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.
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 | |
| 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 |