Home // SMART 2013, The Second International Conference on Smart Systems, Devices and Technologies // View article
Authors:
Farzad Amirjavid
Abdenour Bouzouane
Bruno Bouchard
Keywords: activity recognition, temporal data mining, modeling, fuzzy logic
Abstract:
Abstract— Resident of a smart home, who may be an Alzheimer patient needing permanent assistance behaves non-linearly to achieve the intended goals, which are special desired world states. To achieve the intended goals, he actuates the world by realizing strategies, scenarios, actions, activities and operations, which can be observed through the embedded sensors of the smart home. To assist him automatically and live independently at home, it is needed to capture information and knowledge from world to reason if the world state is normal and to evaluate how much the intelligent system succeeds; therefore, for recognizing the activities and their correct realizations, we propose to consider the activities as a sort of fuzzy temporal concepts that can be formalized as a multivariable mathematical problem. In order that an Activity Recognition Reasoning System perceives the observations it makes hypotheses and concepts around them. These hypotheses are resumed in a smoothing curve or line and at the recognition time, the activities functions check how much the observations are closed (similar) to their smoothing curve. Finally, the activities are ranked based on the inferred similarities to the observations. All the introduced processes are data-driven and a case study that deals with recognition of simultaneous activities based on the proposed modeling approach is presented.
Pages: 36 to 45
Copyright: Copyright (c) IARIA, 2013
Publication date: June 23, 2013
Published in: conference
ISSN: 2308-3727
ISBN: 978-1-61208-282-0
Location: Rome, Italy
Dates: from June 23, 2013 to June 28, 2013