Designing and deploying telecommunications and broadcasting networks in the challenging terrain of the Amazon region pose significant obstacles due to its unique morphological characteristics. Within low-power wide-area networks (LPWANs), this research study introduces a comprehensive approach to modeling large-scale propagation loss channels specific to the LoRaWAN protocol operating at 915 MHz. The objective of this study is to facilitate the planning of Internet of Things (IoT) networks in riverside communities while accounting for the mobility of end nodes. We conducted extensive measurement campaigns along the banks of Universidade Federal do Pará, capturing received signal strength indication (RSSI), signal-to-noise ratio (SNR), and geolocated point data across various spreading factors. We fitted the empirical close-in (CI) and floating intercept (FI) propagation models for uplink path loss prediction and compared them with the Okumura–Hata model. We also present a new model for path loss with dense vegetation. Furthermore, we calculated received packet rate statistics between communication links to assess channel quality for the LoRa physical layer (PHY). Remarkably, both CI and FI models exhibited similar behaviors, with the newly proposed model demonstrating enhanced accuracy in estimating radio loss within densely vegetated scenarios, boasting lower root mean square error (RMSE) values than the Okumura–Hata model, particularly for spreading factor 9 (SF9). The radius coverage threshold, accounting for node mobility, was 945 m. This comprehensive analysis contributes valuable insights for the effective deployment and optimization of LoRa-based IoT networks in the intricate environmental conditions of the Amazon region.

In this study, a methodology for automatic recognition of multiple simultaneous types of partial discharges (PDs) in hydro-generator stator windings was proposed. All the seven PD sources typical in rotating machines were considered, and up to three simultaneous sources could be identified. The functionality of identifying samples with no valid PDs was also incorporated using a new technique. The data set was composed of phase-resolved partial discharge (PRPD) patterns obtained from on-line measurements of hydro-generators. From an input PRPD, noise and interference were removed with an improved version of an image-based denoising algorithm previously proposed by the authors. Then, a novel image-based algorithm that separates partially superposed PD clouds was proposed, by decomposing the input pattern into two sub-PRPDs containing discharges of different natures. From the sub-PRPDs, one extracts features quantifying the PD distribution over amplitudes and the contour of PD clouds. Those features are fed as inputs to several artificial neural networks (ANNs), each of which solves a part of the classification problem and acts as a block of a larger system. Once trained, ANNs work collaboratively to identify an unknown sample. Good results were obtained, with overall accuracies ranging from 88% to 94.8% for all the considered PD sources.

The 5G deployment brings forth the usage of Unmanned Aerial Vehicles (UAV) to assist wireless networks by providing improved signal coverage, acting as relays or base-stations. Another technology that could help achieve 5G massive machine-type communications (mMtc) goals is the Long Range Wide-Area Network (LoRaWAN) communication protocol. This paper studied these complementary technologies, LoRa and UAV, through measurement campaigns in suburban, densely forested environments. Downlink and uplink communication at different heights and spreading factors (SF) demonstrate distinct behavior through our analysis. Moreover, a neural network was trained to predict the measured signal-to-noise ratio (SNR) behavior and results compared with SNR regression models. For the downlink scenario, the neural network results show a root mean square error (RMSE) variation between 1.2322–1.6623 dB, with an error standard deviation (SD) less than 1.6730 dB. For the uplink, the RMSE variation was between 0.8714–1.3891 dB, with an error SD less than 1.1706 dB.

In this paper, a novel image denoising algorithm and novel input features are proposed. The algorithm is applied to phase-resolved partial discharge (PRPD) diagrams with a single dominant partial discharge (PD) source, preparing them for automatic artificial-intelligence-based classification. It was designed to mitigate several sources of distortions often observed in PRPDs obtained from fully operational hydroelectric generators. The capabilities of the denoising algorithm are the automatic removal of sparse noise and the suppression of non-dominant discharges, including those due to crosstalk. The input features are functions of PD distributions along amplitude and phase, which are calculated in a novel way to mitigate random effects inherent to PD measurements. The impact of the proposed contributions was statistically evaluated and compared to classification performance obtained using formerly published approaches. Higher recognition rates and reduced variances were obtained using the proposed methods, statistically outperforming autonomous classification techniques seen in earlier works. The values of the algorithm’s internal parameters are also validated by comparing the recognition performance obtained with different parameter combinations. All typical PD sources described in hydro-generators PD standards are considered and can be automatically detected.

The Internet of Things (IoT) device scenario has several emerging technologies. Among them, Low-Power Wide-Area Networks (LPWANs) have proven to be efficient connections for smart devices. These devices communicate through gateways that exchange points with the central server. This study proposes an empirical and statistical methodology based on measurements carried out in a typical scenario of Amazonian cities composed of forests and buildings on the Campus of the Federal University of Pará (UFPA) to apply an adjustment to the coefficients in the UFPA propagation model. Furthermore, an Evolutionary Particle Swarm Optimization (EPSO) metaheuristic with multi-objective optimization was applied to maximize the coverage area and minimize the number of gateways to assist in the planning of a LoRa network. The results of simulations using the Monte Carlo method show that the EPSO-based gateway placement optimization methodology can be used to plan future LPWAN networks. As reception sensitivity is a decisive factor in the coverage area, with −108 dBm, the optimal solution determined the use of three gateways to cover the smart campus area.

This letter provides a model using Dyadic Green's Functions for predicting the electric field in mixed paths for UHF. A new approach is used considering propagation in vertical layers to obtain new equations. The development of the model was accomplished in a mixed City-River-Forest path located in the Amazon Region. Measurement data were collected from a digital TV broadcasting transmitter. A comparative analysis was carried out among the proposed model, ITU-R P.1546-5, measurement data and ITU-R P.1546-5 using Millington's curve-fitting. The measurement data and the model using Dyadic Green's Function are in a good agreement. The results confirm the efficiency and applicability of the proposed model with RMS error no greater than 1.5 dB.