Detecção de sons respiratórios adventícios utilizando TensorFlow Lite
In this work, we aim to develop a system for recognizing adventitious respiratory sounds, such as wheezes and crackles, using the framework TensorFlow Lite. To achieve this goal, we proposed a model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), and the dataset used...
| Autor principal: | Brandão, André Luiz Miranda |
|---|---|
| Grau: | Trabalho de Conclusão de Curso |
| Idioma: | por |
| Publicado em: |
Brasil
2024
|
| Assuntos: | |
| Acesso em linha: |
http://riu.ufam.edu.br/handle/prefix/8062 |
| Resumo: |
|---|
|
In this work, we aim to develop a system for recognizing adventitious respiratory sounds, such as wheezes and crackles, using the framework TensorFlow Lite. To achieve this goal, we proposed a model combining Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), and the dataset used was the ICBHI 2017. Two instances of the proposed model were trained and validated and then converted to TensorFlow Lite, with the implementation of a proof of concept. The results obtained by the proposed model showed an accuracy of 94% for crackles and 96% for wheezes. |