Skip to main content
main-content
Top

About this book

This book constitutes the refereed proceedings of the 4th International Conference on Technology Trends, CITT 2018, held in Babahoyo, Ecuador, in August 2018.

The 53 revised full papers presented were carefully reviewed and selected from 204 submissions. The papers are organized in topical sections on communications; security and privacy; computer and software engineering; computational intelligence; e-government and e-participation.

Table of Contents

Frontmatter

Correction to: Perso2U: Exploration of User Emotional States to Drive Interface Adaptation

The second and third author names were removed. The name of the second and third authors were removed at the request of the corresponding author and with consent from the second and the third authors.

Julián Andrés Galindo

Communications

Frontmatter

Coalition Game Theory in Cognitive Mobile Radio Networks

In this work, the impact and performance of the Coalition Game Theory applied directly to the detection and decision stages of a Cognitive Radio (CR) system is evaluated. The performance of the Coalitional Game was analyzed in terms of the Probability of detection ( $${P_d}$$ ) and Probability of false alarm ( $${P_{fa}}$$ ) versus number of secondary users (SUs). In addition, the detection accuracy and simulation time versus SU were analyzed in a structured network adapted for WiFi and LTE technologies with cognitive parameters. The results were compared using simulation scenarios to obtain data using the theoretical Non-cooperative decision method and the theoretical Centralized decision method. The evaluated system outperformed the other methods in terms of $${P_d}$$ , $${P_{fa}}$$ , detection accuracy and simulation time.

Pablo Palacios, Carlos Saavedra

Monitoring of Small Crops for the Measurement of Environmental Factors Through the Internet of Things (IoT)

This paper shows the development of a small crop monitoring system through the measurement of environmental factors and the use of the Internet of Things (IoT). The purpose of this research article is the deployment of a system that allows the collection of data generated by environmental factors included in crop growth. Its objective is to monitor the processes in small-scale crops, as elements that ensure the food security of certain rural populations. This system allows the collection, interaction and management of the information provided by the monitored variables. The results show that the system can present complete information of controlled environmental factors.

Jorge Gomez, Alexander Fernandez, Miguel Zúñiga Sánchez

Management of SSL Certificates: Through Dynamic Link Libraries

This article describes the process of creating a dynamic-link library for SSL certificate management. The use of these libraries is usually between client-server, for communication security. The programming of a dynamic link infrastructure entails a sequence of modules for the adaptation of the requirements of a client-server system. Each module is managed by external libraries, between them the OpenSSL libraries. The proposed infrastructure uses OpenSSL libraries in client-server communication environments, resulting in interoperability between programming languages for example, Java to C/C++ migration for the creation of a secure communication environment.

Javier Vargas, Franklin Mayorga, David Guevara, H. David Martinez

IoT-Based System to Help Care for Dependent Elderly

The aging of the population in most developed countries has increased the need of proposing and adopting systems to monitor the behaviour of elder people with cognitive impairment. Home monitoring is particularly important for caregivers and relatives, who are in charge of these persons in potentially risky environments (e.g., the kitchen, the bathroom, the stairs, go out alone to the street, etc.), while they perform their household activities. On the other hand, the paradigm of Internet of Things (IoT) allows the interconnection of everyday objects to implement sophisticate, yet simple-to-use, computer systems. In this paper, we analyse the existing IoT-based proposals to monitor elder people at home. Moreover, we propose a generic design of an IoT-based home monitoring system that allows caregivers, relatives and/or emergency services to be notified of potentially risky demeanours. Finally, some scenarios or situations are presented in order to better understand the proposal, and to validate its design to cover some common use cases.

Gleiston Guerrero-Ulloa, Carlos Rodríguez-Domínguez, Miguel J. Hornos

VoIP System Dimensioning the Radio-Links and the VSAT of the MINTEL School Connectivity Project Through the TELCONET S.A. Network

Due to the constant changes that technology offers, it has allowed us to integrate various services to telecommunication networks, to improve solutions and offer advantages in connectivity and remote access to places where you do not have access to networks, problems with cellular coverage have allowed us to look for alternative ways of communication and to improve education in rural and urban areas deployed in the connectivity project between Telconet S.A. and Mintel. For which it is appropriate to design a network and to deploy a robust VoIP system through radio links guaranteeing high transmission rates, so you can expand and better the services that contribute to the development of telecommunications in Ecuador. The proposed system provides technical features that make the system more efficient and allow the incorporation of quality of service protocols that provide optimum service to the user with imperceptible latency, as well as the possibility of permanent VoIP service availability through a backup system that is part of the contingency plan allowing to have universal access to information technologies and thus to the society of knowledge.

Joffre León-Acurio, Enrique Ismael Delgado Cuadro, Luis Miguel Navarro Veliz, Miguel Botto-Tobar, Luis Isaías Bastidas Zambrano, Byron Oviedo

A Systematic Mapping Study of Specification Languages in Cloud Services Development

Specification languages offer abstractions and notations that facilitate the systematic and analytical reasoning about important aspects in a specific domain problematic. In a software engineering process domain, the usage of specification languages improve the quality and delivery time of the artefacts generated during the execution of the process activities. Cloud applications, or cloud services, are service-oriented applications whose consumption is constantly growing; however, their development require support for new roles and activities. In this work we are interested in knowing how specification languages are being used by researchers and practitioners to support the development of cloud services. This work presents a systematic mapping that provides guidance to determine the current state and to characterize the specification languages that support the service life cycle activities in a cloud services development domain.

Jorge Bermeo Conto, Miguel Zúñiga-Prieto, Lizandro Solano-Quinde

Security and Privacy

Frontmatter

Implementation and Detection of Novel Attacks to the PLC Memory of a Clean Water Supply System

Critical infrastructures such as nuclear plants and water supply systems are mainly managed through electronic control systems. Such control systems comprise of a number of elements, such as programmable logic controllers (PLC), networking devices, sensors and actuators. With the development of online and networking solutions, such control systems can be managed online. Even though network connected control systems permit users to keep up to date with system operation, it also opens the door to attackers taking advantages of such availability. In this paper, a novel attack vector for modifying PLC memory is proposed, which affects the perceived values of sensors, such as a water flow meter, or the operation of actuators, such as a pump. In addition, this attack vector can also manipulate control variables located in the PLC working memory, reprogramming decision making rules. To show the impact of the attacks in a real scenario, a model of a clean water supply system is implemented on a Festo MPA rig. The results show that the attacks on the PLC memory can have a significant detrimental effect on control system operations. Further, a mechanism of detecting such attacks on the PLC memory is proposed based on monitoring energy consumption and electrical signals using current-measurement sensors. The results show the successful implementation of the novel PLC attacks as well as the feasibility of detecting such attacks.

Andres Robles-Durazno, Naghmeh Moradpoor, James McWhinnie, Gordon Russell, Inaki Maneru-Marin

Vulnerabilities in Banking Transactions with Mobile Devices Android: A Systematic Literature Review

This qualitative systematic literature review (SLR) corresponds to the search for vulnerabilities in banking transactions by means of ANDROID Intelligent mobile devices and the incidents in the users. In these devices there is leaking information that is captured by hackers and with it the dissatisfaction of users to ignore how to treat these insecurities. For this, initially of between 123 studies, 18 were selected according to the search criteria corresponding to the research questions in vulnerability and incidence, it was mainly found the bank Phishing, the injections of malware in mobile applications and to a large extent victims of bank fraud.

Pablo F. Ordoñez-Ordoñez, Domingo D. Herrera-Loaiza, Roberth Figueroa-Diaz

Computer and Software Engineering

Frontmatter

Towards a Merged Interaction Design Pattern Focused on University Prospective Students: Results from a Pretest–Posttest Intervention Study

Usability in the software arena is a hot topic that has attracted the attention of researchers. Usability has been studied in different application contexts. In the context of Higher Education Institutions, some usability aspects have started to be incorporated into university websites. In this work, we present a merged interaction design pattern oriented to improve the usability experience of prospective students. The assessment of the pattern was done through a pretest-posttest intervention study, using a sample of 266 prospective students. Our results suggest that the use of an interaction design pattern has significantly improved the usability experience of the participants in this study.

Shirley M. Martínez, Omar S. Gómez

Gesture-Based Children Computer Interaction for Inclusive Education: A Systematic Literature Review

Gestural interfaces are closely related with cognition and physical activity, and can be powerful tools for cognitive training and motor skills. Their use has been proposed by researchers in various areas, including education, and within this field, inclusive education. In this study, a systematic literature review about children computer gestural interactions (touch, body, face and motion) and on its application to digital educational resources for learning disabilities has been conducted. Applying the Torres-Carrión method, a “conceptual mindfact” and research problem has been structured, as a basis to build the search script, to be applied in the selected scientific databases (Scopus, WoS and Google Scholar). Five research questions are proposed, which involves standards of gesture-based computer interaction for children, design guides, methods and instruments, non-invasive interaction environments and personalization of didactic resources for children with special needs, in particular children with Down’ syndrome. As a final product, a list of relevant magazines and databases of the area has been obtained; 47 valid papers were analyzed to answer the research questions, and they are organized in a structured way, allowing the researcher to establish a valid context from which to focus future research.

Pablo Torres-Carrión, Carina González-González, César Bernal-Bravo, Alfonso Infante-Moro

Portability Approaches for Business Web Applications to Mobile Devices: A Systematic Mapping

Applications on mobile devices have had an exponential grow; however, there are business legacies 1.0 that have not migrated or have not been adapted due to the operating or economic cost involved in the required migration. The companies are not often aware of the benefits the mobile applications have to generate new business models. This paper aims to study the different approaches used in the portability of web applications 1.0 to mobile devices in the last decade, in order to identify the edges and perspectives of the area. A systematic mapping is carried out on the main databases in the area, such as SCOPUS, IEEE, and ACM. 44 articles are selected from 824 initials and are classified with respect to the approach, the type of research and contribution. This systematic review shows that while the technical achievements on the mobile development have been outstanding, there are still many issues to be solved for migrating Web applications.

Viviana Cajas, Matías Urbieta, Yves Rybarczyk, Gustavo Rossi, César Guevara

Design of an Augmented Reality Serious Game for Children with Dyscalculia: A Case Study

Numeracy skills are essential in the modern world. However, many children experience difficulties in learning mathematics. This disorder is known as Dyscalculia, and it has a negative impact on the children affected by it. The students might find difficult to work with numbers, mental calculations and mathematical functions and symbols. From this context, several studies agree using Serious Games as an assistive mechanism in therapies can improve the students’ motivation, motor skills, and mathematical abilities. This article presents the design and a prototype of the Augmented Reality Serious Game named ATHYNOS for children with Dyscalculia. In the case study, forty children aged between 7–9 years with difficulties in learning mathematics from private and public primary schools, completed 4 weeks of computer game training for 15 min per day, twice a week. Results shown that children took significantly advantage from the training regarding basic numeracy, sequential order and mathematical reasoning, this game allows flexible adaptation to children’s learning.

Diego Fernando Avila-Pesantez, Leticia Azucena Vaca-Cardenas, Rosa Delgadillo Avila, Nelly Padilla Padilla, Luis A. Rivera

Software Estimation: Benchmarking Between COCOMO II and SCOPE

This article presents the result of a comparative study that best determines the most useful software assessment tool applicable to software development costs. This study was applied to Systems Engineering faculty students and teachers from Técnica del Norte University as well as to IT companies’ end users. This research work carried out defined quantitative parameters, reflected on aspects regarding supplies, friendly user tools, methodologies, in addition to documentation and data language contained. These features were incorporated in a survey that allowed us to analyze the opinions and preferences of the respondents. The tools selected to carry out this process were SCOPE at a private environment and COCOMO II at a free environment. The results of this research showed that the best option for a software assessment tool applied to software development costs is COCOMO II with 83.33% over 75% of SCOPE.

Cathy Guevara-Vega, Andrea Basantes-Andrade, Joseph Guerrero-Pasquel, Antonio Quiña-Mera

Proactive Approach to Revenue Assurance in Integrated Project Management

In project management organizations, it is advisable to conduct a proactive and positive management to improve the implementation of processes. Moving forward in a project without a proactive approach to risk management is likely to lead to a greater number of problems and income leaks, because of unmanaged threats. Revenue assurance allows to reduce costs and maximize the income in organizations, for them it applies statistical techniques, risk management, scope, and time. The objective of this work is to present a proactive approach for revenue assurance that is applied in Integrated Project Management. Risk management is developed with a proactive approach, based on the application of PMBOK and computing with words techniques for planning and qualitative risk assessment. For validation, the proposal is applied in a real environment, using data from concluded projects, criteria of multiple experts and soft computing techniques. A final analysis is carried out that shows the great advantages of the proposal with respect to the results obtained with the traditional PMBOK technique. The proposed method is integrating into a platform for project management that support decision-making in organizations and have many functionalities for revenue assurance.

Gilberto F. Castro, Anié Bermudez-Peña, Francisco G. Palacios, Fausto R. Orozco, Diana J. Espinoza, Inelda A. Martillo

User-Centered-Design of a UI for Mobile Banking Applications

A rapid increase in the number of smartphone users and wireless internet subscribers has brought about a digital revolution. Today, mobile devices serve not only as a medium of voice communication, but are also used to streamline daily activities. For instance, mobile banking allows clients to conduct financial transactions remotely using a mobile device such as a smartphone or tablet. As the influence of mobile technology continues to grow, financial institutions need to develop applications that guarantee customer usability. Ergo, there is a need to explore the role user interface design plays in enhancing the usability of a mobile application. This document describes the design and evaluation processes of the user interface of a mobile banking application that provides three functions: payments, balance inquiries and transfers. An experiment is carried out to test two different user interface prototypes. The prototypes differ in the implementation of Nielsen heuristics’ for user interface design. Prototype A is designed empirically, whereas prototype B is based on the application of Nielsen’s rules. Usability tests results demonstrate that credit union customers appraise the user interface designed according to the heuristics as more usable than the empirical one.

Diana Minda Gilces, Rubén Fuentes Díaz

How to Govern VSE Teams: Experiences Through a Model and Case Study

The software development organizations need an understanding of the governance process and their practical approach to reach their strategic goals, a subject where there is a research opportunity. This study proposes a model type artifact to govern Very Small Entities (VSE) Teams for Software Development. The model design is based on COBIT 5 and IT governance best practices, with structural and dynamic governance components. The validation is done through the model application, in a case study, in a Public Sector Organization, using a SCRUM software process. The model application allows the appropriate responses to the software development needs and facilitate the solution of the problems in the project development. Besides, a survey shows that in a developing country, the model applicability can be generalizable. Thus, the study tests a tool for the practitioners and academics and contributes to the growth of the current knowledge concerning the Software Development Governance.

René Arévalo, Carlos Montenegro

Maturity Level of Software Development Processes in SMEs Guayaquil

The software process improvement has gained a lot of space in recent years; the Software Engineering community has developed models that improve the software process. Knowing the reality of software development companies is fundamental for the application of some process improvement model. In the case of SMEs, due to lack of resources, this improvement may be unattainable. In this document, we present an analysis of the processes and activities that are considered by the CMMI process improvement models, Competisoft and ISO/IEC 29110. The aspects that must be fulfilled are established within the different activities that correspond to two processes: planning/management of the project and development/implementation of software; the instrument was designed and 10 SME software developers were evaluated. The results obtained indicate that the companies surveyed do not comply with all the aspects required to complete the initial level of a process improvement model.

Vanessa Jurado Vite, Shirley Coque Villegas, Guillermo Pizarro Vásquez

Integration and Evaluation of Social Networks in Virtual Learning Environments: A Case Study

Higher education institutions objective is to establish a quality learning process in which faculty members and students may use the most suitable digital communication channel. In this context, this study’s intention is to integrate and evaluate the social networks Twitter and Facebook in the Virtual Learning Environment (VLE). The study was conducted in a Technological Institute (ITSI) to determine the level of impact virtual communication has on faculty and students. In order to accomplish this goal, a Moodle platform was implemented with the following services: (i) user authentication (ii) cloud storage and file sharing and (iii) Twitter extension for message replication processes from VLE-ITSI to social networks. The proposal evaluation was performed using (i) usability and satisfaction metrics set up by the ISO/IEC 9126 standard and (ii) through a statistical analysis. The results from the standard application and the Wilcoxon statistical testing proved that social networks integration with the VLE-ITSI significantly contribute to faculty-student digital interaction during educational processes.

Alexandra Juma, José Rodríguez, Jorge Caraguay, Miguel Naranjo, Antonio Quiña-Mera, Iván García-Santillán

Towards the Implementation of a Software Platform Based on BPMN and TDABC for Strategic Management

The strategic management of resources and processes has become a key element to enable industries to achieve their goals of minimising costs and maximising profits. Business Process Management (BPM) and Time-Driven Activity-Based Costing (TDABC) are two important tools that allow business managers to identify both activities performed and resources used within a company. Therefore, taking advantage of the integration of these tools may result in a deeper analysis of the state of a company. This paper presents the development of a platform for integrating Business Process Management Notation (BPMN), to represent and store process flows, and TDABC, to obtain an estimation of their associated costs. To achieve this aim, the study reviews some methodologies used for modelling costing-oriented processes and for estimating process costs. The resulting software is a tool to support the first three phases of the BPM lifecycle, i.e., process identification, discovery and analysis, and the TDABC calculations.

Erik Sigcha, Villie Morocho, Lorena Siguenza-Guzman

Calyx and Stem Discrimination for Apple Quality Control Using Hyperspectral Imaging

The production of high-quality food products needs an efficient method to detect defects in food, this is particularly true in the production of apples. Hyperspectral image processing is a popular technique to carry out this detection. However, the stem and calyx of the apple provoke frequent detection errors. We analyze the spectrum of our apple data set, propose an algorithm that uses the average of the principal components of two regions of the spectrum to identify the defects, and couple this detection routine with a two-band ratio that discriminates the calyx and stem. Our study considers the spectral range between 403 nm and 998 nm. Our results include the detection of scab, bruise, crack, and cut with and without stem and calyx. We describe all the necessary parameters provided by our spectral analysis. Our algorithm has an overall accuracy of 95%. We conclude that our algorithm effectively detects defects in the presence of stem and calyx.

Israel Pineda, Nur Alam MD, Oubong Gwun

Perso2U: Exploration of User Emotional States to Drive Interface Adaptation

Taking into account dynamic user properties such as emotions for interfaces adaptation at runtime is a challenging task. To deal with this issue, we propose to personalize user interfaces at runtime based on user’s emotions. This approach depends on emotion recognition tools to allow an Inferring Engine to deduce user emotions during the interaction. However, this inference releases many emotions without aggregating them. It makes more difficult the interpretation of user experience. Thus, we explore the feasibility of inferring similar emotional states (negative, positive and neutral) by grouping individual emotions. To achieve our goal, this paper reports on the results of an experiment to compare detected emotional states from different face recognition tools in web interaction. It evidences that it is feasible to infer similar emotion states (positive, negative, and neutral) from different emotion recognition tools, and the level of this similarity is still premature to have a robust categorization.

Julián Andrés Galindo

Mobile Based Approach for Accident Reporting

When facing car accidents a lot of people are not prepared to respond or provide first aids to injured passengers. This paper presents the architecture and operation of a mobile tool equipped with a panic button to notify the situation to relatives of injured people in traffic accidents. The application has the necessary information to allow any passerby to be the first person to assist in this situation. The application provides critical information to enable a passerby to display relevant patient clinical information such as blood type, allergies, etc. With the panic button, a passerby can know victim information such as allergic reactions. The construction of the application follows the guidelines of the design science methodology, which consists in considering the research as base for creating the final product. In addition, the results of acceptance technology were measured with the Technology Acceptance Model that allows evaluating the perceived usefulness and ease of use. Finally, possible improvements for the mobile application are presented.

Luis Wanumen, Judy Moreno, Hector Florez

Systematic Mapping Study of Architectural Trends in Latin America

Software architecture has become an important aspect on systems development; however, despite the fact that there are several architectures that are already popular in the computer world, they do not seem to fully meet the demands of the developer due to the fact that system requirements are becoming increasingly stringent. This paper aims to carry out a systematic mapping study that allows publicizing the different architectures used in research accomplished in Latin America. For the study, numerous articles searches were executed in different bibliographic databases from acknowledged scientific journals, where several articles were obtained and through filters a total of 10 articles were obtained with which this project was worked on. Applying the systematic mapping process, a series of analyses were carried out on the selected scientific articles that allowed a detailed study of the investigations, which led to a varied collection of data that determined the focus of the studies when applying architecture to their systems. The final results of this work show that the scientific articles analyzed are focused on proposing new architectures based on existing ones.

Diana Alomoto, Andrés Carrera, Gustavo Navas

Augmented Reality as a Methodology to Development of Learning in Programming

Learning programming is a complicated task and there is a high rate of students’ failure or desertion. It requires the student to think abstractly and acquire a high level of affinity and discipline. It requires the student to think abstractly and acuire a high level of affinity as well as discipline. The basis is to find studies based on the development of tools for learning programming, which attract a high level of students’ attention. The purpose is to carry out an analysis of the main characteristics, advantages and disadvantages of augmented reality as a learning methodology for programming, as well as the tools necessary for its development. After the review, we have found different types of applications which purpose range from business applications, maintenance support and equipment assembly to the development of kinesthetic skills. Regarding the support in learning, this is applied in different areas of study, with very few results in programming. It is intended to make a proposal of an augmented reality model for learning programming. Its high potential in education serves as support for pedagogical activities and the development of cognitive skills. However, there are still problems, such as the dependence of a device with a camera and special capabilities that support its proper functioning. Another impediment is that; the use of technology can be a cause of distraction when teaching a class. Nevertheless, all this with the advance of technology and research related to the subject of study, can certainly be overcome.

Mónica Daniela Gómez Rios, Maximiliano Paredes Velasco

Analyzing Mid-Air Hand Gestures to Confirm Selections on Displays

The use of applications based on mid-air gestures has been increasing during last years, but there are still challenges to be addressed. One of them is the type of hand gestures that should be employed in specific scenarios and/or tasks. A particular case is the selection of an item on a display or surface, with the following confirmation of that selection. Thought several gestures have been proposed to confirm a selection, user interface designers should know the differences between them to make an appropriate decision. Therefore, we analyzed a set of confirmation hand gestures using performance metrics and subjective measures to make comparisons between the chosen gestures. According to our results, all the studied gestures can be perceived to be intuitive, but hover was the best gesture for confirming a selection. The reported findings should help designers to make distinctions between confirmation gestures and made decisions according to the desired scenarios.

Orlando Erazo, Ariosto Vicuña, Roberto Pico, Byron Oviedo

Educational Software Development in Ecuadorian Universities: A Systematic Mapping Study

Context: Ecuadorian universities to guarantee a quality higher education, contribute to the country’s growth and train student researchers, allow to develop undergraduate theses as final career work to obtain their professional degree. Objective: In this paper, we present a systematic mapping study of the educational software development in the undergraduate theses done in Ecuadorian universities. Method: A systematic mapping study was conducted with a set of six research questions to analyze the undergraduate theses considered as the primary studies, dated from 2000 to 2017. Results: From a total of 522 undergraduate theses retrieved by an initial search string, 42 undergraduate theses were selected. This research classifies, quantifies, and qualifies the educational software development that has contributed to the education of Ecuador. We observe that 54,76% of the software developed is applied in elementary education, most of them are the tutorial type, and the pedagogical objective that has been mostly covered is to improve teaching-learning. Conclusions: Although universities are interested in developing educational software, there is a declining interest in the last two years analyzed. Also, it is necessary to develop educational software that covers other little attended pedagogical areas.

Jessica Guerra-Gaibor, Angel Cuenca-Ortega, Mariela Tapia-León

Computational Intelligence

Frontmatter

A Real-Time Method to Remotely Detect a Target Based on Color Average and Deviation

This paper presents a new semiautomatic method to remotely segment a target in real-time. The aim is to obtain a fast distinction and detection based on RGB color space analysis. Firstly, a pixel of the desired target manually is selected and evaluated based on weighing different surrounding areas of interest (Ai). Later, statistical measures, identification of deviation parameters and the subsequent assignation of identifiers (ID’s) that are obtained from the color information of each region Ai. The performance of the algorithm is evaluated based on segmentation quality and computation time. These tests have been performed using databases as well in real-time and accessed in remote way (distance from the control-site 8.828.12 km) to prove the robustness of the algorithm. The results revealed that the proposed method performs efficiently in tasks as; objects detection in forested areas with high density (jungle images), segmentation in images with few color contrasts, segmentation in cases of partial occlusions, images with low light conditions and crowded scenes. Lastly, the results show a considerable decrease of the processing time and a more accurate detection of a specific target in relation with other methods proposed in literature.

Henry Cruz, Juan Meneses, Gustavo Andrade-Miranda

A Hybrid Approach of Recommendation via Extended Matrix Based on Collaborative Filtering with Demographics Information

In view of the growth in the use of methods based on matrix factorization, this research proposes an hybrid approach of recommendation based on collaborative filtering techniques, which exploits demographic information of the user and item within the factorization process, considering an extended rating matrix in order to generate more accurate prediction. In this paper we present an approach of collaborative filtering that is at least as accurate as the biased matrix factorization models or better than them in terms of precision and recall metrics. Several experiments involving different settings of the proposed approach show predictions of improved quality when extended matrix is used. The model is evaluated on three open datasets that contain demographic information and apply metrics to measure the performance of the proposed approach. Additionally, the results are compared with the traditional bias-based factorization model. The results showed a more expressive precision and recall than the model without demographic data.

Priscila Valdiviezo-Díaz, Jesus Bobadilla

Simple Bayesian Classifier Applied to Learning

In this article, we propose the use of a new simple Bayesian classifier (SBND) that quickly learns a Markov boundary of the class variable and a network structure relating class variables and the said boundary. This model is compared with other Bayesian classifiers, then experimental tests are carried out for which 31 well-known ICU databases and two bases of artificial variables have been used. With these databases we compare the results obtained by such algorithms studied in the state of the art such as Naive Bayes, TAN, BAN, RPDag, CRPDag, SBND and combinations with different metrics such as K2, BIC, Akaike, BDEu. The experimental work was done in Elvira software.

Byron Oviedo, Cristian Zambrano-Vega, Joffre León-Acurio, Alina Martinez

An Overview of Multiple Sequence Alignment Methods Applied to Transmembrane Proteins

Transmembrane proteins (TMPs) have received a great deal of attention playing a fundamental role in cell biology and are considered to constitute around 30% of proteins at genomic scale. Multiple Sequence Alignment (MSA) problem has been studied for some years and researchers have proposed many heuristic and stochastic techniques tailored for sequences of soluble proteins, considering that there are a few particular differences that ought to be taken into consideration aligning TMPs sequences, these techniques are therefore not optimal to align this special class of proteins. There is a small number of MSA methods applied specifically to TMPs. In this review, we have summarized the features, implementations and performance results of three MSA methods applied to TMPs: PRALINE $$^\mathrm{TM}$$ , TM-Coffee and TM-Aligner. These methods have illustrated impressive advances in the accuracy and computational efforts aligning TMPs sequences.

Cristian Zambrano-Vega, Byron Oviedo, Ronald Villamar-Torres, Miguel Botto-Tobar, Marcos Barros-Rodríguez

Detection of Desertion Patterns in University Students Using Data Mining Techniques: A Case Study

Student desertion is a phenomenon that affects higher education and academic quality standards. Several causes can lead to this issue, the academic factor being a potential reason. The main objective of this research is to detect dropout patterns in the “Técnica del Norte” University (Ecuador), based on personal and academic historical data, using predictive classification techniques in data mining. The KDD (Knowledge Discovery in Databases) process was used to determine desertion patterns focused on two approaches: (i) Bayesian, and (ii) Decision Trees, both implemented on Weka. The classifiers performance was quantitatively evaluated using the confusion matrix and quality metrics. The results proved that the technique based on decision trees had slightly better performance than the Bayesian approach on the processed data.

Dayana Vila, Saúl Cisneros, Pedro Granda, Cosme Ortega, Miguel Posso-Yépez, Iván García-Santillán

An Evolutionary Intelligent Approach for the LTI Systems Identification in Continuous Time

Identification and modeling of systems are the first stage for development and design of controllers. For this purpose, as an alternative to conventional modeling approaches we propose using two methods of evolutionary computing: Genetic Algorithms (GA) and Particle Swarm Optimization (PSO to create an algorithm for modeling Linear Time Invariant (LTI) systems of different types. Integral Square Error (ISE) is the objective function to minimize, which is calculated between the outputs of the real system and the model. Unlike other works, the algorithms make a search of the most approximate model based on four of the most common ones found in industrial processes: systems of first order, first order plus time delay, second order and inverse response. The estimated models by our algorithms are compared with the obtained by other analytical and heuristic methods, in order to validate the results of our approach.

Luis Morales, Oscar Camacho, Danilo Chávez, José Aguilar

Geographical Information System Based on Artificial Intelligence Techniques

The Electrical Union in Cuba develops the Business Management System of the Electrical Union (SIGE) that focuses on the automation of electrical processes. The geographic information systems (SIGOBE) developed don’t meet the specific requirements for their generalization due to their limited updating facilities and the small spectrum they cover. The general objective of the research is: to develop the geographic information system of the transmission and distribution processes in the Electric Union, with the use of artificial intelligence techniques, on a deep conceptual scheme of the domain, that responds to the requests of consultation of users as support for decision making. A case-based system on type problem solved was designed, using as an initial case database, the 265 static queries registered in SIGERE. The queries are described by eight data-type predictive traits and three objective traits. The similarity between two cases was determined by the weighted sum of the distance of their traits and the calculation of the distance between traits was done according to its nature. An intelligent real-time queries system was implemented for the SIGOBE, achieving the generation of automatic queries that allow the system to respond to any type of queries in real-time. The experimental study shows the feasibility of the proposal.

Nayi Sánchez Fleitas, Raúl Comas Rodríguez, María Matilde García Lorenzo, Frankz Carrera

Classification Models Applied to Uncertain Data

In the field of learning models, the quality directly depends on the training data. That is the reason why data preparation is one of the stages in the knowledge extraction process where more time is invested. In fact, the most common scenario consists in a training created under perfect conditions. However, the situation is often entirely different during the model deployment phase, since, in the real world, data usually contain noise, there may be missing or incorrect values, or even be uncertain, in the sense that we do not know their exact value, but have an approximate knowledge of its value. In this paper, we will study how to apply the learning models to uncertain data. Specifically, we will focus on classification problems in which uncertainty is only present in numerical attributes and present a new approach to apply classification learned models. Experimental results show that the accuracy achieved by our methods improve the case of having maximum uncertainty.Random Forest has a 3.60% control of uncertainty when its maximum value is achieved. Also, there is a higher level of degradation of 5.59% and 9.60% for both Decision Trees and Naive Bayes.

Yandry Quiroz, Willian Zamora, Alex Santamaria-Philco, Elsa Vera, Patricia Quiroz-Palma

Data Scientist: A Systematic Review of the Literature

The commercial activities of services and production have accumulated plenty of data throughout the years, hence today’s necessity of a professional agent to interpret data, generates information in order to produce valuable results and conclusions. The scope of the current article is to present a systematic review of the literature which main goal was to spot the work and career profile of the so called Data Scientist; realizing that, as a new work field, there are not concretely defined profiles, although knowledge areas are indeed defined, as well as characteristics that are needed to be counted, apart from some technologies that can serve as supporting means for the labor these new technicians do in the IT (Information Technology) area.

Marcos Antonio Espinoza Mina, Doris Del Pilar Gallegos Barzola

Fault-Tolerant Model Based on Fuzzy Control for Mobile Devices

Nowadays, mobile devices incorporate many sensors to monitor operational parameters, so that possible failures in the systems can be detected and prevented. Therefore, failure detection has become crucial to ensure the automation of certain applications, such as, health monitoring or unmanned aerial vehicles. On the other side, fuzzy models perfectly fit when the input-output relationships use categorical values and they are not deterministic. However, find a feasible model is not a trivial task due to the interaction of many variables at time. In this work, we propose a fault detection model based on fuzzy logic to early detect potential fault in mobile devices. Our approach considers the interaction of four variables, all of them could be measured from sensors of the device. As a proof of concept, we have tested our model in a simulated scenario with random values taken from all the possible combinations of the input fuzzy sets. The mapping into the fuzzy output called, risk of fault, shows accordance with the expected values in literature. Finally, results show that our model can distinguish four levels of failure risk and it is able to be implemented in a production environment.

Diego Vallejo-Huanga, Julio Proaño, Paulina Morillo, Holger Ortega

Monitoring for the Evaluation Process On-Line Prototype Based on OpenFace Algorithm

This project was designed to present a prototype of facial authentication system that allows for the recognition of students who are using an online platform to take final evaluations in our Distance Learning Program, with the purpose of detecting fraud and identity theft. It uses the OpenFace algorithm based on neural networks, taking input from two-dimensional images of the student from time to time during the participation on the exam. We present a system for face recognition using an image database of faces in classroom setting to demonstrate the improvement using this OpenFace algorithm for the preprocessing approach. The preliminary results indicate a high accuracy in the recognition of students, in terms of brightness, size and quality of the image of the face.

Omar Ruiz-Vivanco, Alexandra Gonzalez-Eras, Jorge Cordero, Luis Barba-Guaman

Application of Data Mining for the Detection of Variables that Cause University Desertion

College desertion is one of the problems currently addressed by most higher education institutions throughout Latin America. From different investigations, it is known that a large percentage of students do not complete their studies, with the consequent social cost associated with this phenomenon. Some countries have begun to design deep improvement processes to increase retention in the first years of university studies. The process considered for the improvement of the desertion is through the data mining, the use of its algorithms allows discovering patterns in the students that help to explain this effect. The algorithms also identify the independent variables that influence the desertion and analyze them according to a level of depth previously established by the interested parties. The purpose of this study is to determine a model that explains the desertion of undergraduate students at the university and design actions that tend towards the decrease of the desertion.

X. Palacios-Pacheco, W. Villegas-Ch, Sergio Luján-Mora

Mobile Biometric Authentication by Face Recognition for Attendance Management Software

In this paper we present bioFACE, a novel mobile application for the biometric authentication by face recognition of the users of the attendance management software provided by the Human Resources department of the State Technical University of Quevedo. This application converts the smartphones in a biometric device that allows register the workday entries and workday exits from any place inside of the university campus. The user-location is validated by the GPS coordinates using the Android Geofence API and the biometric authentication of the users (employees and professors) is carried out by face recognition performed by Microsoft Face API features.

Cristian Zambrano-Vega, Byron Oviedo, Jorge Chiquito Mindiola, Jacob Reyes Baque, Oscar Moncayo Carreño

Computer Aided Diagnosis of Gastrointestinal Diseases Based on Iridology

Gastrointestinal diseases are important causes of mortality and expenses around the world. Since conventional methods for diagnosing gastrointestinal problems are expensive and invasive, alternative medicine techniques emerge as a possibility for helping physicians in this type of diagnosis. Hence, this work proposes a computer aided diagnosis system based on iridology for early detection of gastrointestinal diseases. The proposed system employs image processing and machine learning algorithms to identify gastrointestinal disorders in iris images. The evaluation of the system uses 100 iris images showing a maximum accuracy of 96% and a predictive capacity of 99%. This work shows that alternative medicine techniques have potential for diagnosing problems associated to gastrointestinal disorders.

Enrique V. Carrera, Jennifer Maya

Method for the Automated Generation of a Forest Non Forest Map with LANDSAT 8 Imagery by Using Artificial Neural Networks and the Identification of Pure Class Pixels

In this work, a methodology for the automated classification of Landsat 8 images from the integration of Artificial Neural Networks and the identification of pixels of pure classes is presented. The exercise carried out in this research by using the SEPAL platform, allowed to obtain a mosaic L8 of the study area, fully preprocessed and calibrated, and it was generated automatically in a short period of time. This result represents a significant advance in terms of preprocessing capacity that currently exists for the management of satellite data compared to the state of the area a decade ago. This relevant advance has been possible due to the use of artificial neural networks and the cross-correlation coefficient of the pixels of the Landsat 8 satellite platform images. Their use and differentiation of areas in remote sensing of wooded, agricultural and water areas are discussed.

Juan-Carlos Tituana, Cindy-Pamela Lopez, Sang Guun Yoo

A Computer Aided Diagnosis System for Skin Cancer Detection

Melanoma is the deadliest form of skin cancer, accounting for about 75% of deaths related to this type of disease. Fortunately, melanoma early detection can increase the survival rate of victims considering that melanoma skin cancer is often visible to patients and physicians. However, recommended self-examinations or physician-directed exams are not significantly reducing melanoma deadly cases due to the absence of knowledge of the patients or the lack of access to well-trained physicians. Based on that, this paper proposes a computer aided diagnosis system that detects melanoma skin cancer using dermatoscopy images, image processing techniques, and machine learning algorithms. Our main goal is to create a cheap, relatively accurate, and easy-to-use system available as an initial procedure to detect melanomas. The evaluation of the designed system using 748 dermatoscopy images shows sensitivities around 98%, when a simple feature-extraction stage is applied and a classifier based on support vector machines is utilized.

Enrique V. Carrera, David Ron-Domínguez

Modeling 911 Emergency Events in Cuenca-Ecuador Using Geo-Spatial Data

We present several techniques for modeling emergency events using data from 911 emergency calls in the city of Cuenca-Ecuador. We apply three types of models. First, we use a probabilistic description of events using Gaussian kernels based on both, regular segmentation and mixture models, to represent the spatial distribution of occurrences. Second, we verify the qualitative relation of the clusters obtained with our kernel model with respect to the geo-political organization of the city. Finally, we develop an emergency model using a large dataset corresponding to the period January 1st 2015 through December 31st 2016 and test various data mining algorithms for prediction purposes. We verify the usefulness of our approach experimentally.

Pablo Robles, Andrés Tello, Miguel Zúñiga-Prieto, Lizandro Solano-Quinde

Optimization of the Network of Urban Solid Waste Containers: A Case Study

This paper presents the results of the optimization of the urban solid waste container network in the urban sector of the Ibarra City, Ecuador by the implementation of an optimization model, which consists of a multi-objective mixed integer programming model which has been successfully used in the context of recycling in past studies. This model was modified so that possible locations of the containers at each corner of the blocks containing the constructed buildings were considered. As well, a restriction to count the containers to be installed was added. Furthermore, to add robustness to the model, it was also considered the filling of the container based on the density of the deposited waste and the model objective functions – being, a weighted sum of the cost of the installation of the network along with the average walking distance between users and the assigned containers. The outputs of the model are the total number of containers and a map with the optimal locations of municipal solid waste containers for Ibarra city. The model was implemented in GAMS platform wherein parameters can be permanently revised so that the results may be updated in case of variations of the initial conditions.

Israel D. Herrera-Granda, Wilson G. Imbaquingo-Usiña, Leandro L. Lorente-Leyva, Erick P. Herrera-Granda, Diego H. Peluffo-Ordóñez, Diego G. Rossit

Inductive Machine Learning with Image Processing for Objects Detection of a Robotic Arm with Raspberry PI

Goals. The present study was designed to build a prototyping and develop algorithms that allow the detection, classification, and movement of objects of a robotic arm of 4 DOF with the following technologies: ArmUno arm structure, Raspberry Pi 3 B+, PiCam 2.1, driver PCA9685 for servomotors, Opencv3, and python. Another goal was to measure the effectiveness of prediction and classification of objects photographed by the robotic arm, using machine learning with the KNN classifier method.Methodology. The generation of a dataset of 800 photographic images was proposed, in 4 categories: volumetric geometric shapes conformed by 200 images each one of them. With this, processing techniques were applied to the image captured by the camera to detect the object in the image: Grayscale filtering, Gaussian filtering, and threshold.Then, the characteristics of the object were obtained through the first two invariant moments of HU, and finally, the machine learning method KNN was applied to predict, that the image captured by the robotic arm belongs or not to a certain category. In this way, the robotic arm decides to move the object or not.Results. According to the plot of the obtained data described in the results section; the level of correct answers increases markedly by using the techniques described above. The prediction and classification using KNN were remarkable, For all the tests carried out The average effectiveness of KNN method was 95.42%. Once the scripts were integrated, the operation of the robotic arm was satisfactory.

Mao Queen Garzón Quiroz

Dynamic Difficulty Adjustment for a Memory Game

Working memory is an important function for human cognition, it is related to some skills, such as remembering information or developing a mental calculation. Several games have been developed to train the working memory. Nevertheless, sometimes the game does not adjust adequate to users. Consequently, they end up bored by the game and leave it. This article presents a system of dynamic adjustment of the difficulty for a working memory training game, which allows generating customized levels so that the users obtain a better performance during the training of the memory. The proposed system was tested with young people, the results show that the training performance was better in comparison with a classic game and provide a better game experience to the users.

Vladimir Araujo, Alejandra Gonzalez, Diego Mendez

Machine Learning Methods for Classifying Mammographic Regions Using the Wavelet Transform and Radiomic Texture Features

Automatic detection and classification of lesions in mammography remains one of the most important and challenging problems in the development of computer-aided diagnosis systems. Several machine learning approaches have been proposed for supporting the detection and classification of mammographic findings, and are used as computational tools during different diagnosis process by the radiologists. However, the effectiveness of these approaches depends on the accuracy of the feature representation and classification techniques. In this paper, a radiomic strategy based on texture features is explored for identifying abnormalities in mammographies. For doing that, a complete study of five feature extraction approaches, ten selection methods, and five classification models was carried out for identifying findings contained in regions of interest extracted from mammography. The proposed strategy starts with a region extraction process. Some square regions of interest (ROI) were manually extracted from the Mammographic Image Analysis Society (miniMIAS) database. Then, each ROI was decomposed into different resolution levels by using a Wavelet transform approach, and a set of radiomic features based on texture information was computed. Finally, feature selection algorithms and machine learning models were applied to decide whether the ROI undergoing analysis contains or not a mammographic abnormality. The obtained results showed that radiomic texture descriptors extracted from wavelet detail coefficients improved the performance obtained by radiomic features extracted from the original image.

Jaider Stiven Rincón, Andrés E. Castro-Ospina, Fabián R. Narváez, Gloria M. Díaz

Balanced Scorecard as Evaluation Tool with Sterilization Processes by Using Fuzzy Logic

The sterilization plants, in the different public hospitals in Guayaquil city, are responsible for the manipulation and handling of surgical instruments. However, the lack of adequate control of these materials due to the possible failure to comply with the norms and procedures, can generate both in patients and in the persons who manipulate the surgical instruments, a certain uncertainty degree, therefore we conducted an analysis based on an organizational use management tool, which measures the performance of the company, as the Balanced Scorecard (BSC), so that this tool can integrate techniques to reduce the uncertainty and to be able to treat the inaccurate data as if they were true through fuzzy logic (FL), guaranteeing the performance and contributing to the optimal decision making, determined by the experts.

Lorenzo J. Cevallos-Torres, Miguel Botto-Tobar, Jefferson Nuñez-Gaibor, David Cardenas-Giler, Alexandra Wilches-Medina, Joffre León-Acurio

An Approach to the Detection of Post-seismic Structural Damage Based on Image Segmentation Methods

Crack detection is critical in ensuring basic structural security, however manual identification of cracks is time-consuming and is subject to the judgments of reviewers. This research presents a crack detection technique based on image processing. The digital image processing is divided into different phases and each of them follow techniques that improve the quality of the images. In the segmentation phase, images traits need to be highlighted. This document portrays the image segmentation of a set of digital photographs of cracks and crevices of the different structures of the buildings of the faculties of the University of Guayaquil. In this study, a function is developed using the computational tool, Matlab, to obtain results by submitting the images to the different segmentation techniques applied during the investigation, for which methods are proposed such as: The Canny transform, The Sobel Operator and the Prewitt Transform. With the obtained results, crack measurement is applied based on the manual selection of pixels in order to generate damage assessment.

Lorenzo J. Cevallos-Torres, Diana Minda Gilces, Alfonso Guijarro-Rodriguez, Ronald Barriga-Diaz, Maikel Leyva-Vazquez, Miguel Botto-Tobar

Application of Genetic Algorithms in Software Engineering: A Systematic Literature Review

Software engineering was born from the need to establish an adequate and efficient methodology for the development of the software, not using appropriate methods in the software produces a large number of errors, today on Software has evolved drastically and is considered as a discipline that has its own principles and requirements to obtain more structured solutions with planning, development and culmination. The genetic algorithms present an alternative to solve problems of optimization in the software engineering, therefore in this work a systematic literature review (SLR) of the application and technologies was carried out of the genetic algorithms in it. The results are presented based on 127 initial documents which, after passing through a review protocol, were reduced to 20 chords to the research topic, where it was indicated that the greatest application is in the tests of software.

Pablo F. Ordoñez-Ordoñez, Milton Quizhpe, Oscar M. Cumbicus-Pineda, Valeria Herrera Salazar, Roberth Figueroa-Diaz

Automatic Categorization of Tweets on the Political Electoral Theme Using Supervised Classification Algorithms

The increase and use of social networks to share content and opinions with different characters allows to have a large volume of information. Twitter, is just one of the most used social networks and has been selected for this study; the users of this network they become not only passive actors of reception and consumption of information, they are also generators of contents. Tweets analysis requires a systematic process for collecting, processing and classification, which is why this article determines the best Classifier categories: positive, negative and neutral public opinion corresponding electoral political issues. For this, a total of 745 tweets collected in Spanish from the main accounts of media, political figures and political organizations of Ecuador. These tweets were preprocessed, transformed and the results indicated that the vector support machines (SMO) with a sensitivity error rate (RECALL) of 0.8% proved to be the best. Likewise, the algorithm Syntetic Minority Over-Sampling Technique was used (SMOTE) to balance classes and increase capacity predictive of the models excluding the decision trees for the categorization of this type of tweets.

Oscar M. Cumbicus-Pineda, Pablo F. Ordoñez-Ordoñez, Lisset A. Neyra-Romero, Roberth Figueroa-Diaz

e-Government and e-Participation

Frontmatter

Citizen Participation in the Use of the IRS Portal that Electronic Government Brings in the City of Milagro

The purpose of this article is to analyze the importance of using the electronic government portal for the collection of taxes and their involvement in the city of Milagro. At present, the use of technological tools for process of control has allowed several activities to be carried out in such a way that the citizens does not have to go the government offices.In the review of literatures, important concepts related to the e-government plan, the use of ICTs in the government of Milagro and e-government in Milagro and its surroundings were researched, the methodology used for the data collection was the survey, the same one that allowed obtaining quantitative and statistical information to carry out a detailed analysis of the use of ICTs in local government.The results obtained from the researched detail the services offered by the Internal Revenue Service (IRS) in the city of Milagro, as well as the utility that the web page provides to citizens.It is important to establish that this work was carried out with the purpose of determining the degree of impact in terms of the participation of the people in the use that is given to the IRS portal of the electronic government, it is possible to conclude that previously there had not been carried out a similar study, because people did not have knowledge and showed little interest in the inclusion of institutional portals that dynamically help to generate processes saving time for users.

Oscar Bermeo-Almeida, Mario Cardenas-Rodriguez, Ivan Ramirez-Sánchez, Enrique Ferruzola-Gómez, William Bazán-Vera

Analysis of e-Government Strategy Implementation in Ecuador

E-Government is a comprehensive process of improvement of State management, the following is an analysis of the inclusion of the strategy, and the roles that have played the political sector, Academy, civil society, and development achieved on the implementation in the public sector within the planning of Ecuador, with a comparison of successful models in Latin America, to determine how necessary is the change of management and the transformations of the State in the construction of an organizational model to achieve its full operation.

Galo Enrique Valverde Landívar

Backmatter

Additional information

Premium Partner

    Image Credits