Unsupervised Segmentation of Smart Home Logs for Human Habit Discovery

Esposito, Lucia; Leotta, Francesco; Mecella, Massimo; Veneruso, Silvestro

doi:10.1109/ie54923.2022.9826776

Cited by 11 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another important research direction is represented by the automated segmentation of logs. Here, statistics-based techniques have been proposed [17], as well as technique based on the structure of possibly mined processes [7].…”

Section: Process Mining Using Iot Datamentioning

confidence: 99%

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

Bertrand,

Veneruso,

Leotta

et al. 2024

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

More and more so-called IoT-enhanced business processes (BPs) are supported by IoT devices, which collect large amounts of data about the execution of such processes. While these data have the potential to reveal crucial insights into the execution of the BPs, the absence of a suitable event log format integrating IoT data to process data greatly hampers the realisation of this potential. In this paper, we present the Native Iot-Centric Event (NICE) log, a new event log format designed to incorporate IoT data into a process event log ensuring traceability, flexibility and limiting data loss. The new format was linked to a smart spaces data simulator to generate synthetic logs. We evaluate our format against requirements previously established for an IoTenhanced event log format, showing that it meets all requirements, contrarily to other alternative formats. We then perform an analysis of a synthetic log to show how IoT data can easily be used to explain anomalies in the process.

show abstract

Section: Process Mining Using Iot Datamentioning

confidence: 99%

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

Bertrand,

Veneruso,

Leotta

et al. 2024

Lecture Notes in Business Information Processing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The goal of this project is to treat environments as intelligent agents, where the status of the residents and their physical surroundings are perceived using sensors; on the basis of this information, a smart home can select and automate actions that meet the needs and preferences of its inhabitants, improving the comfort, the safety and/or the productivity. The reason for this choice relies on the major impact this project has had on the community and the availability as source code of algorithms that are often used as benchmarks [15,16,20,23,28,37].…”

Section: Truthfulness Evaluationmentioning

confidence: 99%

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

Veneruso

Bertrand

Leotta

et al. 2023

AIS

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…From this point of view, the open research challenge is to perform segmentation by using the process semantics and the context. An initial proposal has been given in [10] where process model quality measures are used to iteratively segment the log.…”

Section: Log Segmented Into Tracesmentioning

confidence: 99%