Guevara Maldonado, César Byron
Thumbnail Image
Preferred name
Guevara Maldonado, César Byron
Main Affiliation
Quito
Email
cesarguevara@uti.edu.ec
ORCID
Scopus Author ID
56452706300

Research Output

Filters
Reset filters

Settings
Now showing 1 - 10 of 47
No Thumbnail Available
Publication

Development of Behavior Profile of Users with Visual Impairment

2020 , Guevara Maldonado, César Byron , Arias Flores, Hugo Patricio , Varela Aldas, José , Castillo Salazar, David Ricardo , Borja M. , Fierro-Saltos W. , Rivera R. , Hidalgo-Guijarro J. , Yandún-Velasteguí M.

The interaction of the user with visual impairment with assistive technologies, and in particular with screen readers, generates a group of actions and events during their navigation. These interactions are defined as behavioral patterns, which have a sequence that occurs at specific time slot. Understanding user behavior by analyzing their interaction with applications, in addition, details the characteristics, relationships, structures and functions of the sequence of actions in a specific application domain. The objective of this document is to find activity patterns from a set of commands used by the user, combining data mining and a Bayesian model. This model calculates the probability of the functions used with the screen reader and generates a behavior profile to improve the user experience. For this study, the screen reader JAWS version 2018, the Open Journal Systems platform version 3.0.1 and a computer with Windows 10 operating system were used. During the first phase, command history used by the user by interacting with the Open Journal Systems platform were collected. The result is that the accessibility of users with visual impairment to interact with the computer and its applications has been improved by applying this model. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Emotion classification using EEG headset signals and Random Forests [Clasificación de emociones utilizando señales de auriculares EEG y Random Forests]

2023 , Vasquez R. , Carrion-Jumbo J. , Riofrio-Luzcando D. , Guevara Maldonado, César Byron

Emotions are one of the important components of the human being, thus they are a valuable part of daily activities such as interaction with people, decision making and learning. For this reason, it is important to detect, recognize and understand emotions using computational systems to improve communication between people and machines, which would facilitate the ability of computers to understand the communication between humans. This study proposes the creation of a model that allows the classification of people's emotions based on their EEG signals, for which the brain-computer interface EMOTIV EPOC was used. This allowed the collection of electroencephalographic information from 50 people, all of whom were shown audiovisual resources that helped to provoke the desired mood. The information obtained was stored in a database for the generation of the model and the corresponding classification analysis. Random Forest model was created for emotion prediction (happiness, sadness and relaxation), based on the signals of any person. The results obtained were 97.21% accurate for happiness, 76% for relaxation and 76% for sadness. Finally, the model was used to generate a real-time emotion prediction algorithm; it captures the person's EEG signals, executes the generated algorithm and displays the result on the screen with the help of images representative of each emotion. © 2023 ITMA.

View
No Thumbnail Available
Publication

An adversarial risk analysis framework for software release decision support

2025 , Refik Soyer , Fabrizio Ruggeri , David Rios Insua , Cason Pierce , Guevara Maldonado, César Byron

Recent artificial intelligence (AI) risk management frameworks and regulations place stringent quality constraints on AI systems to be deployed in an increasingly competitive environment. Thus, from a software engineering point of view, a major issue is deciding when to release an AI system to the market. This problem is complex due to, among other features, the uncertainty surrounding the AI system's reliability and safety as reflected through its faults, the various cost items involved, and the presence of competitors. A novel general adversarial risk analysis framework with multiple agents of two types (producers and buyers) is proposed to support an AI system developer in deciding when to release a product. The implementation of the proposed framework is illustrated with an example and extensions to cases with multiple producers and multiple buyers are discussed

View
No Thumbnail Available
Publication

Framework based on gestalt principles to design mobile interfaces for a better user experience

2020 , Ripalda D. , Guevara Maldonado, César Byron , Garrido A.

This paper presents the results of the user experience test comparing a real functional application and a high fidelity prototype that used a Framework to design graphic user interfaces on mobile devices. This Framework links Nielsen’s heuristics with the principles of perception of Gestalt, offering to developers and usability experts, references to generate and evaluate mockups and prototypes. The constructive and evaluative model of the Framework allows to recognize usability criteria in visual components of the interfaces, during the initial phases of a project that uses agile software development methodologies, reducing the “trial - error” regressions. The experiment allowed obtaining data about satisfaction measures and specific user attitudes regarding the interfaces developed. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Development of a Convolutional Neural Network for Detection of Ovarian Cancer Based on Computed Tomography Images

2024 , Gabriela Narvaez-Chunillo , Ronny Ordoñez-Sanchez , Lizbeth Ortiz-Vinueza , Diego Almeida-Galárraga , Fernando Villalba-Meneses , Roberto Bravo-Freire , Andrés Tirado-Espín , Carolina Cadena-Morejón , Paulina Vizcaíno-Imacaña , Guevara Maldonado, César Byron

Ovarian cancer is one of the most frequent gynecologic malignancies in women, but it is often detected in late stage, leaving patients with little time to follow a successful therapy. Specialists have opted to use computer-aided diagnosis (CAD) for the detection of ovarian cancer through the analysis of computed tomography (CT) images, in which the professional examines the size, shape and different characteristics that enable a precise diagnosis in the ovary. This present project purposes a Convolutional Neural Network (CNN) which consist on four convolutional layers; including two pooling layer and two fully-connected layer. The cancerous ovaries images is selected from the Cancer Imaging Achive dataset for training and validation of the model. Moreover, the training of the CNN contain filters to ensure that all of the images are the same dimensions and pixel size. The testing results from the training of the images showed that the proposed model obtained a range of accuracy that goes from 90.0% to the best of the cases 98.85%. The variables obtained like the data of the pressure and loss of the training were compared with those of the validation, allowing for the determination of a successful CNN training.

View
No Thumbnail Available
Publication

Development of an accessible video game to improve the understanding of the test of honey-alonso

2020 , Salvador-Ullauri, L. , Acosta-Vargas, P. , Jadán Guerrero, Janio , Guevara Maldonado, César Byron , Sanchez-Gordon, S. , Calle-Jimenez, T. , Lara Álvarez, Patricio

When evaluating the learning styles of several individuals using the Honey-Alonso test, some users did not understand the meaning of several of the questions. This may be due to problems of context, tiredness in front of the extension of the test, lack of understanding or disinterest. The Honey-Alonso test consists of four groups of twenty questions each. Each group of questions allows identifying the level that an individual possesses on each one of the four learning styles. These styles are: active, reflective, theoretical and pragmatic. Answering a questionnaire of eighty questions is not an easy task from an andragogical point of view. This article proposes the creation of an educational video game designed with a script based on the questions of the Honey-Alonso test. The answers selected by the player are taken as a condition to determine the order of the next questions presented to the player. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Preparation of Higher Education Students in Ecuador: An Analysis Based on the Knowledge Economy

2024 , Varela Lascano Darwin Marcelo , Diego Fernando Salas Heredia , Silvana Micaela Coloma Gudiño , Guevara Maldonado, César Byron

The knowledge economy has emerged as a key paradigm in global socioeconomic development, highlighting the importance of higher education in the formation of human capital capable of generating, applying and disseminating innovative knowledge. This study aims to evaluate the preparation of higher education students in Ecuador, considering critical variables such as soft skills, perception of the knowledge economy, university-business linkage and internationalization, and their impact on academic training. The methodology employed was quantitative, using a multiple linear regression model to analyze the relationship between the independent variables and the academic formation of a sample of 205 students from two Ecuadorian universities. Advanced statistical techniques were applied to evaluate the significance and impact of each variable. The results indicate that soft skills (r = 0.713, p < 0.01), perception of the knowledge economy (r = 0.602, p < 0.01) and internationalization (r = 0.594, p < 0.01) have a significant and positive impact on academic training. However, university-business linkage showed a lower and non-significant correlation (r = 0.407, p < 0.01). In conclusion, academic training in Ecuador benefits significantly from the development of soft skills, a positive perception of the knowledge economy and internationalization. However, the lack of significant impact of university-business linkages suggests the need for future studies to explore barriers and improve these collaborations. These findings underscore the importance of educational policies that integrate these factors to improve the preparation of students in a global knowledge economy.

View
No Thumbnail Available
Publication

Autonomous Learning Mediated by Digital Technology Processes in Higher Education: A Systematic Review

2020 , Fierro-Saltos W. , Sanz C. , Zangara A. , Guevara Maldonado, César Byron , Arias Flores, Hugo Patricio , Castillo Salazar, David Ricardo , Varela Aldas, José , Borja Galeas, Carlos , Rivera R. , Hidalgo-Guijarro J. , Yandún-Velasteguí M.

The concept of autonomous learning has been resignified in recent years as a result of the expansion of the different types of study. Online education in higher education institutions has become an effective option to increase and diversify opportunities for access and learning, however, high rates of dropout, reprisal and low averages still persist. academic performance. Recent research shows that the problem is accentuated because most students have difficulty self-regulating their own learning process autonomously. From this perspective, the purpose of the study was to examine and analyze, through a systematic review of the literature, on autonomous/self-regulated learning, theoretical models and determine which variables influence a learning process mediated by technology processes in the higher education. The findings indicate that: (1) autonomous learning is a synonym of self-regulation; (2) Pintrich’s self-regulatory model is the most used in digital contexts; and (3) the self-regulatory variables identified are wide and varied. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Detection of Student Behavior Profiles Applying Neural Networks and Decision Trees

2020 , Guevara Maldonado, César Byron , Sanchez-Gordon S. , Arias Flores, Hugo Patricio , Varela Aldas, José , Castillo Salazar, David Ricardo , Borja M. , Fierro-Saltos W. , Rivera R. , Hidalgo-Guijarro J. , Yandún-Velasteguí M.

Education worldwide is a significant aspect for the development of the peoples and much more in developing countries such as those in Latin America, where less than 22% of its inhabitants have higher education. Research in this field is a matter of interest for each of the governments to improve education policies. Therefore, the analysis of data on the behavior of a student in an educational institution is of utmost importance, because multiple aspects of progress or student dropout rates during their professional training period can be identified. The most important variables to identify the student’s behavior are the socio-economic ones, since the psychological state and the economic deficiencies that the student faces while is studying can be detected. This data provides grades, scholarships, attendance and information on student progress. During the first phase of the study, all the information is analyzed and it is determined which provides relevant data to develop a profile of a student behavior, as well as the pre-processing of the data obtained. In this phase, voracious algorithms are applied for the selection of attributes, such as greedy stepwise, Chi-squared test, Anova, RefiefF, Gain Radio, among others. In this work, we apply the artificial intelligence techniques, the results obtained are compared to generate a normal and unusual behavior of each student according to their professional career. In addition, the most optimal model that has had a higher accuracy percentage, false positive rate, false negative rate and mean squared error in the tests results are determined. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Diagnosis and Degree of Evolution in a Keratoconus-Type Corneal Ectasia from Image Processing

2023 , Otuna-Hernández D. , Espinoza-Castro L. , Yánez-Contreras P. , Villalba-Meneses F. , Cadena-Morejón C. , Guevara Maldonado, César Byron , Cruz-Varela J. , Tirado-Espín A. , Almeida-Galárraga D.

Keratoconus is a degenerative ocular pathology characterized by the thinning of the cornea, thus affecting many people around the world since this corneal ectasia causes a deformation of the corneal curvature that leads to astigmatism and, in more severe cases, to blindness. Treating physicians use non-invasive instruments, such is the case of Pentacam®, which takes images of the cornea, both the topography and the profile of the cornea, which allows them to diagnose, evaluate and treat this disease; this is known as morphological characterization of the cornea. On the other hand, Berlin/Ambrosio analysis helps in the identification and subsequent diagnosis since this analysis uses a mathematical model of linear progression, which identifies the different curves with the severity of the disease. Therefore, the aim of this study is to use the images provided by Pentacam®, Berlin/Ambrosio analysis, and vision parameters in a convolutional neural network to evaluate if this disparity could be used to help with the diagnosis of keratoconus and, consequently, generate a more precise and optimal method in the diagnosis of keratoconus. As a result, the processing and comparison of the images and the parameters allowed a 10% increase in the results of specificity and sensitivity of the mean and severe stages when combining tools (corneal profile and vision parameters) in the CNN reaching ranges of 90 to 95%. Furthermore, it is important to highlight that in the early-stage study, its improvement was around 20% in specificity, sensitivity, and accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

View