Discovery of Resident Behavior Patterns Using Machine Learning Techniques and IoT Paradigm

TLDR

Internet of Things and machine learning are increasingly important for creating automatic control systems that adapt to individual user preferences in home automation, and discovering resident behavior patterns is essential for improving personalized device configuration. The study introduces Smart Home Control, an intelligent platform that customizes home automation by extracting residents’ behavior patterns from device state logs and applying machine learning. The platform employs the C4.5 decision‑tree algorithm through the Weka API to detect behavior patterns and generate configuration rules for home devices. An experimental case study demonstrates the platform’s effectiveness by identifying residents’ behavior patterns from IoT device usage history.

Abstract

In recent years, technological paradigms such as Internet of Things (IoT) and machine learning have become very important due to the benefit that their application represents in various areas of knowledge. It is interesting to note that implementing these two technologies promotes more and better automatic control systems that adjust to each user’s particular preferences in the home automation area. This work presents Smart Home Control, an intelligent platform that offers fully customized automatic control schemes for a home’s domotic devices by obtaining residents’ behavior patterns and applying machine learning to the records of state changes of each device connected to the platform. The platform uses machine learning algorithm C4.5 and the Weka API to identify the behavior patterns necessary to build home devices’ configuration rules. Besides, an experimental case study that validates the platform’s effectiveness is presented, where behavior patterns of smart homes residents were identified according to the IoT devices usage history. The discovery of behavior patterns is essential to improve the automatic configuration schemes of personalization according to the residents’ history of device use.