View in EDS

AI and IoT based Home Automation System

Saved in:
Bibliographic Details
Title: AI and IoT based Home Automation System
Authors: Ashish S. Gawali, Rupali S. Kalokar, Monali M. Jawanjal, Tanushri S. Dharmik, Gaurav H. Bakade, Chinmayee S. Deotare, Sushmit S. Gaikwad
Publisher Information: IJAITE
Publication Year: 2025
Collection: Zenodo
Subject Terms: Internet Of Things Microcontroller, HTTP protocols, Relay, Jumper Wires
Description: This paper aims to develop a smart home automation system that enables users to control electronic devices using hand gestures. By leveraging computer vision and deep learning techniques, a webcam captures hand gestures, which are processed using a Convolutional Neural Network (CNN) model for real-time classification. The recognized gestures are then transmitted to an ESP8266 microcontroller via Wi-Fi, triggering the corresponding on/off commands for connected IoT devices. This system enhances touchless interaction, offering an intuitive and accessible solution for smart home automation, particularly benefiting individuals with mobility impairments. The project integrates Open CV for image pre-processing, Tensor Flow/Keras for model training, and HTTP protocols for seamless communication between the Python application and the ESP8266.
Document Type: article in journal/newspaper
Language: English
ISSN: 2455-6491
Relation: https://zenodo.org/records/15425539; oai:zenodo.org:15425539; https://doi.org/10.5281/zenodo.15425539
DOI: 10.5281/zenodo.15425539
Availability: https://doi.org/10.5281/zenodo.15425539
https://zenodo.org/records/15425539
Rights: Creative Commons Attribution 4.0 International ; cc-by-4.0 ; https://creativecommons.org/licenses/by/4.0/legalcode
Accession Number: edsbas.8551683B
Database: BASE
Description
Abstract:This paper aims to develop a smart home automation system that enables users to control electronic devices using hand gestures. By leveraging computer vision and deep learning techniques, a webcam captures hand gestures, which are processed using a Convolutional Neural Network (CNN) model for real-time classification. The recognized gestures are then transmitted to an ESP8266 microcontroller via Wi-Fi, triggering the corresponding on/off commands for connected IoT devices. This system enhances touchless interaction, offering an intuitive and accessible solution for smart home automation, particularly benefiting individuals with mobility impairments. The project integrates Open CV for image pre-processing, Tensor Flow/Keras for model training, and HTTP protocols for seamless communication between the Python application and the ESP8266.
ISSN:24556491
DOI:10.5281/zenodo.15425539