IoH: A Platform for the Intelligence of Home with a Context Awareness and Ambient Intelligence Approach

Carlos Ramos,Aria Jozi,Lucas Paiva,Zita Vale,Bruno Serra,Luis Gomes

doi:10.3390/fi11030058

Abstract

This paper presents IoH (Intelligence of Home), a platform developed to test some basic intelligent behaviors in Home context. Internet of Things, ambient intelligence and context awareness approaches motivated the development of IoH. The platform involves six layers, responsible by connectivity, persistency, unification, Internet of Things integration, subsystems integration and user interface. The integrated subsystems involve intelligent systems for light control, television brightness control, desk light control, persons counting and air conditioner control. The IoH platform is then tested for a real building, and results and conclusions are obtained. Different intelligent methods and technologies are used, form the use of a diversity of sensors, actuators, and controllers and processing units to a set of artificial intelligence approaches varying from machine learning and optimization algorithms to the use of sensor fusion and computer vision. The use of IoH day-by-day demonstrated an intelligent performance for the real building occupants.

Highlights

Our homes can be better in terms of resource management and user interactions
The presented results of this section take into account the deployment of the Intelligent of Home (IoH) platform in one of our buildings
This paper proposes a new Intelligent of Home (IoH) platform architecture

Summary

Introduction

Our homes can be better in terms of resource management and user interactions. A smart home may have multiple purposes, such as home automation [1,2], energy management [3,4,5,6], security and safety [7,8,9] or even assisted living [10,11,12]. From an energy point of view, there are some advantages in the smart home concept, where the home has smart capabilities to manage energy resources [13]. This type of smart homes enables the active participation of residential homes in the smart grid environment [14], bringing clear advantages to the users. Energy management systems can use learning algorithms to better understand the users’ preferences [15]

Objectives

Results

Conclusion