Repositorio Institucional Universidad EAFIT :: Examinando por Materia "Artificial Intelligence"

Examinando por Materia "Artificial Intelligence"

Mostrando 1 - 20 de 31

Artificial Intelligence for Modelling Dengue Transmission in Bello
(Universidad EAFIT, 2014) Lobo, Elisabet; Quintero, O.L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado Matemático
Autonomous Cycle of Data Analysis Tasks based on Machine Learning Techniques for the Management of Small Agroindustrial Producers
(Universidad EAFIT, 2025) Fuentes Camargo , Jairo Alberto; Aguilar Castro, José Lisandro; This study was partially funded by Colombian Administrative Department of Science, Technology and Innovation - COLCIENCIAS (grant number 111572553478) (J. Aguilar) and Colombian Ministry of Science and Technology Bicentennial PhD Grant (J. Fuentes).
Colombian Energy Market: An approach of Anfis and Clustering Techniques to an Optimal Portfolio
(Universidad EAFIT, 2014) Palacios, Alejandro; Giraldo, Marcela; Quintero, O. L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado Matemático
This paper focuses on the study of a first approach to an optimal portfolio in the Colombian Energy Market using Artificial Intelligence. Specifically, ANFIS and Clustering techniques are applied. The methodology is implemented using the Matlab Toolboxes for clustering and FIS generation. Te results are presented, as well as the analysis of them. A first approximation to an optimal portfolio obtained with this methodology is shown. Consequently, some conclusions of the different techniques available for the same purpose are discussed. Finally the future work is proposed.
Colombian Energy Market: Optimal Portfolio
(Universidad EAFIT, 2014) Palacios, Alejandro; Giraldo, Marcela; Quintero, O. L.; Universidad EAFIT. Escuela de Ciencias. Grupo de Investigación Modelado Matemático
This paper focuses on the study of an optimal portfolio in the Colombian Energy Market using the Artificial Intelligence techniques specifically, Fuzzy Modeling and Neural Networks. The methodology at first, is implemented using the Matlab Fuzzy Logic Toolbox and with the help of a script the process is automatized. Secondly, a Neural Network is implemented in Matlab and its results are compared with the ones obtained in the Matlab Neural Network Toolbox. The results of the Fuzzy model and the Neural Network are presented and conclusions of both techniques are discussed. Finally possible future work are proposed.
Desarrollo de librería para manejo de redes neuronales en Java para tecnofactor
(Universidad EAFIT, 2019) Arboleda Echeverry, Juan Camilo; Rincón Bermúdez, Rafael David
The aim of the present project is to design and develop a working library that enables the creation and adaptation of Neural Networks, defined in a way that is simple to use by Java developers. The developed library will be used to design and obtain a neural network capable of recognizing handwritten digits, from the MNIST database.
Desarrollo de un modelo de negocio innovador apalancado en IA para el aprendizaje autónomo del inglés en profesionales
(Universidad EAFIT, 2025) Higuita Pulgarín, María Camila; García Uribe, Sandra; Franco Ruiz, Camilo
This research proposes the design and validation of an innovative business model based on artificial intelligence to facilitate autonomous English learning among Colombian professionals. The solution takes shape in Monamate, a virtual AI-powered assistant that interacts via WhatsApp, enabling natural conversations, contextual feedback, and personalized recommendations. The methodological process combined qualitative interviews, surveys, and a five-day experimental test with 20 users, structured in three phases: diagnosis, proposal, and validation. Frameworks such as the Business Model Canvas, Design Thinking, and Lean Startup were applied. Key barriers, tensions, and motivations were identified using user archetypes (Cooper, 1999) and the Jobs to Be Done method (Christensen et al., 2016). During the experimental phase, value and growth hypotheses were formulated and evaluated according to Ries (2012), allowing analysis of the initial desirability, usability, and viability of the model. The results show a positive perception of the channel, high perceived utility, and willingness to pay, supporting the potential to scale the model. This early experiment informs key strategic decisions for the future development and monetization of the proposal, providing applied evidence for an innovative and context-sensitive educational solution.
Detection of carbapenem resistance in Klebsiella pneumoniae using convolutional vision transformers and MALDI-TOF proteomic profiles.
(Universidad EAFIT, 2025) Salazar Marín, Valentina; Fernández García, Geysson Javier; Bravo Ortíz, Mario Alejandro
Antimicrobial resistance is a growing global health problem, significantly increasing morbidity, mortality and healthcare costs. Traditionally, the identification of antibiotic resistance is based on phenotypic methods such as agar diffusion or automated systems such as VITEK, which require 24-72 hours to yield definitive results, delaying appropriate patient management. In this context, the need for faster and more accurate diagnostic aid strategies arises. This study explores the integration of artificial intelligence (AI) and mass spectrometry techniques for the classification of carbapenem-resistant Klebsiella pneumoniae strains. Specifically, matrix-assisted laser desorption/ionization-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) data were used to generate proteomic profiles potentially associated with resistance mechanisms. However, the complexity and high volume of these data make the use of AI tools capable of identifying robust patterns indispensable. A convolutional vision transformer (CVT) model was implemented to classify carbapenem-resistant Klebsiella pneumoniae strains from a set of 180 proteomic spectra collected by Synlab Colombia. The CVT model outperformed traditional convolutional neural networks and other automated learning approaches, achieving higher accuracy and stability. Grad-CAM visualization improved model interpretability by identifying key spectral regions associated with resistance. The results highlight the potential of Vision Transformers in microbiological diagnostics by significantly reducing resistance detection time and contributing to a timelier clinical response. Future studies should explore the applicability of this methodology on other resistant pathogens to improve global surveillance efforts against antimicrobial resistance.
Diseño de mecanismos cuatro barras asistido por métodos de aprendizaje reforzado
(Universidad EAFIT, 2021) Muñoz Betancur, Juan Manuel; Gallego Sánchez, Juan Andrés; Sánchez Gallego, Juan Andrés
An economical solution to the quality of service problems of electricity supply
(Universidad EAFIT, 2006-12-01) Barrera Núñez, Víctor; Mora Flórez, Juan José; Carrillo, Gilberto; Ordóñez Plata, Gabriel; Asesor Programa Nacional de Investigaciones en Energía y Minería, Colciencias, Asistente de Investigación GISEL.; Universidad Tecnológica de Pereira; Universidad Industrial de Santander; Universidad Industrial de Santander
Emerging Technologies and Knowledge Management in the Financial System : Advances, Tensions, and Future Agenda
(Universidad EAFIT, 2025) Giraldo Palacio, Diana María; Diez Gaviria, Ana Cecilia
Estimación del precio de oferta de la energía eléctrica en Colombia mediante inteligencia artificial.
(Universidad Pablo de Olavide, 2014-12) Hurtado Moreno, Laura; Quintero Montoya, Olga Lucía; García Rendon, John Jairo; Universidad Eafit,Escuela de Economía y Finanzas, Medellín, Antioquia, Colombia; Universidad Eafit,Escuela de ciencias básicas, Medellín, Antioquia, Colombia; Universidad Eafit,Escuela de Economía y Finanzas, Medellín, Antioquia, Colombia; Escuela de Economía y Finanzas; Economía; Estudios en Economía y Empresa
Estimation of mechanical properties of rock using artiﬁcial intelligence
(Universidad EAFIT, 2011-12-01) Galvis, Laura Viviana; Augusto Ochoa, César; Arguello Fuentes, Henry; Carvajal Jiménez, Jenny Mabel; Calderón Carrillo, Zuly Himelda; Universidad Industrial de Santander (UIS)
Estrategia digital basada en inteligencia artificial : optimización del tofu para la calificación de prospectos y mejora de la experiencia del cliente en el sector inmobiliario colombiano
(Universidad EAFIT, 2025) Monsalve Molina, Luis Daniel; Uribe de Correa, Beatriz Amparo; Serrano Rivero, Sergio Andrés
This study proposes a digital strategy powered by artificial intelligence to strengthen customer acquisition at the top of the funnel in the Colombian real estate market. The central idea is to improve the quality of prospects and enrich their experience from the first contact, combining a specialized CRM with automated WhatsApp conversation flows. With this proposal, we seek to ease the burden on sales teams, who often spend time on low-value leads, which increases Customer Acquisition Cost (CAC) and erodes closing rates. By implementing AI chatbots and leveraging "digital footprint" análisis (online behavioral data about each visitor) we automate the detection of those who truly show purchase intent. We thus optimize key metrics such as CAC, conversion rate, Return on Investment (ROI), Return on Ad Spend (ROAS), Net Promoter Score (NPS), and Customer Experience Score (CXS).
Estudio de prefactibilidad de un proyecto de información con inteligencia artificial, para empresas clientes de una entidad financiera
(Universidad EAFIT, 2019) Ortiz García, Jorge Mario; Ciro Parra, Jefferson Ferney; Gómez Salazar, Elkin Arcesio
The purpose of this research is to evaluate the pre-feasibility studies elaborated for the creation of a service that uses analytics and Artificial Intelligence (AI), oriented to provide information and recommendations to the shops that have contracted with Bancolombia S. A. the sales service with debit and credit cards. There is a great opportunity to generate value for the commercial sector through the processing of the information produced in the transactions made in POS (point of sale) and its join with the customer databases that the bank already has. Furthermore, are considered technologies that have taken great relevance in the last decade, such as analytics and Artificial Intelligence, because of the abundance of processable data that arise daily. In the first stage were consulted in the literature the backgrounds, generalities and advances that have occurred in both technologies, as well as their implementations, to have a general overview of their evolution and to know their scopes; later, to carry out the research, the viability of a project was evaluated through pre-feasibility studies of the UNIDO methodology. The studies covered by such methodology include the analysis of the national environment and the specific sector in which the project is to be developed, the market that exists for the service that is intended to be created, the technical characteristics necessary to carry it out, the staff, their academic background and the professional experience needed to be able to participate in the project, the financial properties that must be kept in mind and the risk management to prevent negative impacts on their implementation. All previous is complemented to build a perspective that allowed us to make the best decision regarding carrying out the project or to desist in such endeavor.
Gestión del conocimiento de colorantes naturales para bebidas a partir de una herramienta de inteligencia artificial generativa
(Universidad EAFIT, 2025) Cardona Guerra, Paola; Palacio Peña, Juan Alejandro; Ninguno
Hacia un modelo predictivo que apoye el logro de KPI comerciales más asertivos : caso Empresa Comercializadora de MaderaHacia un modelo predictivo que apoye el logro de KPI comerciales más asertivos : caso Empresa Comercializadora de Madera
(Universidad EAFIT, 2023) Tavera Rodríguez, Jhon Walter; Tabares Betancur, Marta Silvia
Herramientas tecnológicas de talento humano : impacto en empresas latinoamericanas
(Universidad EAFIT, 2025) Álvarez Moreno, Juan Felipe; Betancur Hurtado, Carlos Mario
This research analyzes the impact of technological tools on human talent management in Latin American organizations. The implementation of technological platforms in human resources processes has transformed the way organizations manage their talent, enhancing both efficiency and strategic decision-making. These tools enable the automation and optimization of processes such as recruitment, selection, performance management, and professional development. This ensures that the right people are placed in the right roles, based on accurate and up-to-date data. Furthermore, technology facilitates access to relevant information, which drives the growth and development of human capital. The study highlights that technology not only improves operational efficiency but also strengthens the relationship between employees and the organization. The implementation of these tools allows for a more personalized and closer approach to management, addressing the needs and expectations of employees. However, the adoption of technology also presents challenges, such as the need to adapt existing processes and the resistance to change among staff. It is essential for organizations to conduct a thorough analysis of their needs and select the appropriate tools to maximize benefits. In conclusion, technological tools are essential for modern human talent management, providing competitive advantages to organizations that implement them effectively. This study underscores the importance of technology in transforming human resources processes and its positive impact on organizational performance.
IA en el comercio colombiano : un análisis desde las leyes del consumidor y de la competencia
(Universidad EAFIT, 2024) Carvajal Salazar, Camilo; Villa García, Luis Felipe
The following text aims to analyze Colombian laws to determine if the legislation of the Latin American country has the capacity to regulate the application of Artificial Intelligence (AI) in their national market, while they protect the rights of consumers and the fair competition, keeping the purpose of avoiding situations that may generate chances of monopolies. In this way, the author discusses the concepts of AI, consumer rights, unfair competition, and free market development to conclude, with the help of the study of laws, doctrines, and interviews, whether or not there is indeed a risk to the market.
Infracción de derechos marcarios en el Metaverso
(Universidad EAFIT, 2025) Caro Castaño, Ana María; Muñoz Gaitán, Valentina; Correa Márquez, María Camila
Due to the increased growth of technology, the internet, and the metaverse has created significant legal challenges, particularly regarding the protection of intellectual property rights. This paper explores the complexities surrounding trademark infringement in the metaverse environment, focusing on the role of artificial intelligence (AI) in the creation and commercialization of digital goods. In the decentralized and global nature of the metaverse, traditional legal frameworks struggle to address new forms of protection, breaking with principles such as territoriality and specialty, and in consequence new forms of infringement, where users may intentionally or unintentionally violate intellectual property rights. A critical issue is determining the liability of infringers in these virtual environments. This research investigates how existing intellectual property laws, particularly in Colombia, can be applied to protect registered trademarks in the metaverse. By analyzing the legal gaps in current legislation, this monograph provides insight into how AI-generated digital assets challenge conventional legal frameworks. It also evaluates the impact of trademark violations on brand value and the necessity of developing new legal mechanisms to safeguard trademarks in virtual spaces.
Inteligencia Artificial en la economía : un análisis multidimensional de oportunidades y desafíos en el mercado laboral
(Universidad EAFIT, 2023) Cadavid Londoño, Ana María; Hernández Flórez, Mónica

Examinando por Materia "Artificial Intelligence"

Resultados por página

Opciones de ordenación