Browsing by Author "Neyem, Andrés"

Now showing 1 - 20 of 23
  • Thumbnail Image
    Item
    A Cloud-based Mobile System for Improving Vital Signs Monitoring During Hospital Transfers
    (2015) Neyem, Andrés; Valenzuela, Guillermo; Risso, Nicolas; Rojas Riethmuller, Juan S.; Benedetto Causa, José Ignacio; Carrillo, Marie J.
  • Thumbnail Image
    Item
    A Cloud-Based Mobile System to Improve Project Management Skills in Software Engineering Capstone Courses
    (2018) Neyem, Andrés; Diaz-Mosquera, Juan; Benedetto Causa, José Ignacio
  • Thumbnail Image
    Item
    A cloud-based mobile system to improve respiratory therapy services at home
    (2016) Risso, N.; Benedetto, J.; Carrillo, M.; Farias, A.; Gajardo, M.; Loyola, O.; Neyem, Andrés
  • Thumbnail Image
    Item
    A Cloud-based Mobile System to Manage Lessons-learned in Construction Projects
    (2016) Ferrada Calvo, Ximena Verónica; Nuñez, Daniela; Neyem, Andrés; Serpell, Alfredo; Sepúlveda Fernández, Marcos Ernesto
  • Thumbnail Image
    Item
    A cloud-based mobile system to support effective collaboration in higher education online courses
    (2017) Rojas Riethmüller, Juan Sebastián; Neyem, Andrés; Pontificia Universidad Católica de Chile. Escuela de Ingeniería
    Actualmente existen más de cuatro mil cursos MOOC ofrecidos mediante distintas Plataformas MOOC. Estas plataformas son robustas y soportan grandes volúmenes de datos y un alto número de usuarios. Debido a estas características, las instituciones de educación superior han adoptado estas plataformas para extender las prácticas del aula tradicional. La forma más común en que adoptan estas Plataformas MOOC, consiste en desarrollar cursos online exclusivamente para sus estudiantes. Estos cursos reciben el nombre de Small Private Online Courses (SPOCs), y solo pueden ser accedidos por un número reducido de estudiantes de dicha institución. El uso de las Plataformas MOOC permite a las universidades innovar y tener más flexibilidad en sus currículos. Sin embargo, estas plataformas no están preparadas para promover el aprendizaje colaborativo entre los estudiantes, ya que no cuentan con las herramientas necesarias. Respecto a este problema, Mobile Cloud Computing (MCC) ofrece varias ventajas para diseñar un sistema que promueva la colaboración entre estudiantes de educación superior, pero estas ventajas no han sido aprovechadas. Entonces, esta investigación se enfoca en el desarrollo de un sistema basado en MCC para promover la colaboración entre estudiantes en una Plataforma MOOC, en el contexto de la educación superior. Se siguió una metodología de Design Based Research para recopilar información, y producir y testear prototipos funcionales de manera iterativa e incremental. El sistema resultante es MyMOOCSpace, un sistema MCC que incluye dinámicas de colaboración enriquecidas con elementos de gamificación. Se realizaron evaluaciones para medir la usabilidad y el efecto en la colaboración de MyMOOCSpace. Los resultados de usabilidad muestran que los estudiantes se sintieron a gusto interactuando con el sistema, que logra también cumplir los requerimientos técnicos. Finalmente, los resultados muestran que MyMOOCSpace logró generar un aumento en la colaboración y las interacciones entre los estudiantes.
  • Thumbnail Image
    Item
    A Lessons-learned System for Construction Project Management: A Preliminary Application
    (2016) Ferrada Calvo, Ximena Verónica; Nuñez, D.; Neyem, Andrés; Serpell, A.; Sepúlveda Fernández, Marcos Ernesto
  • Thumbnail Image
    Item
    A Mobile Cloud Shared Workspace to Support Homecare for Respiratory Diseases in Chile
    (2015) Neyem, Andrés; Risso, Nicolas A.; Carrillo, Marie J.; Farías Cancino, Angélica; Gajardo, Macarena J.
  • Thumbnail Image
    Item
    Anatomicis network: Una plataforma de software educativa basada en la nube para mejorar la enseñanza de la anatomía en la educación médica
    (2017) Inzunza H., Oscar; Neyem, Andrés; Sanz, María Eliana; Valdivia, Iván; Villarroel, Mauricio; Farfan C., Emilio; Matte, Andrés
    In this article, we describe a novel proposal of an educational software platform to enhance the anatomy teaching in medical education. In order to determine the usefulness and impact of this platform, between 2016 and 2017, an interinstitutional experience was developed, which included the Universities of Antofagasta, Playa Ancha, Austral and Catolica de Chile. The participation of anatomy departments in this experience, used the educational software platform to access 2D and 3D anatomical images and online multimodal practical-theoretical evaluations, being able to perform usability tests with their students. This project aims to improve teaching in the different anatomy departments throughout the country.
  • Thumbnail Image
    Item
    Biomechanical analysis of expert anesthesiologists and novice residents performing a simulated central venous access procedure
    (2021) Villagrán Gutiérrez, Ignacio Andrés; Moenne Vargas, Cristóbal Matías; Aguilera Siviragol, Victoria Ignacia; Garcia, Vicente; Reyes, Jose Tomas; Rodriguez, Sebastian; Miranda Mendoza, Constanza; Altermatt Couratier, Fernando René; Fuentes López, Eduardo; Delgado Bravo, Mauricio Antonio; Neyem, Andrés
    Background Central venous access (CVA) is a frequent procedure taught in medical residencies. However, since CVA is a high-risk procedure requiring a detailed teaching and learning process to ensure trainee proficiency, it is necessary to determine objective differences between the expert’s and the novice’s performance to guide novice practitioners during their training process. This study compares experts’ and novices’ biomechanical variables during a simulated CVA performance. Methods Seven experts and seven novices were part of this study. The participants’ motion data during a CVA simulation procedure was collected using the Vicon Motion System. The procedure was divided into four stages for analysis, and each hand’s speed, acceleration, and jerk were obtained. Also, the procedural time was analyzed. Descriptive analysis and multilevel linear models with random intercept and interaction were used to analyze group, hand, and stage differences. Results There were statistically significant differences between experts and novices regarding time, speed, acceleration, and jerk during a simulated CVA performance. These differences vary significantly by the procedure stage for right-hand acceleration and left-hand jerk. Conclusions Experts take less time to perform the CVA procedure, which is reflected in higher speed, acceleration, and jerk values. This difference varies according to the procedure’s stage, depending on the hand and variable studied, demonstrating that these variables could play an essential role in differentiating between experts and novices, and could be used when designing training strategies.
  • Thumbnail Image
    Item
    Code Offloading Solutions for Audio Processing in Mobile Healthcare Applications: A Case Study
    (IEEE, 2018) Sanabria Quispe, Pablo; Benedetto Causa, José Ignacio; Neyem, Andrés; Navón Cohen, Jaime; Poellabauer, C.
    In this paper, we present a real-life case study of a mobile healthcare application that leverages code offloading techniques to accelerate the execution of a complex deep neural network algorithm for analyzing audio samples. Resource-intensive machine learning tasks take a significant time to complete on high-end devices, while lower-end devices may outright crash when attempting to run them. In our experiments, offloading granted the former a 3.6x performance improvement, and up to 80% reduction in energy consumption; while the latter gained the capability of running a process they originally could not.
  • Thumbnail Image
    Item
    Connection-Aware Heuristics for Scheduling and Distributing Jobs under Dynamic Dew Computing Environments
    (2024) Sanabria Quispe, Pablo; Montoya Tapia, Sebastián Ignacio; Neyem, Andrés; Toro Icarte, Rodrigo Andrés; Hirsch, Matías; Mateos, Cristian
    Due to the widespread use of mobile and IoT devices, coupled with their continually expanding processing capabilities, dew computing environments have become a significant focus for researchers. These environments enable resource-constrained devices to contribute computing power to a local network. One major challenge within these environments revolves around task scheduling, specifically determining the optimal distribution of jobs across the available devices in the network. This challenge becomes particularly pronounced in dynamic environments where network conditions constantly change. This work proposes integrating the “reliability” concept into cutting-edge human-design job distribution heuristics named ReleSEAS and RelBPA as a means of adapting to dynamic and ever-changing network conditions caused by nodes’ mobility. Additionally, we introduce a reinforcement learning (RL) approach, embedding both the notion of reliability and real-time network status into the RL agent. Our research rigorously contrasts our proposed algorithms’ throughput and job completion rates with their predecessors. Simulated results reveal a marked improvement in overall throughput, with our algorithms potentially boosting the environment’s performance. They also show a significant enhancement in job completion within dynamic environments compared to baseline findings. Moreover, when RL is applied, it surpasses the job completion rate of human-designed heuristics. Our study emphasizes the advantages of embedding inherent network characteristics into job distribution algorithms for dew computing. Such incorporation gives them a profound understanding of the network’s diverse resources. Consequently, this insight enables the algorithms to manage resources more adeptly and effectively.
  • Thumbnail Image
    Item
    Enriching Capstone Project-Based Learning Experiences Using a Crowdsourcing Recommender Engine
    (IEEE, 2017) Diaz-Mosquera, Juan; Sanabria Quispe, Pablo; Neyem, Andrés; Parra Santander, Denis; Navón Cohen, Jaime
    Capstone project-based learning courses generate a suitable space where students can put into action knowledge specific to an area. In the case of Software Engineering (SE), students must apply knowledge at the level of Analysis, Design, Development, Implementation and Management of Software Projects. There is a large number of supportive resources for SE that one can find on the web, however, information overload ends up saturating the students who wish to find resources more accurate depending on their needs. This is why we propose a crowdsourcing recommender engine as part of an educational software platform. This engine based its recommendations on content from StackExchange posts using the project's profile in which a student is currently working. To generate the project's profile, our engine takes advantage of the information stored by students in the aforementioned platform. Content-based algorithms based on Okapi BM25 and Latent Dirichlet Allocation (LDA) are used to provide suitable recommendations. The evaluation of the engine was held with students from the capstone course in SE of the University Catholic of Chile. Results show that Cosine similarity over traditional bag-of-words TF-IDF content vectors yield interesting results, but they are outperformed by the integration of BM25 with LDA.
  • Thumbnail Image
    Item
    Improving Healthcare Team Collaboration in Hospital Transfers through Cloud-Based Mobile Systems
    (2016) Neyem, Andrés; Carrillo, M.; Jerez, C.; Valenzuela, G.; Risso, N.; Benedetto Causa, José Ignacio; Rojas Riethmuller, J.
  • Thumbnail Image
    Item
    Live ANDES: Mobile-Cloud Shared Workspace for Citizen Science and Wildlife Conservation
    (IEEE, 2015) Bonacic Salas, Cristián; Neyem, Andrés; Vásquez Guerra, Andrea Fernanda
    One of the weakest points of scientific research is the loss of data. A tiny fraction of the information generated onsite is published or released to public knowledge, and many useful studies end up stored in papers or emails without being utilized. Live ANDES is a mobile-cloud shared workspace designed to address this problem, promoting citizen science, data collection and analysis for wildlife conservation. It works by gathering geo-localized data provided by the scientific community, amateur naturalists, park rangers and people at large through web and mobile applications. Live ANDES offers filters, visualization and download options to work with existing data. Researchers can use this new information to identify species, ranges of distribution, and detect key habitat factors and potential threats to their conservation. Live ANDES is implemented using the Backend as a Service pattern on Microsoft Azure to manage the processing of the large amounts of data generated from sightings. It includes an API for mobile and desktop clients hosted in an Azure Virtual Machine, cloud storage and connection with external services to complement the existing information about recorded sightings. This paper discusses Live ANDES software design, architecture and a study case, in order to demonstrate an actual application of data management in the cloud and its impact on conservation.
  • Thumbnail Image
    Item
    Medicine-Hub: A New Teaching Tool for the Study of Sectional Anatomy
    (Lancaster Univeristy, 2023) Montt Blanchard, Denise; Inzunza, Oscar; Neyem, Andrés; Caro Pinto, Iván
    Medicine-Hub is a platform that integrates analogue and digital components, specially designed for the visualization of -and interaction with- high-fidelity anatomical structures matching the reality of a cadaveric preparation. This project presents a solution to the inequality gap generated by the scarcity of cadaveric dissections available for health career students.
  • Thumbnail Image
    Item
    Minimally Invasive tele-mentoring opportunity – the mito project
    (2019) Quezada González, José Luis; Achurra Tirado, Pablo; Jarry, Cristián; Tejos, Rodrigo; Inzunza, Martín; Ulloa, Gabriel; Neyem, Andrés; Martínez, Carlos; Martino, Carlo; Escalona, Gabriel
  • Thumbnail Image
    Item
    MobiCOP : A Scalable and Reliable Mobile Code Offloading Solution
    (2018) Benedetto Causa, José Ignacio; Valenzuela, Guillermo; Sanabria Quispe, Pablo; Neyem, Andrés; Navón Cohen, Jaime; Poellabauer, Christian
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    MyMOOCSpace: A Cloud-Based Mobile System to Support Effective Collaboration in Higher Education Online Courses,
    (2017) Ramirez, L.; Rojas, J.; Pérez Sanagustín, Mar; Neyem, Andrés; Alario, C.
  • Thumbnail Image
    Item
    Performance of single-agent and multi-agent language models in Spanish language medical competency exams
    (Springer Nature, 2025) Altermatt Couratier, Fernando René; Neyem, Andrés; Sumonte Fuenzalida, Nicolás Ignacio; Mendoza Rocha, Marcelo; Villagrán Gutiérrez, Ignacio Andrés; Lacassie Quiroga, Héctor
    Background Large language models (LLMs) like GPT-4o have shown promise in advancing medical decision-making and education. However, their performance in Spanish-language medical contexts remains underexplored. This study evaluates the effectiveness of single-agent and multi-agent strategies in answering questions from the EUNACOM, a standardized medical licensure exam in Chile, across 21 medical specialties. Methods GPT-4o was tested on 1,062 multiple-choice questions from publicly available EUNACOM preparation materials. Single-agent strategies included Zero-Shot, Few-Shot, Chain-of-Thought (CoT), Self-Reflection, and MED-PROMPT, while multi-agent strategies involved Voting, Weighted Voting, Borda Count, MEDAGENTS, and MDAGENTS. Each strategy was tested under three temperature settings (0.3, 0.6, 1.2). Performance was assessed by accuracy, and statistical analyses, including Kruskal–Wallis and Mann–Whitney U tests, were performed. Computational resource utilization, such as API calls and execution time, was also analyzed. Results MDAGENTS achieved the highest accuracy with a mean score of 89.97% (SD = 0.56%), outperforming all other strategies (p < 0.001). MEDAGENTS followed with a mean score of 87.99% (SD = 0.49%), and the CoT with Few-Shot strategy scored 87.67% (SD = 0.12%). Temperature settings did not significantly affect performance (F2,54 = 1.45, p = 0.24). Specialty-level analysis showed the highest accuracies in Psychiatry (95.51%), Neurology (95.49%), and Surgery (95.38%), while lower accuracies were observed in Neonatology (77.54%), Otolaryngology (76.64%), and Urology/Nephrology (76.59%). Notably, several exam questions were correctly answered using simpler single-agent strategies without employing complex reasoning or collaboration frameworks. Conclusions and relevance Multi-agent strategies, particularly MDAGENTS, significantly enhance GPT-4o’s performance on Spanish-language medical exams, leveraging collaboration to improve diagnostic accuracy. However, simpler single-agent strategies are sufficient to address many questions, high-lighting that only a fraction of standardized medical exams require sophisticated reasoning or multi-agent interaction. These findings suggest potential for LLMs as efficient and scalable tools in Spanish-speaking healthcare, though computational optimization remains a key area for future research.