Luis Barba-Guaman

Detection of the characters from the license plates by cascade classifiers method

This article describes the detection of the characters of the license plate through of computer vision techniques: such as cascade of classifiers based in sobel algorithm, analysis of peaks and valleys, and support vector machines; the search for the region of the plate begins by detecting vehicles, then character segmentation and concludes with the recognition of these. The system was tested in different scenarios such as: different lighting provided by the day or night and weather changes. The average time to execute these phases it was 434 ms.

Cloud Computing in Smart Educational Environments: Application in Learning Analytics as Service

In this paper, we present an extension of a Middleware for Smart Educational Environments based in agents, using the paradigm of Cloud Computing. In that sense, we detail the Middleware components, which enable the process of management of the Cloud Computing. We also present the utilization of this Middleware to provide services on the cloud about task of Learning Analytics that allow processing of data of students and learning environments, to understand and optimize the learning processes.

Open Drugstores Mobile App

Nowadays, various mobile applications are used to solve everyday problems, saving time, and resources to users. The present research aims to solve one of the needs from the city of Loja that is related to health services. The city of Loja as well as the rest of the Ecuadorian country does not have the technology that facilitates quick search of the drug stores on duty. The model of the proposed mobile app includes interactivity features, automatic update of easy use for users that do not offer other applications of similar characteristics. During the development of this work, it has been considered various aspects related to the users that will make use of this application as: the type of mobile device that is used, the operating system, and software architectures. Considering the features and services, it was chosen the SOA-based architecture. Through this work, it is intended to measure the impact that the application might have in the city of Loja and the benefits that this can bring. Likewise, it has been specified the operation of the application as well as the options of search; in the same way, it is presented all the prototype from the perspective of the user in order to provide an efficient service to customers, who are looking for a drug store on duty according to the sectors of the city during 24 h a day.

Learning analytics tasks as services in smart classrooms

Abstract A smart classroom integrates the different components in a traditional classroom, by using different technologies as artificial intelligence, ubiquitous, and cloud paradigms, among others, in order to improve the learning process. On the other hand, the learning analytics tasks are a set of tools that can be used to collect and analyze the data accumulated in a smart classroom. In this paper, we propose the definition of the learning analytics tasks as services, which can be invoked by the components of a smart classroom. We describe how to combine the cloud and multi-agent paradigms in a smart classroom, in order to provide academic services to the intelligent and non-intelligent agents in the smart classroom, to adapt and respond to the teaching and learning requirements of students. Additionally, we define a set of learning analytics tasks as services, which defines a knowledge feedback loop for the smart classroom, in order to improve the learning process in it, and we explain how they can be invoked and consumed by the agents in a smart classroom.

EMG signal patterns recognition based on feedforward Artificial Neural Network applied to robotic prosthesis myoelectric control

The present work is part of the “Hand of Hope” project, which seeks to develop low-cost robotic prostheses with the aim of contributing to the social and labor inclusion of people with motor disabilities of their upper extremities. The specific objective to address in this work is the design and development of the system architecture to recognition of EMG (Electromyography) signal patterns, the purpose is to control the functions of objects handling by the robotic prosthesis. There are proposed methods to the recognition of EMG signal patterns; however it defined using a Feedforward-backpropagation Artificial Neural Network (ANN) because have high success rate (Sr) using the least amount of channels, can be supported on platforms on-line and real-time; and moreover in order to improve the ANN-Sr values, it was used as input the envelope of the EMG signal instead of the original signal. For the performance evaluation 20 assessments for each of the four EMG signal patterns (relaxed hand/cylindrical grip, pinch grip, thumb adduction, and index finger extended) were performed, from the results it is observed that the average success rate is equal to 95%.

Detection of moving objects through color thresholding

In image processing area and segmentation algorithms based on thresholding, the intensity of the image (grayscale) is usually obtained in order to differentiate the regions of the objects and the background. The segmentation based on the threshold works well when the image has a high intensity in the contrast, this characteristic is key to make a good classification of the pixels. This document will explain some theoretical concepts to identify objects by means of their color (thresholding), this technique was implemented in the development of a game program. Furthermore, the thresholding range for the red, yellow and green colors was found in order to achieve a better approach in the object detection. This project used the python programming language, Pygame graphical interface libraries and the OpenCV library free open source about artificial vision.

Development of software prototypes through model game jam and basic vision artificial techniques

The artificial vision is a part of the artificial intelligence that pretends to simulate the human vision, is to say, from the acquisition, processing, analysis and interpretation of images through an intelligent system. This work presents the creation of prototypes under the game jam model as a software product. In this context, the objective of the present work was to apply basic artificial vision algorithms such as linear discriminant analysis (LDA), principal component analysis (PCA), Fisherface, Otsu, CamShift and color spaces such as RGB and HSV in order to be able to motion detection of objects, face recognition and pedestrian detection. As a result of applying this model in rapid prototyping, we found significant factors (such as: participatory design, light construction, product value approach, aesthetics and technology) in the implementation of innovative strategies in creating of prototypes focused on Software development.

Use of SQALE and tools for analysis and identification of code technical debt through static analysis

Technical Debt (TD), also known as technical debt design or technical debt code, analyze the consequence that could have a system once it has been designed architecturally, coding or implemented. TD refers to work to be performed rather than software design or coding is considered complete or correct. Static analysis is a technique to identify and analyze software characteristics from source code; through static analysis we can identify elements such as packages, classes, relationships, lines of code (LOCs), bugs, complexity, coding violations and others. In addition subsystems, components and their relationships supported by tools, algorithms, frameworks to analyze the code were identified. SQALE[1] is a quality and analysis model contains the internal properties expected from the code in the context of the evaluation, it has been used to perform many assessments of software source code, of various sizes in different application domains and programming language. SonarQube[2], Kiuwan[3] and PMD[4] are an open source platform to manage the source code quality, this cover seven axes of code quality among which stand: architecture and design, duplications, unit test, complexity, potential bugs, codifications rules, comments, among others; this platform work with over 20 programming languages. This paper, use as input the source code of the software applications written in different programming language for through static analysis identify metrics, characteristics, and technical debt with the aim to improve the quality when writing code, also supported in static analysis identify aspects such as correct apply of quality attributes, standards and best practices of programming that based in ISO 9126 and SQALE ensure the correct software development in terms of design and coding.

Referent framework to government of IT using standards: COBIT 5 and ISO 38500

A framework of government of the technologies of information helps in the direction and control of it today and its future forecast, also allows organizations to improve their effectiveness and efficiency to support the implementation of the organizational objectives, this allows you to have a competitive advantage with companies that offer the same services. A good management of IT not only allows you to have savings into investment of technology but that opens the way to innovations, new alliances, increase the portfolio of products and services, establishing standards, policies, processes and IT procedures which lead them to be the main strategic partner organizations. This contribution will allow to Junta Nacional de Defensa del Artesano (JNDA) of Ecuador have a framework for government based on the international standard ISO/IEC 38500 and COBIT 5.