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

34
25 9
Reset filters

Settings
Now showing 1 - 10 of 34
No Thumbnail Available
Publication

Twitter Mining for Multiclass Classification Events of Traffic and Pollution

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

During the last decade social media have generated tons of data, that is the primal information resource for multiple applications. Analyzing this information let us to discover almost immediately unusual situations, such as traffic jumps, traffic accidents, state of the roads, etc. This research proposes an approach for classifying pollution and traffic tweets automatically. Taking advantage of the information in tweets, it evaluates several machine learning supervised algorithms for text classification, where it determines that the support vector machine (SVM) algorithm achieves the highest accuracy value of 85,8% classifying events of traffic and not traffic. Furthermore, to determine the events that correspond to traffic or pollution we perform a multiclass classification. Where we obtain an accuracy of 78.9%. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Editorial Design Based on User Experience Design

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

This research deals with editorial design based on user experience design. The traditional editorial design has had to adapt to the new digital media composition, where multimedia audiovisual elements unthinkable a few years ago need to be integrated. The participation of the reader, as an external observer who only receives information through texts and images, now has new scenarios in which he can actively participate and decide what will come to his hands. In this study, a work methodology based on UxD User Experience Design is presented, in which will generate the editorial design of an educational book on environmental issues, which includes augmented reality for children from 6 to 8 years of age. The aim of this study is to know if an editorial product with augmented reality and developed from the user experience design can improve meaningful learning in a playful and active way. For its development, a composition model based on the Fibonacci sequence and the golden ratio will be used. Additionally, its graphic composition will be guided by the Massimo Vignelli canon and will be complemented by the reticular model of Beth Tondreau. The augmented reality markers position will also be based on the composition model previously mentioned, which will allow keeping the attention of the reader in the printed document and in the augmented reality animations. The user experience design will be applied with teachers, parents and students from 4 schools in Quito and Ambato. Once the production is completed, the impact on teaching-learning process will be evaluated with a control and a test group, and the methodology with which they will work in the classroom with the educational material developed will be defined. At the end of the study, copies of the book will be delivered to the participating schools of this research for its implementation. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Application to guide people with visual disability on internal buildings, using beacon bluetooth positioning systems

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

In the actuality there are many devices to help people with visual disability, at the level of mobile devices like Smart Phones, tablets, PCS, some of them increasing the size of the letter, or reading icons or maybe incorporating voice technology to read the text or to recognize the voice, these devices help to people with visual disability that they can interact and do things that people couldn’t do every day, helping their day by day, and above all do activities of interaction of man with machine. Additionally there are several applications that incorporate GPS navigation technology, for localization and geography location, one person can use navigation applications for be able to locate even using just the GPS module without the need to have internet connection, little by little this service has become very popular, it is include in autonomous cars, to be able to go to one place to another easily, just showing the destination the people are directed without the need to drive, however this system doesn’t work inside of the buildings or internal structures because the GPS signal could be lost and the navigation and obtaining the location is not accurate. The propose of this article is for the use of beacons with techniques based on the received signal strength indication (RSSI), also distance mediation techniques to calculate the exact position of the individual, solving the lost signal of GPS devices, this calculation is done using triangulation algorithms to get the localization, Additionally, it was used beacons, this devices are operate with Bluetooth technology 4.0, and by not having GPS location antenna this devices can be obtained a proximity value and distance to the beacon using UUID, and proximity, connecting to an Smart Phone device or a tablet to the connection through the Bluetooth, In addition an application was developed using Studio Android and a library called proximi.io this library is absolutely compatible with IOS and Android, this application connects to a database to determinate the position and identify the beacons, Additionally to identify the location of the individual through his Smart We use a triangulation algorithm to obtain data with greater precision it is necessary to use at least 3 beacons, to complete the study, were performed test in corridors of buildings and several places obtaining good results it could be verified that the triangulation algorithm with some improvement variants facilitates to obtain the location with greater effectiveness in general, for our purpose it was possible to determine that is feasible to use these devices in favor of people with visual disabilities, you can use many projects with beacons and applications in public places such as hospitals, airports, educational institutions, museums, shopping centers, etc.,. In short, the application is very broad and many benefits can be obtained. © Springer Nature Switzerland AG 2020.

View
No Thumbnail Available
Publication

Fuzzy model for back posture correction during the walk

2020 , Guevara Maldonado, César Byron , Jadán Guerrero, Janio , Bonilla-Jurado, Diego , Salvador-Ullauri L. , Acosta-Vargas P. , Calle-Jimenez T. , Lara Álvarez, Patricio

The body posture is not a purely aesthetic problem, due to it can produce a multitude of adverse effects on health, even extremities disorders (injuries) and malfunction of organs. This study focuses on the correct and incorrect detection of the position of the spine and extremities while walking. A database of three patients with lumbago and sciatica, with diagnosis of muscle tension due to poor posture while walking, has been used in this article. These patients underwent physiotherapy treatment and were later filmed taking a short walk of 2 min to see the results. This process was developed for a period of 4 weeks, divided into 2 h of physiotherapy per week and 1 h of compilation of videos with the results obtained. To detect the correct movement of each of the patients, the Kinect Xbox One device was used. It identifies all body points, alignment, speed and angles during the walk. 25 points of human body in three dimensions are detected in real time by the Kinect, which allows to generate a data collection in real time and more efficiently. With the database of patients, a pre-processing of the information is done to identify the most relevant points for our study. A fuzzy model is generated which determines maximum and minimum thresholds for the posture of the back (angle of inclination), shoulders posture (shoulders inclination with respect to the spine), head posture (inclination with respect to horizontal vision) and movement of arms. The model dynamically identifies which position is correct for the movement during the walk, and in addition, the progress that is generated during a time series. This prototype detector is used for rehabilitation of high-performance athletes and is an approximation for the correct posture during long and medium distance races, jumps, among other sports that use the walk as a basis in their workouts. This study was based on the solution of back problems in clinical patients. These preliminary tests have given excellent results in the testing phase, which validates it as an option to prevent injuries in patients with these conditions. © 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

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

BackMov: Individualized Motion Capture-Based Test to Assess Low Back Pain Mobility Recovery after Treatment

2024 , Villalba-Meneses F. , Guevara Maldonado, César Byron , Velásquez-López P.A. , Arias-Serrano I. , Guerrero-Ligña S.A. , Valencia-Cevallos C.M. , Almeida-Galárraga D. , Cadena-Morejón C. , Marín J., Marín J.J.

Low back pain (LBP) is a common issue that negatively affects a person’s quality of life and imposes substantial healthcare expenses. In this study, we introduce the (Back-pain Movement) BackMov test, using inertial motion capture (MoCap) to assess lumbar movement changes in LBP patients. The test includes flexion–extension, rotation, and lateralization movements focused on the lumbar spine. To validate its reproducibility, we conducted a test-retest involving 37 healthy volunteers, yielding results to build a minimal detectable change (MDC) graph map that would allow us to see if changes in certain variables of LBP patients are significant in relation to their recovery. Subsequently, we evaluated its applicability by having 30 LBP patients perform the movement’s test before and after treatment (15 received deep oscillation therapy; 15 underwent conventional therapy) and compared the outcomes with a specialist’s evaluations. The test-retest results demonstrated high reproducibility, especially in variables such as range of motion, flexion and extension ranges, as well as velocities of lumbar movements, which stand as the more important variables that are correlated with LBP disability, thus changes in them may be important for patient recovery. Among the 30 patients, the specialist’s evaluations were confirmed using a low-back-specific Short Form (SF)-36 Physical Functioning scale, and agreement was observed, in which all patients improved their well-being after both treatments. The results from the specialist analysis coincided with changes exceeding MDC values in the expected variables. In conclusion, the BackMov test offers sensitive variables for tracking mobility recovery from LBP, enabling objective assessments of improvement. This test has the potential to enhance decision-making and personalized patient monitoring in LBP management. © 2024 by the authors.

View
No Thumbnail Available
Publication

COVID-19 spread algorithm in the international airport network-DetArpds

2023 , Guevara Maldonado, César Byron , Coronel D. , Maldonado B.E.S. , Flores J.E.S.

Due to COVID-19, the spread of diseases through air transport has become an important issue for public health in countries globally. Moreover, mass transportation (such as air travel) was a fundamental reason why infections spread to all countries within weeks. In the last 2 years in this research area, many studies have applied machine learning methods to predict the spread of COVID-19 in different environments with optimal results. These studies have implemented algorithms, methods, techniques, and other statistical models to analyze the information in accuracy form. Accordingly, this study focuses on analyzing the spread of COVID-19 in the international airport network. Initially, we conducted a review of the technical literature on algorithms, techniques, and theorems for generating routes between two points, comprising an analysis of 80 scientific papers that were published in indexed journals between 2017 and 2021. Subsequently, we analyzed the international airport database and information on the spread of COVID-19 from 2020 to 2022 to develop an algorithm for determining airport routes and the prevention of disease spread (DetARPDS). The main objective of this computational algorithm is to generate the routes taken by people infected with COVID-19 who transited the international airport network. The DetARPDS algorithm uses graph theory to map the international airport network using geographic allocations to position each terminal (vertex), while the distance between terminals was calculated with the Euclidian distance. Additionally, the proposed algorithm employs the Dijkstra algorithm to generate route simulations from a starting point to a destination air terminal. The generated routes are then compared with chronological contagion information to determine whether they meet the temporality in the spread of the virus. Finally, the obtained results are presented achieving a high probability of 93.46% accuracy for determining the entire route of how the disease spreads. Above all, the results of the algorithm proposed improved different computational aspects, such as time processing and detection of airports with a high rate of infection concentration, in comparison with other similar studies shown in the literature review. © 2023 Guevara et al.

View
No Thumbnail Available
Publication

Biomechanical Study of the Eye with Keratoconus-Type Corneal Ectasia Using a 3D Geometric Model

2023 , Sánchez-Real E. , Otuna-Hernández D., , Fajardo-Cabrera A. , Davies-Alcívar R. , Madrid-Pérez M. , Cadena-Morejón C. , Almeida-Galárraga D. , Guevara Maldonado, César Byron , Tirado-Espín A. , Villalba-Meneses F.

Keratoconus is an eye disease that distorts the shape of the cornea. This study aimed to analyze the effect of an increase in intraocular pressure applied to eyes with different severity of keratoconus disease using patient-specific models. Finite element models of the normal eye, eye with keratoconus, and eye with keratoglobus were constructed. The loading conditions considered the intraocular pressure increment as well as their physiological intraocular pressure. The analysis was performed with distinct materials for normal and keratoconic eyes. The finite element analysis revealed differences in the three models in terms of their deformation and maximum principal stress, and differences were observed in corneal curvature and thickness. These findings could enhance research in the biomechanical area, leading to more successful treatment options and a more individualized approach in the field of practical ophthalmology. Further investigation with larger sample sizes and more precise data on eye material would allow us to evaluate whether these disparities could inform the diagnosis of keratoconus. © 2023 by the authors.

View
No Thumbnail Available
Publication

Generation of User Profiles in UNIX Scripts Applying Evolutionary Neural Networks

2020 , Hidalgo J. , Guevara Maldonado, César Byron , Yandún M.

Information is the most important asset for institutions, and thus ensuring optimal levels of security for both operations and users is essential. For this research, during Shell sessions, the history of nine users (0–8) who performed tasks using the UNIX operating system for a period of two years was investigated. The main objective was to generate a classification model of usage profiles to detect anomalous behaviors in the system of each user. As an initial task, the information was preprocessed, which generates user sessions, where u identifies the user and m the number of sessions the user has performed u. Each session contains a script execution sequence, that is where n is the position where the command was executed. Supervised and unsupervised data mining techniques and algorithms were applied to this data set as well as voracious algorithms, such as the Greedy Stepwise algorithm, for attribute selection. Next, a Genetic Algorithm with a Neural Network model was trained to the set of sessions to generate a unique behavior profile for each user. In this way, the anomalous or intrusive behaviors of each user were identified in a more approximate and efficient way during the execution of activities using the computer systems. The results obtained indicate an optimum pressure and an acceptable false positive rate. © 2020, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

View