• Hybrid Model Based on Machine Learning for the Prediction of Consumer Credit Delinquency in the Banking Sector of Peru

  Kraenau, Nicole; Silva, Mariano; Castaneda, Pedro (Institute of Electrical and Electronics Engineers Inc., 2024-01-01)

  The delinquency rate among clients of banking institutions in Peru has increased exponentially in recent years, due to the lack of early detection of potentially delinquent clients, mainly due to the use of inadequate prediction techniques for the identification of delinquent clients. This causes profitability to be reduced, credit risk to increase and the country's economy to be unstable. Previously, different solutions were generated to prevent non-payment, however these studies were not applied in the Peruvian environment and did not cover the personal and financial variables necessary to improve the detection of delinquent clients. In this work, a delinquency prediction system is proposed using classification algorithms such as logistic regression and Random Forest, with the aim of improving and automating the early detection of delinquent clients and counteracting the increase in delinquency, so that banks can of Peru can reduce their financial losses due to non-payment by delinquent clients, and prevent the granting of consumer loans to clients who have a high probability of delinquency. After validating the performance of the algorithm using key indicators, it was obtained that the results are superior to the compared algorithms, thus showing a precision of 90 percent, a recall of 95 percent and an accuracy of 91 percent.

  Acceso restringido temporalmente
• A Machine Learning-Based Predictive Model for the Management of Incidents in Small and Medium-Sized Enterprises in Peru

  Cribillero, Luis F.; Quispe, Jeyson I.; Castañeda, Pedro (Association for Computing Machinery, 2024-03-22)

  In the context of IT incident management, the prioritization and automation of tickets can be a challenge for companies that lack advanced technologies. However, these difficulties can be overcome today by applying machine learning algorithms and techniques that use historical data to train predictive models, which allows for more efficient and effective IT incident management. The article proposes the implementation of a predictive model that uses machine learning to prioritize IT incidents in these companies. The goal of this proposal is to allow small and medium-sized enterprises to prioritize their incidents automatically, using a model that has been previously trained with a supervised multi-label classification algorithm technique to achieve high accuracy. Experimental results show that the Mean Absolute Error (MAE) is 2.79 and a Mean Squared Error (MSE) of 8.21, using the metrics provided by the scikit-learn library. Additionally, the entropy loss approaches a value of 0, suggesting a precise ability of the model to predict real values. Additionally, an average accuracy level of 93.74% was achieved.

  Acceso restringido temporalmente
• 

  A Performance Evaluation of Convolutional Neural Network Architectures for Pterygium Detection in Anterior Segment Eye Images

  Moreno-Lozano, Maria Isabel; Ticlavilca-Inche, Edward Jordy; Castañeda, Pedro; Wong-Durand, Sandra; Mauricio, David; Oñate-Andino, Alejandra (Multidisciplinary Digital Publishing Institute (MDPI), 2024-09-01)

  In this article, various convolutional neural network (CNN) architectures for the detection of pterygium in the anterior segment of the eye are explored and compared. Five CNN architectures (ResNet101, ResNext101, Se-ResNext50, ResNext50, and MobileNet V2) are evaluated with the objective of identifying one that surpasses the precision and diagnostic efficacy of the current existing solutions. The results show that the Se-ResNext50 architecture offers the best overall performance in terms of precision, recall, and accuracy, with values of 93%, 92%, and 92%, respectively, for these metrics. These results demonstrate its potential to enhance diagnostic tools in ophthalmology.

  Acceso abierto
• Web application based on the Fuzzy Analytic Hierarchy Process (FAHP) to optimize the selection of suppliers

  Rantes, Ronnie; Acosta, Piero; Castaneda, Pedro (Institute of Electrical and Electronics Engineers Inc., 2024-01-01)

  Small and medium-sized enterprises have always proven to be crucial to national economies, yet many of them fail for a variety of reasons. One of them is selecting an inadequate supplier that does not meet the needs that the company requires to properly perform its core business. Therefore, this project proposes to develop a web application to select the best supplier option for a company. The main objective is to assist in decision making and reduce costs with a web application that implements the Fuzzy Analytic Hierarchy Process (FAHP), based on a series of criteria and priorities chosen by the company itself. After testing the application, the result was a relative score assigned to each alternative, thus identifying the supplier with the highest value as the most optimal choice. Finally, through the measurement of the consistency ratio for each pair matrix developed, it was possible to verify that the solution achieved acceptable results that do not exceed the range of inconsistency.

  Acceso restringido temporalmente
• System to optimize the process of booking medical appointments for people with upper extremity disabilities

  Monrroy, Gino P.; Castaneda, Pedro S. (Institute of Electrical and Electronics Engineers Inc., 2024-01-01)

  People with upper extremity disabilities often face significant challenges when attempting to book medical appointments through conventional online booking systems. These barriers can hinder their ability to access essential healthcare services in a timely manner. To address this problem, this research focuses on the development of an innovative medical appointment booking system that uses voice interaction, complemented by a chatbot interface, to improve the user experience for people with upper extremity disabilities. As a result, a marked improvement in medical appointment booking times was achieved, increasing satisfaction and compliance levels among all users.

  Acceso restringido temporalmente
• Technological System for Improving Physical Performance in Children from 4 to 8 Years Old with High Obesity Rates of Type 1 and 2 Using IoT-Based Wearables in Private Schools in Metropolitan Lima

  Espejo-Gonzalez, Alejandro; Bancayan-Aranda, Felix; Burga-Durango, Daniel (Springer Science and Business Media Deutschland GmbH, 2024-01-01)

  According to a study conducted by UNICEF, the main causes of childhood obesity are the high consumption of processed foods and the low amount of physical activity performed by children, generating a higher risk of respiratory, metabolic and cardiovascular conditions. Based on research conducted in different studies, we found that there are not many technologies that monitor and improve the physical performance of children. This paper presents a technological system based on IoT and using wearables to improve the physical performance of children with high obesity rates type 1 and 2. This technological system was verified by conducting a study with 30 children between 4 and 8 years old, evaluating their physical activity and collecting the data obtained from the smartwatch. This study showed, according to the conclusions found, that it is a useful tool for the collection of data required by specialists and easy to use for children and their parents. In addition, it is a means to overcome the obesity problem.

  Acceso restringido temporalmente
• ERP System Based on Process Mining for Improving Logistic Management Efficiency in Small and Medium-Sized Enterprises in the Industrial Sector

  Rojas, Kevin J.; Dávila, Emerson M.; Castañeda, Pedro (Springer Science and Business Media Deutschland GmbH, 2024-01-01)

  The logistics process in small and medium-sized enterprises (SMEs) in the industrial sector is often exposed to various challenges, such as information loss, redundant activities, prolonged waiting times, and delivery failures, due to poor logistics management. In response to this problem, the implementation of an ERP system based on Process Mining is proposed to enhance the management of the logistics process in SMEs within the industrial sector. This system represents a comprehensive technological solution specifically designed to address logistics inefficiencies and optimize processes in the supply chain of these companies. As part of the evaluation methodology, performance indicators have been established to discuss the results obtained. These indicators have been defined using the Celonis tool, which has been employed for process mining. Findings obtained from the analysis of 30,000 records validate the optimization of the logistics process in companies within this sector, demonstrating a significant reduction in the percentage of key indicators for undesired activities in the logistics process.

  Acceso restringido temporalmente
• System to Prevent the Development of Dermatological Diseases Generated by Overexposure to UV Radiation during Childhood using Open Weather Map API and IoT Wearables

  Uribe, Rodrigo A.; Santamaria, Pedro A.; Castañeda, Pedro S. (Institute of Electrical and Electronics Engineers Inc., 2024-01-01)

  Excessive UV exposure during childhood significantly elevates the risk of dermatological issues, such as premature aging and liver spots, compared to exposure during adulthood. Children typically receive a substantially higher UV dose annually compared to adults, with an average of three times the exposure. By the age of 18, a child may have already received a significant portion, ranging from 50% to 80%, of their lifetime solar radiation exposure. During childhood, children are particularly vulnerable to the harmful effects of excessive sun exposure, as this stage of life often entails prolonged periods of direct UV radiation. This dependency on parental decisions regarding sun exposure duration and protective measures underscores a critical issue. Despite the importance of informed decisions, factors such as insufficient understanding of skin types and misconceptions about UV radiation on cloudy days contribute to inadequate prevention measures. To tackle this problem, our project proposes an innovative solution leveraging the Open Weather Map API in conjunction with wearable IoT devices. This system aims to provide real-time updates on UV radiation levels, empowering parents with valuable information to make more informed choices regarding their children's sun protection. Additionally, personalized reminders and advice tailored to the current weather conditions could be integrated into the system.

  Acceso restringido temporalmente
• Predictive model based on machine learning for raw material purchasing management in the retail sector.

  Antunez, Julio C.; Salazar, Johnny D.; Castañeda, Pedro S. (Association for Computing Machinery, 2024-06-28)

  Making raw material purchase forecasts for companies is very difficult and, if inadequately controlled, can affect the company's decision making and profitability. Currently, there are optimized systems or mathematical models to try to predict the demands and solve this problem. In this study, a raw material purchase prediction model is proposed that uses the Elastic Net algorithm to analyze historical sales and inventory data. The model is used to improve prediction accuracy, allowing SMEs to optimize inventories, reduce costs and improve efficiency. Experimental results indicate that the proposed model obtains better results in the MAE, RMSE and R2 indicators.

  Acceso restringido temporalmente
• 

  Predicting Smartphone Addiction in Teenagers: An Integrative Model Incorporating Machine Learning and Big Five Personality Traits

  Osorio, Jacobo; Figueroa, Marko; Wong, Lenis (Science Publications, 2024-01-01)

  Smartphone addiction has emerged as a growing concern in society, particularly among teenagers, due to its potential negative impact on physical, emotional social well-being. The excessive use of smartphones has consistently shown associations with negative outcomes, highlighting a strong dependence on these devices, which often leads to detrimental effects on mental health, including heightened levels of anxiety, distress, stress depression. This psychological burden can further result in the neglect of daily activities as individuals become increasingly engrossed in seeking pleasure through their smartphones. The aim of this study is to develop a predictive model utilizing machine learning techniques to identify smartphone addiction based on the "Big Five Personality Traits (BFPT)". The model was developed by following five out of the six phases of the "Cross Industry Standard Process for Data Mining (CRISP-DM)" methodology, namely "business understanding," "data understanding," "data preparation," "modeling," and "evaluation." To construct the database, data was collected from a school using the Big Five Inventory (BFI) and the Smartphone Addiction Scale (SAS) questionnaires. Subsequently, four algorithms (DT, RF, XGB LG) were employed the correlation between the personality traits and addiction was examined. The analysis revealed a relationship between the traits of neuroticism and conscientiousness with smartphone addiction. The results demonstrated that the RF algorithm achieved an accuracy of 89.7%, a precision of 87.3% the highest AUC value on the ROC curve. These findings highlight the effectiveness of the proposed model in accurately predicting smartphone addiction among adolescents.

  Acceso abierto
• Framework for the Adaptive Learning of Higher Education Students in Virtual Classes in Peru Using CRISP-DM and Machine Learning

  Bautista, Maryori; Alfaro, Sebastian; Wong, Lenis (Science Publications, 2024-01-01)

  During the COVID-19 pandemic, virtual education played a significant role around the world. In post-pandemic Peru, higher education institutions did not entirely dismiss the online education modality. However, this virtual education system maintains a traditional teaching-learning model, where all students receive the same content material and are expected to learn in the same way; as a result, it has not been effective in meeting the individual needs of students, causing poor performance in many cases. For this reason, a framework is proposed for the adaptive learning of higher education students in virtual classes using the Cross-Industry Standard Process for Data Mining (CRISP-DM) and Machine Learning (ML) methodology in order to recommend individualized learning materials. This framework is made up of four stages: (i) Analysis of student aspects, (ii) Analysis of Learning Methodology (LM), (iii) ML development and (iv) Integration of LM and ML models. (i) evaluates the student-related factors to be considered in adapting their learning content material. (ii) Evaluate which LM is more effective in a virtual environment. In (iii), Four ML algorithms based on the CRISP-DM methodology are implemented. In (iv), The best ML model is integrated with the LM in a virtual class. Two experiments were carried out to compare the traditional teaching methodology (experiment I) and the proposed framework (experiment 2) with a sample of 68 students. The results showed that the framework was more effective in promoting progress and academic performance, obtaining an Improvement Percentage (IP) of 39.72%. This percentage was calculated by subtracting the grade average of the tests taken at the beginning and end of each experiment.

  Acceso restringido temporalmente
• 

  AyudaMujer: A Mobile Application for the Treatment of Violence Against Women in Peru

  Mauricio, David; Zeña, Alejandro; Avila, Umer; Castañeda, Pedro; García, Lupe; Maculan, Nelson (Routledge, 2024-01-01)

  Violence against women in Peru is a problem that has a high incidence and is increasing, despite the policies undertaken by past governments and the creation of the Ministry of Women and Vulnerable Populations in 1996, causing that one in two women have been abused at some point in their lives. However, the treatment of abused women is still insufficient even though there are more Women’s Emergency Centers (WEC) each year, where victims can ask for professional support and treatment quickly and effectively. The chatbot provides an alternative to eliminate the distance between the abused woman and the WEC; therefore, a mobile application called AyudaMujer is proposed that includes a chatbot, news, a map of nearby WECs, and the connection with specialists for the treatment of violence against women. The chatbot identifies, automatically and through a natural dialogue, the type of violence and its level of risk. Additionally, it assigns a specialist to provide personalized professional treatment. The testing of AyudaMujer with 20 abused women from Lima, Peru, shows that the risk of violence is reduced by an average of 19.43% after three weeks of use. The results show that this tool can contribute to the treatment of abused women.

  Acceso abierto
• Generator of User Interfaces for Mobile Applications from the Recognition of Patterns in Wireframes

  Namuche, Valerie; Silva, Alexia; Barrientos, Alfredo (International Institute of Informatics and Cybernetics, 2023-01-01)

  The importance of mobile development has significantly grown as technology becomes more accessible, leading to increased interconnectivity in society. To keep pace with evolving trends, businesses and companies allocate development departments to create mobile applications that meet current and ever-changing needs. However, developers often encounter numerous challenges during the software development cycle. One common issue is the conversion of wireframes, which are designed to meet functional requirements and engage customers, into functional GUI code. This manual conversion process can be cumbersome, slow, and error-prone, consuming valuable time that could be spent on developing other functionalities. This paper aims to address this problem by introducing a website that offers an automated alternative to the wireframe-to-graphic user interface transformation process. Leveraging pattern recognition and machine learning techniques, the website streamlines and accelerates the conversion, eliminating the need for manual coding. Furthermore, the paper presents the results of a questionnaire administered to a group of software developers specializing in mobile development. The developers were shown a demo of the website, and their feedback and responses are analyzed and discussed.

  Acceso restringido temporalmente
• Competency Model for Product Owners and Product Managers

  Barnett Urtecho, Sebastian J.; Muñoz Gonzales, Joaquin; Barrientos Padilla, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)

  The objective of this article is to develop a competency model for Product Owners and Product Managers that enables them to perform successfully in their roles. The article goes through several stages, with the first being the study and analysis phase. In this stage, the problems, related work for the mentioned roles, and the literature used for the model design process will be analyzed. Subsequently, the competency model for Product Owners and Product Managers will be designed to establish the competencies that these roles should possess. This will also help companies in hiring qualified individuals for product development. Finally, the model will be validated through the evaluation of experts in the field, using virtual interviews and a Likert scale-based survey. These techniques will allow for the collection of quantitative data to support the validity of the model. © 2023 CISCI 2023 - Vigesima Segunda Conferencia Iberoamericana en Sistemas, Cibernetica e Informatica, Vigesimo Simposium Iberoamericano en Educacion, Cibernetica e Informatica, SIECI 2023

  Acceso restringido temporalmente
• Software for Generating Reports of Automated Tests Using RPA in Web Applications

  Arévalo, Fernando R.; Alvarado, Manuel A.; Barrientos, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)

  Many companies have adopted the Agile methodology for software project implementation, which involves an iterative and incremental approach. This introduces changes to the software testing lifecycle, as the developed functionalities need to be validated in each iteration. Thus, to avoid manual testing and human error, test automation emerges as a technique for executing functional tests. However, automating tests and analyzing their results in Agile environments can be a complex process due to constantly changing requirements. Therefore, this study focuses on the development of software for generating reports of automated tests, presenting key performance indicators that measure the efficiency and effectiveness of the testing process. Additionally, RPA technology was used for the automation and execution of functional tests in web applications. Finally, the satisfaction level of the developed software was validated with a group of users, resulting in a 46.72% improvement in user perception regarding the ease of performing tasks with the proposed solution compared to the current context in their workplaces. © 2023 CISCI 2023 - Vigesima Segunda Conferencia Iberoamericana en Sistemas, Cibernetica e Informatica, Vigesimo Simposium Iberoamericano en Educacion, Cibernetica e Informatica, SIECI 2023

  Acceso restringido temporalmente
• Development of an Online Multiplayer RTS Video Game for Windows PC

  Gonzales, André G.; Gavilano, Guillermo G.; Barrientos, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)

  In recent years, the video game industry has experienced significant growth, as a large portion of the global population has turned to gaming as a pastime during the COVID-19 pandemic. However, not all genres of video games have been part of this surge in popularity. This is the case for real-time strategy (RTS) games, whose popularity has been declining over time, despite the cognitive benefits they offer, such as improved information processing and visual cognitive enhancement. Therefore, the development of a multiplayer real-time strategy game for Windows PC called “Cosmic Crusade” is proposed. This game is designed to provide a quick understanding of its mechanics and gameplay. This article outlines the development procedures for the Cosmic Crusade video game and includes validation efforts aimed at confirming and ensuring user satisfaction with the game. © 2023 CISCI 2023 - Vigesima Segunda Conferencia Iberoamericana en Sistemas, Cibernetica e Informatica, Vigesimo Simposium Iberoamericano en Educacion, Cibernetica e Informatica, SIECI 2023 - Memorias.

  Acceso restringido temporalmente
• A Model for Tracking Indicators and Achieving Goals Under an Agile Approach Using Scrum and OKRs

  Gutierrez Navarrete, Giovanni Raul; Martinez Sanchez, Jason Alexander; Barrientos Padilla, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)

  Organizations across different industries are gradually transforming their operational approaches toward an agile mindset. This shift is driven by the need and demand in a constantly changing and competitive environment. One of the most well-known and adopted agility frameworks is Scrum, which advocates for activities with incremental value delivery. While Scrum offers a way to streamline team work, it doesn't necessarily guarantee success or ensure that teams are working on what truly matters. This work presents a model that combines Scrum with OKRs (Objectives and Key Results), allowing organizations to define relevant, challenging, and meaningful objectives while also specifying how progress toward these objectives will be measured through Key Results. OKRs contribute to focus and alignment so that teams implementing and working under the Scrum framework can make improvements to products, services, or operations and generate more value. Through validation using expert judgment and a Top Two Box analysis, it was determined that professionals perceive a high level of interest and potential in this proposal. © 2023 CISCI 2023 - Vigesima Segunda Conferencia Iberoamericana en Sistemas, Cibernetica e Informatica, Vigesimo Simposium Iberoamericano en Educacion, Cibernetica e Informatica, SIECI 2023

  Acceso restringido temporalmente
• Product Management Model for Entrepreneurship

  Mascaro Sifuentes, Jose; Garcia Muñoz, Alvaro; Barrientos Padilla, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)

  After the COVID pandemic in 2019, the number of startups and entrepreneurship ventures grew exponentially. This article aims to develop a Product Management Model for Entrepreneurship, which allows users to have a better view of the company's financial status. The goal is to facilitate decision-making and optimal resource management. This research consists of several stages. In the first stage, an analysis of the environment and the current situation of the problem was conducted, along with a review of related research papers. Additionally, an analysis of the most important Product Management models currently in use was performed to understand the most relevant aspects and implement an innovative model. Following the study process, the foundational elements of the model were designed, including the metrics involved, as well as the relationships and connections between them, the projection time, and the financial values for simulating the model in a real-world scenario. Finally, the model will be validated by experts in the field through virtual interviews and a Likert scale-based survey. The quantitative data collected will support the validity of the model. © 2023 CISCI 2023 - Vigesima Segunda Conferencia Iberoamericana en Sistemas, Cibernetica e Informatica, Vigesimo Simposium Iberoamericano en Educacion, Cibernetica e Informatica, SIECI 2023 - Memorias.

  Acceso restringido temporalmente
• Implementation of a system for documentary procedures in public institutions applying Robotic Process Automation (RPA)

  Ramirez, Christian Flores; Reyes Guzman, Judyth; Cornejo, Richard Copaja (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)

  The research has shown that, in Peru, public institutions have a deficient service in document management, as a result, it generates loss of time, accumulation and low security of documents, which affects citizens. Therefore, this paper proposes to implement RPA technology through a web system, which has been developed, as objective of automating the workflow and avoiding performing repetitive tasks. This technological solution will generate great improvements for public institutions such as the reduction of the attention time for a procedure in order to prevent the dissatisfaction of citizens. The proposed solution is verified through evaluations based on the indicators presented. Finally, a considerable improvement was shown in the procedures, improving the experience of citizens and workers by reducing the attention time from 516 minutes to 490 minutes on average, which implies a saving of approximately 26 minutes, but it should be noted that the attention time for a procedure may vary depending on the type of procedure.

  Acceso restringido temporalmente
• Maturity model for data leakage security protocols in telecommunications companies applying the NIST framework

  Leon, Solis; Joel, Brian; Jara, Di Paola; Giovanni, Renzo; Cornejo, Copaja; Nivaldo, Richard (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)

  Attacks on information security and data leaks in telecommunications companies in Peru cause considerable losses both financially and in terms of social reputation. For this reason, response protocols have been implemented to deal with these situations. However, the mere implementation and development of these protocols is not enough to effectively prevent or counter attacks. Therefore, a technological solution is proposed that combines a maturity assessment model for protocols and a reporting system that provides information on the current level and possible improvements that can be applied to the assessed protocols. The project aims to reduce attacks on companies in the telecommunications sector and at the same time enable them to assess the state of their protocols in terms of cybersecurity, giving them greater insight into possible situations that could result from protocol misuse. To validate the project, 4 cybersecurity experts were involved, who have used it for a given period to obtain sufficient information to offer their opinion. At the end of the period of use, a form was sent to them to evaluate the level of satisfaction with the project, using the indicators that were established. The final level of satisfaction obtained was 81.39%, which indicates that the project has been successful according to the evaluation of the security experts.

  Acceso restringido temporalmente

View more