- Remote health monitoring system hardware
- Welcome to Module 1! Medical systems for remote monitoring of patients have become extremely popular in recent years. Most of them have a similar structure, which will be discussed in detail in this module using the example of an electrocardiogram signal registration device. We will talk about hardware part of modern ECG recorders, and problems, connected with processing of biomedical signals.
- Data Exchange Between Device And Personal Computer
- Welcome to Module 2! The implementation of the protocol for transferring data from a patient’s wearable device to a computer is an extremely important step in the entire development of a telemedicine system. This module will consider the easiest and most affordable wired data transfer method using the RS-232 interface, virtual Com ports and the MatLab software environment.
- Preprocessing of Biomedical Signals
- Welcome to Module 3! Use you may know, biomedical signals are corrupted by a significant amount of noise. So, noise removal is used in order to increase signal quality. We will talk about basics method to prepare your signal for future analysis. In the Programming part of the Module we will learn how to evaluate and analyze ECG-signal spectrum and create a digital filter using MATLAB.
- Event Detection in Biomedical Signals
- Welcome to Module 4! In most cases, biomedical signal analysis assumes that we have some reference or basic events in the signal. It can be QRS-complexes (for ECG), breaths (for spirogram), eyes movements (for EEG) or steps (for accelerometric signal). We will look closely to this task in the context of ECG-analysis. You will learn different QRS-detection algorithms and create QRS-detector using MATLAB.
- Developing Data-Driven Recommendation System
- Welcome to Module 5! In this module you will further develop your mobile-based health monitoring system. How to deal with extracted features and how can they help you in creating recommendations – these are the primary questions for this module. This is a very broad topic, involving methods from statistical analysis, machine learning and medical practice. We will study a practical approach to use these methods in developing monitoring systems on the example, which is, in our case, a recognition of noisy ECG complexes and their removal.
