ABSTRACT. Energy from non-conventional renewable sources is a strategic alternative for diversification of the Brazilian electric matrix. Brazil, given its large territorial extent, geographical diversity and climate, presents a natural complementarity in the energy supply. The North and North-East regions have high energy potential due to the high incidence of solar, wind and tidal current primary sources. The availability of these sources has an intermittent feature making it necessary, in the case of isolated microgrid, a storage system to ensure uninterrupted service of the load. This feature of renewable sources makes the process of sizing the microgrid more complex, especially when a mix between diverse sources is proposed. This article addresses the problem of sizing non-conventional renewable sources wind, solar and tidal and the storage system in an isolated microgrid. In addition, a sensitivity analysis study is carried out to verify the best use of each individual source and to minimize the total cost of the system.

ABSTRACT. Biomass residues generated from agricultural production (corn and barley) represent an important source of potentially sustainable raw material for the production of bioethanol. However, the use of agricultural waste for the production of alternative fuels will only be successful if sufficient biomass can be guaranteed for bioethanol generation. This paper studies the problem of designing a supply chain to produce bioethanol through the use of agricultural biomass (corn and barley) with a four-echelon approach, a transport channel and two agricultural raw materials (corn and barley). The decisions to be made are the opening of storage centers, biorefineries, mixing plants and finding the optimal biomass and bioethanol flow between the facilities. The proposed approach is presented as a mixed integer mathematical programming model (MILP); additionally, a practical case study is presented for the area of Tulancingo, Hidalgo, in Mexico, which is solved with CPLEX (Version 12.5). Finally, an analysis of results and conclusions are presented.

ABSTRACT. Solar energy use is spreading rapidly in the world. Determining adequate tilt and orientation angles of flat panels represent environmental, economic and energy benefits. In this study, the influence of local climate on the optimal fixed flat surfaces position is analyzed to maximize the capture of solar irradiation. Five mathematical models are used to estimate the total radiation received by a flat surface. These models use meteorological variables such as: global, direct, diffuse and reflected radiation, as well as incidence angles of the solar radiation for each of the 8760 hours of a year. The data were taken from 2 meteorological stations located in Cuenca-Ecuador city (2.88 ° S, 78.99W). The five used models: diffuse isotropic, Lui & Jordan, Klucher, Temps & Coulson, and Perez concur in the results. The authors recommend in Cuenca-Ecuador, that the flat solar panels must be oriented 35 ° with respect to the North (NNE) and inclined 15° with respect to the horizontal. The obtained results suggest that, in areas close to the equator, the local climate influence is not dramatic. However, a further analysis ensures greater energy capture, so the tilt and orientation angles should not be established only with the geographical position information.

ABSTRACT. In this paper, a reflective structure is proposed and modeled by the authors to increase the irradiance on solar panels. In such a way, an increase irradiance factor is obtained and it can be used to analyze the behavior of the panel in terms of efficiency, output power and temperature. The proposed reflective structure consists of mirrors whose magnitudes at both orientation and dimensions will be determined through mathematical equations. During the modeling process, factors of great importance have been considered, such as the behavior of the different types of solar concentrators currently in existence, in order to analyze the reflective effect of the same and apply it. The proposed solution can increase solar panel irradiation in up to 60%.

ABSTRACT. The modeling and representation in state space of conventional single-phase distributed generation system (in particular PV systems) allow, in the time domain, their analysis under operating conditions in steady state and transient state. The research reported in this article is oriented in particular to the determination of the periodic steady state under conditions of harmonic distortion of single-phase distributed generation systems. The analysis is carried out in the domain, considering the particular modeling of the components of the PV systems, their associated controls and their representation in the frame of reference of the state space. Results are validated against the simulator PSCAD/EMTDC, widely accepted by the power industry.

ABSTRACT. A comparative study of three methodologies for estimating transmission line parameters together with nodal voltage state variables at the system level is presented in this paper. The estimation process to determine both conventional system variables and some parameters of transmission lines is simultaneously performed by using the weighted least squares (WLS) formulation. The parameters to be determined are the series impedance and shunt admittance of the associated π model of transmission lines. In this context, the type of parameters included in the WLS-based formulation as state variables is what differentiates the methodologies considered. Numerical results are presented using the IEEE 14-bus test system and show that the methodology employing the lowest number of state variables performs extremely well even though the number of transmission lines parameters to be estimated increases.

ABSTRACT. One of the main elements for the development and implementation of bidirectional converters applied to smart grids and micro CD grids is the medium frequency transformer (MFT). This element integrates a high efficiency together with a high power density due to the increase in the design frequency of the transformer, compared to conventional transformers at 60 Hz. This change requires the analysis and development of new methodologies and materials in the design to support the needs of these new transformers applied to DC-DC converters in photovoltaic systems, wind systems, solid-state transformers, and electric vehicles. This article describes the design and construction of an MFT, it´s computer simulation and experimental validation by building a prototype in the laboratory. The MFT has an efficiency of 98.94 % which was obtained for a laboratory prototype with 2.5 kVA, 250 V / 670 V and a frequency of 5 kHz.

ABSTRACT. Interdependence between gas and electricity transmission networks is a subject of concern due to the expanding use of gas for electricity generation in combined-cycle plants around the world. In this work, a novel and much more precise representation of natural gas and electricity infrastructures is proposed, including all assets of both systems and their coupling by the use of graph theory, which offers a more realistic topological method of both coupled networks. The representation is proposed as a scale-free graph and is mathematically validated in test networks, which facilitates their application for vulnerability analysis, while less information on their technical parameters and shorter computational times are required.

ABSTRACT. In this paper, an adaptive Morlet wavelet neural sliding mode controller (AMWNSMC) is proposed to stabilize a ballbot robotic system. The performance of our proposal is verified via numerical simulations using the mathematical model for a benchmark prototype based on LEGO Mindstorms NXT kit, showing the robustness against time-varying uncertainties and disturbances. Moreover, the AMWNSMC here proposed shows a better performance in contrast with an adaptive neural sliding mode controller (ANSMC) whose neural network is based on Gaussian functions and with more neurons in its hidden layer.

ABSTRACT. A family of bounded controls that stabilize the Roessler system in finite time is constructed. We employ V. I. Korobov’s controllability function method which, consists of the use of a Lyapunov-type function. The controllability function is the solution of a certain implicit equation.

ABSTRACT. The use of the genetic algorithm to obtain the appropriate switching sequence of a multilevel inverter has been increasing during the last years; this algorithm has been implemented through a Matlab solver. However, the choosing of the solver parameters have been by means of trial-and-error or by the use of user experience. In order to maximize the Matlab genetic algorithm performance, this paper proposes the use of the Taguchi design approach as a way to obtain the appropriate switching sequence of a five-level multilevel inverter, and therefore to get a low THD in the output voltage.

ABSTRACT. In this paper show the behavior of a DC electric arc in a Vacuum Arc Remelting (VAR) Furnace based on the results obtained from the numerical simulation performed from the finite volume method (FVM) using free software (Code Saturne). For the solution of the government equations that describe the phenomenon, an AISI 1018 steel electrode has been considered as a case study. Also an electric model in a software of electromagnetic transients (PSCAD) is proposed to coupling the electric and thermal characteristics in a process of remelting in this type of furnaces.

ABSTRACT. The large amount of data generated from the monitoring of electrical transformers generates the need to compress such information in order to store large volumes of data and transmit them at high speeds. The methodology proposed in this document focuses on the implementation of a data compression algorithm based on the Discrete Wavelet Transform. The algorithm is applied to a database of current signals demonstrating its suitability according to the high compression ratio achieved and the storage in hierarchical data format. Its high effectiveness is confirmed by demonstrating that the compressed files reduce their size considerably, presenting a performance superior to 78 in terms of compression ratio. In addition, it is demonstrated that the decompressed signal can be used to detect short circuit faults in a single phase transformer, obtaining percentages of classification effectiveness above 96.6%.

ABSTRACT. A hybrid ripple injection circuit to improve the power quality of a typical 12-pulse autotransformer rectifier for aerospace applications is presented in this paper. This injection circuit enhances the performance of the 12-pulse rectifier bestowing line current waveforms of a 36-pulse. It consists of a low-rated Vienna rectifier leg and an injector transformer. The proper operation of the Vienna rectifier transistor causes the transformer injector to modify the voltages in the main rectifier to improve the rectifier performance. The injector current rating is 2.2% of the output current. The hybrid ripple injector and rectifier principle of operation are described throughout this paper together with experimental results obtained with a 4-kW prototype.

ABSTRACT. In this paper, the one leak isolation problem in a water pipeline is tackled using a Time Delay Neural Network. This scheme comes as an alternative to achieve better computing performance since the classical model-based methods usually have high workloads due to the pipe mathematical model complexity compared with the leak dynamics speed. The Neural Network structure could have better time performance exploiting the parallel architecture of some electronics devices like an FPGA.

The authors propose a scheme where, due to the difficulty in obtaining training data from a real pipeline, a mathematical model is used to generate synthetic training data. Such training data is obtained using different leak magnitudes and leak positions and it is also corrupted by random noise in order to emulate real data pipe. Finally, to show the potentiality of this method, some results are presented by using real-noisy databases coming from a pipeline prototype.

Following the classical leak diagnosis hypothesis, only flow and pressure sensor at both ends of the aqueducts are used for the treatment.

ABSTRACT. The experimental verification of the dynamic behavior of an electric vehicle is necessary to design a control algorithm based on the actual behavior of the vehicle. In this work, the implementation of a control algorithm based on the backstepping technique using the simplified model of the electric vehicle is performed. For the verification of this algorithm in a real situation, the real parameters of the traction force of the vehicle are used and the validation of the obtaining of these parameters was developed by means of an experimental prototype, a system of rollers transverse to the axis of the tires of the vehicle and once these parameters are obtained they are added in the control algorithm to obtain the tracking of a constant longitudinal trajectory through the Matlab Simulink software.

ABSTRACT. With the growing of electricity demand and the rise of alternative energies, different sources of energy have been looked, including energy from the oceans, which covers a large part of the earth's surface. The present work focuses in the analysis of the parameters of behavior of the waves in the slope of the Mexican South Pacific, in some points of the coast of the state of Guerrero and Oaxaca, for the obtaining of the maximum wave potential absorbed by an asymmetrical body, in a period of study of six years. From the characteristic parameters of the wave, like significant height and peak period of different points, a simulation tool is developed to represent the behavior of the wave power.

ABSTRACT. This article presents the design of a multipurpose system for sending and receiving information remotely (long range) using GPRS technology. The system is composed of a device connected to different sensors and actuators, and a low-cost web platform for viewing information and controlling actuators. As an application example, a real-time vehicle monitoring system is shown.

ABSTRACT. There are different algorithms to track agents in indoor environments through the Wi-Fi radio frequency signal. Real-time location technologies, require many configurations and are not easy to apply. This document shows results of the development and practical use of an android application to track the position of an agent using the Received signal strength indicator (RSSI) from Wi-Fi emitters, taking advantage of the portability and wide spread use of mobile devices.

ABSTRACT. In recent years, smart grids have changed the energy distribution sector. This paper proposes a strategy for the active and reactive power flow control, applied to a three-phase power inverter connected to a microgrid. The power quality and reactive compensation are essential in the integration of renewable energy sources into small microgrids. These renewable microgrids can operate in stand-alone mode or connected to the utility grid. This document presents a Generalized Discontinuous PWM technique applied to a grid-connected converter. The control algorithm of the grid-connected system is applied for voltage control. This control technique provides independent control active and reactive power flow into the utility grid while maintain the dc-link voltage constant. As a novelty it is implements a GDPWM technique in the control of the grid-connected converter. In this way the losses in the converter are reduced while the efficiency of the equipment is increased. As a technological innovation, a modular multilevel converter (MMC) is introduced, as well as the power flow control technique. The purpose is to improve the voltage unbalance and harmonic compensation in stand-alone grids. Advantages of the developed model include: the cellular concept, easy thermal design, increased system efficiency, low overall cost as well as improvement in the system expansion capacity. The simulation model has been developed using the MATLAB/Simulink software. The results obtained have been satisfactory.

ABSTRACT. The continuous increasing demand for electric power for renewable sources, such as off-shore wind power or solar generation, along with the economic access to remote sources of these type have revived the interest in high-voltage direct current multi-terminal systems (MTDC). In this context, the Modular Multilevel Converter (MMC) configuration is considered to be the most promising VSC topology, but it lacks DC fault clearance capability. There are several ways to solve the earlier drawback, but they are costly, slow in response to faults or with large power losses. In this paper a hybrid HVDC breaker and the corresponding fault isolation strategy are proposed to overcome these drawbacks. The assemble of the hybrid HVDC consist of an active short-circuit breaker (ASCB), a main mechanical disconnector, a main breaker (MB), and an accessory discharging switch (ADS). A dc-side bus short-circuit fault is used to test the performance of the breaker in this particular situation. The MB opens isolating the faulted line and then the mechanical disconnector opens. The proposed breaker can handle the dc-side fault with competitively low cost, and the operating speed is fast enough. The time that it takes to isolate the fault is about 5ms, and the full restore of voltage at converters is about 0.2 s. A model of an eleven-terminal monopolar and bipolar MTDC grid, based on the CIGRE model, is developed in EMTDC/PSCAD simulation tool to prove the validity and the feasibility of the proposed solution.

ABSTRACT. Wind energy has become one of the alternatives with larger penetration for the replacement of conventional energy generation systems based on fossil fuels. The energy acquisition and integration are performed by a double-stage energy conversion process, the first one that converts the mechanical energy of wind in electrical energy by means of a generator engine, and the second stage is performed by a power electronics interface that converts the electrical power in accordance with the load requirements. This paper presents the modeling and simulation of a grid-connected wind turbine generator based on a permanent magnet synchronous generator and a back-to-back converter. The model has been simulated in a real-time simulation platform OP4510 by using the software eFPGASIM (eHS) that allows a realistic simulation of the power electronics stage.

ABSTRACT. The present work presents a study on the energy consumption of an electric forklift truck. It shows the profile of energy consumption in real operating conditions. The average and maximum consumption is determined from its storage system. The study proposes a replacement of the set of available lead acid batteries, with a system based on a hydrogen fuel cell and supercapacitors, which is modeled on Psim®. From an electric model, a buck converter is coupled to supply the necessary power to the forklift in 24Vdc. The study presents the design of the power supply system from a nominal 5kW hydrogen fuel cell, an equivalent capacitor of 130F, and a storage tank of 78L @ 200bar in order to have a theoretical autonomy of 8h of operation. The study demonstrates the feasibility of replacing the storage system of a conventional electric forklift with one that is powered by hydrogen, as an energy efficient alternative.

ABSTRACT. In the next work an automatic fringe projection system with a mobile camera has been proposed. A set of experimental images in order to scanning all the set positions in an automated rail are obtained. In each position, four profileometric images shifted pi/2 were taken and use the phase shift of 4 steps algorithm to obtain the wrapped phase. A qualitative process to analyze the profilometry of an object with an irregular surface is applied, getting good results.

ABSTRACT. This paper presents a strategy to choose an evacuation route of several places in a city such as: buildings, plazas, sectors of the city, etc. This strategy makes use of a distributed client-server system where the client software has information about the user while the server software has an algorithm that decides which evacuation route is the most appropriate for the person. It considers multiple objectives: minimize travel time to the refuge, and maximize the distance to the incident during the travel. This distributed system is suitable for smart cities with open databases because it helps users to choose an evacuation route based on health issues, city's services available and help users in case of emergency.

ABSTRACT. Long Short-Term Memory (LSTM) is a type of recurrent neural network that has become important in machine learning research thanks to its high precision to solve problems such as speech recognition, handwriting recognition, natural text compression, sequential data processing among others. Although classic LSTM are powerful tools to solve such problems, their adaptation is far from showing a smooth behavior which represents a drawback to LSTM be used in applications such as realtime control of physical systems in which to fulfill restrictions of ranges of values of the control variables is important in order to preserve the physical integrity of the systems. In this paper we present a design of architecture of LSTM that overcomes the non-smooth adaptation problem by using a single forget gate for all the LSTM units and furthermore improves the accuracy of classic LSTMs in problems such as rebber grammar learning, time series forecasting and control of physical systems as it is shown in the experimental and comparison results.

ABSTRACT. In this paper an adaptive neural network controller is used to solve the problem of tracking trajectories of a delta parallel robot (DPR) with three degrees of freedom. This controller used an adaptive artificial B-Spline neural network (BSNN) for online training. The BSNN improves the performance of DPR on a closed loop and update the parameters of control scheme online. This algorithm sets the control signal without using a detailed mathematical model nor exact values of the parameters of the DPR. The proposed adaptive controller was compared with a traditional control based a PD+G contoller. Analytical and numerical results prove the robust and efficient performance of the adaptive neural network controller.

ABSTRACT. K-Means is one of the most used cluster algorithms. However, because of its optimization process is based on a greedy iterated gradient descent, $K$-Means is sensitive to the initial set of centers. It has been proved that a bad initial set of centroids can reduce clusters' quality. Therefore, numerous initialization methods have been developed to prevent a lousy performance of K-Means clustering. Nonetheless, we may notice that all of these initialization methods are usually validated by using the Sum of Squared Errors (SSE), as quality measurement. In this study, we evaluate three state-of-the-art initialization methods with three different quality measures, i.e., SSE, the Silhouette Coefficient, and the Adjusted Rand Index. The analysis is carried out with seventeen benchmarks. We provide new insight into the performance of initialization methods that traditionally are left behind; our results describe the high correlation between different initialization methods and fitness functions. These results may help to optimize K-Means for other topological structures beyond those covered by optimizing SSE with low effort.

ABSTRACT. One of the biggest problems of the internet is information overload. A way to handle this is Collaborative Filtering. However, they can present some problems as they work with large rating matrices and they are always really sparse. In this paper, we purpose a model that finds the closest neighbors efficiently incorporating dimensionality reduction, using Truncated Singular Value Decomposition which helps with sparse data and avoids noise caused by lack of ratings, then using clustering as we have a dense reduced matrix, and finally applying the correct similarity metric to improve predictions. To evaluate the prediction quality we use the mean absolute error. The experiments are executed with MovieLens 1M Open Data Set. And to explain the model we use a running example, named datatoy.

ABSTRACT. The system and methods specified in this article provide a systematic approach to analyze both physiological and sociodemographic risk factors that contribute to the individual's current or potential for disease. This system allows for an adequate taking of additional actions and decisiones based on that analysis to achieve the best possible level of health and well-being for the entire population throughout the life cycle of the individual. This platform is a system based on complex networks that includes a drug layer, a disease layer and a health infrastructure layer. The drug layer provides information on active substances, indications, doses, interactions, rules about medication during pregnancy and lactation, food interactions and adverse effects, and is represented by bipartite network. The disease layer is represented by a network of comorbidities identified nationwide in 8 years of information from patients who entered the emergency unit. The medical infrastructure layer provides information on the number of hospitals, their location, the number and type of beds per hospital, the medical procedures used in patients and the medical services available per hospital and is also represented by bipartite network. Each layer is coupled by links between them and filtered by the information of new patients entering the platform for evaluation. In addition, some preliminary results of the interaction between the different layers that are part of the smart platform are presented.

ABSTRACT. User recommendation is a big challenge for collaborative
filtering, due to the large number of users a company
can have today. In addition, the data to recommend products,
entertainment programs, among others, have to be very dispersed,
there are not many users sent a vote towards a product,
generating a high spread to make a recommendation. To solve this
problem, we propose a hybrid system, which uses collaborative
filtering and content-based filtering techniques where we use the
user’s personal information (in this case the occupation or work)
to segment them into groups and then use the rating of the items
to be able to make predictions. We then make recommendations
using aggregation techniques such as average, maximum and
minimum, which will be evaluated with metrics such as RMSE
and MAE in order to obtain the best recommendation approach.
To carry out this hybrid recommendation system, we have used
a public database called Movielens. The research aims to leave
a baseline for future research so that the proposed system can
be improved with different methods.

ABSTRACT. The meteorological data in networks are susceptible to errors and irregularities, one of the reasons is because they are collected by different types of meteorological stations, the possibility of heterogenous data, so they limit their assimilation to models and interpretation platforms. This paper presents a project that aims to assist the Laboratorio de Climatología y Calidad del Aire in the analysis of the Red-Clima UACJ, through the creation of a NoSQL environment in which there is a process for the quality assessment of the data, as well as the necessary management for the homogenization and visualization of it. The quality assessment using a series of quality control algorithms can detect possible anomalies in the behavior of the data for later review and modification. For the management it is necessary to create a framework with the objective to homogenize the climatic information contained in MongoDB, providing as a result a dataset in JSON, CSV or XML format.

Los datos meteorológicos en redes son susceptibles de errores y sesgos, así como, debido a que son recolectados por diferentes tipos de estaciones meteorológicas, también son heterogéneos, por lo que limitan su asimilación a modelos y plataformas de interpretación. El presente trabajo pretende auxiliar a el Laboratorio de Climatología y Calidad del Aire en el análisis de los datos generados en la Red climatológica UACJ (Clima-UACJ), mediante la creación de un ambiente NoSQL en el cual se realiza un proceso para la evaluación de la calidad de los datos, así como la gestión necesaria para la homogeneización y preparación para su visualización. La evaluación de la calidad mediante la utilización de una serie de algoritmos de control de calidad podrá detectar posibles anomalías en el comportamiento de los datos para su posterior revisión y modificación. Para la gestión es necesario la creación de un framework con el objetivo homogenizar la información climática contenida en MongoDB, proporcionando como resultado un dataset en formato JSON, CSV o XML.

ABSTRACT. The electric power industry has undergone dramatic changes in recent years driven by the emergence and increasing adoption of new technologies. These changes present new challenges for system operators, who must face greater complexity in the operation and control of the electrical infrastructure. This talk summarizes and discusses several technical challenges and methods to solve them associated with the increasing penetration of renewable energies, interdependence between critical infrastructures, cybersecurity threats and the latest advances of the role of state estimation in power system operation.

ABSTRACT. Based on the standards IEC 60060-1 (High-voltage test techniques) and IEC 60270 (High-voltage test techniques - Partial discharge -PD- measurements) tests were carried out on high voltage industrial frequency and lightning impulse on glass fibre reinforced polyester –GFRP- post samples, in order to determine PD and breakdown voltage; contrasting with the results obtained by insulation coordination determining the suitability of the insulating material; the data obtained was processed and analyzed using MATLAB software, digital filters and the fast Fourier transform (FFT).

ABSTRACT. This paper describes a new model to analyzes the performance of grounding systems during direct lightning strikes on a power substation. The proposed model uses three different types of multi-conductor transmission lines for representing the substation grounding system, including the substation shielding conductors. The model calculates currents and transient voltages in the aerial and underground structures, including the leakage currents dissipated into the soil. A methodology to calculate the aerial and underground parameters is also included. The model was validated successfully. Computer simulations results show that the inclusion of shielding conductors into the analysis reduce current and voltage magnitudes, leading to a less conservative design.

ABSTRACT. With the currently grid code applied to load centers in Mexico, an special attention is taking care on power quality solutions, mainly for power factor correction, reduction of total harmonic distortion of demand and current imbalance. It is desire that all the technical solutions for these power quality problems includes life cycle cost analysis in order to obtain the best economical solution. In this paper an analysis is presented, showing a technical solution for harmonic distortions, power factor and impacts in the reliability of equipment, complemented with the analysis of life cycle costs of an asset, thus obtaining criteria to select the better system that maximizes the profitability of a process in a plant under a cost-risk-benefit approach.

ABSTRACT. Wind parks based on doubly fed induction generators can provide primary frequency regulation if additional control loops are implemented - the blade pitch angle control is used for endowing variable-speed wind turbines with frequency regulation capabilities. This technique is proposed in this paper for wind turbines to provide frequency support in the Mexican power system, which is fully evaluated under the perspective of the Mexican grid code. To this end, the performance of a recently commissioned 180-MW DFIG-based wind farm in Mexico, with pitch angle control for frequency support is studied. In addition, an equivalent model of the mexican power system is assessed using credible scenarios with high wind power penetration and different demand scenarios. The impact of the wind parks is thoroughly assessed under the perspective of the Mexican grid code, identifying under which operating scenarios and wind turbine parameters, the wind parks comply with the requirements imposed by the grid code for primary frequency control.

ABSTRACT. Induction motors (IM) are one of the most used electromechanical devices in industrial applications. However, several factors could cause their failure and lead to economical or even human losses. For this reason the IM condition monitoring has been studied for many years. Most of the proposed techniques utilize sophisticated and high-computational-load time-frequency transforms for isolating the signal components related to the IM faults. For this reason to propose low-complex and efficient tools for IM condition monitoring is still necessary. In this work an adaptive second-order digital notch filter for attenuating main frequency component from a signal is introduced for assisting the IM condition monitoring. The effectiveness of the proposed method is validated through simulations and experimentation.

ABSTRACT. Nowadays, virtual simulators are playing a crucial role in the training of the armed forces of a country. Proof of this, is that most First World countries have developments of virtual simulation systems and virtual environments concentrated on military training. Due to the growing demand for this type of systems, virtual shooting simulators based on digital image processing (DIP) have been developed in recent years. In this paper, a DIP algorithm focused on the detection of impacts on a fixed target aided by a laser attachment is proposed. The operation of the algorithm is based on the Euclidean distance metric, generating a decorrelation in the area of interest when an impact of the laser light beam occurs, and maintaining a high correlation in areas of no interest between adjacent video frames. Significant gains are achieved by the proposed algorithm against the typical DIP algorithms found in the literature, which were measured quantitatively by the peak-to-average power ratio (PAPR) metric, obtaining a gain of more than one order of magnitude. Finally, the rms error performance of the detection system was obtained by real fire in a shooting stand.

ABSTRACT. The paradigm of the Internet of Things (IoT) has incorporated new applications for human daily life. Some of these applications are based on architectures which include wireless sensor-actuator networks. The information which is collected by the sensors is processed in order to decide when to enable or disable an actuator to perform a particular task. Often, the processing of the information is performed in the cloud consuming a lot of computing resources and bandwidth. In this paper, we propose a circuit which includes the SCT-013-030 sensor and the ESP8266 NodeMcu V2 module for energy monitoring consumption in smart homes using a wireless sensor network. An artificial neural network is implemented using the processor of the ESP8266 NodeMcu module to recognise when there is unusual energy consumption in home appliances. The consumption information obtained by the wireless sensor is collected in a MySQL database, for which a Raspberry Pi 3B is used as server. Our artificial-neural-network-enabled circuit will be capable of warning the user of an abnormal energy consumption.

ABSTRACT. In this paper we compare the performance of variants of Genetic Programming (GP) typically used for high dimensional machine learning problems. First we propose a taxonomy based on GP primitives that allow us to clearly differentiate GP variants found in literature; then we implement and test three GP variants in a set of image denoising tasks. Results show a clear advantage of the variant most commonly used for those kind of problems. We then compare our results with those reported in other GP works as well as those from deep learning. Comparisons suggest that GP cannot compete with deep learning unless it is embedded with expert's knowledge of the problem domain.

ABSTRACT. This article presents a methodology to automate the production of forecasting models. The kind of models we produce is Seasonal ARIMA. The search for the best model structure is performed using the compact Genetic Algorithm, which uses a binary codification of the individuals. An important feature of compact Genetic Algorithms is the lack of an explicit represen- tation of the population, which is replaced by an estimation of the probability distribution of each bit of the binary encoding of chromosomes in the population. The proposed methodology was tested with 7 time series from different application fields; the results were satisfactory. As an extension of this work more extensive evolutionary processes will be developed, aiming to produce models that reduce the forecasting errors.

ABSTRACT. Memetic approaches are composed of three general processes, a global optimizer, a set of local-search operators, and a coordination mechanism; which are defined depending on the problem to be optimized. For constrained optimization problems (COPs), memetic algorithms require the incorporation of a constraint handler that guides the search to the feasible regions of the search space. In this regard, the epsilon-constrained method has demonstrated to operate correctly in memetic approaches by transforming a COP into an unconstrained problem during a certain period of the search process. This constraint handler uses a tolerance level that promotes the exploration, mainly in COPs where there are disjoint feasible regions or equality constraints. Nevertheless, epsilon-constrained depends on a set of parameters that determine its behavior, so five variants have emerged in the control of its tolerance, (1) static, (2) dynamic, (3) truncated, (4) threshold, and (5) adaptive. This study focuses on determining the most appropriate control technique in a memetic approach and its relation to the performance and final results of the algorithm. For the study, a memetic differential evolution (MDE) is implemented, whose coordination mechanism controls the activation of three local search methods. Each epsilon-level control mechanism is incorporated separately within the MDE and is tested in eighteen well-known test problems. The results suggest that there is a benefit through the use of adaptive/dynamic mechanisms while reducing the budget for fitness evaluations. Likewise, its advantage is exhibited in functions with non-separable equality constraints. Finally, results determine that there is no benefit relationship between how to control the epsilon-level and the performance of the local optimizers used in this study.

ABSTRACT. Outdoor color images are often degraded due to uncontrolled conditions such as lighting, pollution, fog, shadows or haze. Those conditions cause loss of contrast and detail as the scattering has attenuation and smoothing effect. Considering Near Infrared (NIR) light is lower scatters than visible light due to its long wavelength, the NIR is spread through the fog. NIR images usually contain important information that can complement the visible image (V ) in the same scene. In this work, we propose to fused V and NIR images, of the same scene, by pixel weight assignation of the luminance. The results show that color images are capable to enhance certain features not visible at the input V image. Moreover, the proposed fusion method provides relevant information from the NIR image while preserves the V information. The main characteristic of our approach to fusing is that only the relevant information is fused and the resulting colors are consistent with the scene.

ABSTRACT. The talk will introduce the research of power grid wide-area monitoring and some fascinating observations that were made possible from the grid edge synchronized data. The critical roles of wide-area phasor measurement in situation awareness, operation, and control will be discussed. The concept of electromechanical wave propagation in power grid will be demonstrated using measurement data collected from the actual grids. Applications of time synchronized data in event location, oscillation detection, model validation, and others will be discussed.