Performance Comparison of Breathing Signal Classifiers Using Machine Learning Techniques

One of the most important indicators of a person’s health status is their rate of respiration, which is why clinical exams should closely monitor it. In the medical field, respiratory signal classification plays a vital role in the diagnosis and management of a range of respiratory conditions. However, effectively categorising respiratory signals remains a considerable issue due to the complexity and diversity of these signals. This study presents a thorough analysis of machine learning models for the categorization of respiratory signals, using a comparative method to assess each model’s performance. A variety of machine learning approaches, encompassing both conventional techniques investigated such as Random Forest, Support Vector Machine (SVM) and k-Nearest Neighbors (kNN) to see how well the algorithm classifies the respiratory signals. Processing procedures, data modeling, data classification, and data analysis used in the classification process are all included in the paper. The findings of each model in terms of classification accuracy, computational efficiency, and interpretability are examined through thorough testing on benchmark datasets. SVM was found to execute 92% more accurately than the other ML technique. This study can be expanded to compare with the various deep learning approaches to obtain better classification capable of real time application.