Incremental Learning of Daily Routines as Workflows in a Smart Home Environment

Abstract

Smart home environments should proactively support users in their activities, anticipating their needs according to their preferences. Understanding what the user is doing in the environment is important for adapting the environment's behavior, as well as for identifying situations that could be problematic for the user. Enabling the environment to exploit models of the user's most common behaviors is an important step toward this objective. In particular, models of the daily routines of a user can be exploited not only for predicting his/her needs, but also for comparing the actual situation at a given moment with the expected one, in order to detect anomalies in his/her behavior. While manually setting up process models in business and factory environments may be cost-effective, building models of the processes involved in people's everyday life is infeasible. This fact fully justifies the interest of the Ambient Intelligence community in automatically learning such models from examples of actual behavior. Incremental adaptation of the models and the ability to express/learn complex conditions on the involved tasks are also desirable. This article describes how process mining can be used for learning users' daily routines from a dataset of annotated sensor data. The solution that we propose relies on a First-Order Logic learning approach. Indeed, First-Order Logic provides a single, comprehensive and powerful framework for supporting all the previously mentioned features. Our experiments, performed both on a proprietary toy dataset and on publicly available real-world ones, indicate that this approach is efficient and effective for learning and modeling daily routines in Smart Home Environments.

Incremental on-line learning: A review and comparison of state of the art algorithms

“…Incremental algorithms are also very suitable for learning beyond the production phase which enables devices to adapt to individual customer habits and environments. This is particularly interesting for smart home products [2,3]. Here the main challenge is not large-scale processing but rather continuous and efficient learning from few data.…”

Radial Basis Function Neural Network with Localized Stochastic-Sensitive Autoencoder for Home-Based Activity Recognition

“…In addition, many machine-learning methods on smart homes have been proposed [27], such as process mining [28], active learning and dynamic K-means [29]. Van Kasteren et al recorded 25 days' activities data in the home of a 26-year-old male by using a wireless sensor network [30].…”

Understanding Coding Behavior: An Incremental Process Mining Approach

“…Thus, this study also proposes a framework to capture the interactions of a programmer involved in a development task with both the Eclipse IDE and the Version Control System (VCS) and record all of them in an event log. The logs are then mined using an incremental process mining technique [7][8][9] to discover the coding workflow carried out by each programmer and support the managers in their evaluation and understanding of the behavior of single programmers.…”