<!--#set var="TITLE" value="Biometric Human Identification based on ECG"-->
<!--#include virtual="/head.shtml"-->
<center><h1>Biometric Human Identification based on ECG</h1></center>
<p align="center">T. Lugovaya</p>
<p align="center">Department of Applied Mathematics and Computer Science,
Electrotechnical University "LETI", Saint-Petersburg, Russian Federation</p>
<p>
<center><table bgcolor="lightblue">
<tr>
<td>This material originally appeared in master's thesis "Biometric human identification based on ECG" in 2005.
Please cite this publication when referencing this material.</td>
</tr>
</table></center></p>
<a name="abstract">
<h2>Abstract</h2></a>
<p><i>This research investigates the feasibility of using the electrocardiogram (ECG) as a new biometric for human identification.
It is well known that the shapes of the ECG waveforms depend on human heart anatomic features and are different for different persons.
But it is unclear whether such differences can be used to identify different individuals. This research demonstrates that it is possible
to identify a specific person in a predetermined group using a one-lead ECG. A one-lead ECG is a one-dimensional, low-frequency signal that
can be recorded from electrodes on the hands. ECG fragments containing QRS complex, P and T waves extracted from the ECG are processed by
principal component analysis and classified using linear discriminant analysis. Using this method on a predetermined group of 90 subjects,
the experimental results showed that the rate of correct identification was 96%.</i></p>
<a name="introduction">
<h2>1. Introduction</h2></a>
<p>Biometric technologies are among fast-developing fields of information security, gradually entering into all
spheres of human activity. Today only three biometric methods have proved their efficiency, namely, identification based on
fingerprints, iris or retina, and face. Hand geometry, voice, writing and typing dynamics, etc.
are also useful, depending on the purpose and range of application.</p>
<p>This research aims to develop identification system based on ECG (figure 1).
ECG is assumed as an almost unique human characteristic because morphology and amplitudes of registered cardiac complexes are
governed by multiple individual factors, in particular, by formation and position of the heart, presence and nature
of pathologies, etc.</p>
<center>
<img src="ecg.png" alt="[example of ECG]">
<p><b>Figure 1.</b> Example of ECG with agreed notations.</p>
</center>
<a name="database">
<h2>2. The ECG-ID Database</h2></a>
<p>Database contains 310 ECG recordings, obtained from 90 persons:
<li>each recording contain 20-second I-lead ECG signal;
<li>10 beats in every recording are annotated (unaudited R- and T-wave peaks annotations from an automated detector);
<li>signals were digitized at 500 Hz with 12-bit resolution;
<li>number of records for each person vary from 2 (collected during one day) to 20 (collected periodically during 6 months);
<li>each recording is supplied with an information containing age, gender and record date;
<li>records were obtained from volunteers among students, colleagues and friends (44 men and 46 women aged from 13 to 75 years);</p>
<p>Collected raw data is rather noisy and contain both high and low frequency noise components.
Each recording combine both raw and filtered signals:
<li>Column 0 "ECG I": raw signal;
<li>Column 1 "ECG I filtered": filtered signal;</p>
<p>The ECG-ID Database itself is available <a href="../">here</a>.</p>
<center>
<img src="ecg_db_record.png" alt="[example of ECG-ID database record]">
<p><b>Figure 2.</b> Example of ECG-ID Database record.</p></center>
<a name="system">
<h2>3. Identification system</h2></a>
<p>The system feasibility was discussed in [1, 2]. This study suggests other data interpretation and classification
techniques, with the system tested on a higher level of live input data. The respective findings are compared
below (table 2).</p>
<p>The identification system uses a classical scheme including data preprocessing, formation of input data space, transition to reduced
feature space, ECG cycles classification and ECG record identification.</p>
<p>On usability grounds, the study uses brief ECG (10-20 sec) records from a single upper extremity lead
(lead I) with sample rate 500Hz and digit 12.</p>
<a name="preprocessing">
<h3>3.1. Data preprocessing</h3></a>
<p>Collected raw data is rather noisy and contain distortions of various origins, both high and low frequency noise components are in presence (figure 3).</p>
<center>
<table>
<tr>
<td align=center><img src="ecg_noise_net.png" alt="[power-line noise]"><br>A. ECG with power-line noise</td>
<td align=center><img src="ecg_noise_high.png" alt="[high-frequency noise]"><br>B. ECG with high-frequency noise</td>
</tr>
<tr>
<td align=center><img src="ecg_noise_both.png" alt="[power-line and high-frequency noise]"><br>C. ECG with both power-line and high-frequency noise</td>
<td align=center><img src="ecg_noise_drift.png" alt="[isoline drift]"><br>D. ECG with isoline drift</td>
</tr>
</table>
<b>Figure 3.</b> Examples of noisy ECG.
</center>
<p>Frequency-selective signal filtering was implemented using a set of adaptive bandstop filter and low-pas filter (figure 4).</p>
<center>
<table>
<tr>
<td><img src="noise_filter_1.png" alt="[signal filtering 1]"></td>
<td><img src="noise_filter_2.png" alt="[signal filtering 2]"></td>
</tr>
</table>
<b>Figure 4.</b> Examples of frequency-selective signal filtering results.
</center>
<p>Isoline drift correction was implemented using multilevel one-dimensional wavelet analysis. Original signal was decomposed at level 9
using biorthogonal wavelet. Signal reconstructed using final approximation coefficients is assumed to be drifting isoline, which is subtracted
from the original signal (figure 5). This method shows good results in both cases of clear and rather noisy ECG signals.</p>
<center>
<table>
<tr>
<td><img src="wavelet_drift_correction.png" alt="[wavelet drift correction]"></td>
<td><img src="wavelet_drift_correction_noisy.png" alt="[wavelet drift correction noisy]"></td>
</tr>
</table>
<b>Figure 5.</b> Examples of isoline drift correction results.
</center>
<a name="feature_space">
<h3>3.2. Initial feature space</h3></a>
<p>The study focuses on ininitial feature space formation. Obviously information on cardiac performance is basically held in the pulse cycle
fragment containing the QRS complex and P- and T waves (referred here as the PQRST-fragment). Therefore the stage begins with extraction of
a set of R-peak synchronized PQRST-fragments (figure 6). The PQRST fragments length is invariably 0.5 sec or 250 counts.</p>
<center>
<table>
<tr>
<td><img src="pqrst_set_1.png" alt="[PQRST-fragments extraction]"></td>
<td><img src="pqrst_set_2.png" alt="[PQRST-fragments extraction]"></td>
</tr>
</table>
<b>Figure 6.</b> R-peak detection and PQRST-fragments extraction.
</center>
<p>PQRST-fragment samples are used as informative features. Therefore extracted PQRST-fragments are then processed to enhance their similarity as follows:
<table>
<tr>
<td>1.</td>
<td colspan=3>Correcting PQRST-fragment mutual "vertical" shift due to eventual residual isoline drift:</td>
</tr>
<tr>
<td></td>
<td colspan=3 align="center"><img src="pqrst_set_vertical_correction.png" alt="[vertical shift correction]"></td>
</tr>
<tr>
<td>2.</td>
<td colspan=3>Culling eventual "atypical" PQRST-fragments due to gestures, deep breathing or certain pathologies:</td>
</tr>
<tr>
<td></td>
<td colspan=3 align="center"><img src="pqrst_set_atypical.png" alt="[atypical PQRST-fragments]"></td>
</tr>
<tr>
<td>3.</td>
<td colspan=3>Correcting PQRST-fragments depending on heart rate using Bazett's formula:</td>
</tr>
<tr>
<td></td>
<td align="center"><img src="pqrst_set_rate_original.png" alt="[heart rate influence]"></td>
<td align="center"><img src="arrow_hor.png"></td>
<td align="center"><img src="pqrst_set_rate_corrected.png" alt="[heart rate correction]"></td>
</tr>
</table>
</p>
<p>Thus in the initial feature space (dimension N=250) ECG appears as a set of PQRST-fragments with each seen as a separate pattern at subsequent
system stages, to be interpreted and classified independently.</p>
<a name="reduction">
<h3>3.3. Feature space reduction</h3></a>
<p>The feature space is reduced using Principal Components Analysis (PCA) so that space dimension can be reduced to 30 (with the Kaiser criterion)
or even to 10 (with the scree test).</p>
<p>Or, alternately, the space is reduced with wavelet transform (WT) providing the same space reduction but with
slightly poorer final identification.</p>
<a name="classification">
<h3>3.4. Classification and Identification</h3></a>
<p>The resulting PQRST-fragment patterns are then classified in reduced feature space using linear discriminant analysis.</p>
<p>At the final stage, the ECG record identification is based on PQRST-fragments classification results.</p>
<a name="results">
<h2>4. Results</h2></a>
<p>Experimental studies involve 90 human. ECG records were made in the sitting position, heart rate, physical and emotional state were not limited.
Collected data set contains 320 records, of which 200 records were assigned to the training set and 120 records to test set.
Differentiation between trainig and test sets aimed to provide for maximum performance complexity, i.e. maximum difference between records
in different sets both in monitoring time and human physical state.</p>
<p>Averaged results of series of experiments on PQRST-fragments classification and ECG record identification with different feature space reduction
methods are tabulated in Table 1. ECG identification leveling is thus 96%.
<center>
<table border="1" cellspacing="2" bordercolor="#808080" cellpadding="3">
<tbody>
<tr>
<td align="center" rowspan="2">Reduction technique</td>
<td align="center" rowspan="2">Number of features</td>
<td align="center" colspan="2">PQRST-fragments classification, %</td>
<td align="center">ECG identification, %</td>
</tr>
<tr>
<td align="center">Training set</td>
<td align="center">Test set</td>
<td align="center">Test set</td>
</tr>
<tr>
<td align="center">PCA</td>
<td align="center">10</td>
<td align="center">99</td>
<td align="center">85</td>
<td align="center">89</td>
</tr>
<tr>
<td align="center">WT</td>
<td align="center">9</td>
<td align="center">98</td>
<td align="center">79</td>
<td align="center">82</td>
</tr>
<tr>
<td align="center"><b>PCA</b></td>
<td align="center"><b>30</b></td>
<td align="center">99</td>
<td align="center">91</td>
<td align="center"><b>96</b></td>
</tr>
<tr>
<td align="center">WT</td>
<td align="center">34</td>
<td align="center">99</td>
<td align="center">88</td>
<td align="center">91</td>
</tr>
</tbody></table>
<b>Table 1. </b>Experimental results.
</center></p>
<p>Additionally, results from [1, 2] and this research are compared in Table 2.
<center>
<table border="1" cellspacing="2" bordercolor="#808080" cellpadding="3">
<tbody>
<tr>
<td align="center">Research</td>
<td align="center">Class count</td>
<td align="center">Identification results, %</td>
</tr>
<tr>
<td align="center">[1]</td>
<td align="center">20</td>
<td align="center">98</td>
</tr>
<tr>
<td align="center">[2]</td>
<td align="center">9</td>
<td align="center">95</td>
</tr>
<tr>
<td align="center">this</td>
<td align="center">90</td>
<td align="center">96</td>
</tr>
</tbody></table>
<b>Table 2. </b> Results comparison.
</center></p>
<p>As a result of this research a recognition system was developed, it solved the problem of biometric human identification based on ECG on
sufficiently large set of input data. The findings represent primary arguments for ECG usability as a biometric characteristic in various biometric
access control problems, opening up brand new perspective for the study of biometric technologies, and extending potentialities of security- and modern
amenity systems.</p>
<a name="refs">
<h2>References</h2></a>
<p>[1] L.Biel, O.Pettersson, L.Philipson, P.Wide "ECG Analysis: A New Approach in Human Identification",
IEEE Transactions on Instrumentation and Measurement, vol.50, N3, June 2001, pp. 808-812.</p>
<p>[2] W.J. Yi, K.S. Park, D.U. Jeong "Personal Identification From ECG Measured Without Body Surface Electrodes
Using Probabilistic Neural Networks".</p>
<!--#include virtual="/footer.shtml" -->