Breaking the Performance Gap of Fully and Semi-Supervised Learning in Electromagnetic Signature Recognition
Abstract
Intelligent electromagnetic signature recognition is one of the key technologies in Internet-of-Things (IoT) device connection, which can improve system security and speed up the authentication process. In practical scenarios, as the number of IoT devices increases, electromagnetic features such as fingerprint and modulation signals also increase substantially. However, since intelligent recognition technology, such as Automatic Modulation Classification (AMC), requires a large amount of labeled data to train the neural network classifier, it is challenging to collect so much labeled data. To address the performance degradation challenges with small training data, we propose an efficient semi-supervised electromagnetic recognition framework to break the performance gap with the fully supervised learning scheme. This framework can fully use the unlabeled electromagnetic data collected during the authentication process for self-training to improve the classifier’s performance. According to the idea of consistency regularization, we design a signal augmentation method and propose an ensemble pseudo-label design algorithm to improve confidence. Moreover, we perform a convex combination of electromagnetic features to smooth the model decision boundary while generalizing to unknown data distribution regions. Experimental results on the modulated data demonstrate the performance superiority of the proposed algorithm, i.e., use less than 5% of data with no more than 10% performance drop. IEEE
Collections
Related items
Showing items related by title, author, creator and subject.
-
Click prediction boosting via Bayesian hyperparameter optimization-based ensemble learning pipelines
Demirel, Ç.; Tokuç, A.A.; Tekin, A.T. (Elsevier B.V., 2023)Online travel agencies (OTA's) advertise their website offers on meta-search bidding engines. The problem of predicting the number of clicks a hotel would receive for a given bid amount is an important step in the management ... -
Benchmark Static API Call Datasets for Malware Family Classification
Gencaydin, B.; Kahya, C.N.; Demirkiran, F.; Duzgun, B.; Cayir, A.; Dag, H. (Institute of Electrical and Electronics Engineers Inc., 2022)Nowadays, malware and malware incidents are increasing daily, even with various antivirus systems and malware detection or classification methodologies. Machine learning techniques have been the main focus of the security ... -
MuscleNET: Smart Predictive Analysis for Muscular Activity Using Wearable Sensors
Gemici, M.; Korkmaz, K.; Ayhan, N.T.; Soylu, S.; Guc, F.; Ogrenci, A.S. (Institute of Electrical and Electronics Engineers Inc., 2022)Doing weightlifting training at home has become more popular during the pandemic. Unfortunately, exercising without professional help can lead to dangerous injuries such as muscle tearing. It is possible to create a smart ...