Using argumentation to solve conflicting situations in users' preferences in ambient assisted living

Oguego, Chimezie, Augusto, Juan Carlos ORCID: https://orcid.org/0000-0002-0321-9150, Springett, Mark ORCID: https://orcid.org/0000-0003-3609-8241, Quinde, Mario and James-Reynolds, Carl ORCID: https://orcid.org/0000-0002-5892-5415 (2021) Using argumentation to solve conflicting situations in users' preferences in ambient assisted living. Applied Artificial Intelligence: An International Journal, 35 (15) . pp. 2327-2369. ISSN 0883-9514 [Article] (doi:10.1080/08839514.2021.1966986)

Preview

PDF - Final accepted version (with author's formatting) Download (2MB) | Preview

Abstract

Preferences are fundamental in decision making, so understanding preference management is key in developing systems that guide the choices of the users. These choices can be decided through argument(s) which are known to have various strengths, as one argument can rely on more certain or vital information than the other. We explored argumentation technique from a previous study, and validated its potentials by applying to it several real life scenarios. The exploration demonstrates the usefulness of argumentation in handling conflicting preferences and inconsistencies, and provides effective ways to manage, reason and represents users' preferences.

Using argumentation, we provide a practical implementation of a system to manage conflicting situations, and a simple interface that aids the flow of preferences from users to the system. We illustrated using the interface, how the changes in users' preferences can effect system output in a smart home. This article describes the functionalities of the implemented system, and illustrates the functions by solving some of the complexities in users' preferences in a real smart home. The system detects potential conflicts, and tries solve them using a redefined precedence order among some preference criteria. We also show how our system is capable of interacting with external sources data. The system was used to access and use live data of a UK supermarket chain store, through their application programming interface (API) and provide users suggestions on their eating habits, based on their set preference(s). The system was used to filter specific products from the live data, and check the product description, before advising the user accordingly.

Actions (login required)

View Item

Statistics

DownloadsShow export options

Export as CSVXMLJSON

Activity Overview

6 month trend

32Downloads

6 month trend

324Hits

Additional statistics are available via IRStats2.