Signal Preprocessing for Enhanced IoT Device Identification Using Support Vector Machine

Device identification based on radio frequency fingerprinting is widely used to improve the security of Internet of Things systems. However, noise and inconsistencies in raw radio frequency signals can reduce the accuracy of identification, classification, and authentication algorithms. This paper investigates how preprocessing methods affect the performance of a support vector machine classifier based on radio frequency fingerprinting. Four preprocessing methods are evaluated, each of which is applied to the raw radio frequency signals in an attempt to improve the consistency between signals emitted by the same Bluetooth device. Experiments conducted on a dataset of raw Bluetooth signals from sixteen smartphone radios, provided by Uzundurukan, show that selecting appropriate preprocessing methods can significantly improve the classification accuracy of a support vector machine classifier.