Ingeniería de Sistemas y Computación

URI permanente para esta comunidad

https://hdl.handle.net/1992/52324
Encuentre en acceso abierto la producción académica, investigativa y de creación del Pregrado en Ingeniería de Sistemas y Computación de la Universidad de los Andes.

Navegar

Examinando Ingeniería de Sistemas y Computación por Autor "1018487363"

Mostrando 1 - 5 de 5
  • Miniatura
    PublicaciónAcceso abierto
    Automatic GUI testing for android using reinforcement learning
    (Universidad de los Andes, 2023-01-28) Valbuena Bautista, Daniel; Mojica Hanke, Anamaría Irmgard; Linares Vasquez, Mario; Escobar Velasquez, Camilo Andres; 80728886; 1018487363; 1022396145; The Software Design Lab
    The developers focus on testing applications, which can be a time-consuming task. To address this issue, we developed AgentDroid, a tool that utilizes reinforcement learning techniques to automate test execution. So far, the results have been impressive, outperforming state-of-the-art RL-based automated testing tools for Android, such as ARES. In fact, AgentDroid achieved a 20% improvement in cumulative coverage compared to ARES. However, its effectiveness has only been evaluated on a single application, making it challenging to find compatible apps for testing. To address this, we tested 61 open-source apps and successfully executed 11 to verify that the tool's performance was consistent. During this experimentation, we also identified and corrected bugs in the tool, improved error detection, and generated code coverage reports at the package, class, and method levels.
  • Miniatura
    PublicaciónAcceso abierto
    Automatic multi-platform Interaction testing for android using reinforcement learning
    (Universidad de los Andes, 2022-07-25) Pantoja Gómez, Camila; Díaz Suárez, Edgar Camilo; Rozo Benítez, Camilo Esteban; Mojica Hanke, Anamaria Irmgard; Linares Vasquez, Mario; Escobar Velasquez, Camilo Andres; 80728886; 1018487363; 1022396145; The Software Design Lab
    Mobile testing is a time-consuming and expensive task necessary to guarantee high-quality applications. Moreover, mobile apps have become increasingly oriented to multiple user and platform interactions. Test execution tools, as well as test generation tools, have been developed to automate this task. Among these, KrakenMobile 2.0 is the first open-source tool developed to enable automatic test execution supporting cross-device interaction. A new testing tool was developed, extending on KrakenMobile's multi-user interaction with automatic test generation using Reinforcement Learning techniques. The resulting tool, Smart Kraken, achieved better results in the training phase of one open-source application than another RL-based state-of-art tool for automated testing in Android, ARES. It achieved a cumulative method coverage of 47.81% over 118 episodes, showing an increase of over 20% compared with ARES. This improvement is mainly attributed to the design of the reward function. Finally, a multi-agent scenario was proposed seeking to draw upon its collaboration capabilities to improve multi-user interaction, though implementation was not finished.
  • Miniatura
    PublicaciónAcceso abierto
    SeneCare 3.0
    (Universidad de los Andes, 2022-07-25) Cárdenas Cortés, Nicolás Esteban; Manosalva Salgado, David Fernando; Blanco Torres, Kevyn Steve; Arteaga Mendoza, Daniella; Mojica Hanke, Anamaría Irmgard; Linares Vasquez, Mario; 80728886; 1018487363; The Software Design Lab
    Con el fin de facilitar la gestión y el reporte de tanto emergencias como condiciones inseguras dentro de la Universidad de los Andes, se desarrollaron nuevas funcionali- dades dentro de la aplicación SeneCare. Esto, debido a la afinidad ya pre-establecida de los estudiantes con ésta dado el uso que se le dió para gestionar el autocuidado de la comunidad durante la emergencia sanitaria por el COVID-19. Por otra parte, el desarrollo de dichas funcionalidades permite un almacenar un registro del historial de emergencias, habilitando un posterior análisis con el objetivo de mitigar estas situaciones. El presente documento evidencia el proceso de desarrollo junto con el diseño planteado para las diferentes soluciones a nivel de aplicaciones móviles, back-end y front-end, presentando finalmente los resultados obtenidos.
  • Miniatura
    PublicaciónAcceso abierto
    Software best practices for machine learning
    (Universidad de los Andes, 2022-07-19) Munar González, Nicolás; Tobo Urrutia, Nicolás Andrés; Mojica Hanke, Anamaría Irmgard; Linares Vasquez, Mario; 1018487363; 80728886; The Software Design Lab
    Throughout this document, an analysis of which best practices of Software Engineering (SE) for Machine Learning (ML) are discussed in Community Question Answering (CQA), scientific articles, and surveys. Furthermore, we will investigate if these rules are being used in SE, and how these techniques can affect multiple actors inside an ML project. To achieve this, we will follow a series of steps: First, we will extract data from different CQA communities, websites, Scientific articles, and surveys related to best practices of SE for ML. Second, we will analyze and classify this information to associate these techniques with examples of SE implementations and roles inside a project of SE for ML. Third, we will create a chatbot with deterministic behavior. Through a conversation about the project being implemented of SE for ML, it returns some practices to follow. Finally, we will publish this research in an online documentation format, where the techniques, the chatbot, and the survey will be accessible to the public in general.
  • Miniatura
    PublicaciónAcceso abierto
    Spärck: Information retrieval system of machine learning good practices for software engineering
    (Universidad de los Andes, 2022-12-15) Cabra Acela, Laura Helena; Mojica Hanke, Anamaría Irmgard; Linares Vasquez, Mario; 80728886; 1018487363
    In this project, we propose a tool for the developers to search for good machine learning (ML) practices appropriate for the software engineering (SE) assignments they are working on. We expect this tool makes ML good practices easily accessible and promotes their use. For this, we defined a structure that described the relationships between stages of the ML pipeline, tasks, and good practices. Moreover, we implemented and validated an information retrieval (IR) model for the good practices gathered. Furthermore, we developed and validated a platform that allows users to search for good practices in ML for SE. This platform includes three main features: (i) a search bar that uses the implemented IR model. (ii) a tool to filter the practices by tasks. (iii) an interactive tool that classifies the information by the relationship between stages, tasks, and practices.