Cargando…

IoT based smart home automation using blockchain and deep learning models

For the past few years, the concept of the smart house has gained popularity. The major challenges concerning a smart home include data security, privacy issues, authentication, secure identification, and automated decision-making of Internet of Things (IoT) devices. Currently, existing home automat...

Descripción completa

Detalles Bibliográficos
Autores principales: Umer, Muhammad, Sadiq, Saima, Alhebshi, Reemah M., Sabir, Maha Farouk, Alsubai, Shtwai, Al Hejaili, Abdullah, Khayyat, Mashael M., Eshmawi, Ala’ Abdulmajid, Mohamed, Abdullah
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280418/
https://www.ncbi.nlm.nih.gov/pubmed/37346725
http://dx.doi.org/10.7717/peerj-cs.1332
_version_ 1785060790049439744
author Umer, Muhammad
Sadiq, Saima
Alhebshi, Reemah M.
Sabir, Maha Farouk
Alsubai, Shtwai
Al Hejaili, Abdullah
Khayyat, Mashael M.
Eshmawi, Ala’ Abdulmajid
Mohamed, Abdullah
author_facet Umer, Muhammad
Sadiq, Saima
Alhebshi, Reemah M.
Sabir, Maha Farouk
Alsubai, Shtwai
Al Hejaili, Abdullah
Khayyat, Mashael M.
Eshmawi, Ala’ Abdulmajid
Mohamed, Abdullah
author_sort Umer, Muhammad
collection PubMed
description For the past few years, the concept of the smart house has gained popularity. The major challenges concerning a smart home include data security, privacy issues, authentication, secure identification, and automated decision-making of Internet of Things (IoT) devices. Currently, existing home automation systems address either of these challenges, however, home automation that also involves automated decision-making systems and systematic features apart from being reliable and safe is an absolute necessity. The current study proposes a deep learning-driven smart home system that integrates a Convolutional neural network (CNN) for automated decision-making such as classifying the device as “ON” and “OFF” based on its utilization at home. Additionally, to provide a decentralized, secure, and reliable mechanism to assure the authentication and identification of the IoT devices we integrated the emerging blockchain technology into this study. The proposed system is fundamentally comprised of a variety of sensors, a 5 V relay circuit, and Raspberry Pi which operates as a server and maintains the database of each device being used. Moreover, an android application is developed which communicates with the Raspberry Pi interface using the Apache server and HTTP web interface. The practicality of the proposed system for home automation is tested and evaluated in the lab and in real-time to ensure its efficacy. The current study also assures that the technology and hardware utilized in the proposed smart house system are inexpensive, widely available, and scalable. Furthermore, the need for a more comprehensive security and privacy model to be incorporated into the design phase of smart homes is highlighted by a discussion of the risks analysis’ implications including cyber threats, hardware security, and cyber attacks. The experimental results emphasize the significance of the proposed system and validate its usability in the real world.
format Online
Article
Text
id pubmed-10280418
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-102804182023-06-21 IoT based smart home automation using blockchain and deep learning models Umer, Muhammad Sadiq, Saima Alhebshi, Reemah M. Sabir, Maha Farouk Alsubai, Shtwai Al Hejaili, Abdullah Khayyat, Mashael M. Eshmawi, Ala’ Abdulmajid Mohamed, Abdullah PeerJ Comput Sci Artificial Intelligence For the past few years, the concept of the smart house has gained popularity. The major challenges concerning a smart home include data security, privacy issues, authentication, secure identification, and automated decision-making of Internet of Things (IoT) devices. Currently, existing home automation systems address either of these challenges, however, home automation that also involves automated decision-making systems and systematic features apart from being reliable and safe is an absolute necessity. The current study proposes a deep learning-driven smart home system that integrates a Convolutional neural network (CNN) for automated decision-making such as classifying the device as “ON” and “OFF” based on its utilization at home. Additionally, to provide a decentralized, secure, and reliable mechanism to assure the authentication and identification of the IoT devices we integrated the emerging blockchain technology into this study. The proposed system is fundamentally comprised of a variety of sensors, a 5 V relay circuit, and Raspberry Pi which operates as a server and maintains the database of each device being used. Moreover, an android application is developed which communicates with the Raspberry Pi interface using the Apache server and HTTP web interface. The practicality of the proposed system for home automation is tested and evaluated in the lab and in real-time to ensure its efficacy. The current study also assures that the technology and hardware utilized in the proposed smart house system are inexpensive, widely available, and scalable. Furthermore, the need for a more comprehensive security and privacy model to be incorporated into the design phase of smart homes is highlighted by a discussion of the risks analysis’ implications including cyber threats, hardware security, and cyber attacks. The experimental results emphasize the significance of the proposed system and validate its usability in the real world. PeerJ Inc. 2023-05-22 /pmc/articles/PMC10280418/ /pubmed/37346725 http://dx.doi.org/10.7717/peerj-cs.1332 Text en © 2023 Umer et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Computer Science) and either DOI or URL of the article must be cited.
spellingShingle Artificial Intelligence
Umer, Muhammad
Sadiq, Saima
Alhebshi, Reemah M.
Sabir, Maha Farouk
Alsubai, Shtwai
Al Hejaili, Abdullah
Khayyat, Mashael M.
Eshmawi, Ala’ Abdulmajid
Mohamed, Abdullah
IoT based smart home automation using blockchain and deep learning models
title IoT based smart home automation using blockchain and deep learning models
title_full IoT based smart home automation using blockchain and deep learning models
title_fullStr IoT based smart home automation using blockchain and deep learning models
title_full_unstemmed IoT based smart home automation using blockchain and deep learning models
title_short IoT based smart home automation using blockchain and deep learning models
title_sort iot based smart home automation using blockchain and deep learning models
topic Artificial Intelligence
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10280418/
https://www.ncbi.nlm.nih.gov/pubmed/37346725
http://dx.doi.org/10.7717/peerj-cs.1332
work_keys_str_mv AT umermuhammad iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT sadiqsaima iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT alhebshireemahm iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT sabirmahafarouk iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT alsubaishtwai iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT alhejailiabdullah iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT khayyatmashaelm iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT eshmawialaabdulmajid iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels
AT mohamedabdullah iotbasedsmarthomeautomationusingblockchainanddeeplearningmodels