Year: 2024
Type: article
Abstract: This study aims to address the challenge of IoT device classification by proposing a method based on the random forest classifier. By analyzing the network traffic characteristics of four common household IoT devices, we constructed a feature set and utilized the RF classifier for device identification. The experimental results demonstrate that the random forest classifier performs excellently in terms of precision, recall, and F1 score. By analyzing the network traffic characteristics of four common household IoT devices, we constructed a feature set that includes 20 important device feature information which can effectively represent device identity characteristics, and used the RF classifier for device identification. We conducted numerous experiments on a publicly available dataset and achieved an accuracy rate of 97.22%. The findings offer valuable references for the development of the IoT device identification field and point out potential directions for future research to further enhance the performance and adaptability of the classifier.
DOI: 10.54097/5xa99r80
Author: Yuanchen Jiang
Institution: Qingdao University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4405808952