BIOE7902 Event Detection

BIOE7902 – Assignment 2 – Event DetectionThe goal of this assignment is to reproduce the results of this paper as close aspossible: Raúl Alonso Álvarez, Arturo J. Méndez Penín, X. Antón Vila Sobrino - AComparison of Three QRS Detection Algorithms Over a Public Database

Tasks:

1. 1) Implement the 3 algorithms from the paper in Matlab:
2. Pan & Tompkins algorithm
3. Hamilton & Tompkins algorithm
4. Phasor transform algorithm
5. 2) Run these algorithms on all datasets from the MIT-BIH database:https://archive.physionet.org/physiobank/database/mitdb/

3. 3) Reproduce Table 2 from the paper.
4. 4) Reproduce Figure 2 from the paper.
5. 5) Implement an algorithm of your choice that is even better than the 3mplemented and compared in the paper E.g.https://ieeexplore.ieee.org/abstract/document/898536

6. 6) why did the Phasor transform algorithm not perform as well in this paper as inthe original publication?

Submission:

Submit one Matlab file (either .m or .mlx) which reproduces Table 2 and Figure 2from the paper starting from the raw files. Name this file main_analysis.m or

main_analysis.mlx. You should create helper functions as separate m-files andupload all these files as one zip file. Do NOT submit the datafiles from the MIT

BIH database - your code should expect that these files are one level up fromyour code in your file hierarchy. Make sure to comment your code.

Hints:

1. 1) The code that was originally used for the paper is not available anymore underthe address listed in the paper but can be found here:https://github.com/milegroup/Recg

1. This code is written in R, so it will not be directly usable in your Matlabscripts, but could ofer hints about implementation details

2. 2) One way to load these files in Matlab is to use:https://archive.physionet.org/physiotools/matlab/wfdb-app-matlab/This is how you install the toolbox:[old_path]=which('rdsamp'); if(~isempty(old_path)) rmpath(old_path(1:end-8)); endwfdb_url='https://physionet.org/physiotools/matlab/wfdb-app-matlab/wfdb-apptoolbox-0-10-0.zip';[filestr,status] = urlwrite(wfdb_url,'wfdb-app-toolbox-0-10-0.zip');unzip('wfdb-app-toolbox-0-10-0.zip');

cd mcode

addpath(pwd)

savepath

Here is an example how to load a dataset and the R-peak annotations (you need theseto compute if your algorithm does the right thing to compute sensitivity and Pos.Predictivity):

[sig, Fs, tm] = rdsamp('234', 1);

[ann,anntype,subtype,chan,num,comments]=rdann('234', 'atr', [], [], [], []);

[RR,tms]=ann2rr('234','atr',[],[],[])figure(1);clf

plot(tm, sig);

hold on;

plot(tms/Fs, 1,'gv','MarkerFaceColor','k');