Cloud Computing and Big Data Analytics in Healthcare

Course ID   MSC07

Semester   B

Type   Compulsory

The course of Cloud Computing and Big Data Analytics in Healthcare aims at introducing basic concepts of Cloud Computing and the use of Cloud and Big Data services for application in medical data. 

Emphasis is placed on object storage services, metadata usage, data management and sharing services, data analysis tools as well as interconnection flows between services. 

Upon successful completion of the course, students will possess the basic knowledge about the types and structure of Cloud services as well as the ability to combine them to create workflows. In addition, they will become familiar with modern software environments such as Docker Containers, Apache Spark and Node-RED, as well as storage services such as Minio.

Contents


Introduction to cloud services (SPI model, platforms, infrastructure)

Cloud Infrastructure Services (IaaS)

Virtualization technologies

Environments and use of Docker containers

Composition of services from multiple containers

Practical training in the management and use of Docker containers

Introduction to Big Data

Map-Reduce Model Presentation

Apache Hadoop and Apache Spark ecosystem

Practical examples of programming and data management with Apache Spark

Concept and use of RDDs, Operations on RDDs and Dataframes

Apache Spark Machine Learning Libraries (MLib)

Open sources of health data

Obtaining health data through service-oriented interfaces, the REST protocol

Data acquisition, filtering, and storage flows in the Node-RED tool

Object-oriented data storage services, features and capabilities, the Minio tool

Combination and interaction of services, notifications and management automation

Project including application to healthcare datasets