Answers are grounded in this paper and cite their sources.
Adopting a malicious IoT device connected to a company’s network is a hazard to the enterprise. Firms must be able to distinguish between legitimate devices connected to their network and those that are threats. It is essential to comprehend the device’s properties and recognize it once it has been added to a network. Various machine learning algorithms for device identification have been introduced for this task, including Support vector machines, Adaboost classifiers, Logistic regression, KNeighbors classifiers, decision trees classifiers, XGBoost, Gradient boosting classifiers, and Random forests. However, there is a research gap in identifying the best-performing classification pipeline that adapts to the features and types of the associated data in the device identification problem while providing high recognition accuracy. For this purpose, we propose a Multiple Transformers Single Estimator (MTSE) Learning pipeline that captures the best-performing feature sets and the best-performing machine learning algorithm for the recognition problem. The MTSE uses transformers and estimators; the transformers filter or modify the data. The estimator learns and builds a recognition model from the data. Experimental results through different transformers and estimators achieved an accuracy of 89.50% compared to the existing classification methods.
No takes yet. Share an insight, caveat, or question.
Xiao et al. (2023) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: