Abstract
In recent years, the scale and application scenarios of the Internet of Things (IoT) have been expanding. Since traditional algorithms are unable to meet wireless networks computing capability requirement in the IoT, more and more research institutions and scholars have turned their eyes to artificial intelligence (AI) methods. Because the IoT device uses wireless networks to communicate in most scenarios, this paper systematically studies the method of feature dimension reduction of wireless communication signals. In this paper, we will take the power amplifier radio frequency (RF) fingerprinting as an example. Focusing on reducing the high dimensionality of RF fingerprint features and the uncorrelated or redundant features in the features space, the RF fingerprint feature dimension reduction method is mainly studied. Based on the principal component analysis (PCA), linear discriminant analysis (LDA), and auto encoder (AE) research, this paper studies the PCA-LDA method and uses the distance ratio criterion to evaluate the separability of features. The simulation results show that the classification accuracy of PCA-LDA is superior to PCA, LDA, and AE in most SNR, and the characteristics of PCA-LDA is more separable.
Highlights
In the last two decades, the rapid development of wireless communication and hardware devices has promoted the maturity of Internet of Things (IoT) technology
Dimensionality reduction is to project high dimensional space into low dimensional space in a certain way, so that the feature dimension after dimensionality reduction is much smaller than the dimension before dimension reduction, which realizes the compression of features and reduces the probability of dimensionality disaster
The rest of the paper is arranged as follows: The second part introduces the basic feature dimension reduction method and the evaluation method, the third part talks about the principle of the principal component analysis (PCA)-linear discriminant analysis (LDA) method proposed in this paper, and simulation experiment and analysis are in the fourth part, In part we draw conclusion
Summary
In the last two decades, the rapid development of wireless communication and hardware devices has promoted the maturity of Internet of Things (IoT) technology. The linear dimensionality reduction method assumes that the projection relationship from the original space to the dimensionality reduction space is linear, mainly including principal component analysis (PCA) [9] and linear discriminant analysis (LDA) [10]. These two methods are proposed earlier and the theoretical system is perfect, and the practical application effect is good. Through there exists the research on the feature dimension reduction of high-dimensional data in machine learning and intelligent data processing, this paper completes some relevant theoretical research and simulation analysis in. The rest of the paper is arranged as follows: The second part introduces the basic feature dimension reduction method and the evaluation method, the third part talks about the principle of the PCA-LDA method proposed in this paper, and simulation experiment and analysis are in the fourth part, In part we draw conclusion
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
