Browsing by Autor "Luiz da Silva Mello"

Now showing 1 - 5 of 5

Artificial Intelligence Enabled Radio Propagation: Path Loss Improvement and Channel Characterization in Vegetated Environments
(Sociedade Brasileira de Microondas e Optoeletrônica; Sociedade Brasileira de Eletromagnetismo, 2024) Leonardo Henrique Gonsioroski; Amanda Santos; Jairon Viana; Sandra Ferreira; Rogerio Silva; Luiz da Silva Mello; Leni Matos; Marcelo Molina Silva
In this paper, the application of AI and machine learning (ML) to the study of wireless propagation channels is investigated in two parts: first, an artificial neural network model is used to improve path loss prediction, and then, a pattern recognition model using multilayer perceptron (MLP) networks is used to identify and remove impulsive noise in power delay profiles (PDP). These studies were conducted based on field measurements in the 2400 MHz band in a public square with vegetation. The results are analyzed and compared with ordinary least squares (OLS) nonlinear regression results and results from similar studies. The Root Mean Square Error (RMSE) values between the experimental results of mean path loss and those provided by each propagation model are presented. The adjustment performed by OLS nonlinear regression and ANN significantly reduced the RMSE. The best results are those presented by artificial neural networks, with RMSE of 0.39 when using four neurons in the hidden layer of the ANN. The ANN used to identify and remove impulsive noise in power delay profiles (PDP) through pattern recognition proved to be more efficient than the CFAR technique. ANN technique found a larger number of valid multipaths compared to the CFAR technique.
Evaluation of Cooperative Cognitive Radio System for White Spectral Space Detection using the Covariance Detector
(2025) Rafael G. Ramirez Montecinos; Mateo I. Luna Rico; Marcelo Molina Silva; Jussif J. Abularach Arnez; Luiz da Silva Mello; Carlos V. Rodriguez R.; Leonardo Henrique Gonsioroski
Wireless spectrum is increasingly scarce, which motivates the need for robust methods to detect unused bands—especially under challenging conditions like low SNR and fading. This study proposes integrating Spectral Covariance Sensing (SCS) into a cooperative cognitive radio framework, leveraging hard-decision fusion schemes (AND, OR, Majority) to enhance detection stability. Using real Advanced Television Systems Committee(ATSC) signal data, the detection performance was evaluated across various SNR levels. The results show that cooperative sensing significantly improves detection probability under low SNR, with the OR rule achieving the highest detection rate (e.g., ≈90% at –30 dB) and the majority rule providing the best overall trade-off between reliability and false alarms. These findings demonstrate the practical value of cooperative SCS systems in dynamic spectrum environments.
Predicción de cobertura en sistemas LMDS/LMCS
(2001) Antonio Guillén Pérez; Luiz da Silva Mello; Jörg Sebastian Michaelis
The growing demand for communication services such as voice, data, video, audio, multimedia y/o any combination of these has increased the demand for broadband systems. In this context, the LMDS system (Local Multipoint Distribution Service) and their Canadian version LMCS (Local Multipoint Communication System), which utilize minimum bandwidths of 1.3 GHz, have become in strong candidates to cover this necessity. In this article, an algorithm is developed to determine one of the most important aspects in the planning of systems LMDS/LMCS and of a wireless system in general: coverage system. Additionally, coverage radiuses in the systems LMDS/LMCS for temperate climates and tropical and equatorial regions in analytical way and through the use of the NETDimensionTM software are compared. Finally, the influence of diverse factors is also analyzed in coverage radio of the LMDS/LMCS systems.
Preliminary Results of the Indoor Coverage Field Tests of the Advanced ISDB-T System in Brazil
(2023) Amanda B. Santos; Leonardo Henrique Gonsioroski; Rodrigo Ribeiro de Oliveira; Luiz da Silva Mello; Alberto Leonardo Penteado Botelho; Cristiano Akamine; Natália C. Fernandes; Marcelo Molina Silva
This article presents the preliminary results of field tests with the Advanced Integrated Services Digital Broadcasting for Terrestrial Television Broadcasting (ISDB- T) system in indoor environments. Received channel power and error-free system reception threshold records were performed at four different measurement sites. Five different H/V dual-polarized MIMO antennas are used in measurements to evaluate system performance when using antennas from different manufacturers. The results show that the advanced ISDB-T system is robust to indoor penetration losses and when subjected to the use of different antennas.
Un nuevo modelo para la atenuación diferencial por lluvias en enlaces terrestres convergentes operando en frecuencias superiores a 10 ghz, para climas inter-tropicales
(Universidad Autónoma del Estado de México, 2010) Pedro M. Rey‐Araújo; Nelson Pérez; José Miguel Sánchez; José-Luís Paredes; Luiz da Silva Mello
"Los sistemas inalámbricos de comunicación que operan en frecuencias superiores a 10 GHz son fuertemente afectados por la presencia de eventos de lluvias. En el caso de los enlaces punto-multipunto, como por ejemplo los sistemas LMDS (Local Multipoint Distribution Services), que operan en dicho rango de frecuencias, existe otro efecto producido por las lluvias, conocido como atenuación diferencial, que degrada significativamente la relación señal-interferencia (S/I) de los enlaces, pudiendo causar indisponibilidad en el servicio. Para la predicción de este fenómeno existen pocos modelos disponibles en la literatura, los cuales, además, presentan ciertas desventajas (inconsistencia con el comportamiento físico del fenómeno, dependencia de las atenuaciones totales de cada enlace y excesivo número de parámetros de ajuste). En este artículo se desarrolla un nuevo modelo semi-empírico para la estimación de la atenuación diferencial, que supera las desventajas mencionadas, y puede ser aplicado en Venezuela. Para ello, se dispone de una base de datos de medidas realizadas en Brasil, que al igual que Venezuela, también está ubicado en la zona inter-tropical del globo terrestre. El modelo desarrollado se basa en el ajuste de la distribución acumulativa de Weibull a los datos obtenidos a partir de las medidas, y se utilizaron diversos métodos de regresión no lineal para la obtención de los respectivos parámetros de ajuste. Los resultados son bastantes satisfactorios, ya que, dicho modelo además de superar las desventajas de los modelos existentes (presentando una muy buena correlación del 95,96% con respecto a toda la muestra de datos medidos, para el caso de modelos no dependientes de atenuaciones totales de enlaces), presenta un mejor desempeño en términos del valor RMS de los errores, para bajos porcentajes de tiempo (entre 0,01 % y 0,1%), los cuales son ampliamente utilizados como parámetro en la planificación y dimensionamiento de sistemas de alta disponibilidad."