Deep neural networks (DNNs) have become a relevant subject in the classification of radio frequency signals and remote sensing data. A primary challenge is a tradeoff between obtaining data that are suitable for DNN training and the effort that making experimental measurements requires. Hence, the quality and quantity of data used for the training and testing of models are crucial for effective classifier development. The training dataset should cover a wide range of cases that synthesize the actual scenarios being classified. This work proposes a novel data augmentation method based on a deterministic model to generate a simulated dataset of radar micro-Doppler signatures suitable for unmanned aerial vehicle (UAV) target classification, without requiring measurement data. It is shown that the DNN trained using the properly generated model-based data offers improved classification accuracy performance. Results are presented for a two-class classification of the number of UAV motors using a 77-GHz frequency-modulated continuous-wave (FMCW) automotive radar system. The effectiveness of the proposed methodology is proven: a classification accuracy of 78.68% is achieved using a convolutional neural network (CNN) trained using the synthetic dataset, while an accuracy of 66.18% is achieved by using a typical signal processing data augmentation method on a limited measured dataset.

Assuming a reliable and responsive spatial contextualization service is a must-have in IEEE 802.11 and 802.15.4 wireless networks, a suitable approach consists of the implementation of localization capabilities, as an additional application layer to the communication protocol stack. Considering the applicative scenario where satellite-based positioning applications are denied, such as indoor environments, and excluding data packet arrivals time measurements due to lack of time resolution, received signal strength indicator (RSSI) measurements, obtained according to IEEE 802.11 and 802.15.4 data access technologies, are the unique data sources suitable for indoor geo-referencing using COTS devices. In the existing literature, many RSSI based localization systems are introduced and experimentally validated, nevertheless they require periodic calibrations and significant information fusion from different sensors that dramatically decrease overall systems reliability and their effective availability. This motivates the work presented in this paper, which introduces an approach for an RSSI-based calibration-free and real-time indoor localization. While switched-beam array-based hardware (compliant with IEEE 802.15.4 router functionality) has already been presented by the author, the focus of this paper is the creation of an algorithmic layer for use with the pre-existing hardware capable to enable full localization and data contextualization over a standard 802.15.4 wireless sensor network using only RSSI information without the need of lengthy offline calibration phase. System validation reports the localization results in a typical indoor site, where the system has shown high accuracy, leading to a sub-metrical overall mean error and an almost 100% site coverage within 1 m localization error.

With the increase in small unmanned aerial vehicle (UAV) applications in several technology areas, detection and small UAVs classification have become of interest. To cope with small radar cross-sections (RCSs), slow-flying speeds, and low flying altitudes, the micro-Doppler signature provides some of the most distinctive information to identify and classify targets in many radar systems. In this paper, we introduce an effective model for the micro-Doppler effect that is suitable for frequency-modulated continuous-wave (FMCW) radar applications, and exploit it to investigate UAV signatures. The latter depends on the number of UAV motors, which are considered vibrational sources, and their rotation speed. To demonstrate the reliability of the proposed model, it is used to build simulated FMCW radar images, which are compared with experimental data acquired by a 77 GHz FMCW multiple-input multiple-output (MIMO) cost-effective automotive radar platform. The experimental results confirm the model’s ability to estimate the class of the UAV, namely its number of motors, in different operative scenarios. In addition, the experimental results show that the motors rotation speed does not imprint a significant signature on the classification of the UAV; thus, the estimation of the number of motors represents the only viable parameter for small UAV classification using the micro-Doppler effect.

In this paper, we present a distributed positioning system for indoor environment based on a mesh of compact independent anchor nodes. Each node is built of low-cost off-the-shelf components and operates as specialized access points capable of standard connectivity at 2.45 GHz. The key technology for the localization strategy is the switched beam antenna (SBA), which enables a space division multiple access (SDMA) paradigm. The coordinated operation of SBA-equipped anchor nodes constitutes a legacy unmodified IEEE 802.11 network which can exploit the multiplexing mechanism. The latter is the driving force of the estimation strategy, with the positional information obtained as the result of a maximum likelihood algorithm driven by the comparison of a real-time received signal strength indicator (RSSI) with the predicted signal level distribution, which can be estimated and stored without the need of lengthy offline measurement. The signal level prediction is based on a simple propagation model which is effective because benefits of both the elementary antenna radiation beams directivity and the circular polarization operation, two strong aids for the mitigation of the multipath impairment. In turn, these feature make the estimation procedure tolerant to noisy power measurements, hence particularly suitable for cost-effective solutions based on RSSI. Experimental validations demonstrate the performance of a network composed of four anchors arranged in a 2.6 × 3.8 m ² mesh in a 6 × 7 m ² office room, and dealing with a single target node. The mean error inside the mesh area is 63 cm while the mean error in the entire room is 1.1 m. Focusing on the cumulative distribution of the error, the 90th percentile value is 1 m considering only the mesh and 1.9 m for the entire room.

This paper describes a distributed point-source monitoring platform for gas level and leakage detection in hazardous environments. The platform, based on a wireless sensor network (WSN) architecture, is organised into sub-networks to be positioned in the plant’s critical areas; each sub-net includes a gateway unit wirelessly connected to the WSN nodes, hence providing an easily deployable, stand-alone infrastructure featuring a high degree of scalability and reconfigurability. Furthermore, the system provides automated calibration routines which can be accomplished by non-specialized maintenance operators without system reliability reduction issues. Internet connectivity is provided via TCP/IP over GPRS (Internet standard protocols over mobile networks) gateways at a one-minute sampling rate. Environmental and process data are forwarded to a remote server and made available to authenticated users through a user interface that provides data rendering in various formats and multi-sensor data fusion. The platform is able to provide real-time plant management with an effective; accurate tool for immediate warning in case of critical events.

This paper presents a technique capable to ameliorating the impairment caused by radio channel multipath, in the estimation of the wireless communications direction of arrival (DoA). This feature is enabled by a space division multiple access approach supported by a DoA technique based on the combination of the estimates achieved at both 2.45 and 5.2 GHz. The DoA estimation relies on a comparison between the real-time received signal strength indicator and the predicted signal level distribution, which can be estimated and stored without the need of lengthy offline measurement. The experimental setup adopted for the technique validation involves an active interferer, by which arbitrary multipath levels can be implemented. An equivalent reflection coefficient signal-to-interference ratio is defined as the ratio of the unperturbed signal and the induced coherent isofrequency interferer signal, compatible with the two-ray model of the multipath impairment. The proposed technique exploits a dual-band frequency planning, and because of the combined use of the data at the two frequencies, a mean error of 2.6° is observed within a domain ranging from 0.5 to 4 m, for the entire 360° angle in the reference anechoic scenario. The 90th percentile of the cumulative error distribution is 5.4°. In the presence of a strong coherent interferer, compatible with a total reflection from the walls, the mean error is 4.9°, while the 90th percentile of the cumulative error distribution is 10.5°. In the presence of the strongest coherent interferer signal available, which is more severe than the worst case of total reflection, the mean error is 7.1°, while the 90th percentile of the cumulative error distribution is 15.1°.