A MACHINE LEARNING-BASED SPAM DETECTION METHOD FOR INTERNET OF THINGS DEVICES
DOI:
https://doi.org/10.62643/Keywords:
REFIT, IOT, ML, power, spam detectionAbstract
Data is sent and received by the millions of devices that comprise the Internet of Things (IoT), which are linked by wired or wireless networks. Data quality is defined by its rapidity with regard to time and place, and by no small increase in volume, as a result of the vast quantities of data generated by Internet of Things (IoT) devices via a variety of methods. Protecting IoT devices, guaranteeing biotech-based security, and generating strange discoveries to improve functionality might all be greatly aided by ML algorithms in this context. At the same time, cybercriminals often use learning algorithms to find the weak spots in smart IoT equipment. Keeping these things in mind, we provide a solution for protecting IoT devices against spam in this short article. Using Spam Discovery in IoT using an AI framework is suggested as a means to accomplish this objective. In this case, five distinct ML versions are tested using various metrics, with a huge number of input feature sets. The updated input functions are used by all the models to determine a spam score. A high score across multiple categories indicates that the IoT device is reliable. Data acquired from REFIT Smart Homes is used to verify the proposed plan. The findings show that the proposed approach outperforms the alternatives in terms of efficiency.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.