Advances and Applications in Computer Science, Electronics and Industrial Engineering

In the present article, an algorithm based on cellular automata for noise elimination and edge detection in grayscale images is proposed. However, the focus of this project will be on the process of identifying contours, since this represents a higher challenge at the research level. Also, the cellular automaton has an adaptive behavior, which allows it to expand when it considers that the information coming from its initial neighbors is insufficient to determine if the pixel in evaluation is a “border pixel” or not, as this is an important feature together with a set of transition rules useful to accentuate relevant details within the image. By integrating these characteristics, we find the results obtained by the Proposed Algorithm presented greater similarity compared to images with ideal borders, since the edge recovery ranges between 92.30% and 97.21%, which indicates that MEDCA is in general terms, more efficient compared to similar algorithms.

Concept maps are powerful visual tools for organizing and representing knowledge. The development of computational systems for building and managing concept maps has facilitated the creation of concept maps repositories, which can be considered valuable knowledge models. In this paper, a semantic processing method to improve a query-based approach for mining concept maps repositories is proposed. The method is based on a mechanism of semantic extension of the represented concepts in the concept maps and a set of rules for guiding the semantic integration of the conceptual structures and retrieval information processes. WordNet is used for the semantic extension of concepts, which is supported in a disambiguation algorithm. Results of experimental evaluations of the disambiguation algorithm applied to several concept maps are presented and compared with the state of the art. The application of the proposed method is illustrated through a study case with promising results.

In scenarios where capturing and efficiently managing data from heterogeneous data sources can be an advantage, the development and use of ontologies is increasingly common. In this paper, an ontology-based data management model applied to the Geographic Information System denominated SIGOBE as part of the Business Management System of the Cuban Electric Union (SIGE), is presented. The proposed data management model combines the use of a developed domain ontology (OntoSIGOBE), with an intelligent query answering process based on the case-based reasoning technic. OntoSIGOBE represents the conceptualization associated to the distribution and transmission processes of electrical energy, and the captured knowledge from the heterogeneous data sources of SIGE. OntoSIGOBE allows achieve the semantic interoperability between the data sources and the query answering process. The obtained results evidence that the proposed model provides a flexible and integrated data access in SIGOBE reaching high satisfaction to the end users.

Precision agriculture (AP) is a management strategy that uses ICT (Information and Communication Technologies) to obtain information from different sources in order to support decision-making, considering environmental and economic aspects to optimize the Farmer’s tasks and provide quality products to the costumer. The application of AP in agriculture can reduce time spent in manual activities, avoid the indiscriminate use of chemicals, increase production costs, soil deterioration and environmental pollution. Nowadays, AP is a booming area that, taking advantage of technological advances, in computer vision, heterogeneous architectures (Multicore, GPU, FGPA) and artificial intelligence techniques (Machine learning, Deep learning), has allowed to systematize a variety of agricultural activities, such as disease detection, plant counting, and identification of weed, pests and insects in different crops. This paper presents a systematic review of literature (SRL) of image analysis and processing techniques applied in precision agriculture using heterogeneous technologies. Therefore, 32 scientific articles of the last five years from four relevant bibliographic databases (Scopus, ScienceDirect, IEEE Xplore, SpringerLink) were analyzed and synthesized. The selected publications answer to four research questions proposed in this study. From the obtained results, great opportunities for image analysis (segmentation), machine learning and the use of graphic accelerators (GPU) were identified, which stand out as promising techniques and tools for the development of efficient and precise automatic systems, with the perspective to its application in real time for many agricultural tasks.

Modern education at different levels has integrated the use of technology as a teaching-learning assistant, especially in the initial stage of training because it motivates curiosity and helps the abstraction of knowledge. This paper presents the development of an educational robot using components of the Lego Mindstorms EV3 kit and a mobile app to interact with the student; the robot is build using two motors and two sensors, one to differentiate colours and the other one to measure proximity. The objective is to teach the different colours and explain the spatial position to children under five years old, while the screen of the mobile device interacts with the user. The results show the finished product, the data generated by a learning test, and a usability test, concluding that the robot fulfils its purpose, but requires certain improvements.

The ability of listening comprehension is fundamental in the learning process of any foreign language. The objective was the application of the audio-lingual method with the support of E-learning in the development of listening comprehension skills in English language teaching. The study was implemented with 58 students of English of level A2, divided equally, 29 for the experimental group where an intervention was carried out based on the method and use of E-learning, while 29 students were from the control group with a teaching traditional. The analysis of the academic performance was based on the scores obtained by the students in the diagnostic test, the mid-term exam and the final exam. The results showed that there were significant improvements in the experimental group, exceeding the control group by 1.6 points in the average scores of the final test, which demonstrates the usefulness of the method.

Nowadays, there are two important techno-social confluent phenomena: the increasing interest of citizenship to participate on the public decision-making process and the rising use of ICTs in all vital areas. For this reason, there are many participation instruments being developed and implemented using ICTs and Internet. This paper aims: to deploy a generic and flexible ICT architecture for supporting e-participation in the university and to present the results of several experiments carried out with this ICT tool. This web-based platform supports many tasks such as debate, dissemination of information, vote, clarifying issues concerning the university community, use of questionnaires, among others. The stakeholder decides how to manage each task. The use of ICTs and Internet will allow to take advantage of the necessary technical hardware in order to enhance the university processes and tasks. The experiments were carried out in the Technical University of Ambato, in four different scenarios of the decision-making process. The obtained results may be used as reference by other universities or groups needing to improve the quality of the e-participation and decision-making processes with the use of ICTs.

Tetris is a popular videogame developed by Alexey Pajinov, where the player will never win. This special feature makes it a popular reason to be used in Artificial Intelligence and Computational Intelligence techniques research to study the improvement in a game’s performance. In this work, a genetic algorithms based approach will be presented, applying it to a game engine with some of the modern Tetris’ gameplay features, where the objective is to observe the game agent performance in various test scenarios. The obtained results show the feasibility of using AI as a player in a game of Tetris.

Unmanned vehicles (UAVs) are technological tools whose application is carried out in the civil and military areas for surveillance, recognition and intelligence tasks. Given its versatility and features, in this paper the implementation of an autopilot is determined, after an analysis of commercial models. Said device must comply with technical requirements for the automatic flight control of a medium-sized UAV, considering the operation scenarios in the northern border of Ecuador. In addition, the parameters that intervene in the control loops and the relevant simulations are specified. The results obtained from the experimental flights of the aircraft are reflected in graphs, where the stability of the plant properly calibrated for autonomous flight is verified.

This document presents the development of a Proportional Integral Derivative (PID) and a Fuzzy-PID, for the control of the level of the MPS PA plant, which is constituted by industrial sensors and actuators. The mathematical model and the parameters of the system were obtained using the software the MATLAB environment using a STM32F4 card. The experimental results show the robustness of the Fuzzy PID, because it improves the response of the system and its parameters are tuned automatically according to the state of the process, thus enhancing the performance of the system. Besides, the conventional PID controller requires an adjustment of its parameters to operate in an optimal for each change of variable, and it does not respond efficiently to disturbances.

Hand gestures are a non-verbal type of communication ideally suited for Human-Machine Interaction. Nevertheless, accuracy rates and response times still are a matter of research. One unattended problem has been the difficulty and vagueness of the evaluation of the models proposed in the literature. In this paper, a protocol for evaluating recognition is proposed. A Hand Gesture Recognition system using electromyography signals (EMG) is also presented. This model works in real time, is user dependent and is based in Long Short-Term Memory Networks. The model recognizes 5 different classes (wave in, wave out, fist, open, pinch) apart from the relax state. A data set with 120 people was collected using the commercial device Myo Armband. The data set was divided 50% for tuning and 50% for testing. Following the evaluation protocol proposed, the presented model achieves a 95.79% in classification and a 88.1% in recognition accuracy. An analysis of the characteristics of this model shows the advantage over similar models and its capability for being applied in all sort of fields.

The design and implementation of a solar charge controller for lead–acid batteries is intended to supplement a component of the water purification module of the water treatment unit for natural disaster relief. This unit contains a solar panel system that supplies power to the module by charging batteries through a controller comprising an Atmega 328 processor. The solar panel feeds voltage to the batteries through fuzzy logic-based software, which allows up to 6 A DC to pass through the controller’s power circuit. Consequently, the battery was charged in less time (an average of 7 h to reach maximum capacity), wherein battery lifespan is related to the charge wave frequency. Thus, our software may be adapted in different control algorithms without having to change hardware.

Institutions of Higher Education of Ecuador for its intrinsic characteristics remain to face adverse trends anthropic events such as work accidents. Also, the location of the state in the Ring of Fire substantiates the existence of natural hazards such as earthquakes and volcanic eruptions. The management of these adverse events is done by precept, methods and resolutions previously planned; generating the tendency to confront disasters when managing identified risks is inadequate. The risks are directly influenced by the product of threats and vulnerabilities. The threat is the possibility of occurrence of an adverse event and vulnerability is a sensitive factor of a system exposed to a threat that has low resilience. Threats can only be detected, but not removed unlike the vulnerabilities, the threat detection and vulnerability reduction decrease risks in order to avoid disasters. The Huachi, Querochaca and Ingahurco campus, belong to the Technical University of Ambato, do not have an adequate system to inform the university community the need for evacuation to the occurrence of adverse events (fires, volcanic eruptions), turning this into a detected vulnerability. This project designed an electronic acoustic signaling system integrating the three campuses through a communications system. The purpose is to report immediately alert conditions for staff risk management protocols run evacuation drills and preventive actions. The system monitors and alerts locally or remotely, using a client-server architecture with Internet devices of things and Web Application Server using WebSockets.

The productivity and revenue of a company depend clearly on the correct corporate decision making and the management of productive data. Since most industries want speed and impact in their systems, the implementation of an IoT network manages to connect both field-mounted devices and sensors, as well as automated devices such as robots, which provides a considerable advantage within the planning. In this paper, two conventional IoT communication protocols are compared, such as the AMQP and CoAP, both within an automated system, making use of low-cost devices such as RaspBerry cards. The results obtained show that the CoAP protocol is designed to be so small that it fits inside a microcontroller, however, it does not provide satisfactory communication speed, but it can be fully applied in cyber-physical environments, in another aspect the AMQP protocol is more complex, there is no official support and you need bigger installation packages; but it provides a higher communication speed. In the present paper, analyze these behaviors and other questions with respect to both IoT protocols, how and why they should be implemented in an automated system.

The electromyography signals (EMG) analysis in the field of robotics has had a great impact due to its application in prosthesis and system control using electrical signals resulting from the action of muscles associated with different parts of the human body. In this article, an embedded system of hand gesture recognition based on EMG signals measured in the forearm is implemented. The EMG signals are acquired through the Myo Armband sensor and processed with a 32-bit STM microcontroller. The signals are classified with the Naïve Bayes algorithm (NB) and by recognizing an established pattern (open or closed), the system sends control signals to a robotic hand to replicate the movement. As main contribution, a comparative analysis of the performance of the embedded system is presented based on: number of samples (analysis windows), acquisition and processing times, as well as the macro and micro-evaluation of multiclass metrics (Accuracy, Precision, Recall and F-Score) for the recognition of movements.

Hand gesture recognition consists of identifying the class among a set of classes of a hand movement given. Surface electromyography (sEMG) measures the electrical activity generated by voluntary contractions of skeletal muscles. The performance of a recognition system is affected significantly by the orientation of the armband. This orientation could change every time that the user wears the armband. In this paper, a novel technique to improve the robustness in a recognition system with variation in the orientation of the armband is proposed. To test the performance of the proposed model, 4 experiments at recognizing 6 hand gestures are executed. In these experiments the proposed method shows a recognition accuracy of 92.4% versus 59.5%, which corresponds to the accuracy of a traditional recognition model without the correction of orientation.

Global competition and economic dynamism force the assembly industry to look for productive philosophies of improvement, optimizing processes, and resources. The challenge in the optimization process involves finding tools that will grant an optimal process. This article proposes a process optimization through the application of Lean Manufacturing tools, with the necessary guidelines analyzed and verified by computational simulation in a motorcycle assembler. Firstly, applying a plant distribution, together with the change of productive system, allowed the reduction of distances, elimination of unnecessary movements, and reprocessing. Then, Pull System reduced the stock of both the product in process and the final product in the warehouse, avoiding the generation of future waste and expenses due to overproduction. Finally, the use of the 5S tool entailed maintaining order and cleanliness inside the plant to facilitate the management of internal resources. In the study reported, an average reduction of 40% in assembly time and an average increase in production of 30% of all motorcycle models that were part of the study are achieved.

This research seeks through the simulation software FlexSim 2017 to model, analyze, visualize and optimize the automobile painting process in a mechanical workshop whose areas are: preparation, sanding, painting, baking, washing and storage of automobiles. The methodology used is field research, applied, qualitative and explanatory, obtaining statistical data that is analyzed through the use of software libraries such as Fluid, Time Tables, Process Flow, Expert-Fit and Experimenter. The results of Experimenter identify the bottleneck and on the basis of the simulation, productivity is improved by 27.45%, which represents the processing of another car in the sanding area. These results can be replicated to other industry workshops, achieving substantial improvements in productivity.

The research consists in the study of cutting workplaces, in order to subsequently develop an ergonomic evaluation of the workers in this area and to obtain results of the ergonomic risks associated with the work. It could be determined that the appropriate method for the ergonomic evaluation was RULA. Once these workplaces had been evaluated in the traditional way, the postural risk evaluation system was developed and programmed. This system works with the Kinect V2 sensor, specifically with the depth, skeleton tracking, and color sensors; the system determines angles and measurement points between each joint of the body, each of them referenced to the value established in the RULA evaluation matrices at certain times.

The modeling, simulation and analysis of the energy conversion equations describing the behavior of a hybrid system of wind turbine and biomass system for power generation are presented in this paper. A numerical model based on the aforementioned equations, encoded in MATLAB and the results were compared with the experimental data. The model predicted quite interesting results compared to the experimental data provided by the EMAC EP under various conditions. This study seeks to contribute to the new demands of future energy for the City of Cuenca, its possibilities for expansion according to the Territorial Planning Plan and with a vision that this electric energy be part of a reliable and growing smart grid.

A flyback source was designed together with a control study which allows its safe voltage range operation. The performance of a fractal PID type control was evaluated, starting from full conditions which allow the controller initialization considering lineal behaviors in a nominal point of operation corresponding to a case study of 2000 W flyback source. To achieve the proposed targets, a non-linear model was developed which reproduces the commuted behavior with the elements necessary to close the control loop. The use of the closed-loop controller took place by implementing an “in series” filtering strategy operated by the controller that avoids overcompensation and control hits, introduced by the fractal derivative prediction. To get a better adjustment on each of the controller effects, an individual fractal index was incorporated for each one of them. The source behavior was evaluated with and without the controller, and the performance of the entire and fractal controller was compared with the same values for the Kp, Ti and Td parameters, demonstrating that the fractal structure is able to improve the operating conditions. The evaluation was carried out with a selected set of static load, and with dynamic tests of both gradual and sudden load variation in time. The capacity of the fractal PID control to correct the deviation during the different tests was demonstrated.

Musculoskeletal injuries affect the health of workers worldwide. This research relates the repetitive movements with the generation of musculoskeletal injuries in workers of the post-harvest area of a flower company. The evaluation methodology is the OCRA check list. The symptomatology of musculoskeletal pain was evaluated applying the Nordic questionnaire. The injuries were determined comparing morbidity rates and medical records of a sample of eighteen workers in Flores del Cotopaxi S.A. The results show that there is risk due to repetitive movements in activities like classification and bunching. Statistical tests established significant incidence (p = 0.015) for chi-square and (OR = 15), Odds Ratio. In both tests a confidence level of 95% was used. In the post-harvest area exist risks as a consequence of repetitive movements linked to the generation of musculoskeletal injury, mainly in the shoulders and wrists.

Technology intervention within the field of physical rehabilitation allows to improve conventional processes and long-term results. Therefore, this research project proposes a design and implementation of an ergonomic device to exercise the upper and lower limbs of patients suffering from paraplegia, as part of their rehabilitation process. Despite attending conventional therapy sessions, the feeling of dissatisfaction is generalized by the need to complement these exercises. The general design of structure which includes the set of materials used, as well as the belt, power and control transmission systems. This design considers both weight of the structure exerted by gravity, as well as the exerted by the patient and the total dead load. In addition, the maximum stress analysis that supports the structure and the maximum deformation is carried out, taking into account that established safety factor is high. Experimental tests and surveys allow to corroborate the proper functioning and acceptance that this proposal has, given that its impact on rehabilitation process will be observed in long term.