Using Rough Sets to Improve Activity Recognition Based on Sensor Data †

Activity recognition plays a central role in many sensor-based applications, such as smart homes for instance. Given a stream of sensor data, the goal is to determine the activities that triggered the sensor data. This article shows how spatial information can be used to improve the process of recognizing activities in smart homes. The sensors that are used in smart homes are in most cases installed in fixed locations, which means that when a particular sensor is triggered, we know approximately where the activity takes place. However, since different sensors may be involved in different occurrences of the same type of activity, the set of sensors associated with a particular activity is not precisely defined. In this article, we use rough sets rather than standard sets to denote the sensors involved in an activity to model, which enables us to deal with this imprecision. Using publicly available data sets, we will demonstrate that rough sets can adequately capture useful information to assist with the activity recognition process. We will also show that rough sets lend themselves to creating Explainable Artificial Intelligence (XAI).

[1]  Diane J. Cook,et al.  Learning Setting-Generalized Activity Models for Smart Spaces , 2012, IEEE Intelligent Systems.

[2]  Anthony G. Cohn,et al.  The EGG/YOLK reliability hierarchy: semantic data integration using sorts with prototypes , 1994, CIKM '94.

[3]  Hans W. Guesgen,et al.  Spatio-Temporal Reasoning and Context Awareness , 2010, Handbook of Ambient Intelligence and Smart Environments.

[4]  Ahmad Lotfi,et al.  Smart homes for the elderly dementia sufferers: identification and prediction of abnormal behaviour , 2012, J. Ambient Intell. Humaniz. Comput..

[5]  Anthony G. Cohn,et al.  A Spatial Logic based on Regions and Connection , 1992, KR.

[6]  Rong Chen,et al.  Hidden State Conditional Random Field for Abnormal Activity Recognition in Smart Homes , 2015, Entropy.

[7]  Ahmad Lotfi,et al.  User Activities Outliers Detection; Integration of Statistical and Computational Intelligence Techniques , 2016, Comput. Intell..

[8]  Zhibo Pang,et al.  Smart Homes for Elderly Healthcare—Recent Advances and Research Challenges , 2017, Sensors.

[9]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[10]  Yuto Lim,et al.  A Novel Human Activity Recognition and Prediction in Smart Home Based on Interaction , 2019, Sensors.

[11]  Chris D. Nugent,et al.  Simulation of Smart Home Activity Datasets , 2015, Sensors.

[12]  Diane J. Cook,et al.  Active Lezi: an Incremental Parsing Algorithm for Sequential Prediction , 2004, Int. J. Artif. Intell. Tools.

[13]  Diane J. Cook,et al.  Coping with multiple residents in a smart environment , 2009, J. Ambient Intell. Smart Environ..

[14]  Hani Hagras,et al.  Detection Of Normal and Novel Behaviours In Ubiquitous Domestic Environments , 2010, Comput. J..

[15]  Juan Carlos Augusto,et al.  The Use of Temporal Reasoning and Management of Complex Events in Smart Homes , 2004, ECAI.

[16]  Vikramaditya R. Jakkula,et al.  Anomaly Detection Using Temporal Data Mining in a Smart Home Environment , 2008, Methods of Information in Medicine.

[17]  Juan Carlos Augusto,et al.  Learning Accurate Temporal Relations from User Actions in Intelligent Environments , 2009, Ubicomp 2009.

[18]  MahmoudSawsan,et al.  User Activities Outliers Detection; Integration of Statistical and Computational Intelligence Techniques , 2016 .

[19]  Hans W. Guesgen,et al.  Unsupervised Learning of Patterns in Data Streams Using Compression and Edit Distance , 2011, IJCAI.

[20]  Albert Ali Salah,et al.  Searching for Temporal Patterns in AmI Sensor Data , 2007, AmI Workshops.

[21]  Juan Carlos Augusto,et al.  Handbook of Ambient Intelligence and Smart Environments , 2009 .

[22]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[23]  Henry A. Kautz,et al.  Location-Based Activity Recognition using Relational Markov Networks , 2005, IJCAI.

[24]  Wing W. Y. Ng,et al.  Neural Network Ensembles for Sensor-Based Human Activity Recognition Within Smart Environments , 2019, Sensors.