Recognition of Cough on Sequence Images Using Deep Learning and Computer Vision

Quispe Siancas N.L.; Monroy Barrios J.E.; Choquehuayta W.N. · Lecture Notes in Networks and Systems (2024) · DOI: 10.1007/978-3-031-66431-1_26

Resumen

In recent years, we have witnessed a pandemic that has had a significant impact on global health due to the spread of respiratory diseases. This crisis has resulted in the loss of thousands of lives. Respiratory diseases, in particular, are primarily transmitted through actions such as coughing and sneezing. It is of utmost importance to implement early measures to detect these diseases, as this can significantly contribute to preventing the spread of viruses and protecting public health globally. The research aims to implement a system for recognizing flu symptoms, such as coughing and sneezing, using Deep Learning techniques. An exhaustive background review has been conducted, and an effective solution is proposed to assist healthcare professionals through intelligent systems. The proposed neural network model for this study is YOLOv7. The research process consists of three phases: Data collection, Training of the proposed neural network model, and Evaluation of results. The results of this study reveal that the proposed model achieves an accuracy of 96%in detecting the mentioned classes. This was accomplished using a training dataset that includes 608 images, along with validation data comprised of 152 images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Instituciones: Universidad de San Martín de Porres