A model-based simulator for smart homes: Enabling reproducibility and standardization

Abstract

Scientific contributions in the area of smart environments cover different tasks of ambient intelligence including action and activity recognition, anomaly detection, and automated enactment. Algorithms solving these tasks need to be validated against sensor logs of smart environments. In order to acquire these datasets, expensive facilities are needed, containing sensors, actuators and an acquisition infrastructure. Even though several freely accessible datasets are available, each of them features a very specific set of sensors, which can limit the introduction of novel approaches that could benefit of particular types of sensors and deployment layouts. Additionally, acquiring a dataset requires a considerable human effort for labeling purposes, thus further limiting the creation of new and general ones. In this paper, we propose a model-based simulator capable to generate synthetic datasets that emulate the characteristics of the vast majority of real datasets while granting trustworthy evaluation results. The datasets are generated using the eXtensible Event Stream – XES international standard commonly used for representing event logs. Finally, the datasets produced by the simulator are validated against two real scenario’s logs from the literature.

NICE: The Native IoT-Centric Event Log Model for Process Mining

“…For our experiments, the simulator presented in [28], which was originally designed to produce logs in the XES format, has been adapted to generate NICE logs. Using a Python script, the synthetic log produced was then processed to fit the meta-model proposed in this article, following the XML structure described above.…”

“…In the last years, several data formats have been adapted to IoT-enhanced event logs [9,20,28,22]. In this section, we present these new alternatives and compare them to our data format with respect to the requirements identified in [5].…”

“…Another format based on XES is described in [28] and represents IoT-enhanced logs generated by the smart home simulator used in this paper. It generates multiple files: a segmented high-level event log, an unsegmented high-level event log and a sensor log.…”