Conv-Random Forest-Based IoT: A Deep Learning Model Based on CNN and Random Forest for Classification and Analysis of Valvular Heart Diseases

Cardiovascular diseases are growing rapidly in this world. Around 70 % of the world’s population is suffering from the same. The entire research work is grouped into classification and analysis of heart sound. We defined a new Squeeze network based deep learning model -Convolutional Random Forest for real time valvular heart sound classification and analysis using industrial raspberry pi 4B. The proposed electronic stethoscope is internet enabled using ESP32, and raspberry pi. The said IOT based model is also low cost, portable, and can be reachable to distant remote places where doctors are not available. As far as the classification part is concerned, the multiclass classification is done for seven types of valvular heart sound. The random forest classifier scored a good accuracy among other ensemble methods in small training set data. The CNN-based Squeeze Net model achieved a decent accuracy of 98.65 % after its hyper parameters were optimized for heart sound analysis. The proposed IOT based model overcomes the drawbacks faced individually in both squeeze network and random forest. CNN-based Squeeze net model and Random Forest classifier combined together improved the performance of classification accuracy. The squeeze net model plays a pivotal part in feature extraction of heart sound, and a Random forest classifier acts as a classifier in the class prediction layer for predicting class labels. Experimental results on several datasets like the Kaggle dataset, Physio net challenge, and Pascal Challenge showed that the Conv-RF model works the best. The proposed IOT based Conv-RF model is also applied on selected subjects with different age groups and genders having history of heart diseases. The Conv-Random Forest method scored an accuracy of 99.37± 0.05% on the different test datasets with a sensitivity of 99.5 ± 0.12% and specificity of 98.9 ± 0.03%. The proposed model is also examined with the current state of art models in terms of accuracy.