Automatic modulation classification (AMC) has been studied for more than a quarter of a century; however, it has been difficult to design a classifier that operates successfully under changing multipath fading conditions and other impairments. Recently, deep learning (DL)-based methods are adopted by AMC systems and major improvements are reported. In this paper, a novel convolutional neural network (CNN) classifier model is proposed to classify modulation classes in terms of their families, i.e., types. The proposed classifier is robust against realistic wireless channel impairments and in relation to that, when the data sets that are utilized for testing and evaluating the proposed methods are considered, it is seen that RadioML2016.10a is the main dataset utilized for testing and evaluation of the proposed methods. However, the channel effects incorporated in this dataset and some others may lack the appropriate modeling of the real-world conditions since it only considers two distributions for channel models for a single tap configuration. Therefore, in this paper, a more comprehensive dataset, named as HisarMod2019.1, is also introduced, considering real-life applicability. HisarMod2019.1 includes 26 modulation classes passing through the channels with 5 different fading types and several number of taps for classification. It is shown that the proposed model performs better than the existing models in terms of both accuracy and training time under more realistic conditions. Even more, surpassed their performance when the RadioML2016.10a dataset is utilized.

Digital revolution and recent advances in telecommunications technology enable to design communication systems which operate within the regions close to the theoretical capacity limits. Ever-increasing demand for wireless communications and emerging numerous high-capacity services and applications mandate providers to employ more bandwidth-oriented solutions to meet the requirements. Trend and predictions point out that marketplace targets data rates around 10Gbps or even more within the upcoming decade. It is clear that such rates could only be achieved by employing more bandwidth with the state-of-the-art technology. Considering the fact that bands in the range of 275GHz-3000GHz, which are known as Terahertz (THz) bands, are not allocated yet for specific active services around the globe, there is an enormous potential to achieve the desired data rates. Although THz bands look promising to achieve data rates on the order of several tens of Gbps, realization of fully operational THz communications systems obliges to carry out a multidisciplinary effort including statistical propagation and channel characterizations, adaptive transceiver designs, reconfigurable platforms, advanced signal processing algorithms and techniques along with upper layer protocols equipped with various security and privacy levels. Therefore, in this study, several important statistical parameters for line-of-sight (LOS) channels are measured. High resolution frequency domain measurements are carried out at single-sweep within a span of 60GHz. Impact of antenna misalignment under LOS conditions is also investigated. By validating exponential decay of the received power in both time and frequency domain, path loss exponent is examined for different frequencies along with the frequency-dependent path loss phenomenon. Furthermore, impact of humidity is also tested under LOS scenario. Measurement results are presented along with relevant discussions and future directions are provided as well.

User-centric and low-latency communications can be enabled not only by small cells but also through ubiquitous connectivity. Recently, the vertical heterogeneous network (V-HetNet) architecture has been proposed to backhaul/fronthaul a large number of small cells. Like an orchestra, the V-HetNet is a polyphony of different communication ensembles, including geostationary Earth orbit and low Earth orbit satellites (e.g., CubeSats), and networked flying platforms along with terrestrial communication links. In this study, we propose terahertz (THz) communications to enable the elements of V-HetNets to function in harmony. As THz links offer large bandwidth, leading to ultra-high data rates, it is suitable for backhauling and fronthauling small cells. Furthermore, THz communications can support numerous applications from inter-satellite links to in-vivo nanonetworks. However, to savor this harmony, we need accurate channel models. In this article, the insights obtained through our measurement campaigns are highlighted to reveal the true potential of THz communications in V-HetNets.

Spectrum sensing is one of the means of utilizing the scarce source of wireless spectrum efficiently. In this paper, a convolutional neural network (CNN) model employing spectral correlation function (SCF) which is an effective characterization of cyclostationarity property, is proposed for wireless spectrum sensing and signal identification. The proposed method classifies wireless signals without a priori information and it is implemented in two different settings entitled CASE1 and CASE2 . In CASE1 , signals are jointly sensed and classified. In CASE2 , sensing and classification are conducted in a sequential manner. In contrary to the classical spectrum sensing techniques, the proposed CNN method does not require a statistical decision process and does not need to know the distinct features of signals beforehand. Implementation of the method on the measured over-the-air real-world signals in cellular bands indicates important performance gains when compared to the signal classifying deep learning networks available in the literature and against classical sensing methods. Even though the implementation herein is over cellular signals, the proposed approach can be extended to the detection and classification of any signal that exhibits cyclostationary features. Finally, the measurement-based dataset which is utilized to validate the method is shared for the purposes of reproduction of the results and further research and development.

Opportunistic spectrum access feature of cognitive radio systems is a method to improve frequency underutilization of wireless spectrum. One of the techniques for detecting the unused bands is the energy detection for which selection of the threshold defines detection performance. In this paper, the adaptive threshold method is proposed as an alternative approach to estimate the threshold as a function of first and second order statistics of recorded signals. The proposed method does not require estimation of noise variance or signal to noise ratio and aims to minimize the effects of impairments introduced by wireless channel and non-stationary noise. The simulation results indicate that adaptive threshold has low false alarm and missed detection rates that can satisfy the detection requirements of multi-channel cognitive radios for either narrow or wideband spectrum sensing, when the standard deviation coefficient is selected properly.