A learning model of intelligent home

Abstract

Purpose - This paper aims to review the extant intelligent home specifications and put forward a new dimension for the specifications of intelligent home (IHS). Design/methodology/approach - This study adopts a learning (bottom-up) algorithm which emphasizes the importance of learning and adaptability to the dynamic environmental changes in the IHS. Findings - The study finds that the intelligent home has been characterized by automation, integration of facilities and communication. However, it is contended here that an intelligent home specification in such a hard-wired (top-down) approach cannot be sustained in the light of the continuous changes of user requirements. Hence, adaptation to users' needs must be encompassed in a system of home intelligence. Research limitations/implications - This study provides a framework for all stakeholders to work for a common goal and a platform for benchmarking the performance of intelligent home in the long run. Originality/value - This is the first to adopt the learning (bottom-up) algorithm in defining home intelligence. © Emerald Group Publishing Limited.