Write a Blog >>
ACSOS 2020
Mon 17 - Fri 21 August 2020
Tue 18 Aug 2020 20:17 - 20:29 at Presentation Room A - Poster and Demo Session Chair(s): Ioan Petri, Gabriele Valentini

The problem of adaptation space reduction has been tackled recently using machine learning. While the result has been interesting, the accuracy of the predictions was not outstanding. In this paper, we propose a deep learning approach using a convolutional neural network (CNN) to tackle the adaptation space reduction. As the inherent nature of deep learning models to behave like a black box makes them difficult to follow and to interpret, we also explore the use of Explainable AI (XAI) in the process of the learning and prediction. XAI helps to build trust in the system by explaining the predictions and the behavior of the deep learning model. We plan to evaluate our approach on two simulated IoT applications for smart environment monitoring.

Tue 18 Aug

Displayed time zone: London change

20:05 - 21:05
Poster and Demo SessionPosters and Demos at Presentation Room A
Chair(s): Ioan Petri Cardiff University, Gabriele Valentini Arizona State University
20:05
12m
Poster
Architecture for a Dynamic Security Service Function Chain Reordering Framework
Posters and Demos
20:17
12m
Poster
A Deep Explainable Model for Adaptation Space Reduction
Posters and Demos
20:29
12m
Demonstration
Enhancing a Communication System with Adaptive Behavior using REACT
Posters and Demos
Martin Pfannemüller University of Mannheim, Martin Breitbach University of Mannheim, Christian Krupitzer University of Würzburg, Germany, Christian Becker University of Mannheim, Andy Schürr TU Darmstadt
20:41
12m
Poster
HeyCitI: Healthy Cycling in a City using Self-Adaptive Internet-of-Things
Posters and Demos
20:53
12m
Poster
dTAS: A Decentralized Self-Adaptive Service-Based System Exemplar
Posters and Demos
Jelle Van De Sijpe , Danny Weyns Linnaeus University, Sweden