Applied Technologies

In this article we discuss how users of Mobile Instant Messaging (MMI) (WhatsApp) applications collaborate in environments that promote knowledge networks. For this study the researcher analyzed the interaction of users added to a group in WhatsApp, which is based on concepts of connectivism, communication, collaborative learning and knowledge creation. This study deals with the granting of knowledge on a specific computer subject and its transmission by all the members of the group, facilitating the work for the instructor and increasing the users’ compression capacity. Each user can become an instructor for the new members of the group. Strengthening collaborative learning processes. Part of the study is the use of the questionnaire tool that collected information from group members, reception capacity, age and difficulties with MMI.

In order to realize climate prediction or weather forecast, there exist large and expensive meteorological stations which monitor various weather variables, such as temperature, wind speed, humidity, etc. However, these prediction systems are deployed to monitoring urban zones or large population areas. Therefore, predictions for communities far from urbanization are in the practice, imprecise. Currently, these inaccurate predictions for the climate changes, affect the agriculture in several areas, due to inadequate planning by the farmer, which is based on a priori knowledge that the inhabitants have with the experience from the observation of the climate behavior, action that is highly imprecise and unpredictable. Therefore, in this work, for a more accurate weather forecast in rural regions, a portable low-cost meteorological device is proposed, which using suitable sensors measures and record the weather variables such as temperature, humidity of the air, luminosity, rain, humidity, and atmospheric pressure. Using these weather data, a classification of the target class set {rainy, cloudy, sunny}, is made based on the parameters obtained through the device. Then, using a combinations of assembled algorithms with deep learning, optimum results are obtained with the following classifiers: MultiClassClassifier$$+$$Multilayer perceptron, using the sampling criteria 2/3-1/3, cross validation and representative sample. The classification results are comparable and competitive, with respect to those reported in the state-of-the-art, and stands out by distinguishing the target classes with a high degree of precision.

In the present article, the main needs of collection centers and immediate care facilities in case of disasters are analyzed. A model is proposed for the services provided by these collection centers based on queuing theory, including an assessment of the arrival rates and service capacities, waiting times before being treated or receiving no healthcare service. A management algorithm is proposed that allows changes in real time of the system dynamics so it can adjust to queuing models with different features in order to carry out an effective help for system users. This reduces the service time and integral attention of the people affected by a disaster in favor of rapid recovery from a psychological and social point of view.

The consumption of alcohol, drugs and substances constitutes one of the most serious public health problems worldwide, in particular due to the social consequences related to violence, abandonment of studies, family disintegration and the great problem of drug trafficking that is strengthened at the increase consumption. In addition, Artificial Intelligence is consolidating as an area of ​​interdisciplinary knowledge, helping with the agile relationship of variables and indicators, which facilitates the discovery of behavioral patterns of human and material entities. From this perspective, the present investigation is proposed, which details universal indicators regarding the research carried out in the conjunction of these areas of knowledge. A systematic search has been carried out of scientific articles of journals indexed in the Scopus and WoS databases. There is an exhibition organized by subareas, countries, researchers, problems raised, regarding scientific production to facilitate possible future research in these areas.

In this study, data of 42 healthy individuals walking over a treadmill was used to train and test a neural network that produced individual kinetic patterns of gait cycle as output for a set of atomic features (gender, age, mass, height and gait speed) used as input. The proposed method implements a 3-layer feedforward architecture capable to produce the 3D gait patterns of ankle, knee and hip moment at once, with an average root mean squared error (RMSE) of 7% and average correlation coefficient ($$\rho $$) of 0.94 with respect to the ground truth patterns of the test set. The presented strategy may be used to support individual gait clinical analysis as an alternative to the use of the normal literature pattern that do not take into account the specific characteristics of the patients.

The physiotherapists analyse gait patterns to recognize normal and pathological gait movements. The gait patterns are affected by the characteristics of the individual (gender, age, weight and height) and the walking speed. In this paper, a gait analysis system to evaluate the severity of gait pathology is proposed. The Machine Learning (ML) algorithm can generate reference knee patterns for specific individuals. Gait index are used to compare the patterns generated by the ELM and patterns of the patients who suffered a surgical knee reconstruction. Two gait index are compared: The Gait Variable Score (GVS) and the Global Index (GIndex) developed by the authors. The GIndex classified 7 patients as not recovery, corroborating with the opinion of physiotherapists, while the GVS only classified 2 as not recovered. The proposed gait analysis system using the Extreme Learning Machine (ELM) and the GIndex can be useful tool for physiotherapy team in the gait pathology diagnosis and evaluation of future pathologies.

In this paper a driving mode estimation model based in machine learning architecture is presented. With the statistic method, Random Forest, the highest inference of driving variables is determined through the best attributes for a training model based in OBD II data. Engine sensors variables are obtained with the aim of explaining the behavior of the PID signals in relation to the driving mode of a person, according to specific consumption and engine performance, characterizing the signals behavior in relation to the different driving modes. The investigation consists of 4 power tests in the dynamometer bank at 25%, 50%, 75% and 100% throttle valve opening to determine the relationship between engine performance and normal vehicle circulation, through the engine most influential variables like MAP, TPS, VSS, Ax and each the transmission ratio infer in the fuel consumption study and engine performance. In this study Random Forest is used achieving an accuracy rate of 0.98905.

The purpose of this paper is to make a concise description of the current deep learning methods for natural language processing (NLP) and discusses their advantages and disadvantages. The research further discusses the applicability of each deep learning method in the context of natural language processing. Additionally, a series of significant advances that have driven the processing, understanding, and generation of natural language are also discussed.

Hyperthermia using High-Intensity Focused Ultrasound (HIFU) is an acoustic therapy used in clinical applications to destroy malignant tumors of bone, breast, brain, kidney, pancreas, prostate, rectum and testicle. This technique consists in increase the temperature in the tumor or the specific area, to achieve coagulative necrosis and immediate cell death. Although hyperthermia can cure cancer, it can also cause side effects and even damage healthy cells or tissues. Therefore, for having a successful treatment, it is important to monitor and observe what is the tissue behavior, as well as its changes, before, during and after the procedure. Mathematical models are tools that can be useful to simulate an adequate therapy by differentiating characteristics that will depend on each individual. An attenuation coefficient estimation for a forward model with a rectangular two-dimensional domain is presented, the estimation was made with simulated numerical data and simulated experimental data by Levenberg Marquardt and Gauss-Newton Methods. The results demonstrate that by identifying the attenuation coefficient of each patient. By estimating the attenuation coefficient parameter it is possible to predict the thermal responses of the tissue to be treated and, based on them, to plan an adequate cancer treatment by inducing heat by HIFU.

This work evaluates the applicability of machine learning (ML) tools in additive manufacturing (AM) processes. One of the most employed AM techniques is fused deposition modeling (FDM), where a part is created from a computer-aided design (CAD) model using layer-by-layer deposition of a feedstock plastic filament material extruded through a nozzle. Owing to the large number of parameters involved in the manufacturing process, it is necessary to identify printing parameters ranges to improve mechanical properties as yield and ultimate strength. In that sense, ML has proven to be a reliable tool in engineering and materials processing, where hybrid ML algorithms are the best alternative since one-part acts as a forecaster, and the other part acts as an optimizer. To evaluate the performance of wood composite filament fabricated by FDM a uniaxial tensile test was performed at room temperature. The experimental procedure was carried out with a design of experiments of four factors at three levels, where the statistical significance of layer thickness, fill density, printing speed and raster angle was obtained as well as their interactions. Furthermore, ML’s algorithm accuracy was explored, where a neuro-fuzzy system (ANFIS) was trained and tested with the experimental data. Through the development of the present work, it is concluded that layer thickness and raster angle play a significant role in FDM of a wood composite filament where fibers presence increases the layer thickness accelerating the FDM process.

Several systems have been developed in the last years to automatically detect volcanic events based on their seismic signals. Many of those systems use supervised machine learning algorithms in order to create the detection models. However, the supervised training of these machine learning techniques requires labeled-signal catalogs (i.e., training, validation and test data-sets) that in many cases are difficult to obtain. In fact, existing labeling schemes can consume a lot of time and resources without guarantying that the final detection model is accurate enough. Moreover, every labeling technique can produce a different set of events, without being defined so far which technique is the best for volcanic-event detection. Hence, this work proves that the labeling scheme used to create training sets definitely impacts the performance of seismic-event detectors. This is demonstrated by comparing two techniques for labeling seismic signals before to train a system for automated detection of volcanic events. The first technique is automatic and computationally efficient, while the second one is a handmade and time-consuming process carried out by expert analysts. Results show that none of the labeling techniques is completely trustworthy. As a matter of fact, our main result reveals that an improved detection accuracy is obtained when machine learning classifiers are trained with the conjunction of diverse labeling techniques.

In the domain of Big Data, the company’s supply chain has a very high-risk exposure and this must be observed from a preventive perspective, that is, act before such situations occur. As a company grows and diversifies the number of suppliers, customers and therefore increases its number of daily transactions and associated risks. Despite the innovation and improvements that have been incorporated into financial management, credit and debit cards are the main means of exchanging cash online, with the expansion of e-commerce, online shopping has also increased number of extortion cases that have been identified and that continues to expand greatly. It takes a lot of time, effort and investment to restore the impact of these damages. In this paper, we work with machine learning techniques, used in predicting smart supply chain fraud, are valuable for estimating, classifying whether a transaction is normal or fraudulent, and mitigating future dangers.

The brain-computer interfaces - BCIs allow people with disabilities to interact with the outside world using different communication channels than conventional ones. This article deals with the selection of tasks in the protocols for the development of BCI based on the paradigm of mental tasks. It is proposed to use the NASA-TLX index to evaluate the effect of the mental load of each of the tasks and contrast the performance of the interface task by task. In the implementation of BCI, the OPENBCI hardware was used for signal acquisition and the MATLAB software for processing. Five mental tasks were defined that activated different regions of the cerebral cortex. The acquisition protocol consisted of defining the rest time, execution and recovery for the tasks. The extraction methods used temporal, frequency and time-frequency combination characteristics. The classifiers used were neural networks, nearby neighbors and support vector machines. The evaluation of the TLX index seeks to quantify the appreciation of the effort, frustration and complexity of the task, therefore after the acquisition of signals for each task, the participant proceeded to evaluate the mental overload using the NASA-TLX index. The results obtained show that those tasks that require greater complexity to be performed presented a greater repeatability and higher success rate.

Electricity demand management is the process of making appropriate use of energy resources. This process is carried out with the aim of achieving a reduction in electricity consumption. The electrical demand management algorithms are implemented in a domotic system that has the capacity to identify electrical loads using artificial neural networks. An analysis was carried out on the most important physical variables in the home, which have a direct relationship with energy consumption, and strategies were proposed on how to carry out a correct control over these, in search of generating energy savings without affecting comfort levels in the home. It was obtained, as a result that it is possible to generate an energy saving of 63% in comparison to a traditional house, this without affecting to a great extent the comfort of the user and allowing a great level of automation in the home.

The consumption of alcohol, tobacco and other drugs are a health and social problems worldwide. According to several studies, abstemious people are a minority population among university students. The objective of this research is to identify clusters of abstemious students and their psycho-socials patterns. Based on information obtained through five psychological questionnaires (Patient health questionnaire PHQ-9, avoidance and action questionnaire AAQ 7, loneliness scale UCLA-R, the satisfaction with life scale SLQ, the Barratt impulsiveness scale BISS-1, and perceived stress scale PSS-10) a cluster analysis was conduct using Sparse K-means algorithm. The sample comprised 510 abstemious college students from three Ecuadorian universities. Two clusters were obtained: satisfaction with life, loneliness, and avoidance and action are the most representative variables contributing to the cluster distribution.

Automatic and remote monitoring of patients with pain may decrease treatment costs and improve the quality of care. In this sense, the Internet of Things (IoT) emerges as a suitable candidate for developing solutions enabling continuous and remote assessment of pain experience. However, only a few efforts have been devoted to adopting IoT-based solutions for pain assessment. In the present work, an IoT-based system for pain monitoring is proposed on the basis of a performance assessment of several communication protocols for IoT: TCP/IPv4, TCP/IPv6, UDP, MQTT, and HTTP. The peripheral blood flow and the skin’s ability to conduct electricity were chosen as the physiological parameters through which it is possible to measure pain. The capabilities of the aforementioned IoT communication protocols for transmitting the physiological data stream to a cloud server were evaluated by implementing each of those protocols and using the Wireshark protocol analyzer to compute the mean byte rate, the mean packet rate, the mean error value, and the network reliability for 1 h. Results show that the TCP/IPv4 and TCP/IPv6 protocols showed the highest packet transmission rate as well as the highest network reliability. Moreover, given the characteristics of the chosen physiological parameters, the proposed solution does not require a high transmission data rate, so there would be no limitation regarding the wireless communication protocol that could be used for implementing it. Nevertheless, a wider range of parameters needs to be considered in order to carry out a more rigorous performance assessment.

Currently, various sectors including industry, health, academia and others, are facing huge challenges regarding the fast I.T. development, and more broadly, the IoT (Internet of things). The renewable energy sector is not exempt from this new paradigm: for example, an application for monitoring the photovoltaic panel system integrated with a green roof will offer the opportunity to improve resources and energy efficiency. This requires a structured approach to integrate all the elements involved in this context; and although the established technology exists, there is not a methodology to build platforms that integrate hardware and software and can interoperate effectively. Therefore, this document presents a methodology under an enterprise architecture approach, to design and implement an IoT-based service platform for monitoring a photovoltaic system integrated with vegetation. A case study is presented where the developed concept is applied.

In the field of signal processing, for forecasting purposes, the characterization of functions is a key factor to be faced. In most of the cases, the characterization can be achieved by applying least square estimation (LSE) to polynomial functions; however, it is not fully in all cases. To contribute in this field, this article proposes a variant of artificial intelligence based on fuzzy characterization patterns initialized by Lagrange interpolators and trained with neuro-adaptive system. The aim is to minimize a cost function based on the absolute value between samples and their prediction. The proposal is applied to the characterization of cardiac PQRST complex as case study. The results show a satisfactory performance providing an error of around 1.42% compared to the normalized PQRST complex signal.

In the present article a basic design for the snake hunt in the Ecuadorian Jungle at a domestic scale is presented, minimizing the risk of bites and poisoning to the people who carry out these activities in these zones. The mechanism considers a source of autonomous solar energy supply to transform it into electrical energy. In the present work of investigation also the simulations in Matlab and their design characteristics are presented. The research process consisted of collecting data on solar radiation, temperature, through a meteorological station located in the Amazon rainforest.The exposed system does not have the purpose of exploitation on an industrial scale, which is intended to reduce the risk in the snake hunt and promote natural medicine, ancestral knowledge and maintain the cultural production of rural areas, peoples and nationalities that Throughout the times they have been developing in Ecuador.In the end, we present the results of the simulations and general design of the system for the snake hunt with the use of materials from the area and other materials that contribute to the conservation of the environment.

This paper presents a model to classify ambient sounds in an automatic and real-time way using the sound dataset provided in the Kaggle free sounds competition. For this, two data preprocessing techniques are performed, the first, length normalization that unifies the audio inputs to a single time interval and the second, property normalization that standardizes the sampling frequency and bit depth; This also includes a DNN (Deep Neural Network) capable of classifying common environmental sounds, the input for the network is formed by MFCC (Mel Frequency Cepstral Coefficients) vectors, which reduces the processing time improving the response capacity of the model for detect sounds, especially those that are considered warning signs about environmental threats, facilitating the mobility of people with hearing impairment.

Transparency International estimates that the costs of corruption in public procurement reach between 20 and 25% of the contract value, sometimes reaching 40–50%. In this study, we analyzed differentness kinds of corruption like (bribery, collusion embezzlement, misappropriation, fraud, abuse of discretion, favoritism, nepotism), and six types of Artificial Intelligence techniques (classification, regression, clustering, prediction, outlier detection, and visualization). The methodology proposed by Torres-Carrion was used, and four research questions were raised, which allow knowing the types of research carried out, the characteristics of the organizations in which the investigations are carried out, the technological tools, and data mining methodologies and techniques. The search was done in the Scopus and Web of Science databases, getting 102 articles published between 2015 and 2019. The primary data mining techniques used are logistic models, neural networks, Bayesian networks, supported vector machines, and decision trees.

The consumption of alcohol, tobacco and other drugs is considered a public health problem, being one of the main causes of academic failure of university students. The objective of this research was to identify psychosocial characteristics in clusters of alcohol, tobacco and other drug consumers. A sample of 3741 college students from Ecuador who complete a psychosocial questionnaire was used. Sparse K-means algorithm showed three clusters. Cluster CLNA1 represents students with low consume of tobacco and alcohol. Apparently, they do not have depression and are comfortable with their lives. CLNA2 presents low consume of tobacco and alcohol. This group shows signals of depression and they consider that there are aspects of their life to improve and small but significant problems of their life. CLNA3 presents the higher consume of tobacco and alcohol.

The use of genetic algorithms and techniques of big data support the decision-making of manner effective in problems, such as the variation in copper prices. Today, the price of copper and its variations represent a significant financial issue for mining companies and the Chilean government because of its high impact on the national economy. This paper reviews the forecast of volatility for the copper market over a period, which is of interest to different participants such as producers, consumers, governments and investors. To do this, we propose to apply genetic algorithms to predict the variation in copper prices, in order to improve the degree of certainty by incorporating of the inverse of the percentage of sign prediction PSP.

The research consists in the hand gestures are movements that convey information and thus complement oral communication or by themselves constitute a form of communication between people. The function of a hand gesture recognition system is to identify the type of movement, from a given set of movements, and the instant when that movement is performed. Gesture recognition systems have multiple applications including sign language translation, bionics, human-machine interaction, gamming, and virtual reality. For this reason, hand gesture recognition is a problem where many researchers have focused their attention too. In this context, in this paper, we present a systematic literature review for hand gesture recognition using ma-chine learning and infrared information. This work has been made because there is no work in the scientific literature that reviews gesture recognition systems based on machine learning and infrared information. In this work, we answer the research question: what is the architecture of the proposed models for hand gesture recognition based on machine learning and infrared information? For answering this research question, we used Kitchenham methodology. Finally, in this work, we also present trends and gaps with respect to the problem analyzed.

The present work shows the structural behavior of a bus body under frontal impact by explicit analysis of finite elements using LS Dyna software to propose a modification to the Ecuadorian Technical Regulations NTE INEN 1323. For this purpose, different tests were carried out to show the resistance to different types of Design gas proposed in national regulations. Therefore, they are reviewed national and international regulations that provide specific data to achieve this study. In addition, the results were validated by comparing a physical tensile with a computational one, where they were applied analysis criteria for the bus impact test. Convergence was obtained through results between the two tests with a calculated error of 1.89%. Finally, it has been observed that the national construction body of buses is not designed to withstand frontal impact loads.

Student dropout is a phenomenon that affects the majority of higher education institutions in Ecuador. The objective of the research was to design a predictive model to detect possible dropouts before they decide to abandon their studies. This model is based on logistic regression, and the methodology used in this research is based on the Knowledge Discovery in Databases (KDD) Model; which has five stages: selection, processing, transformation, data mining and evaluation. The application of the Logit function of the R tool for the logistic regression helps the construction of the predictive model. This model evaluates possible dropout students and leads to the conclusion that grades have a greater influence on student dropout.

The oil and gas industry assesses the tendency of mineral deposit formation based on the principle of chemical equilibrium of the fluid based on existing production data. Instead of using this approach, the present work has used artificial intelligence to develop predictions of the incrustating tendency within oil extraction pipes using physicochemical analyzes on the extracted oil, using the processing capacity of current computers and the use of artificial neural networks of deep learning with the objective of determining how reliable a prediction based on artificial intelligence can be. Simultaneously, contemporary evaluation methods require on-site inspections that mostly provide remediation measures involving the consumption of labor and financial resources. Consequently, a new method for predicting the embedded trend in pipes based on an artificial neural network using decision trees as classifiers is proposed. The neural network model is trained based on an extensive database of the characteristics of the oil and the incrustation generated in the pipeline to obtain a predictive model. Subsequently, the model generates a decision tree by selecting within the database that information relevant to the solution of the problem and excluding the rest. The results of the experimentation and simulation were satisfactorily compared, obtaining a success rate of 83,26% when evaluated with a dataset dedicated only to the validation phase. Finally, the incrustating trend detection model using decision trees proved to be an applicable technology in the field of engineering within the field of gas and oil belonging to the Ecuadorian industry.

The World Wind Energy Association (WWEA) forecasts that installed wind capacity worldwide will reach 800 GW by the end of 2021. Because wind is a random resource, both in speed and direction, the short-term forecasting of wind energy has become an important issue to be investigated. In this paper, a Systematic Literature Review (SLR) on non-parametric models and techniques for predicting short-term wind energy is presented based on four research questions related to both already applied methodologies and wind physical variables in order to determine the state of the art for the development of the research project “Artificial intelligence system for the short-term prediction of the energy production of the Villonaco wind farm”. The results indicate that artificial neural networks (ANN) and support-vector machines (SVMs) were mainly used in related studies. In addition, ANNs are highlighted in comparison with other techniques of Wind Energy Forecasting.

Consumption forecast models with their proper billing allow establishing strategies to avoid overloads in systems and penalties for high consumption. This paper presents a comparison of multivariate data prediction models that allow detecting the final monthly cost of electricity consumption in relation to the different billing parameters. As relevant results, it was obtained that the models based on decision support machines have a better sensitivity when compared with different metrics that evaluate the prediction error with training set improved by backward elimination criteria.

This paper presents implementation MLP artificial neural networks on embedded low-cost microcontrollers that can be dynamically configured on the run. The methodology starts with the training process, goes through the codification of the neural network into the microcontroller format, and finishes with the execution process of the embedded NNs. It is presented how to compute deterministically the memory space require for a certain topology, as well as the required fields to execute the neural network. The training and verification was done with Matlab and programming with a IDE Arduino compiler. The results show statistical and graphical analysis for several topologies, average execution times for various transfer function, and accuracy.

The present study contributes to the improvement of the processes of conventional agriculture that are still being carried out independently of the Information and Communication Technologies, which show shortcomings in the forms of irrigation carried out suffering an impact on the use of the water supply. From this point, precision agriculture becomes indispensable to improve the processes of agricultural production processes, allowing adequate management of agricultural plots supported by the use of technology to estimate, evaluate and understand the variations of the variables involved and offer quantities of water necessary for cultivation. This analysis covers the design and construction of an intelligent irrigation system based on fuzzy logic applied in vegetable crops. The fundamental mechanism of this system is to realize the control of irrigation through a scheme consisting of two modules, the data acquisition module, and the decision-making module. Considering that the section with the highest degree of responsibility is the integration of fuzzy logic as a control mechanism and that is part of the decision-making module. To achieve this, meteorological variables such as precipitation, temperature, the humidity of the environment and soil moisture are evaluated, which are considered as input variables for the diffuse system. The operation of the prototype is crystallized in a functional graphical interface and tested in two scenarios, where its efficiency in the proper use of the water supply is demonstrated.

This document presents the design and implementation of a videogame with the use of Deep Learning, which helps the rehabilitation of the upper limb in minor patients with hemiplegia. The video game was developed in the Unity silver-form and aims to incite the movement of the affected member, for this, the user’s avatar performs different controlled actions through the gesticulation of the said limb. System tests were performed on a patient with left hemiparesis, which is a condition of the attenuated symptomatology of hemiplegia. The Neuronal Network was trained with 800 images of open hands and 800 images of closed hands of a child with left-hemiparesis. The results showed 99% reliability in the recognition of the hand, both open and closed. In this way, the patient with hemiparesis was motivated to open and close his hand continuously to carry out the control actions required by the videogame, promoting his rehabilitation and improvement of his fine motor skills.

This research paper aims to evaluate structural damage of a building after a telluric movement occurred, by applying a heuristic-diffuse model to support the decision-making of experts in the seismic area. Ecuador is located in a highly seismic area, so it is necessary to study damage to the building structures after a telluric movement. Current damage assessment techniques are based on quantitative results, creating uncertainty. When an earthquake occurs, there is not enough certified staff, so professionals are attended without the experience to carry out the assessments and this involves the final decisions that are made not the most accurate. For the evaluation model proposed in this research, the AHP (Analytical Hierarchical Process) methodology is used in order to be able to determine the relative weights of the groups of variables that make up the building, this methodology consists of a heuristic method based on expert experience on a specific topic and in conjunction with fuzzy logic techniques will allow to work directly with the qualitative values of the data, thus providing subjective results easy to interpret that will serve as a decision-making aid. Once you have entered the data corresponding to the damage in the structural elements such as columns or beams, non-structural elements such as the facade, and data related to the type of soil, you get the levels or index of overall structural damage, non-structural and soil conditions, the level of habitability of the building is determined by applying fuzzy rules based on Mamdani’s inference.

The elastic analysis of a dynamic compression plate (DCP) used for the forearm bone fracture reduction is presented. For this propose is employed a tool based on the Boundary Element Method (BEM) and an iterative domain decomposition technique with which is possible to develop 3D models and non-homogeneous materials. The numerical results obtained for the analysis has been validated establishing a comparison with an experimental test employing a DCP made of steel 316L with real dimensions. The results demonstrate that it is possible to use the BEM for the osteosynthesis devices design.

Over the years, people tend to fail to recall different activities of everyday life, especially those that are performed less frequently. Forgetting a medical appointment, a family member’s birthday, or to take a medicine, is a common problem for many older adults. Although Information and Communication Technologies provide several options to help older adults remember activities like these, many of them could feel discouraged by not being able to properly use these tools and take full advantage of them. In other cases, elderly people may feel intimidated and even refuse to interact with technological devices. For these reasons, this paper proposes the use of a conventional object, which can be found in any home, to help older adults remember certain activities. Specifically, an ordinary chair has been selected to be employed as a device to provide the necessary reminders. The reminders implemented in the designed prototype are provided by audio, lights and vibrations, things that users do not notice at first sight the presence of technology in the chair. This prototype was evaluated through a user study with the collaboration of older adults. The results of the evaluation were positive, which concludes that the proposal has a favorable reception. Thus, this proposal could provide an important contribution to the major goal of helping to improve the quality of life of the elderly population.

It is known that the brain uses the sense of touch, in different parts of the body, to acquire information to react to the environment. With nowadays technology, it is possible to create distinct virtual environments and to feel them with haptic devices. Using haptic devices, it is possible to train and develop different parts of the human body, including the brain. These devices allow users to feel and touch virtual objects with a high realism. The present paper proposes different controller methods to use a haptic device to help the user to exercise their hands. The hand exercises proposed are the straight-line, square, circle and ellipse follow-up. In this work four different types of controllers are compared: proportional, proportional-derivative and logarithmic and sigmoid function based controllers. Each one of the used controllers were tested with the hand exercises mentioned. The sigmoid and logarithmic function based controllers achieves more suitable results for the user haptic perception and trajectory follow-up.

Human activity recognition (HAR) is important for many applications to help healthcare and support systems due to fast increase of senior population worldwide. This paper describes a human activity recognition framework based on feature selection techniques from a waist single accelerometer. The objective is to identify the most important features to recognize static and dynamic human activities based on module acceleration, since a public database. A set of time and frequency features are getting from the module, so to analyze the impact of the features on the performance of the recognition system, a ReliefF algorithm is applied. Finally, a multiclass classification model is implemented thought Support Vector Machine (SVM). Experimental results indicate that the accuracy of the propose model is over of 85%, this percentage is like other works in which use each axes accelerometer. The advantage of this work is the use of the module value that allow identify the activity independently of the sensor position, also it reduces the computer resources.

A first step in the process of automating weed removal in precision agriculture is the semantic segmentation of crops, weeds and soil. Deep learning techniques based on convolutional neural networks are successfully applied today and one of the most popular network architectures in semantic segmentation problems is U-Net. In this article, the variants in the U-Net architecture were evaluated based on the aggregation of residual and recurring blocks to improve their performance. For training and testing, a set of data available on the Internet was used, consisting of 60 multispectral images with unbalanced pixels, so techniques were applied to increase and balance the data. Experimental results show a slight increase in quality metrics compared to the classic U-Net architecture.

Among the various contexts of technological evolution, there is the application of algorithms in cameras for the detection and identification of people and their utilization in various areas, for example surveillance in smart home environments and companies. This is considered as a complex recognition task. Therein, this research presents an algorithm that was designed and implemented in Matlab, the same that through a camera allows to detect the image of a person. The objective in this investigation is to corroborate the process in the detection of the image of a person in multiple cameras through the application of an algorithm. The validation of the data obtained was carried out through a mathematical model, which allowed us to substantiate the detection of the image of a person through five cameras, considering as parameters time and distance. As a result of the study and the application of the algorithm, its functionality was verified in the positive detection of the image of a person, a mathematical model was also obtained to confirm its effectiveness and validity through different tests.

In recent years, the rescue of natural disaster victims has included the support of robotic systems to search for trapped people. However, the victims that are found by robots do not have their vital signs evaluated until the rescue team reaches their location. This can complicate matters in difficult-to-access locations and places affected by toxic waste or radiation, where the physical integrity of rescue teams is at risk. This research proposes the use of an unmanned aerial vehicle in the search for victims and performing basic triage (heart and respiratory rate measurement) through a contactless method to support rescue efforts. The main contribution is a decrease in response time in case of a search-and-rescue emergency. The system consists of navigating over a certain area designated as the disaster zone for the search of possible disaster victims that are lying on the ground. Once the victim is located, the navigation is reprogrammed to carry out the search and face recognition. Finally, by automatically selecting a skin area, the heart and respiratory rates are measured. The measurement is carried out through the photoplethysmography imaging technique, without any contact sensor. The comparison of the basic triage results with and without contact confirms to us the efficacy of the proposed method. The Bland-Altman data analysis shows a close correlation of heart and respiratory rates measured with both approaches (correlation coefficient of 0.90 for heart rate and 0.84 for respiratory rate).

Electricity losses in electric power systems are one of the main challenges for the electric power industry worldwide. Although to some extent electricity losses are inevitable, effective actions must be sought to solve this problem, to reduce both technical and non-technical losses. Consequently, this article proposes a system for measuring the caliber of power lines through the use of an unmanned aerial vehicle (UAV) and computer vision. This system will be a tool to decrease technical losses. At present, the caliber measurement is carried out subjectively. An operator or electrical technician by means of his expertise and a visual examination measures the wire gauge without a tool. This causes outdated global information systems, resulting in poor electrical planning. The proposed system focuses on flight control of the UAV, detection of objects using a mask of convolutional neural networks, distance estimation, and caliber measurement of aerial power lines without contact. The system reliability is high, with a concordance correlation (r = 0.97) between the measurements made with a manual meter and the UAV. Therefore, the proposed system improves data quality, reduces time and costs, and minimizes the risk of accidents.

This paper discusses about elements to be considered for developing a Service Robot that performs its task in a social environment. Due to the social focus of the service, not only technical considerations are demanded in order to accomplish with the task, but also the acceptance of use for the people, who interact with all of them. As our particular research topic, we establish a taxonomy to determine the framework for the development of socially-aware robot assistants for serving tasks such as deliveries. This is a general approach to be considered for any service robot being implemented in a social context. This article presents several previous cases of the implementation of service mobile robots, their analysis and the motivation of how to solve their acceptance and use by people. Therefore, under this approach it is very important not to generate false expectations about the capabilities of the robot, because as it is explained in the state of the art analysis that very high unsatisfied expectations lead to leaving the robot unused....

This paper is aimed at the use of a UAV unmanned aerial vehicle (DJI Phantom 4), and the MicaSense RedEdgeM multispectral camera, for the acquisition of multispectral transported images of the coffee variety of Castilla accessible at Hacienda Los Naranjos in The Cajibío sale located at 1760 m above sea level in the department of Cauca, the gained images were processed using an algorithm developed in the MATLAB® Software to analyze them. The developed routines accept mosaic genres of the images gained through a flight plan that is characterized by having a horizontal and lateral overlap of 75%, the images were gained between February 7 and April 25, 2019 between 11:30 am and 12:00 m, additionally the routines allowed the calculation of vegetation indices such as NDVI, NDRE, GNDVI, and GRVI. That allows us to carry out phenological monitoring in coffee crops, to estimate the vigor or the state of health of the plant.

At present, many researchers and software companies have created a number of mobile applications based on augmented reality that promote learning spaces in children, however, we find few studies where an intervention is carried out with this emerging technology in children with autism. This research sought to verify whether mobile applications can be used in teaching-learning processes in children diagnosed with ASD, the intervention was worked through a multidisciplinary team, which was attended by psychologists, computer engineers, parents and a ASD patient; A curricular strategy was established to verify whether the indicators: cognitive, procedural and communicative after the intervention with RA improve the ability to learn. The experience is described through a case study that shows encouraging results and to some extent promising on the use of new technologies to improve the quality of life of children with ASD.

It is important for farmers to know the level of chlorophyll in plants since this depends on the treatment they should give to their crops. There are two common classic methods to get chlorophyll values: from laboratory analysis and electronic devices. Both methods obtain the chlorophyll level of one sample at a time, although they can be destructive. The objective of this research is to develop a system that allows for obtaining the chlorophyll level of plants using multispectral images.Python programming language and different libraries of that language were used to develop the solution. It was implemented as an image labeling module, a simple linear regression, and a prediction module. The first module was used to create a database that relates the values of the NDVI image with those of chlorophyll, which was then used to obtain a linear regression model for the prediction system to obtain chlorophyll values from the images. The model was trained with 92 images and was obtained a root-mean-square error (RMSE) of 7.27 units CCM (Chlorophyll Content Meter). While the testing was performed using 10 values obtaining a maximum error of 15.5%.It is concluded that the system is appropriate for chlorophyll contents identification on maize leaves in field tests. However, it can also be adapted for other measurements and crops. The system can be downloaded at [1].

The growth of cities and the advancement of technology demands the development of solutions that can help and reduce emerging problems. One of these problems is the control of the population and urban planning based on population count, flow, and density analysis. This paper proposes an approach that could help cities to gather population data in a contextualized manner with the usage of localization, sensor, and weather data. It is based on a method to collect vast quantities of information and a way to validate and analyze gathered data. The data recollection is achieved through crowdsensing and smartphones. Validation and analysis are made with cloud-based image analysis and neural networks. Results show the usefulness and effectiveness of the proposed solution; also, some considerations are presented with the proposal.

This innovative proposal combines the use of the biggest reality and photogrammetry for modeling structures in digital format. It addresses two themes the use of technologies for the restoration of heritage structures in the event of a fortuitous event and the use of a technological tool that allows the dissemination of the religious cultural heritage of the Cathedral of San Pedro in Guayaquil, Ecuador to national and foreign tourists, the interest in knowing a little more about the history of culture and art is encouraged when effective conservation strategies are involved and even more by incorporating the use of technology in smart devices. This allows easy quick access with proper visualization, the use of photogrammetry technique is adopted in several museums around the world and allow tourists to learn about a specific topic in a didactic and interactive way. Another technique is the increasing reality technique, this technique incorporates data in virtual form links on the web audio video, video text or other multimedia through markers to objects serving as a tool that encourages learning more about different topics. The one chosen in this work is the religious cultural heritage. The interface developed in Unity, and the use of the Vuforia development kit, through the mobile application “My Cathedral”, allows users to access relevant historical information, visualizing the photogrammetric images in increasing reality, precisely on the most representative objects of the cathedral of San Pedro in Guayaquil.

Currently, technology opens the doors to a new generation of methodologies in the teaching of various subjects. “Serious games" are a tool that allows students to learn while playing, which has several cognitive and social benefits. Augmented reality by its sensory element becomes a tool suitable for application in serious games for young ages. This paper presents a serious game for teaching numerical place value for children up to 6 years, we called as AR-Math.

This article presents the design of a low-cost prototype mechatronic prosthesis for a leg with transfemoral amputation. The development for construction of this mechanical prosthesis is detailed in “Low Cost Mechatronics Prototype Prosthesis for Transfermoral Amputation Controlled by Myoelectric Signals” [1]. This prototype was designed and implemented with a mechanical brake of the knee and foot to help people walk. This article expands the development of this prosthesis with the implementation of the electronic part. The prosthesis is activated by signals obtained by inertial sensors (IMU), which capture the angles generated when walking (in thigh, knee and foot) allowing to reproduce the human gait cycle through a controller, based on neural networks, which permits to replicate the movement by the activation of servomotors. In addition, the prosthesis has a constant monitoring system of physiological parameters such as temperature and humidity inside the stump, which can be visualized through an application for smart devices to protect and alert about the patient’s wellness.

Robotics has undoubtedly found its way deeper into every day human tasks up to the point where now they even share workspaces with people. In this context, social robotics has increased its field of action, one important part is the advances in aspects that make up the Human-Machine Interaction. This article reports the advance that an investigation team at Universidad de las Fuerzas Armadas ESPE has done to create a test platform for Computer Vision algorithms. This approach consists of a 3-DOF articulated robotic head with anthropomorphic characteristics, considering the guidelines established by different authors for social robotics, besides it provides affordable, flexible and scalable hardware resources to facilitate the implementation, testing, analysis and development of different stereo artificial vision algorithms. The system, called Visart, is intended to work in more natural situations than independent cameras, therefore, work deeply in Human-Robot Interaction. As the first report of the Visart prototype, some basic tests with the platform were performed, they consist of face detection, facial and expression recognition, object tracking, and object distance calculation. The results obtained were consistent, opening a door for further research focusing on the comparison of more computer vision algorithms to examine their performance in real scenarios and evaluate them more naturally with our prototype for Human-Robot Interaction.

The methods and techniques of detection of the human face and facial recognition have presented a great impulse in recent years, thanks to the advance in areas such as artificial vision and machine learning. Although deep neural network techniques are in vogue, traditional techniques allow you to create applications that do not consume many resources from computing devices. In this research, we present a facial recognition system that implements the Eigenfaces method, developed in C # of Microsoft Visual Studio and open-source video processing libraries such as OpenCV as EmguCV. The application is divided into two sections: the first called register where, through an integrated camera, images of the user’s face or other means such as video and stored images are captured, and the second section is known as recognition where the user is compared with all the records of the data set, indicating whether this is registered and the recognition percentage. The project was implemented with a universe of the size of twenty-five users, of which six are men (24%) and nineteen are women (76%), developing tests for five weeks.