Machine Learning approach applied to Human Activity Recognition – An application to the VanKasteren dataset

Reminders are a core component of many assistive technology systems and are aimed specifically at helping people with dementia function more independently by compensating for cognitive deficits. These technologies are often utilized for prospective reminding, reminiscence, or within coaching-based systems. Traditionally, reminders have taken the form of nontechnology based aids, such as diaries, notebooks, cue cards and white boards. This article is based on the use of machine learning algorithms for the detection of Alzheimer’s disease. In the experimentation, the LWL, SimpleLogistic, Logistic, MultiLayerPercepton and HiperPipes algorithms were used. The result showed that the LWL algorithm produced the following results: Accuracy 98.81%, Precission 100%, Recall 97.62% and F- measure 98.80%

• Autores: Ariza-Colpas, Paola; Oñate-Bowen, Alvaro Agustín; Suarez-Brieva, Eydy del Carmen; Oviedo-Carrascal, Ana; Urina Triana, Miguel; Piñeres-Melo, Marlon; Butt, Shariq Aziz,; Collazos Morales, Carlos Andrés; Ramayo González, Ramón Enrique
• Fecha de publicación: 2021
• Institución: Universidad Simón Bolívar
• Repositorio: Repositorio Digital USB
• Idioma: eng
• OAI Identifier: oai:bonga.unisimon.edu.co:20.500.12442/8605
• Acceso en línea: https://hdl.handle.net/20.500.12442/8605; https://doi.org/10.1016/j.procs.2021.07.070; https://www.sciencedirect.com/science/article/pii/S1877050921014733?via%3Dihub
• Palabra clave: Machine learning; HAR; ADL; Human Activity Recognition; Activity Daily Living; VanKasteren Dataset
• Rights: openAccess
• License: Attribution-NonCommercial-NoDerivatives 4.0 Internacional