Modelo predictivo para la identificación de actividades de la vida diaria (ADL) en ambientes INDOOR usando técnicas de clasificación basadas en machine Learning

One of the technological aspects that contribute to improving the quality of life of adults, is precisely the enrichment of physical spaces with sensors, video surveillance equipment and actuators, which favor the performance of their daily life activities, which allows discover patterns of human actions generated from the movement and interaction of individuals with the environment, in such a way that they facilitate the monitoring of data and the understanding of the activity of older adults in surveillance environments, based on technology, with the purpose of automatically detecting abnormal patterns, which affect your health or could endanger your life. All these basic activities give older adults the possibility of interacting in community with the tranquility of a personalized and functional medical attention through the implementation of technology. Although the list of activities that a person can perform is extensive, this study focused on those that take place in indoor environments. The recognition of human activities is a field of research that subscribes to an investigative framework, which is the study of activities of daily life. Monitoring the human activities of daily life is a way of describing the functional and health status of a human being. The rapid population growth of older adults has caused an increase in the demand for personal care, particularly for people with affectations typical of senile dementia, due to the correlation that exists between this and the deterioration of memory, intellect, behavior and the consequent decrease in the ability to carry out activities of daily living. Therefore, the need arises to carry out this project, which establishes a predictive model of activities of daily life carried out by inhabitants in indoor environments, through the use of classification and selection techniques based on Machine Learning.

• Autores: García Restrepo, Johanna Karina
• Fecha de publicación: 2020
• Institución: Corporación Universidad de la Costa
• Repositorio: REDICUC - Repositorio CUC
• Idioma: spa
• OAI Identifier: oai:repositorio.cuc.edu.co:11323/8179
• Acceso en línea: https://hdl.handle.net/11323/8179; https://repositorio.cuc.edu.co/
• Palabra clave: Human Activities Recognition (HAR); Machine learning; Selection techniques; Classification techniques; Activities of Daily Life (ADL); Dataset; Reconocimiento de actividades humanas; Machine learning; Técnicas de selección; Técnicas de clasificación; Actividades de la vida diaria; Bases de datos
• Rights: openAccess
• License: Attribution-NonCommercial-ShareAlike 4.0 International