Air Handling Unit Explainability using Contextual Importance and Utility

Avleen Malhi; Manik Madhikermi; Matti Huotari; Kary Främling

doi:10.1007/978-3-030-94822-1_32

Air Handling Unit Explainability using Contextual Importance and Utility

Avleen Malhi, Manik Madhikermi, Matti Huotari, Kary Främling

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

1 Citation (Scopus)

Abstract

Artificial intelligence has acted as an essential driver of emerg-
ing technologies by employing many sophisticated Machine Learning
(ML) models, while lack of model transparency and results explanation
limits its effectiveness in real decision-making. The eXplainable AI (XAI)
has bridged this gap by providing the explanation of outcomes made by
these complex ML model. In this paper, we classify the functioning of
an air handling unit (AHU) using the neural network and utilise con-
textual importance and contextual utility (CIU) as an XAI module for
explaining outcome of the neural Network. Here, we prove that CIU
(XAI module) can generate transparent and human-understandable ex-
planations, which the end-user can therefore utilize for making decisions
proving the overall applicability of the method in a novel use-case. Vi-
sual and textual explanations for the causes of an individual prediction
have been derived from the CIU that are numeric values calculated from
the machine learning module results. We also have provided contrasting
explanations against some causes that were not involved in the decision.
We provide both in our proposed approach.

Original language	English
Title of host publication	Mobile and Ubiquitous Systems: Computing, Networking and Services
Subtitle of host publication	18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings
Editors	Takahiro Hara, Hirozumi Yamaguchi
Publisher	Springer
Pages	513-519
Number of pages	7
Edition	1
ISBN (Electronic)	978-3-030-94822-1
ISBN (Print)	978-3-030-94821-4
DOIs	https://doi.org/10.1007/978-3-030-94822-1_32
Publication status	Published - 2022
MoE publication type	A4 Conference publication
Event	International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services - Beppu, Japan Duration: 8 Nov 2021 → 11 Nov 2021

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
Publisher	Springer
Volume	419
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services
Abbreviated title	MOBIQUITOUS
Country/Territory	Japan
City	Beppu
Period	08/11/2021 → 11/11/2021

Access to Document

10.1007/978-3-030-94822-1_32

Cite this

Malhi, A., Madhikermi, M., Huotari, M., & Främling, K. (2022). Air Handling Unit Explainability using Contextual Importance and Utility. In T. Hara, & H. Yamaguchi (Eds.), Mobile and Ubiquitous Systems: Computing, Networking and Services: 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings (1 ed., pp. 513-519). (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 419). Springer. https://doi.org/10.1007/978-3-030-94822-1_32

Malhi, Avleen ; Madhikermi, Manik ; Huotari, Matti et al. / Air Handling Unit Explainability using Contextual Importance and Utility. Mobile and Ubiquitous Systems: Computing, Networking and Services: 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings. editor / Takahiro Hara ; Hirozumi Yamaguchi. 1. ed. Springer, 2022. pp. 513-519 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering).

@inproceedings{80d9a595effe40c691f711f506b4c28e,

title = "Air Handling Unit Explainability using Contextual Importance and Utility",

abstract = "Artificial intelligence has acted as an essential driver of emerg-ing technologies by employing many sophisticated Machine Learning(ML) models, while lack of model transparency and results explanationlimits its effectiveness in real decision-making. The eXplainable AI (XAI)has bridged this gap by providing the explanation of outcomes made bythese complex ML model. In this paper, we classify the functioning ofan air handling unit (AHU) using the neural network and utilise con-textual importance and contextual utility (CIU) as an XAI module forexplaining outcome of the neural Network. Here, we prove that CIU(XAI module) can generate transparent and human-understandable ex-planations, which the end-user can therefore utilize for making decisionsproving the overall applicability of the method in a novel use-case. Vi-sual and textual explanations for the causes of an individual predictionhave been derived from the CIU that are numeric values calculated fromthe machine learning module results. We also have provided contrastingexplanations against some causes that were not involved in the decision.We provide both in our proposed approach.",

author = "Avleen Malhi and Manik Madhikermi and Matti Huotari and Kary Fr{\"a}mling",

year = "2022",

doi = "10.1007/978-3-030-94822-1_32",

language = "English",

isbn = "978-3-030-94821-4",

series = "Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering",

publisher = "Springer",

pages = "513--519",

editor = "Takahiro Hara and Hirozumi Yamaguchi",

booktitle = "Mobile and Ubiquitous Systems: Computing, Networking and Services",

address = "Germany",

edition = "1",

note = "International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MOBIQUITOUS ; Conference date: 08-11-2021 Through 11-11-2021",

}

Malhi, A, Madhikermi, M, Huotari, M & Främling, K 2022, Air Handling Unit Explainability using Contextual Importance and Utility. in T Hara & H Yamaguchi (eds), Mobile and Ubiquitous Systems: Computing, Networking and Services: 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings. 1 edn, Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol. 419, Springer, pp. 513-519, International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, Beppu, Japan, 08/11/2021. https://doi.org/10.1007/978-3-030-94822-1_32

Air Handling Unit Explainability using Contextual Importance and Utility. / Malhi, Avleen; Madhikermi, Manik; Huotari, Matti et al.
Mobile and Ubiquitous Systems: Computing, Networking and Services: 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings. ed. / Takahiro Hara; Hirozumi Yamaguchi. 1. ed. Springer, 2022. p. 513-519 (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering; Vol. 419).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Air Handling Unit Explainability using Contextual Importance and Utility

AU - Malhi, Avleen

AU - Madhikermi, Manik

AU - Huotari, Matti

AU - Främling, Kary

PY - 2022

Y1 - 2022

N2 - Artificial intelligence has acted as an essential driver of emerg-ing technologies by employing many sophisticated Machine Learning(ML) models, while lack of model transparency and results explanationlimits its effectiveness in real decision-making. The eXplainable AI (XAI)has bridged this gap by providing the explanation of outcomes made bythese complex ML model. In this paper, we classify the functioning ofan air handling unit (AHU) using the neural network and utilise con-textual importance and contextual utility (CIU) as an XAI module forexplaining outcome of the neural Network. Here, we prove that CIU(XAI module) can generate transparent and human-understandable ex-planations, which the end-user can therefore utilize for making decisionsproving the overall applicability of the method in a novel use-case. Vi-sual and textual explanations for the causes of an individual predictionhave been derived from the CIU that are numeric values calculated fromthe machine learning module results. We also have provided contrastingexplanations against some causes that were not involved in the decision.We provide both in our proposed approach.

AB - Artificial intelligence has acted as an essential driver of emerg-ing technologies by employing many sophisticated Machine Learning(ML) models, while lack of model transparency and results explanationlimits its effectiveness in real decision-making. The eXplainable AI (XAI)has bridged this gap by providing the explanation of outcomes made bythese complex ML model. In this paper, we classify the functioning ofan air handling unit (AHU) using the neural network and utilise con-textual importance and contextual utility (CIU) as an XAI module forexplaining outcome of the neural Network. Here, we prove that CIU(XAI module) can generate transparent and human-understandable ex-planations, which the end-user can therefore utilize for making decisionsproving the overall applicability of the method in a novel use-case. Vi-sual and textual explanations for the causes of an individual predictionhave been derived from the CIU that are numeric values calculated fromthe machine learning module results. We also have provided contrastingexplanations against some causes that were not involved in the decision.We provide both in our proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=85125243156&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-94822-1_32

DO - 10.1007/978-3-030-94822-1_32

M3 - Conference article in proceedings

SN - 978-3-030-94821-4

T3 - Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

SP - 513

EP - 519

BT - Mobile and Ubiquitous Systems: Computing, Networking and Services

A2 - Hara, Takahiro

A2 - Yamaguchi, Hirozumi

PB - Springer

T2 - International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

Y2 - 8 November 2021 through 11 November 2021

ER -

Malhi A, Madhikermi M, Huotari M , Främling K. Air Handling Unit Explainability using Contextual Importance and Utility. In Hara T, Yamaguchi H, editors, Mobile and Ubiquitous Systems: Computing, Networking and Services: 18th EAI International Conference, MobiQuitous 2021, Virtual Event, November 8-11, 2021, Proceedings. 1 ed. Springer. 2022. p. 513-519. (Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering). doi: 10.1007/978-3-030-94822-1_32

Air Handling Unit Explainability using Contextual Importance and Utility

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this