aspects. We present our work with a case study of predictive maintenance for Base Transceiver Stations (BTS) in the telco domain.

Alkuperäiskieli	Englanti
Otsikko	Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021
Toimittajat	Tao Yue, Mehdi Mirakhorli
Kustantaja	IEEE
Sivut	188-194
Sivumäärä	7
ISBN (elektroninen)	978-1-6654-1898-0
DOI - pysyväislinkit	https://doi.org/10.1109/REW53955.2021.00034
Tila	Julkaistu - syysk. 2021
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	International Workshop on Requirements Engineering for Explainable Systems - South Bend, Yhdysvallat Kesto: 20 syysk. 2021 → 21 syysk. 2021 Konferenssinumero: 1

Julkaisusarja

Nimi	Proceedings of the IEEE International Conference on Requirements Engineering
ISSN (painettu)	1090-705X
ISSN (elektroninen)	2332-6441

Workshop

Workshop	International Workshop on Requirements Engineering for Explainable Systems
Lyhennettä	RE4ES
Maa/Alue	Yhdysvallat
Kaupunki	South Bend
Ajanjakso	20/09/2021 → 21/09/2021

Pääsy asiakirjaan

10.1109/REW53955.2021.00034

SCI_Nguyen_etal_Holistic_Explainability_IEEE_REW_2021Accepted author manuscript, 620 KB

OpenUrl-saatavuus

Koko teksti

Muut tiedostot ja linkit

Linkki julkaisuun Scopuksessa

Siteeraa tätä

Nguyen, M-L., Phung, T., Ly, D-H., & Truong, L. (2021). Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems. teoksessa T. Yue, & M. Mirakhorli (Toimittajat), Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021 (Sivut 188-194). (Proceedings of the IEEE International Conference on Requirements Engineering). IEEE. https://doi.org/10.1109/REW53955.2021.00034

Nguyen, My-Linh ; Phung, Thao ; Ly, Duong-Hai et al. / Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems. Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021. Toimittaja / Tao Yue ; Mehdi Mirakhorli. IEEE, 2021. Sivut 188-194 (Proceedings of the IEEE International Conference on Requirements Engineering).

@inproceedings{410dd86a9ccd4f9391b978ac465f135e,

title = "Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems",

abstract = "End-to-end machine learning (ML) in Internet of Things (IoT) Cloud systems consists of multiple processes, covering data, model, and service engineering, and involves multiple stakeholders. Therefore, to be able to explain ML to relevant stakeholders, it is important to identify explainability requirements in a holistic manner. In this paper, we present our methodology to address explainability requirements for end-to-end ML in developing ML services to be deployed within IoT Cloud systems. We identify and classify explainability requirements engineering through (i) involvement of relevant stakeholders, (ii) end-to-end data, model, and service engineering processes, and (iii) multiple explainability aspects. We present our work with a case study of predictive maintenance for Base Transceiver Stations (BTS) in the telco domain. ",

author = "My-Linh Nguyen and Thao Phung and Duong-Hai Ly and Linh Truong",

year = "2021",

month = sep,

doi = "10.1109/REW53955.2021.00034",

language = "English",

series = "Proceedings of the IEEE International Conference on Requirements Engineering",

publisher = "IEEE",

pages = "188--194",

editor = "Tao Yue and Mehdi Mirakhorli",

booktitle = "Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021",

address = "United States",

note = "International Workshop on Requirements Engineering for Explainable Systems, RE4ES ; Conference date: 20-09-2021 Through 21-09-2021",

}

Nguyen, M-L, Phung, T, Ly, D-H & Truong, L 2021, Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems. julkaisussa T Yue & M Mirakhorli (toim), Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021. Proceedings of the IEEE International Conference on Requirements Engineering, IEEE, Sivut 188-194, International Workshop on Requirements Engineering for Explainable Systems, South Bend, Indiana, Yhdysvallat, 20/09/2021. https://doi.org/10.1109/REW53955.2021.00034

Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems. / Nguyen, My-Linh; Phung, Thao; Ly, Duong-Hai et al.

Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021. toim. / Tao Yue; Mehdi Mirakhorli. IEEE, 2021. s. 188-194 (Proceedings of the IEEE International Conference on Requirements Engineering).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

TY - GEN

T1 - Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems

AU - Nguyen, My-Linh

AU - Phung, Thao

AU - Ly, Duong-Hai

AU - Truong, Linh

N1 - Conference code: 1

PY - 2021/9

Y1 - 2021/9

N2 - End-to-end machine learning (ML) in Internet of Things (IoT) Cloud systems consists of multiple processes, covering data, model, and service engineering, and involves multiple stakeholders. Therefore, to be able to explain ML to relevant stakeholders, it is important to identify explainability requirements in a holistic manner. In this paper, we present our methodology to address explainability requirements for end-to-end ML in developing ML services to be deployed within IoT Cloud systems. We identify and classify explainability requirements engineering through (i) involvement of relevant stakeholders, (ii) end-to-end data, model, and service engineering processes, and (iii) multiple explainability aspects. We present our work with a case study of predictive maintenance for Base Transceiver Stations (BTS) in the telco domain.

AB - End-to-end machine learning (ML) in Internet of Things (IoT) Cloud systems consists of multiple processes, covering data, model, and service engineering, and involves multiple stakeholders. Therefore, to be able to explain ML to relevant stakeholders, it is important to identify explainability requirements in a holistic manner. In this paper, we present our methodology to address explainability requirements for end-to-end ML in developing ML services to be deployed within IoT Cloud systems. We identify and classify explainability requirements engineering through (i) involvement of relevant stakeholders, (ii) end-to-end data, model, and service engineering processes, and (iii) multiple explainability aspects. We present our work with a case study of predictive maintenance for Base Transceiver Stations (BTS) in the telco domain.

UR - http://www.scopus.com/inward/record.url?scp=85118443218&partnerID=8YFLogxK

U2 - 10.1109/REW53955.2021.00034

DO - 10.1109/REW53955.2021.00034

M3 - Conference contribution

T3 - Proceedings of the IEEE International Conference on Requirements Engineering

SP - 188

EP - 194

BT - Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021

A2 - Yue, Tao

A2 - Mirakhorli, Mehdi

PB - IEEE

T2 - International Workshop on Requirements Engineering for Explainable Systems

Y2 - 20 September 2021 through 21 September 2021

ER -

Nguyen M-L, Phung T, Ly D-H, Truong L. Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems. julkaisussa Yue T, Mirakhorli M, toimittajat, Proceedings - 29th IEEE International Requirements Engineering Conference Workshops, REW 2021. IEEE. 2021. s. 188-194. (Proceedings of the IEEE International Conference on Requirements Engineering). doi: 10.1109/REW53955.2021.00034

Holistic Explainability Requirements for End-to-End Machine Learning in IoT Cloud Systems

Abstrakti

Julkaisusarja

Workshop

Pääsy asiakirjaan

OpenUrl-saatavuus

Muut tiedostot ja linkit

Sormenjälki

Siteeraa tätä