Pneumonia is an important clinical and public health problem. Identification and prediction of severe pneumonia pose significant concerns. While attempts to identify severe pneumonia are usually correct, they are based on symptom recognition such as cough with phlegm or pus, fever, chills, and difficulty breathing. Recent methods of diagnosis include X-ray analysis are far more accurate.
This project attempts to take a more technical approach by using Machine Learning on chest X-ray scans to classify X-rays of patients with Pneumonia. While other research has been done in this field before. I used a google net to train the ML model. This allowed me to reach high accuracies up to 93%. With more data, I am sure that the accuracy of the model can be improved.
The ML model can be run on an Arduino and the code to make this happen can be generated by the MATLAB export model function. This would allow you to make predictions by sending an image to the Arduino.