Embedded System for ECG Biometrics

Andr

e Matos

, Andr

e Lourenc¸o

1,2

and Jos

e Nascimento

1,2

Instituto Superior de Engenharia de Lisboa, Lisbon, Portugal

Instituto de Telecomunicac¸

oes, Lisbon, Portugal

Keywords:

Electrocardiogram, ECG, Embedded System, ARM, Biometrics, STM32.

Abstract:

Biometric recognition has recently emerged has an alternative solution for applications where the privacy of

the information is crucial. In this paper we present an embedded biometric recognition system based on the

Electrocardiographic signals (ECG). The proposed system implements a real-time state-of-the-art recognition

algorithm, which extracts information from the frequency domain, on an architecture based ARM Cortex 4.

Using a sensor based on a two electrodes apparatus, the system is designed to be autonomous, non-intrusive

and easy to use on different scenarios. Preliminary results show the successful real-time implementation on

the embedded platform enabling its usage on a myriad of applications.

1 INTRODUCTION

Many of our daily tasks are becoming dependent of

automatic and accurate identity validation systems.

Traditional strategies for recognition include PIN

numbers, tokens, passwords and ID cards. Despite

the wide deployment of such mechanisms, the means

for authentication is either entity-based or knowledge-

based which raises serious security concerns with re-

gards to the risk of identity theft (Jain et al., 2005;

Jain et al., 2004; Ross et al., 2006).

The major beneﬁt of security systems based on

biometrics is the full dependency on the individual.

There are no dependencies on objects or memories as

it occurs on the traditional strategies. This leads to a

higher use of biometric systems in order to increase

the difﬁculty in falsiﬁcation of credentials. Currently

one of the major ﬂaws of these systems is the ease of

falsiﬁcation of credentials. For instance, a photo can

fake a face, the iris can be falsiﬁed by contact lenses

and even the ﬁngerprint may be exchanged for a gel

ﬁnger (Jain et al., 2007).

Recently, physiological signals are being used for

this purpose, being the electrocardiogram (ECG), an

emergent and viable alternative (Agraﬁoti et al., 2011;

Biel et al., 2001; Silva et al., 2013; Ye et al., 2010;

Israel et al., 2005; Singh and Gupta, 2009; Odinaka

et al., 2010). The fact that there are subject de-

pendent features in the ECG, enhances its applica-

bility for user recognition. Furthermore, the ECG

has unique properties when looked at in traditional or

multi-biometrics approach; in particular, it is:

• universally available in live subjects, which make

it a never ending source of information, allowing

redundancy on undesirable pieces of acquired sig-

nal;

• measurable non-intrusively using suitable de-

vices;

• acceptable due to the latest advances in the sens-

ing technologies;

• not easily circumvented through latent patterns,

since is rare to see an equipment acquiring at low

sampling frequencies.

The main downside of an ECG recognition is the

intra-person variation caused by different heart-rates

(Ye et al., 2010; Israel et al., 2005; Singh and Gupta,

2009). The frequency domain approach (Odinaka

et al., 2010) aims at an reduction of this thread.

Tipically the ECG-based biometric systems pre-

sented in the literature, are non-integrated systems,

which process the information in two phases: 1) the

acquisition is performed using a dedicated appara-

tus capable of transmiting the signal into a process-

ing unit; 2) the signal processing and recognition al-

gorithm is perfomed on a computer (tipically in an

off-line process). In this paper we propose an inte-

grated solution for ubiquitous ECG biometric recog-

nition. It consists on an embedded system with an

integrated ECG sensor based on a two electrodes ap-

paratus that enables real-time, non-intrusive ECG ac-

quisition at user’s ﬁngers/hands. The proposed sys-

Matos A., Lourenço A. and Nascimento J..

Embedded System for ECG Biometrics.

DOI: 10.5220/0004703300270033

In Proceedings of the International Congress on Cardiovascular Technologies (CARDIOTECHNIX-2013), pages 27-33

ISBN: 978-989-8565-78-5

 2013 SCITEPRESS (Science and Technology Publications, Lda.)

tems focus ubiquitous solution enabling autonomous

and embedded recognition based on ECG.

The proposed embedded system allows real time

processing, samples the ECG using the embed-

ded system internal Analog to Digital Converters

(ADC’s), and uses Odinaka’s recognition approach

(Odinaka et al., 2010) for biometric authentication.

The remain of the paper is organized as follows,

Section 2 introduces the architecture of the embedded

platform, focusing the capacities, advantages and dis-

advantages of the system compared to other possible

solutions. In section 3 the signal ﬁltering, peak detec-

tion, feature selection and the classiﬁcation steps are

described. Section 4 presents some results and section

5 concludes the paper with some remarks.

2 EMBEDDED PLATFORM

An embedded platform is a computer system with a

dedicated function within a larger mechanical or elec-

trical system, often with real-time computing con-

straints. By contrast, a general-purpose computer is

designed to be ﬂexible and to meet a wide range of

end-user needs.

This embedded platforms vary in many ways, of-

ten depending on the usage, or project necessity.

These devices can generally divided in:

• A microprocessor is a multi-purpose, pro-

grammable, clock driven register and an arith-

metic and logic unit (ALU) based electronic de-

vice. Many more microprocessors are part of

embedded systems, providing digital control over

myriad objects from appliances to automobiles

to cellular phones and industrial process control

(Godse, 2008);

• A MicroController(sometimes abbreviated µC,

uC or MCU) is a small computer on a single inte-

grated circuit containing a processor core, mem-

ory, and programmable input/output peripherals.

Microcontrollers incorporates all the features that

are found in a microprocessor, however, it has

also added features to make a complete micro-

computer system on its own. Microcontrollers are

designed for embedded applications, in contrast to

the microprocessors used in personal computers

or other general purpose applications due to on-

chip (build-in) peripheral devices (Godse, 2008);

• A Digital Signal Processor (DSP) is a specialized

microprocessor with an architecture optimized for

the operational needs of digital signal processing;

• A ﬁeld-programmable gate array (FPGA) is, in-

formally thought, a ”blank slate” on which any

digital circuit can be conﬁgured. Moreover, the

desired functionality can be conﬁgured in the

ﬁeld. That is, after the device has been manufac-

tured, installed in a product, or, in some cases,

even after the product has been shipped to the

consumer. In short, and FPGA provides pro-

grammable ”hardware” to embedded system de-

velopers (Sass and Schmidt, 2010).

In this paper the real-time constrain must be ful-

ﬁlled. Samples cannot be lost and the authentication

procedure must be as close as real time as it can be.

Memory is also a need, in order to store the charac-

teristics of the subjects. The microprocessor was dis-

carded for his low versatility and costs to manufacture

the embedded system, such as the FPGA for their high

costs. The proposed system is a mix of a regular MCU

and a DSP processor. The development MCU board,

STM32F4-Discovery, was chosen due to its versatil-

ity, low power consumption, high speeds and DSP in-

tegration.

Figure 1: Hardware block diagram of the system.

An ARM-Based Cortex4 32 bit RISC

STM32F407VGT6, was chosen as the processor

in our system. It works at 168MHZ, with characters

of strong performance and low power consumption,

real-time and low-cost. The processor includes: 1M

FLASH, 192K+4K RAM, and a bluetooth module

will be used for communication with an auxiliary

external visualization Application Programming

Interface (API). The system have the A/D converter

with 12 bits resolution, and the fastest conversion

up to 0.41us, with 3.6 V full-scale of the system.

It also includes an Floating Point Unit (FPU) and

a DSP inside the processor, making ﬂoating point

mathematics faster than integers calculus.

Figure 1 shows the processor peripherals and

hardware used. The bluetooth module uses a stan-

dard serial communication (USART) to ﬂow the data

from/to microprocessor. The acquiring module am-

pliﬁes the ECG signal to the range used by the ADC

peripheral, and digitalizes it using 1000 Hz.

Bluetooth communication allows the system con-

CARDIOTECHNIX2013-InternationalCongressonCardiovascularTechnologies

ﬁguration (selecting between train and test scenarios)

and shows the authentication result. Additionally it

can also be used as debug or simple signal display.

3 RECOGNITION ALGORITHM

The problem of human recognition based on a bio-

metric system, can be formulated in the pattern recog-

nition framework. Fig. 2 contextualize the steps in-

volved in such a system: 1) ﬁrst the signal is ac-

quired by the sensors; 2) the signal is preprocessed

and described in a convenient representation; 3) fea-

tures are extracted; 3) from the extracted features the

most discriminative are selected; 4) a classiﬁcation

block processes the features and delivers a decision

corresponding to the recognition of the subject (Wang

et al., 2008).

Figure 2: Classic structure of a reckoning system applied to

an identiﬁcation issue.

The proposed approach follows a partial ﬁducial

approach (Agraﬁoti et al., 2011), using the wave on-

set, peak (the R complex) as characteristic point for

segmentation. The feature extraction is based on a

frequency approach, and follows Odinaka algorithm

(Odinaka et al., 2010). In Odinaka’s work (Odinaka

et al., 2010) each single heartbeat is segmented into

64ms windows with an overlap between of 54ms.

The analysis is performed in the frequency domain

computing the short time Fourier transform (STFT)

(Oppenheim and Schafer, 1975) for each window (an

Hamming is used for better estimation), in order to es-

timate a mean and a variance of each frequency bin.

The performance of this method, and its suitability

for a real time implementation on embedded system

implementation, were the main aspects considered on

choosing this method for this implementation.

3.1 Frequency Extraction Approach

and Implementation in embedded

System

In Fig. 3 we represent the block diagram of the imple-

mented approach. Our target is to design the system

for real time operation; since each sample comes pe-

riodically each 1 ms (sampling frequency 1KHz), the

system has this time frame for processing all the infor-

mation. This real time constrain lead to a segmenta-

tion of every heartbeat waveform in 140ms windows

without overlap, instead of Odinaka’s 64ms windows

(Odinaka et al., 2010). The processing routine starts

by the arrival of a new digitalized sample, which in-

duces an high-priority interrupt (INT) that adds it to a

First In First Out (FIFO) array. This array is used for

two different tasks: 1) single heart beat segmentation;

2) feature extraction.

For the segmentation the raw signal is ﬁltered with

a band-pass ﬁlter (BPF) with pass-band [5, 15]Hz, and

then fed to the Slope Sum Function (SSF) (Zong

et al., 2003) algorithm, which enables the detection

of the R-complex. The delineation of a single-heart-

beat consists on a ﬁxed window of 700 ms, beginning

200ms prior to the peak, and ending 500 ms after the

peak. The STFT of each segment is then computed

using each segmented piece of the single-heartbeat.

Figure 3: Software block diagram of the system.

The STFT uses a spectral zoom approach, i.e., it

makes a 1024 point STFT for each 50ms window and

subsequently cutting the results to the ﬁrst 50 STFT

points. This creates a low pass digital ﬁlter with

approximately [0, 50]Hz pass-band, to remove noise

present at the acquisition conditions and since the

band of interested of biometric applications is mostly

focused on this frequency bandwidth. This STFT

computation is the step that is most time-consuming,

taking 1.2ms for each STFT alone, making a total of

8.4ms for all the STFT phase.

A study has been made to determine the frame

size and overlap time between frames, which results

in terms of Equal Error Rate (EER) and identiﬁca-

tion performance are presented in ﬁgures 4, 5, 6, 7.

Frame size tests were performed without any over-

lap and overlap tests were performed with a frame

size of 140ms, being this the top performance value.

These tests were performed with 50 separated runs in

order to create a mean and a variance for each vari-

able (frame size and overlapped time). Regarding the

experiment, the best solution is an 140ms frame size

without overlap. Overlapping barely increase the per-

formance and substantially increases processing time.

The STFT is applied to each of the 140ms win-

EmbeddedSystemforECGBiometrics

Figure 4: Identiﬁcation performance over frame size vari-

ance.

Figure 5: Equal Error Rate (EER) performance over frame

size variance.

dow, leading to the creation of 50 frequency bins, to-

talizing a vector with 250 features. The l-th feature

corresponds to the STFT obtained over each segment

window.

3.2 Feature Selection and Classiﬁcation

Odinaka’s work (Odinaka et al., 2010) proposes an

effective away to select informative features using a

robust feature selection method. The two key ele-

ments considered in this feature selection method are

distinguish-ability and stability. The feature should

help distinguish the subject from a reasonably large

subset of other subjects, and it should be stable across

sessions. Let µ

and σ

be mean and standard devia-

tion of the l-th feature of the i-th subject.

The l-th feature of the i-th subject is selected if

the symmetric relative entropy, i.e., the symmetric

Kullback-Leibler divergence, between N (µ

, σ

) and

the nominal distribution N (µ

, σ

) is larger than a

threshold κ > 0, being (µ

, σ

) the maximum like-

lihood estimate from all database. The Kullback-

Leibler divergence is a non-symmetric measure of

Figure 6: Identiﬁcation performance over overlap time be-

tween frames.

Figure 7: Equal Error Rate (EER) performance over overlap

time between frames.

the difference between two probability distributions

P and Q, deﬁned by

D(p||q) =

plog

. (1)

The symmetric relative entropy between the two

densities is deﬁned as

d(p, q) = D(p||q) +D(q||p) (2)

For the Gaussian distributions used in this model,

the symmetric relative entropy between N (µ

, σ

)

and N (µ

, σ

) is

(l),

(l)) =

+ (µ

− µ

)

2σ

+ (µ

− µ

)

2σ

− 1

(3)

where the nominal model is obtained by using the

spectrograms of all the subjects in the database and

θ denotes the maximum likelihood estimate for the

individual in test,

(l), and the train database,

(l).

Using the symmetric relative entropy for feature se-

lection ensures that only those bins whose distribu-

tions are far from the nominal are selected for each

subject, thereby ensuring distinguish-ability.

CARDIOTECHNIX2013-InternationalCongressonCardiovascularTechnologies

The score of a test heartbeat using the i-th

subject’s model is given by the log-likelihood ratio

(LLR):

Λ =

∑

(Y(l)|

(l))

(Y(l)|

(l))

d(θ

(l),θ

(l))>κ

(4)

where I is the truth function indicating which time-

frequency bins are selected; l is the index of the bins.

For authentication, the LLR given in expression 4 is

compared with a threshold τ, so that if Λ > τ, the

heartbeat with the claimed identity is accepted, oth-

erwise the heartbeat is rejected.

4 EXPERIMENTAL EVALUATION

The dataset used to evaluate the this approach was ac-

quired using the proposed system. It is composed by

11 subjects, with two recording sessions per subject.

The acquired signals were obtained following the re-

cent trend “the off-the-person approach”, where the

ECG data is acquired at the ﬁngers with dry Ag/AgCl

electrodes. The ECG sensor consists of a custom, two

lead differential sensor design with virtual ground,

found in (Silva et al., 2011). Figure 8 presents the pro-

totype, composed by the STM32F4-Discovery board

and ECG sensor, used in the experiments.

Figure 8: Prototype of the embedded system.

The features used in this work consist in

frequency-domain representation. In ﬁgure 9 we il-

lustrate the potential of this representation, showing

for two different users, the time (on the left) and fre-

quency (on the right) domain representation. Observ-

ing both the ﬁgures, it is possible to distinguish visu-

ally the difference between both subjects. In the liter-

ature, frequency domain representation is considered

more robust to heart-rhythm variation then the time

domain counterpart (Odinaka et al., 2012).

The performance evaluation over the entire dataset

is summarized in ﬁgure 10, where we plot the false ac-

ceptance rate (FAR) and the false rejection rate (FRR)

curves in terms of the threshold of the system. We

superimpose the equal error rate (EER) point, cor-

responding to the point where the FAR is equal to

the FRR, and in this case corresponds to EER=9.3%.

With this approach we achieve a 100% identiﬁcation

rate with 30 seconds of train signals.

Figure 10: FAR vs FRR curve.

5 CONCLUSIONS AND FUTURE

WORK

Biometric systems are moving towards multi modal

approaches, combining several modalities to over-

come some of the limitations exhibited by each sepa-

rately. Some behavioural biometrics modalities have

the potential to complement existing approaches due

to their intrinsic nature, and the ECG is one such case.

In this paper we present an embedded system

where we implemented a state-of-the-art method for

ECG-based recognition. The implement method is

based on a frequency-domain representation adapted

from Odinaka et. al. (Odinaka et al., 2010). Our sys-

tem also includes an ECG sensor that enables the ac-

quisition at the ﬁngers with dry Ag/AgCl electrodes,

and implements all the steps of recognition workﬂow

focusing real-time processing.

As future work, we intend to test the proposed

method with a larger datasets and compare with other

state-of-the art methods.

EmbeddedSystemforECGBiometrics

(a) time (b) frequency

Figure 9: Comparison of time and frequency domain representation for two different users (arranged by line).

ACKNOWLEDGEMENTS

This work was partially funded by FCT un-

der grants SFRH/PROTEC/49512/2009, PTDC/EEI-

SII/2312/2012 (LearningS project), and by the

ADEETC from Instituto Superior de Engenharia de

Lisboa, whose support the authors gratefully ac-

knowledge.

REFERENCES

Agraﬁoti, F., Gao, J., and Hatzinakos, D. (2011). Biomet-

rics, chapter Heart Biometrics: Theory, Methods and

Applications, Biometrics. InTech.

Biel, L., Pettersson, O., Philipson, L., and Wide, P. (2001).

ECG analysis: a new approach in human identiﬁca-

tion. Instrumentation and Measurement, IEEE Trans-

actions on, 50(3):808–812.

Godse, D. (2008). Microprocessor, Microcontroller & Ap-

plications. Technical Publications.

Israel, S. A., Irvine, J. M., Cheng, A., Wiederhold, M. D.,

and Wiederhold, B. K. (2005). {ECG} to identify in-

dividuals. Pattern Recognition, 38(1):133 – 142.

Jain, A. K., Bolle, R. M., and Pankanti, S. (2005). Bio-

metrics: Personal Identiﬁcation in Networked Society.

Springer.

Jain, A. K., Flynn, P., and Ross, A. A. (2007). Handbook of

Biometrics. Springer-Verlag New York, Inc., Secau-

cus, NJ, USA.

Jain, A. K., Ross, A., and Prabhakar, S. (2004). An intro-

duction to biometric recognition. IEEE Trans. Circuits

Syst. Video Techn., 14(1):4–20.

Odinaka, I., Lai, P.-H., Kaplan, A., O’Sullivan, J., Sirevaag,

E., Kristjansson, S., Shefﬁeld, A., and Rohrbaugh,

J. (2010). Ecg biometrics: A robust short-time fre-

quency analysis. In Information Forensics and Secu-

rity (WIFS), 2010 IEEE International Workshop on,

pages 1 –6.

Odinaka, I., Lai, P.-H., Kaplan, A., O’Sullivan, J., Sirevaag,

E., and Rohrbaugh, J. (2012). Ecg biometric recogni-

tion: A comparative analysis. Information Forensics

and Security, IEEE Transactions on, 7(6):1812 –1824.

Oppenheim, A. V. and Schafer, R. W. (1975). Digital Signal

Processing. PrenticeHall.

Ross, A. A., Nandakumar, K., and Jain, A. K. (2006). Hand-

book of Multibiometrics (International Series on Bio-

CARDIOTECHNIX2013-InternationalCongressonCardiovascularTechnologies

metrics). Springer-Verlag New York, Inc., Secaucus,

NJ, USA.

Sass, R. and Schmidt, A. G. (2010). Embedded Systems

Design with Platform FPGAs: Principles and Prac-

tices. Morgan Kaufmann Publishers Inc., San Fran-

cisco, CA, USA, 1st edition.

Silva, H., Lourenc¸o, A., Canento, F., Fred, A., and Ra-

poso, N. (2013). ECG biometrics: Principles and ap-

plications. In Proceeding of the 6th Conference on

Bio-Inspired Systems and Signal Processing (BIOSIG-

NALS).

Silva, H., Lourenc¸o, A., Lourenc¸o, R. L., Leite, P. L.,

Coutinho, D., and Fred, A. L. N. (2011). Study and

evaluation of a single differential sensor design based

on electro-textile electrodes for ECG biometrics ap-

plications. In IEEE Sensors, pages 1764–1767.

Singh, Y. and Gupta, P. (2009). Biometrics method for

human identiﬁcation using electrocardiogram. In

Tistarelli, M. and Nixon, M., editors, Advances in Bio-

metrics, volume 5558 of Lecture Notes in Computer

Science, pages 1270–1279. Springer Berlin Heidel-

berg.

Wang, Y., Agraﬁoti, F., Hatzinakos, D., and Plataniotis,

K. N. (2008). Analysis of human electrocardiogram

for biometric recognition. EURASIP J. Adv. Signal

Process, 2008.

Ye, C., Coimbra, M., and Kumar, B. (2010). Investigation

of human identiﬁcation using two-lead electrocardio-

gram (ecg) signals. In Biometrics: Theory Applica-

tions and Systems (BTAS), 2010 Fourth IEEE Interna-

tional Conference on, pages 1–8.

Zong, W., Heldt, T., Moody, G., and Mark, R. (2003). An

open-source algorithm to detect onset of arterial blood

pressure pulses. In Computers in Cardiology, 2003,

pages 259–262.

EmbeddedSystemforECGBiometrics