Technologies and Innovation

Agriculture provides most of the world’s food that helps to sustain and enhance human life. Diseases infections and insect pest in crops cause considerable economic losses. Diagnosing or defining the type of insect pest or disease that affects the crop is not an easy task for farmers, even more, when the diversity of insects and diseases is quite numerous. There is a need for tools focused on the knowledge management of experts capable of providing guidelines for the diagnosis and prevention of insect pests. This work presents an ontology-based decision support system for insect pest control in sugarcane, rice, soya, and cacao crops. This system takes advantage of Semantic Web technologies to represent the experts’ knowledge as well as to apply semantic reasoning to diagnose the insect pest that affects the crop. This system was evaluated to measure its efficacy regarding the diagnosis of the insect pest that affects a crop obtaining encouraging results.

In the last decades, the mechanization of productive processes has focused on replacing the tasks performed by people with machines. However nowadays, the integration of software, robots and artificial intelligence point to the automation in agriculture. This is of great importance for the increase of productivity and the economic growth of the country solving in this way the lack of workforce and its associated high costs, offering great benefits to population. Currently, researchers are developing numerous fruit and vegetable classification algorithms, of which essential parameter is color; that allows the detection of nutrient deficiencies, diagnosis of diseases and fruit quality; the same ones that have proven to be accurate and require less time compared to traditional methods. The aim of this article is to provide a systematic review of classifying techniques through machine learning, its components and the utility for the agronomist.

In 2016, Ecuador produced 368,181 tons of shrimp Penaeus vannamei and ex-ported 370,780 tons corresponding to $ 2.58 billion, according to ProEcuador (Institute for Export and Investment Promotion). The shrimp exportation represented 22.76% of the country’s non-oil exports. The Ecuadorian shrimp industry invests in technology focused on improving the production of shrimp and the quality of the postlarvae aiming to avoid falls in production, high mortality rates and disparity in the size of shrimp. However, it is necessary that this industry adopts innovative technologies that allow it to improve the quality and production of its products. In this sense, this work presents a case study where a water monitoring system was implemented in a shrimp culture pond of the CAMASIG S.A. company. This system integrates technologies such as Cloud computing, Arduino-based devices, and mobile applications that allow users to remotely monitor a shrimp culture pond, as well as to receive alerts when an out-of-range water parameter (pH, temperature, and dissolved oxygen) is detected. This last module consists of a set of sensors that allows collecting data about the pH, temperature, and dissolved oxygen in the water. This system was evaluated to test its effectiveness in terms of the size, weight, and the percentage of survival of the shrimp achieved when the shrimp culture pond is monitored by this system.

Blockchain has been used to solve problems from different sectors. In agriculture, Blockchain is being applied for improving food safety, and transaction times. The increasing interest of Blockchain technology in agriculture calls for a clear, systematic overview. In this sense, we present a systematic literature review (SLR) whose objective is to collect all relevant research on Blockchain technology in agriculture to detect current research topics, main contributions, and benefits of applying Blockchain in agriculture. We have extracted 10 primary studies from scientific databases and web sources published between 2016 and 2018, which means that Blockchain is a recent research area in the agricultural sector. The results show that 60% of papers are focused on food supply chain. Also, 50% of the studies on Blockchain in Agriculture are dominated by Asian community researchers, especially from China. Similarly, the half of the studies addressed challenges related to privacy and security of the Internet of Things with Blockchain technology.

Information and Communications Technology play an important role in the agricultural sector due to it helps to perform activities such as agricultural re-sources management. The efficiency in the crop production, i.e. produce more with less, is a challenge that must be addressed. Therefore, it is necessary to develop computer applications that help farmers and/or students of agronomy to perform activities such as treatment of plant diseases and pests, precision agriculture, and quality of production, among others. Smartphones and mobile applications have become part of the daily lives of people. Nowadays, mobile technologies offer optimal and integral solutions for agriculture. Hence, it is important to adopt these technologies for performing daily agriculture tasks. This work presents an evaluation and comparison of mobile applications for agriculture. This comparison considers the applications hosted in both Play Store for Android devices and App Store for IOS devices. Furthermore, this study considers the main characteristics required by farmers for performing crop control and monitoring such as pests and insects’ management, meteorological aspects, machinery, working hours, geolocation, harvest time, tasks management, areas of cultivation, among others.

Cattle husbandry industry is an important development sector in many countries around the world. One of the main problems in this sector concerns cattle diseases which result in low productivity. A rapid diagnosis of the disease is particularly important for its prevention, control, and treatment. However, the main players on cattle husbandry industry highly depend on veterinarians to cope with this problem. Unfortunately, the number of veterinarians in some cities is very limited or they live far away from the farm. In this sense, it is necessary to provide farmers tools that help them to correctly diagnose the cattle diseases. Nowadays, there are technologies that can help to address this issue. On the one hand, expert systems are an active research area for medical diagnosis and recommending treatments. On the other hand, ontologies can be used for modeling the domain of cattle diseases diagnosis and for generating the knowledge base that is required by the expert system to perform its corresponding tasks. In this work, we present SE-DiagEnf, an ontology-based expert system that diagnoses cattle diseases based on a set of symptoms and provides recommendations for tackling the disease diagnosed. The main goal of this system is to decrease the dependency of farmers on veterinarians to cope with cattle diseases diagnosis and treatment. SE-DiagEnf was evaluated by farmers from Ecuador. In this evaluation, farmers had to provide a set of symptoms to allows the system to diagnose the cattle disease. The evaluation results seem promising based on the F-measure metric.

The meteorological records represent atmospheric variables, which capture by means of sensors parameters such as: air temperature, humidity, direction and wind speed among others. Having a system that allows to monitor, visualize and analyze these variables contributes fundamentally to the decision-making of governmental entities, scientists and researchers. This article presents the architecture used in a meteorological data management system based on the analysis of webmapping tools that allow the monitoring and visualization of geospatial data, based on the results obtained by the project executed by researchers from the Agrarian University of Ecuador called “Platform for the monitoring of real-time atmospheric data of the network of meteorological stations of the Agrarian University of Ecuador, Guayaquil and Milagro.”

The present paper makes a study of the maturity of Information Security Management Systems of the Public Sector of Ecuador. Through a theoretical study, 5 factors were determined that make up an effective Information Security Management System: internal organizational control, information security policy, information security culture, and technical activities for the security of information and new technologies. The five factors were evaluated through a scale to determine the level of maturity of the process of information security from the perception of ICT (Information Technology and Communication) managers of public sector entities. Findings of the analysis showed that technical activities for information security was the factor with a higher level of maturity due to the implementation of technological tools by the personnel of ICT area. On the other hand, internal organizational control was the least mature factor, indicating that this area needs more attention. Despite the requirement of the international standards of information security in most public entities, the process is still at a level of maturity between repeatable and defined.

Thermal simulation systems in buildings, contribute to the design of energy-efficient structures; however, a significant amount of computational time is required in order to obtain the results of the simulation process. The main focus of this paper is examining the possibility of reducing time required for thermal simulation systems calculations. More specifically, the paper focuses on one of the major processes that requires computing resources at solving the system of equations obtained as a result of the thermal modeling of a building. This research was undertaken in order to determine the performance of Java library methods: Matrix Tool for Java (MTJ) for solving systems of linear equations, and identifying which of these was the optimum in terms of computation time. For this purpose, tests for the iterative methods combined with pre-conditioners were conducted. The tests of the direct method were done through the development of a software implemented in two case studies of buildings, and that was modeled with the parameters of the thermal simulation software called JEner, from the Thermal Engineering Research Group from the University of Cadiz in Spain.

The increase of competitiveness in global markets has led to the need for improvements in project management organizations aimed at stimulating financial health and revenue. Revenue assurance combines statistical techniques, scope, time and risk management with the goal of reducing costs and maximizing revenue in organizations that apply it. The objective of this paper is to present a revenue assurance model for project management organizations that allows the detection of planning errors and revenues maximization during the projects development. As part of the research novelty, the proposed model combines risk management, outlier mining and soft computing techniques. Risk management is developed with a proactive approach, based on the application of computing with words for qualitative risk assessment. In the research, cross validation tests are carried out comparing different techniques for the detection of anomalous situations. In the comparison, project management databases are used for the development of computer solutions. The model is introduced in a platform for integrated project management and the results of its application are also presented.

The amount of information available on the Internet today makes it difficult to obtain efficient and accurate knowledge. The information obtained by users from the Internet is often not entirely satisfactory. Therefore, it is necessary to design systems that enhance performance and improve the information retrieval process in an intelligent way. The ontologies are useful for knowledge representation. To achieve the goal of enhancing knowledge retrieval in the Nutrition and Food domain, a recommended intelligent system prototype has been developed that can respond and fill gaps in users information about maintenance of a balanced diet, focusing in Mediterranean diets. According to individual characteristics such as age, weight, height, or sex, individuals can see what to eat in order to meet their nutritional needs and maintain a balanced diet. Individuals can also request information to suit health related problems, which foods are recommended and which ones should be avoided.

This article presents a method that extracts relevant concepts automatically, consisting of one or several words, whose main contribution is that it does so from a single document of any domain, regardless of its length; however, documents of short length are used (which are the most frequent to obtain on the web) to perform the work. This research was conducted for documents written in Spanish and was tested in multiple randomized domains to compare their results. For this, an algorithm was used to automatically identify syntactic patterns in the document. This work uses the previous work of [1] to obtain its results. This algorithm is based on statistical approximations and on the length of the identifiable patterns contained in the document, applies certain heuristic that can enhance or decrease the patterns’ choice according to the selection of one of the 5 methods that are processed (M1 to M5), with these patterns the candidate concepts are obtained, which go through another evaluation process that will obtain the final concepts. This proposal presents at least four advantages: (1) It is multi-domain, (2) It is independent of the text length, (3) It can work with one or more documents and (4) It allows the discarding of garbage or undesirable patterns from the beginning. The method was implemented in 11 different domains and its results range varies between 58%–70% of precision and 25%–46% of recall.

A success software development process requires a good design stage. During the design, a set of decisions is made in order to improve the productivity, reduce costs for reimplementation and obtain reliable systems, in special for critical domains, such as bank management systems or systems for aeronautics. Nevertheless, it is not easy to find documentation about design decisions or tools which support this process. To address this issue, this article describes a solution based on ontologies to describe design decisions. In order to identify the main elements a systematic literature review was carried out. This review also helped to identify some of the most common design decisions. These elements were used to develop the ontology which allows answering the problem raised. This ontology could be a useful tool for architects and designers during the design stage of a system.

The present work proposes a security architecture for web servers called Web Attacks Cognitive Patterns Classifier, which makes use of cognitive security concepts to deliver a more complete solution than existing ones. The architecture proposes the development of an integrated software solution where existing tools such as Elasticsearch, Logstash and Kibana are incorporated. The proposed system will be nurtured using data of attacks obtained from honeypots implemented in hacker communities; such data will be analyzed by using machine learning algorithms and behavioral parameters to determinate attack patterns and classifications. The present work also makes a literature review of existing web security solutions, to understand their limitations and to explain the reasons why the creation of the proposed architecture was necessary. We can say that usage of different technologies oriented to a specific problem can generate better solutions; in the case of this work, different technologies such as ELK Stack, Cognitive Security, Machine Learning techniques and Honeypots have been combined for the assurance, prevention and proactive security of Web Servers.

Political marketing is a discipline concerned with the study of the right political communication strategies. Precise decision making in political marketing largely depends upon the thorough analysis of vast amounts of data from a variety of sources. Relevant information from mass media, social networks, Web pages, etc., should be gathered and scrutinized in order to provide the insights necessary to properly adjust the political parties’ and politicians’ messages to society. The main challenges in this context are, first of all, the integration of data from disparate sources, and hence its analysis to extract the relevant information to use in the decision-making process. Big data and Semantic Web technologies provide the means to face these challenges. In this paper, we propose SePoMa, a framework that applies semantic Big data analysis techniques to the political domain to assist in the definition of political marketing strategies for political entities. SePoMa explores the pertinent structured, semi-structured and unstructured data sources and automatically populates the political ontology, which is then examined to generate electorate knowledge. An exemplary use case scenario is described that illustrates the benefits of the framework for the automation of electoral research and the support of political marketing strategies.

Companies and marketing departments are devoting many resources to the implementation of neuromarketing with facial recognition. This document presents a systematic review of the literature whose main objective was to look for computer systems and technologies of facial recognition that are available to support neuromarketing. As a result, it was found that very few academic and scientific articles focus on this topic in a systematic way. None carry out an analysis for a complete solution and the studies are limited with databases that do not offer a group of images which are sufficiently broad to allow the performance of complete tests. Many works emphasize research on algorithms that increase the level of accuracy of the information analyzed at the time of facial recognition.

Prior to the digital era, knowing the perception of society towards the health-system was done through face-to-face questionnaires and interviews. With this knowledge, governments and public organizations have designed effective action plans in order to improve our quality of life. Nowadays, as a result of the irruption of computer networks, it is possible to reach a higher number of people with a minor cost and perform automatic analysis of the collected data. Infodemiology is the research discipline oriented to the study of health information on the Internet. In this work, we explore the reliability of Opinion Mining to measure the subjective perception of people towards infectious diseases during times of high risk of contagion. In short, linguistic characteristics, among other relevant data, were extracted from tweets written in the Spanish Language by the end of 2017 in Ecuador. The built model contains the most relevant linguistics characteristics related to determine positive and negative pieces of text regarding infectious diseases. In addition, the corpus used in this analysis has been published for other researchers to use it in future experiments in this area. The results showed Support Vector Machines achieved the best results with a precision of 86.5%.

During these last years, the use of mobile and Web technologies around the world has reached an increasing impact in society and people’s lifestyle, including different places and social classes. Ecuador is a South American country with intense seismic and volcanic activity, where current politics and contingency plans are not optimal, making it necessary to think about a more efficient solution to mitigate this risks and consequences. Considering the growing amount of mobile device users, the reach of mobile networks and combining the risk of situation in which many countries are alike, such as Ecuador. This paper sets the design and development of an early alert infrastructure, through the use of new technologies such as Cloud computing, geolocation, pervasive computing, and Web services. The implemented architecture, and the provided Web service has the objective to improve the evacuation logistic and subsequent rescue work after the occurrence of a natural disaster. The results obtained demonstrate that the use of the system improves to a good extent of the evacuation by reaching to a safe location.

Gamification is an approach that uses game design elements in nongame contexts. The gamification approach has been successfully applied to a variety of different contexts such as tourism, architecture, and education. In Colombia and Ecuador, there are several works that have generated great contributions to the gamification domain. However, in South America, and specifically in Ecuador, there are few higher education applications based on the gamification approach. In this sense, this work presents Funprog, a gamification-based platform for higher education that aims to generate an emotional and social impact on students. Funprog defines a set of game levels where students face new challenges that allow them to obtain more knowledge and improve their skills. Funprog was used by first-year students from the Agrarian University of Ecuador. Specifically, this application was focused on the teaching of the Programming Fundamentals subject. Finally, a set of surveys were conducted to know the level of acceptance of Funprog among students and teachers. The surveys’ results denote a clear acceptance of this application.

Our world is becomes more and more globalized. Frontiers are not what they once were, thanks to the discovery of the Internet. Knowing several languages is something that is almost essential. When we are studying a new language, we focus on learning vocabulary and all about syntax. In other words, this means we want to know how to coordinate and join words to create sentences and concepts. But language has another dimension that we usually overlook: semantics. This dimension is very important in language because it gives meaning to words. Semantics study could be as wide and complex as language to analyze itself. Therefore, in order to simplify our tasks, we have started with a finite set of terms, Specifically we have the first five levels set up by an English language academy. The objective of this research presented here was the development of a system that allows to analyze and detect semantic errors in simple sentences and syntactically correct to support English learning. Basically, the system we have developed is formed by two different components: a semantic analyzer and a web interface. The semantic analyzer has been built using the programming language Java and utilizes ontology and a reasoner over it. The use of ontologies allows the classification and categorization of different words in a language so that we can apply a reasoner to classified concepts to infer new knowledge and to detect whether a sentence makes sense or not.

E-learning is the delivery of education through digital or electronic methods allowing students to acquire new knowledge and develop new skills. E-learning allows students to expand their knowledge whenever and wherever. Several authors consider sentiment analysis as an alternative to improve the learning process in an e-learning environment since it allows analyzing the opinions of the students in order to better understand their opinion and take more effective, better-targeted actions. In this sense, this work presents a systematic literature review about sentiment analysis in education domain. This review aims to detect the approaches and digital educational resources used in sentiment analysis as well as to identify what are the main benefits of using sentiment analysis on education domain. The results show that Naïve Bayes is the most used technique for sentiment analysis and that forums of MOOCs and social networks are the most used digital education resources to collect data needed to perform the sentiment analysis process. Finally, some of the main benefits of using sentiment analysis in education domain are the improvement of the teaching-learning process and students’ performance, as well as the reduction in course abandonment.