Blockchain and Deep Learning for Smart Healthcare

15Deep Learning-Based Smart e-Healthcare for Critical Babies in Hospitals

Ritam Dutta

Dept. of CSE, Poornima University, Jaipur, Rajasthan, India

Abstract

With the advent of the latest technology, the healthcare system needs smart architecture. New smart technologies are compared with the conventional healthcare system in terms of results, speed, and efficiency. This work reviews several literatures and gives an insight into the demand for NICU beds in hospitals. A smart e-healthcare system that estimates the availability of NICU beds is developed. The framework consists of an application developed using Android that the users can use to interact with hospitals during crisis. Cloud storage has been used to store the data securely using the AES algorithm. Cloud storage also improves data accessibility and is reliable. The proposed framework uses machine learning algorithms to efficiently predict the availability of NICU beds in hospitals for newborn babies. The CNN model extracts the essential features from the dataset, and SVM performs the classification task. Moreover, the number of available beds in a hospital has also been reflected in the application developed so that the users can accordingly contact their respective hospitals in case of any emergency. The proposed framework has outperformed the earlier CNN and SVM models with 90.4% recall, 90.6% precision, and 95.4% accuracy.

Keywords: Cloud computing, electronic sensors, smart healthcare, machine learning, CNN, SVM, ...