Now showing items 1-20 of 51

    • Use of Xception Architecture for the Classification of Skin Lesions

      Tejada, Cledmir; Espinoza, Gustavo; Subauste, Daniel (International Institute of Informatics and Cybernetics, 2024-01-01)
      This study investigates the application of the Xception architecture for accurate classification of skin lesions, focusing on the early detection of melanoma and other malignant skin conditions. Utilizing deep learning techniques, the research aims to enhance the precision and efficiency of skin lesions diagnosis. The study utilizes the TensorFlow framework and the HAM10000 dataset, comprising a vast collection of benign and malignant skin lesion images, for training and evaluating the Xception model. Preprocessing steps, including data splitting, augmentation, and image resizing, are applied to the dataset. The Xception architecture, a deep convolutional neural network, serves as the foundational model, supplemented with customized classification layers for specialized features and predictions. The model’s performance is evaluated using diverse metrics. The experimental outcomes reveal the Xception architecture’s potential in accurately classifying skin lesions. Moreover, the study underscores the significance of extensive and diverse datasets, as well as rigorous clinical validation, in the development of deep learning models for skin cancer detection. The findings contribute to the advancement of early melanoma detection, thereby improving patient outcomes and alleviating the burden of the disease.
      Acceso restringido temporalmente
    • Advergaming: An Advertising Technique to Integrate Deaf People into the Gaming World

      Cortez-Tuesta, María Fernanda; Gallardo-Echenique, Eliana (Universidad de La Sabana, 2024-01-01)
      Advergaming, one of the innovative advertising techniques, has the potential to creatively convey brand messages to the audience. In Peru, there is a gap in integrating deaf individuals into the advertising discourse of brands and campaigns, especially when utilizing advergaming to establish a strong connection with them. This study aims to fill this gap by analyzing how the Pilsen brand, through advergaming, has contributed to creating inclusive spaces. The study also seeks to determine which elements of the advertising technique are relevant for integrating the deaf community into the gaming world. To gain a comprehensive understanding, a qualitative methodology was adopted to analyze the E-nterpreters ad, and semi-structured interviews were conducted with 12 special education students in the tenth semester at a private university in Lima. The findings revealed that Pilsen’s advergaming technique has indeed contributed to creating inclusive spaces.
      Acceso abierto
    • Real-Time Retargeting of Human Poses from Monocular Images and Videos to the NAO Robot

      Burga, Oscar; Villegas, Jonathan; Ugarte, Willy (Korean Institute of Information Scientists and Engineers, 2024-01-01)
      To this point, there has been extensive research investigating human-robot motion retargeting, but the vast majority of existing methods rely on sensors or multiple cameras to detect human poses and movements, while many other methods are not suitable for usage on real-time scenarios. The current paper presents an integrated solution for performing realtime human-to-robot pose retargeting utilizing only regular monocular images and video as input data. We use deep learning models to perform three-dimensional human pose estimation on the monocular images and video, after which we calculate a set of joint angles that the robot must utilize to reproduce the detected human pose as accurately as possible. We evaluate our solution on Softbank’s NAO robot and show that it is possible to reproduce promising approximations and imitations of human motions and poses on the NAO robot, although it is subject to the limitations imposed by the robot’s degrees of freedom, joint constraints, and movement speed limitations. Category: Real-Time Systems
      Acceso restringido temporalmente
    • Framework for Enhancing Customer Service Advisor Training through Gamification

      Sierra, Christian Peña; Cutipa, Enrique Agreda; Wong, Lenis (Institute of Electrical and Electronics Engineers Inc, 2024-01-01)
      In the Peruvian financial sector, deficiencies persist in customer service training due to inadequate comprehension of work motivation and the absence of suitable incentives, reflective of concerns regarding skill shortages and operational inconsistencies among employees. This study proposes a gamification framework tailored to enhance the training of Customer Service advisors within financial entities, addressing the gap in specific training models for this crucial sector. Through analysis, design, and validation stages, the research scrutinizes existing methodologies and implements the framework within a financial Contact Center, yielding impressive results. Notably, a remarkable 85% reduction in training time (from 60 to 8.80 minutes) while maintaining consistent evaluation scores with a 1% increase, alongside a noteworthy 13% decrease in average evaluation duration, underscores the framework's efficacy. These findings emphasize its potential for continual enhancement in training practices, promoting heightened productivity, knowledge retention, and motivation among Customer Service advisors within the financial landscape.
      Acceso restringido temporalmente
    • Optimization model for healthcare processes using Process Mining

      Julca, Marice Aranza Regina Dorador; Cardenas, Angel Ruben L.; Armas-Aguirre, Jimmy; Mayorga, Santiago Aguirre (IEEE Computer Society, 2023-01-01)
      In this paper, we propose an optimization model for medical services processes to reduce waiting time using process mining. In medical services, there is a high percentage of dissatisfaction with medical care due to the processes related to appointment booking and waiting time for medical consultation. As a result, patients change medical services due to the urgency of the symptoms they suffer, generating distrust in health services in Peru. Through a medical information system, events of medical care processes are collected for analysis using the Celonis tool. The process mining discipline uses the discovery of the study process to identify existing bottlenecks in the process and violations that are included when monitoring process events. The proposed model is based on identifying the existing bottlenecks in the processes, which are appointment booking and office care, as these processes take an average of 135 minutes to execute, and this leads to patient dissatisfaction. The model is composed of 4 main phases: 1. Objectives definition and data processing phase; 2. For the validation of the proposal, a test scenario was defined in a Peruvian public health services organization (ESSALUD) in Satipo, Peru. Preliminary results show that the model reduces by 64% the average time corresponding to the medical consultation process and by 98% the appointment booking. Finally, optimization results increased by 45% and 46%, respectively.
      Acceso restringido temporalmente
    • Thermographic image processing analysis in a solar concentrator with hard C-means clustering

      Flores, Marco A.; Serrano, Fernando E.; Cadena, Carlos; Alvarez, Jose C. (Springer, 2023-09-01)
      Style transfer is a natural language processing generation task, it consists of substituting one given writing style for another one. In this work, we seek to perform informal-to-formal style transfers in the English language by using a style transfer model that takes advantage of the GPT-2. This process is shown in our web interface where the user input a informal message by text or voice. Our target audience are students and professionals in the need to improve the quality of their work by formalizing their texts. A style transfer is considered successful when the original semantic meaning of the message is preserved after the independent style has been replaced with a formal one with a high degree of grammatical correctness. This task is hindered by the scarcity of training and evaluation datasets alongside the lack of metrics. To accomplish this task, we opted to utilize OpenAI’s GPT-2 Transformer-based pre-trained model. To adapt the GPT-2 to our research, we fine-tuned the model with a parallel corpus containing informal text entries paired with the equivalent formal ones. We evaluate the fine-tuned model results with two specific metrics, formality and meaning preservation. To further fine-tune the model, we integrate a human-based feedback system where the user selects the best formal sentence out of the ones generated by the model. The resulting evaluations of our solution exhibit similar to improved scores in formality and meaning preservation to state-of-the-art approaches.
      Acceso abierto
    • Chatbot as a Persuasive Technology to Promote Responsible Recycling in the City of Lima

      Flores, Kevin Anderson Franco; Perez, James Jesus Grandez; Sanchez, Luis Martin Canaval (Institute of Electrical and Electronics Engineers Inc., 2022-01-01)
      Persuasive technologies have gained popularity around the world. This type of technology aims to change the behavior of people in different circumstances using the persuasion method. Within this classification of technologies we have virtual assistants whose function is to interact in a personalized way with the user. This research aims to provide a solution to the low levels of recycling habits in citizens, which is caused by inefficient programs and/or activities applied by authorities, educational centers and households of socioeconomic levels. low fees by promoting recycling issues. We proposed the use of a virtual assistant to increase knowledge and show the benefits of recycling, in order to generate an improvement in the behavior of the population. To validate this research, two knowledge tests on recycling issues were administered to 69 university students at the beginning and end of the process. After using our virtual assistant, the participants appeared and increased their knowledge by 70.49%.
      Acceso restringido temporalmente
    • Milchbot: App to Support the Process of Feeding and Caring for Dairy Cows in Peru

      Herrera, Kevin; Miranda, Juan; Mauricio, David (Faculty of Economics and Management, 2022-01-01)
      At present, Peru's agricultural sector has a shortfall of professionals, so livestock producers cannot be provided with relevant and reliable information to ensure good nutrition and care for dairy cows, which affects productivity. Milchbot is a chatbot that answers queries about the feeding and care of dairy cows based on reliable documentation. To do so, a chatbot model was designed to cover the topics of feeding, care, news and frequently asked questions for the planning, feeding and care processes about dairy cows. The model consists of a friendly interface, a dialog engine and a search engine that allows you to find and provide information from a document storage. This model was implemented employing Watson Assistant and Discovery. Milchbot was used and evaluated by 6 livestock producers and 7 zootechnicians. The results of the usability and satisfaction surveys show a high rating for both livestock producers and zootechnicians, and it should be noted that zootechnicians gave very high ratings on satisfaction.
    • Mobile Augmented Reality Application for Augmented Reality Visualization in the Educational Context

      Mazzarri Rodríguez, Carlos J.; Leyva Calle, Juan A.; Padilla, Alfredo Barrientos (International Institute of Informatics and Systemics, IIIS, 2023-01-01)
      Currently, continuous technological advancements are pervasive in society, enhancing various aspects of our lives, including entertainment, information, and communication. In this context, one of the primary domains that can benefit from these advancements is education. The constant technological developments must be applied to the educational system to keep pace with changes in our lifestyle. Augmented reality (AR) is an innovative technology that allows smartphones to combine the real environment with virtual objects. Through the device's accelerometer, gyroscope, and camera, AR places 3D models on the screen based on the user's movements, creating an interactive experience. This technology has the potential to improve the learning experience in schools, making teaching more dynamic and increasing student motivation and interest in subjects such as mathematics and sciences, among others. This paper proposes the creation of a mobile application with tools that will enable not only students but also teachers to visualize and interact with any 3D model related to school subjects, enhancing the learning process and making it more engaging for them. Additionally, teachers can add all the information they deem necessary to the page of each model to describe, explain, or highlight any relevant data for their class. The primary contribution of this study is that the system allows teachers to encapsulate knowledge into an organized learning unit, improving the learning experience for students. The impact of the application on learning was assessed through surveys administered to five high school teachers in the Metropolitan Area of Lima after they had tested the application.
      Acceso restringido temporalmente
    • Implementation Model of Agile Methodologies and Frameworks for the Human Resources Sector

      Revilla Llanos, Cinthy P.; Aguilar Vargas, Francesco A.; Barrientos Padilla, Alfredo E. (International Institute of Informatics and Systemics, IIIS, 2023-01-01)
      The purpose of this project is to develop a guidance implementation model that allows the use of different agile methodologies and frameworks in the Human Resources (HR) areas. The project will be carried out in phases, with the first phase being research and analysis. During this stage, successful cases, frameworks, agile methodologies, and complementary literature on agility for HR areas will be analyzed. Secondly, a useful reference and detailed consultation model for agile methodologies and frameworks will be designed with the aim of positively impacting the transformation of processes and services handled by HR specialists and leaders. Finally, this model will be validated based on feedback from HR experts who have some level of affinity with agility applied in their areas.
      Acceso restringido temporalmente
    • Performance Evaluation Model in Companies with Linear and Matrix Structures

      Rios Moreno, Victor Alejandro; Peña Wisky, Adrián Alexis; Barrientos Padilla, Alfredo E. (International Institute of Informatics and Systemics, IIIS, 2023-01-01)
      This project aims to develop a performance evaluation model that serves as an application guide for companies with both linear and matrix structures. The project will primarily be conducted in three stages. The initial stage involves an analysis of organizational structures and an examination of various performance evaluation models and frameworks. Subsequently, in the second stage of the project, based on the findings from the analysis stage, the model proposal will be developed. Finally, in the third stage, validation will be carried out with experts to assess the feasibility of the proposal.
      Acceso restringido temporalmente
    • Implementation of an RTS Video Game for Windows 10 (PC) Using the Unity Game Engine

      Barrientos, Alfredo; Ríos, Sergio A.; Oviedo, Johan D. (International Institute of Informatics and Systemics, IIIS, 2023-01-01)
      The video game industry has undergone one of the most significant transformations in recent times. This is reflected not only in the economic aspect but also in the increasing number of players who want to explore and interact in the world of video games in recent years. As for the Real-Time Strategy (RTS) genre, which reached its peak in the early 2000s, it did not continue to see the same trend in game development, and the population of active players has been declining [1]. The primary reason for this continuous decline is the competition from games in other genres such as First Person Shooter (FPS), Multiplayer Online Battle Arena (MOBA), and other genres with attractive characteristics that set them apart. In response to this, a solution is offered, which involves the development of a multiplayer RTS video game for Windows operating systems (PC), with the aim of generating greater interest among both beginner and expert players. This document will explain the procedures for the functional and aesthetic development of the video game, as well as validation regarding the user experience.
      Acceso restringido temporalmente
    • Model for Evaluating Employee Engagement in a Matrix Organization

      Dávila Navarro, Joaquín G.; Barrios Sanchez, Stannis G.; Barrientos Padilla, Alfredo (International Institute of Informatics and Systemics, IIIS, 2023-01-01)
      The objective of this project is to implement a model for evaluating employee engagement in a company through mobile and web applications that allow for measuring employee engagement in work teams. The proposed model is defined by seven stages: input, plan, organize, timeline, evaluate, monitor, and output. It also includes the tools, variables, and factors that affect the model. Furthermore, experts in the field evaluated the model using a questionnaire developed to determine its effectiveness. Ultimately, the model received a score of 4.56 out of 5 points for approval and usability in companies, and a continuity plan for future projects is provided.
      Acceso restringido temporalmente
    • Expert System for the Prevention of Occupational Risks in Construction - Residential Buildings

      Hurtado, Gustavo; Rojas, Rosario; Mauricio, David; Santisteban, José (UIKTEN - Association for Information Communication Technology Education and Science, 2022-11-01)
      Construction companies consider it a priority to prevent occupational accidents and diseases, despite this, accidents in this sector prevail. This study presents OHSYS, an expert system specialized in the prevention of occupational safety in the construction of residential buildings, which evaluates a building project and it is recommended to security officer, actions to mitigate occupational risks. The results show that the number of recommendations increases on average by 7 and 13 for OSH levels of 90% and 100% when using OHSYS. In addition, the satisfaction, usability, and efficiency survey applied to 10 experts show that OHSYS has a very high score (4.5 out of 5).
    • Corrigendum: Artificial neural network model to predict student performance using nonpersonal information (Front. Educ., (2023), 8, (1106679), 10.3389/feduc.2023.1106679)

      Chavez, Heyul; Chavez-Arias, Bill; Contreras-Rosas, Sebastian; Alvarez-Rodríguez, Jose María; Raymundo, Carlos (Frontiers Media S.A., 2023-01-01)
      n the published article, the Acknowledgment Statement was mistakenly not included in the publication. The missing statement appears below: Acknowledgments “The authors would like to thank the Research Directorate of the Universidad Peruana de Ciencias Aplicadas for the support provided to carry out this research work through the UPC-EXPOST-2023-1 incentive.” The authors apologize for this error and state that this does not change the scientific conclusions of the article in any way. The original article has been updated.
      Acceso abierto
    • Multiplayer Chess Game Development Using Augmented Reality and 3D Models

      Cerron, Fredy; Villanueva, Ricardo; Barrientos, Alfredo (Institute of Electrical and Electronics Engineers Inc., 2023-01-01)
      The principal aim of this project was to innovate the classic board game chess so people can play at any time and place without the need for physical space and real pieces for the game to run correctly. This project can encourage more people to become interested in this board game by using augmented reality technology and personalized models and animations. Players can use the application without the need to use a physical board or pieces and without any kind of image marker. They just need to point at a flat surface with the phone camera so that all the game objects appear and then they can interact with the game intuitively by selecting the elements on the screen. The system has been created to work on high-end Android phones using the technology of Unity and Vuforia.
      Acceso restringido temporalmente
    • Development of a racing video game using the smartphone as a steering wheel

      Quino, Jorge A.; Crispin, Adolfo G.; Barrientos, Alfredo; Cuadros, Miguel E. (International Institute of Informatics and Systemics, IIIS, 2022-01-01)
      Uno de los géneros más populares de videojuegos han sido los de carreras. Aquí hay una fuerte demanda por controladores con diseño de timón que hacen de la experiencia de juego más inmersiva y entretenida. No obstante, estos controladores suelen ser caros y no todos los jugadores pueden adquirirlos. En el afán de encontrar una alternativa más accesible que ofrezca la misma inmersión a los jugadores de este género se implementó SmartDrive, un videojuego de carreras para Android programado en Unity 3D. SmartDrive utiliza dos smartphones Android 5.0 o superior conectados vía un hotspot WiFi, uno se usa como pantalla del juego y otro como un timón gracias a sus sensores de movimiento. La validación contó con 30 participantes que jugaron y brindaron sus valoraciones mediante una encuesta. Los resultados finales destacaron la aceptación de SmartDrive en los participantes al ofrecer una experiencia inmersiva con una mecánica de juego novedosa e intuitiva, e implementada con recursos más económicos. Este estudio mostró el potencial de SmartDrive como una alternativa accesible y sin perder el grado de entretenimiento.
      Acceso abierto
    • Predictive model to reduce the dropout rate of university students in Perú: Bayesian Networks vs. Decision Trees

      Medina, Erik Cevallos; Chunga, Claudio Barahona; Armas-Aguirre, Jimmy; Grandon, Elizabeth E. (IEEE Computer Society, 2020-06-01)
      This research proposes a prediction model that might help reducing the dropout rate of university students in Peru. For this, a three-phase predictive analysis model was designed which was combined with the stages proposed by the IBM SPSS Modeler methodology. Bayesian network techniques was compared with decision trees for their level of accuracy over other algorithms in an Educational Data Mining (EDM) scenario. Data were collected from 500 undergraduate students from a private university in Lima. The results indicate that Bayesian networks behave better than decision trees based on metrics of precision, accuracy, specificity, and error rate. Particularly, the accuracy of Bayesian networks reaches 67.10% while the accuracy for decision trees is 61.92% in the training sample for iteration with 8:2 rate. On the other hand, the variables athletic person (0.30%), own house (0.21%), and high school grades (0.13%) are the ones that contribute most to the prediction model for both Bayesian networks and decision trees.
      Acceso restringido temporalmente
    • DPF: App for diagnosing the psychological profile of a possible feminicide

      Ramirez, Ivette; Mauricio, David (Institute of Electrical and Electronics Engineers Inc., 2020-03-01)
      The most visible expression of violence against women is feminicide. The majority of feminicide cases are committed by the partner or former partner of the victim. This involves ongoing domestic abuses, threats or intimidation, sexual violence or situations in which women have less energy or resources than their partner. In addition, clinics, public hospitals or private health institutes have mental health evaluation processes, however, these flows are usually carried out in several sessions, which causes a delay in the diagnosis. In this article, a mobile application that supports psychologists or psychiatrists during the process of the psychological profile diagnosis is proposed. The system contains a questionnaire and psychological tests, in this way, based on the patient responses, indicators, and metrics, the psychological profile of the assailant is obtained as a result. The use of the system in 40 patients shows that the selection times and the psychological test qualification have improved, as well as the interpretation of the results and the total process of diagnosis, which, when obtained at opportune time, allows specialists to prevent the victim from a possible feminicide.
      Acceso restringido temporalmente
    • Mobile solution to optimize process for healthcare delivery referral in pediatric patients with a presumptive cancer diagnosis

      Francia Bacilio, Eduardo Alberto; Perez Rosas, Joseph Steven; Armas-Aguirre, Jimmy (Institute of Electrical and Electronics Engineers Inc., 2020-10-21)
      In this paper, we propose a mobile solution to optimize the medical referral process for pediatric patients with presumptive cancer diagnosis. This proposal allows the automation of the process through the identification of the main gaps that are covered by the following functionalities: (1) Registration and interaction of the actors in the process, (2) Support for timely diagnosis with first-hand information, (3) Creation of request tickets and personalized medical appointments, and (4) Creation of reports on the response time and compliance with the process. The proposal is described in three sections: (1) The automation of the medical referral process, (2) The functionalities of the mobile solution, and (3) the designed technology architecture. The validation of the proposal was carried out in a social health insurance in Lima-Peru, with data and information of the process obtained by the institution. The measurement was made through the mobile solution which allowed obtaining the response times of the process with the main actors such as the pediatric doctor, an oncology specialist and a pediatric patient's guardian. The results showed that the time of the referral process is optimized between an interval of [95%-97.5%], which mainly generates a social benefit to the community by assuring a timely treatment of the pediatric cancer patient, based on diagnosis and early care.
      Acceso restringido temporalmente