One of the key parameters in radio link planning is the propagation path loss. Most of the existing methods for its prediction are not characterized by a good balance between accuracy, generality, and low computational complexity. To address this problem, a machine learning approach for path loss prediction is presented in this study. The novelty is the proposal of a compound model, which consists of two regression models and one classifier. The first regression model is adequate when a line-of-sight scenario is fulfilled in radio wave propagation, whereas the second one is appropriate for non-line-of-sight conditions. The classification model is intended to provide a probabilistic output, through which the outputs of the regression models are combined. The number of used input parameters is only five. They are related to the distance, the antenna heights, and the statistics of the terrain profile and line-of-sight obstacles. The proposed approach allows creation of a generalized model that is valid for various types of areas and terrains, different antenna heights, and line-of-sight and non line-of-sight propagation conditions. An experimental dataset is provided by measurements for a variety of relief types (flat, hilly, mountain, and foothill) and for rural, urban, and suburban areas. The experimental results show an excellent performances in terms of a root mean square error of a prediction as low as $7.3$ dB and a coefficient of determination as high as 0.702. Although the study covers only one operating frequency of 433 $\mathrm{M}$$\mathrm{Hz}$, the proposed model can be trained and applied for any frequency in the decimeter wavelength range. The main reason for the choice of such an operating frequency is because it falls within the range in which many wireless systems of different types are operating. These include Internet of Things (IoT), machine-to-machine (M2M) mesh radio networks, power efficient communication over long distances such as Low-Power Wide-Area Network (LPWAN)—LoRa, etc.

In this paper we propose an approach for interference recognition and frequency channel identification based on the analysis of the large amount of data obtained from long term spectrum monitoring. We illustrate the approach with an example of the detection of a specific type of interference in the uplink of a 3G network caused by the effect “ducting”. Further, using Hjorth parameters for the creation of a set of robust feature descriptor, we show how the dimensionality of the space of the primary parameter data could be reduced and apply it to cluster analysis for interference and channel identification.

The development of unmanned ground vehicles and unmanned aerial vehicles requires high-precision navigation due to the autonomous motion and higher traffic intensity. The existing L1 band GNSS receivers are a good and cheap decision for smartphones, vehicle navigation, fleet management systems, etc., but their accuracy is not good enough for many civilian purposes. At the same time, real-time kinematic (RTK) navigation allows for position precision in a sub-centimeter range, but the system cost significantly narrows this navigation to a very limited area of applications, such as geodesy. A practical solution includes the integration of dual-band GNSS receivers and inertial sensors to solve high-precision navigation tasks, but GNSS position accuracy may significantly affect IMU performance due to having a great impact on Kalman filter performance in unmanned vehicles. The estimation of dilution-of-precision (DOP) parameters is essential for the filter performance as the optimality of the estimation in the filter is closely connected to the quality of a priori information about the noise covariance matrix and measurement noise covariance. In this regard, the current paper analyzes the DOP parameters of the latest generation dual-band GNSS receivers and compares the results with the L1 ones. The study was accomplished using two types of antennas—L1/L5 band patch and wideband helix antennas, which were designed and assembled by the authors. In addition, the study is extended with a comparison of GNSS receivers from different generations but sold on the market by one of the world’s leading GNSS manufacturers. The analyses of dilution-of-precision (DOP) parameters show that the introduction of dual-band receivers may significantly increase the navigation precision in a sub-meter range, in addition to multi-constellation signal reception. The fast advances in the performance of the integrated CPU in GNSS receivers allow the number of correlations and tracking satellites to be increased from 8–10 to 24–30, which also significantly improves the position accuracy even of L1-band receivers.

In this paper modified Sierpinski gasket fractal antenna is proposed. It is based on combination of first, second and third Sierpinski fractal iterations. The modified antenna features small size and relatively high gain. The performance (return losses and radiation pattern) of this antenna is investigated and compared to a simple monopole and deterministic Sierpinski gasket. The antenna is fine-tuned to accommodate the full frequency range Wi-Fi 2.4 GHz and 5 GHz bands.

This paper examines the possibility of developing a low profile antenna with fractal design which can achieve high gain for RFID applications in the frequency range from 865 to 868MHz. The advantages of the suggested structure are high gain, small physical dimensions and low profile compared to traditional antennas. The proposed approach is applicable to EMI/EMC sensors and probes as well.

With the exponential growth of technology in satellite communications, the need of high bandwidth is increasing. For the support of high end services and applications higher frequency bands are required. The major limitations for higher frequencies like mm wave are attenuation due to gas, clouds, fog and rain. For satellite communications cloud attenuation plays significant role because of complex structure of clouds. In this paper different aspect of clouds with respect to cloud attenuation is discussed and a theoretical model for cloud attenuation is presented.