Publicação
Automatic annotation of heart rate sequences
| Resumo: | Heart Rate (HR) measurement is one of the most effective ways to determine whether a person is stressed or not. The analysis of a series of HR measurements can help determine whether the HR decreased, increased dramatically, or remained consistent during that time period. With this in mind, an automatic annotator that can automatically label HR sequences, determining these three possible states, is an ideal solution because it eliminates the need for a human to do it manually. This paper presents a web-based application that, given a .csv file containing Heart Rate successive measurements and their respective time stamps, can label sequences of any size that the user specifies. This opens up the possibility of training Machine Learning models with this data and classifying whether the user is in a stressful situation or not, in real time. Although further refinements will be made, our annotator proved to be robust and consistent in its annotation performance. |
|---|---|
| Autores principais: | Lopes, Júlio Castro |
| Outros Autores: | Vieira, João; Antunes, Alexandre Fernandes; Deusdado, Leonel; Lopes, Rui Pedro |
| Assunto: | Heart rate Machine learning Annotation Web application |
| Ano: | 2023 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Instituto Politécnico de Bragança |
| Idioma: | inglês |
| Origem: | Biblioteca Digital do IPB |
| Resumo: | Heart Rate (HR) measurement is one of the most effective ways to determine whether a person is stressed or not. The analysis of a series of HR measurements can help determine whether the HR decreased, increased dramatically, or remained consistent during that time period. With this in mind, an automatic annotator that can automatically label HR sequences, determining these three possible states, is an ideal solution because it eliminates the need for a human to do it manually. This paper presents a web-based application that, given a .csv file containing Heart Rate successive measurements and their respective time stamps, can label sequences of any size that the user specifies. This opens up the possibility of training Machine Learning models with this data and classifying whether the user is in a stressful situation or not, in real time. Although further refinements will be made, our annotator proved to be robust and consistent in its annotation performance. |
|---|