Machine Learning Based Home Automation
Azam, Muhammad Zeeshan (2024)
2024
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2024051311033
https://urn.fi/URN:NBN:fi:amk-2024051311033
Tiivistelmä
The integration of machine learning algorithms into home automation systems represents a significant advancement in modern living. This research explores how machine learning can enhance user experience and optimize energy usage in homes. Multiple sensors are used to collect the data and utilizing insights, from this data the systems can adjust to user behavior to cater the preferences and anticipate needs by offering proactive automation solutions. Machine learning algorithm is implemented to forecast the most suitable output according to the real time sensor data values.
The approach involves validating circuit designs using Proteus simulation software before implementing hardware for real time data collection. Data monitoring is facilitated through a WIFI module with collected data organized and processed using Python libraries for data handling. Machine learning algorithms such as Support Vector Machines (SVM) are employed to optimize energy consumption by determining the times to activate or devices. Performance evaluation metrics, like accuracy, precision, recall and F1 score are used to assess the effectiveness of the models. In endeavors this study suggests integrating sensors, like PIR sensors and enhancing machine learning algorithms with deep learning techniques. The main goal is to create a self learning system that can adjust and grow by observing user actions and changes, in the environment. The focus is on enhancements and upgrades to maintain top notch functionality and improve user satisfaction. By achieving these goals this dissertation plays a role, in pushing forward home technologies shaping the creation of systems that improve quality of life and support sustainability and efficient resource usage.
The approach involves validating circuit designs using Proteus simulation software before implementing hardware for real time data collection. Data monitoring is facilitated through a WIFI module with collected data organized and processed using Python libraries for data handling. Machine learning algorithms such as Support Vector Machines (SVM) are employed to optimize energy consumption by determining the times to activate or devices. Performance evaluation metrics, like accuracy, precision, recall and F1 score are used to assess the effectiveness of the models. In endeavors this study suggests integrating sensors, like PIR sensors and enhancing machine learning algorithms with deep learning techniques. The main goal is to create a self learning system that can adjust and grow by observing user actions and changes, in the environment. The focus is on enhancements and upgrades to maintain top notch functionality and improve user satisfaction. By achieving these goals this dissertation plays a role, in pushing forward home technologies shaping the creation of systems that improve quality of life and support sustainability and efficient resource usage.