V2X Wireless Technology Identification Using Time–Frequency Analysis and Random Forest Classifier

Abstract

Signal identification is of great interest for various applications such as spectrum sharing and interference management. A typical signal identification system can be divided into two steps. A feature vector is first extracted from the received signal, then a decision is made by a classification algorithm according to its observed values. Some existing techniques show good performance but they are either sensitive to noise level or have high computational complexity. In this paper, a machine learning algorithm is proposed for the identification of vehicular communication signals. The feature vector is made up of Instantaneous Frequency (IF) resulting from time–frequency (TF) analysis. Its dimension is then reduced using the Singular Value Decomposition (SVD) technique, before being fed into a Random Forest classifier. Simulation results show the relevance and the low complexity of IF features compared to existing cyclostationarity-based ones. Furthermore, we found that the same accuracy can be maintained regardless of the noise level. The proposed framework thus provides a more accurate, robust and less complex V2X signal identification system.

Wireless Technology Identification Employing Dynamic Mode Decomposition Modeling

“…Recent FB schemes rely on capturing common features shared among similar signal types. Comparing LB methods with FB methods shows that although the latter has suboptimal performance, FB has a simpler implementation, lower computational complexity, and relative robustness for modeling mismatches among various operation cases [1], [8]. FB algorithms are based on wavelets, cumulative distribution functions (CDF), second-order cyclostationarity, machine learning (ML), and deep learning (DL).…”

“…Although DL approaches achieve high accuracy models with the advantage of simple feature pre-processing or even raw data input, they also require large-scale training datasets, resulting in high implementation costs and large computational time. As a result, ML techniques, such as SVM in [1] and [29] and Random Forest (RF) in [8] and [30], have been widely used in related research for identifying various standards' wireless signals. Researchers have demonstrated promising results with reduced-size datasets [8].…”

“…As a result, ML techniques, such as SVM in [1] and [29] and Random Forest (RF) in [8] and [30], have been widely used in related research for identifying various standards' wireless signals. Researchers have demonstrated promising results with reduced-size datasets [8]. Individual and coexisting IEEE 802.11b/g/n, 802.15.4, 802.15.1, and Bluetooth Low Energy (BLE) technologies were categorized by authors in [31] for the 2.4 GHz ISM band.…”

“…These approaches have the advantages of being a) simple to implement and b) proven to provide near-optimal performance. However, they are sensitive to noise level and/or might require prior information about targeted signals [8]. Cyclostationarity-based and wavelet-based schemes require long observation intervals.…”

“…This result confirms the significance of DMD, which required only a few numbers of extracted modes (i.e., dominant modes) for identifying a signal. 4) Number of samples n: This parameter represents the length of the timeseries signal, as indicated in (8). The value can be calculated using ( 4) and (11), given the value of k, as calculated in (18).…”