Development of Simulation for Artificial Intelligence Techniques in Smart Homes

Abstract

With the ever-evolving technology, homes where most of the human life was spent have changed and the concept of smart homes have emerged. In addition to this, artificial intelligence algorithms have been used in smart homes in order to be able to perform many tasks automatically and to produce specialized solutions to residents who live in the house. In order for the artificial intelligence algorithms to work properly, they must be continuously tested and developed under different living conditions. The realization of the algorithm tests in real environments bring many problems and reduce the efficiency. Algorithm development and improvement can also be done in a simulation environment for smart homes as done in similar situations in many different disciplines. In this study, a customized simulation has been developed to test artificial intelligence algorithms for smart homes. In the simulation, a house with the desired number of rooms can be created and smart home components with the desired number and different tasks can be added to this house. Then, virtual individuals who will use this simulated house and weekly living scenarios for these individuals can be created. After all these operations, the system simulates a smart home in real time according to the directives from outside operators. During the simulation, the desired artificial intelligence algorithms can be run on the system and their operations can be monitored. In addition, the system can be intervened from the planned scenarios to create desired conditions at any time. In the study, the simulation was run for over a month and it was demonstrated that the artificial intelligence algorithms were executed successfully by performing the operations according to the determined scenarios without any problems.

Authors and Affiliations

Hüseyin Güneş, Sabri BİCAKCI, Emre ORTA, Davut AKDAŞ

Keywords

Related Articles

Formation of a Fatigue Test Track for a Light Commercial Vehicle According to Customer Correlation

Fatigue life, one of the most critical and difficult parameters of the product design process, is verified by accelerated test by the manufacturers. For this reason, the manufacturers need specific test tracks and / or r...

Drying of orange peel in a heat pump dryer

In this study, the orange peels were experimentally dried in a heat pump dryer and the results obtained during drying process were investigated. The orange that has a high potential in Turkey, is usually grown in Mediter...

Simplify Backup on Virtual Servers

Virtualization technologies are becoming increasingly common in recent years. One of the major problems in institutions and organizations using virtualization technology is backup virtualized servers. Looking at the expe...

Comparison of Load Flow Analysis Methods in Power Systems with Different Number of Buses

Nowadays, generation and consumption points are constantly increasing in parallel with the increasing energy demand and power systems are rapidly growing. However, it is very important to plan, install and operate the po...

A Survey of Hyper-parameter Optimization Methods in Convolutional Neural Networks

Convolutional neural networks (CNN) are special types of multi-layer artificial neural networks in which convolution method is used instead of matrix multiplication in at least one of its layers. Although satisfactory r...

Download PDF file
  • EP ID EP674501
  • DOI 10.29109/gujsc.539645
  • Views 89
  • Downloads 0

How To Cite

Hüseyin Güneş, Sabri BİCAKCI, Emre ORTA, Davut AKDAŞ (2019). Development of Simulation for Artificial Intelligence Techniques in Smart Homes. Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji, 7(3), 554-563. https://europub.co.uk/articles/-A-674501