This article proposes a novel method for detecting coronavirus disease 2019 (COVID-19) in an underground channel using visible light communication (VLC) and machine learning (ML). We present mathematical models of COVID-19 Deoxyribose Nucleic Acid (DNA) gene transfer in regular square constellations using a CSK/QAM-based VLC system. ML algorithms are used to classify the bands present in each electrophoresis sample according to whether the band corresponds to a positive, negative, or ladder sample during the search for the optimal model. Complexity studies reveal that the square constellation $N=2^{2^i}\times 2^{2^i},(i=3)$ yields a greater profit. Performance studies indicate that, for BER = ${10}^{-3}$, there are gains of −10 [dB], −3 [dB], 3 [dB], and 5 [dB] for $N=2^{2^i}\times 2^{2^i},(i=0,1,2,3)$, respectively. Based on a total of 630 COVID-19 samples, the best model is shown to be XGBoots, which demonstrated an accuracy of $96.03\%$, greater than that of the other models, and a $recall$ of $99\%$ for positive values.

In this paper, a rolling shutter optical camera communication system is investigated by analysing the internal working principle of a receiver based on complementary metal oxide semiconductor image sensors. Based on the thorough analysis of system parameters such as the clock signal, integration and read‐out times at the sensor level, and the calculation of the bandwidth and the time span of the image frame containing the information signal, it was demonstrated that the communication functionalities can be enhanced. A new model was proposed and validated by developing an experimental testbed and demonstrating matching between the data packet duration and the predicted time span. This enables the optimisation of the samples obtained by the image postprocessing, using different sensor clock signals and evaluating the bit error rate performances. The experimental results demonstrated that the internal design of the camera and its packet structures have impacts on the read‐out times. For camera settings of pixel clock frequency and exposure time of 300 MHz and 61 s, respectively, a data rate of 14.5 kbps at a bit error rate below the forward error correction limit has been achieved.

In this work, we propose the application of Multiresolution Analysis (MRA) for reducing the noise in the signal generated by the FSK (Frequency Shift Keying) modulation used transmitting information through a VLC (Visible Light Communication) channel. In order to apply MRA, the Wavelets of Daubechies and Symlet are used. The effectiveness of this technique depends on the choice of the Wavelet, the decomposition levels of the signal to be analyzed and the threshold level used to eliminate the noise of the detail part. Finally, there is a significant noise reduction in the analyzed signal. To measure this reduction, we use the Mean Square Error (RMS).

This paper presents a methodology for the generation of detection and classification models of light emitters in digital video frames for indoor and outdoor visible light communication applications, including the generation of a user interface for the generation of Datasets of light emitter characteristics. Showing that is possible to analyze the frames of video by applying a classification model, allowing the development of new models to decrease the processing time per frame.

This work proposes a model for inertia identification of an electrical power system. A non-linear regression is used from a mathematical model that relates power and frequency variation, obtained from a synchrophasor network. Fitting of the non-linear regressions processed with Big Data, from the PMU and the different real generation contingencies, obtained from the national system operator, are presented.

This article presents a low cost solution based on visible light communication to report information from low rate sensors in indoor environments using the MIMO QAM channel and polar codes, encoding in Arduino Nano and decoding in a PYNO-Z1 FPGA.