Fusion of eye movement and mouse dynamics for reliable behavioral biometrics

Abstract

This paper presents the first attempt to fuse two different kinds of behavioral biometrics: mouse dynamics and eye movement biometrics. Mouse dynamics were collected without any special equipment, while an affordable The Eye Tribe eye tracker was used to gather eye movement data at a frequency of 30 Hz, which is also potentially possible using a common web camera. We showed that a fusion of these techniques is quite natural and it is easy to prepare an experiment that collects both traits simultaneously. Moreover, the fusion of information from both signals gave 6.8 % equal error rate and 92.9 % accuracy for relatively short registration time (20 s on average). Achieving such results were possible using dissimilarity matrices based on dynamic time warping distance.

Full text

THEORETICAL ADVANCES
Fusion of eye movement and mouse dynamics for reliable
behavioral biometrics
Pawel Kasprowski
1
•Katarzyna Harezlak
1
Received: 5 November 2015 / Accepted: 11 July 2016 / Published online: 27 July 2016
The Author(s) 2016. This article is published with open access at Springerlink.com
Abstract This paper presents the first attempt to fuse two
different kinds of behavioral biometrics: mouse dynamics
and eye movement biometrics. Mouse dynamics were col-
lected without any special equipment, while an affordable
The Eye Tribe eye tracker was used to gather eye movement
data at a frequency of 30 Hz, which is also potentially
possible using a common web camera. We showed that a
fusion of these techniques is quite natural and it is easy to
prepare an experiment that collects both traits simultane-
ously. Moreover, the fusion of information from both sig-
nals gave 6.8 % equal error rate and 92.9 % accuracy for
relatively short registration time (20 s on average).
Achieving such results were possible using dissimilarity
matrices based on dynamic time warping distance.
Keywords Eye movement Mouse dynamics Biometric
fusion
1 Introduction
There have been many solutions developed for user iden-
tification including passwords, PINs, access tokens, ID
badges and PC cards, yet they are often inconvenient or
even insufficient due to technological development. People
are provided access to so many secured resources that they
are not able to memorize all the necessary PIN codes and
passwords. That is why so-called biometric identification
that uses human body characteristics (like face, iris or
fingerprint recognition) has gained interest. The most
popular methods utilize mostly physiological patterns of a
human body; however, this makes them vulnerable.
The aforementioned inconveniences led to a search for
new solutions. Biometric identification based on human
behavioral features may solve these problems. There are
various human characteristics to be considered and
explored for the purposes of biometric identification.
Among them voice, gait, keystroke, signature [1] as well as
eye movement and mouse dynamics should be mentioned.
The aim of the paper is to provide a new approach to
biometric identification using a combined feature analysis
based on eye movement and mouse dynamics signals. The
main contribution of the paper is the first attempt to build an
identification model based on a fusion of these two different
biometric traits. For this purpose, a novel experiment that
had not previously been studied was designed. Additionally,
the usage of a dissimilarity matrix [2] to prepare samples for
the classification purpose was introduced.
The paper is organized as follows. The state of the art of
both mouse and eye-movement-based identification is
presented in the second section. The third section describes
the scenario of the experiments, the group of participants
and the experimental setup. Section 4contains details of
the methods used to preprocess and extract features. This is
followed by a description of the evaluation procedure.
Section 5contains results of the experiments. The discus-
sion of these results is presented in Sect. 6. Finally, con-
clusions and future work are provided in Sect. 7.
2 State of the art
Both mouse dynamics and eye-movement-based biometrics
have been studied previously; hence, this section provides
some comparative analyses of previous achievements.
&Pawel Kasprowski
pawel.kasprowski@polsl.pl
1
Institute of Informatics, Silesian University of Technology,
ul. Akademicka 16, 44-100 Gliwice, Poland
123
Pattern Anal Applic (2018) 21:91–103
https://doi.org/10.1007/s10044-016-0568-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

2.1 Information fusion in biometrics
Information fusion is a very popular tool for improving
biometric identification system performance. According to
[3], fusion may combine multiple representations of the
same biometric trait, multiple matchers using the same
representation and, finally, multiple biometric modalities.
Multimodal fusion may be done on various levels: (1) a
feature extraction level, in which multiple traits are used
together to form one feature vector; (2) a matching score
level, in which results (typically similarity scores) obtained
from different biometric systems are fused; and (3) a
decision level, in which only output decisions (accept/re-
ject) from different biometric systems are used in a
majority vote scheme.
There are a lot of examples of multimodal biometric
fusions. The most popular are fusions of physiological
modalities like face and iris [4,5] or fingerprint and iris
[6,7]. There are also works that present a fusion of the
same modality measured by different sensors [8]. Finally,
fusions of different algorithms processing the same data on
matching score or decision levels have improved biometric
identification results significantly [9,10].
2.2 Mouse dynamics
Analyzing the research regarding mouse event-based bio-
metric identification, we find various approaches and many
features of mouse movement that have been studied. Data
obtained as a dynamic mouse signal consist of recordings
including low-level mouse events such as raw movement
and pressing or releasing mouse buttons. These are typi-
cally the timestamps and coordinates of an action and can
be grouped in higher-level events such as move and click,
highlight a text, or a drag and drop task. Based on these
aggregated actions, a number of mouse-related features
have been developed and applied for user identification.
Experiments available in the literature may be differ-
entiated by various aspects. The first of them is the type of
experiment, which includes edit text tasks [11], browser
tasks [11,12] and game scenarios [11,13]. Ahmed and
Traore [14] collected data during users’ daily activities.
Similarly, online forum tasks for gathering mouse move-
ment signal were utilized in the studies presented in [15]. A
different type of experiment was proposed in the research
presented in [16], in which a user had to use a mouse to
follow a sequence of dots presented on a screen.
Studies may also be analyzed in terms of the environ-
ments used. In one group of experiments, participants
worked on computers without any specially prepared
environment [11,12,14]. Another approach was to use a
controlled environment to prevent unintended events
influencing the quality of samples [16–18]. Zheng and el.
[15] conducted tests in a self-prepared environment
involving routine, continuous mouse activities as well as
using an online forum.
Research can also be classified by the time in which an
authentication takes place. There are studies that collected
such data only at the beginning of the session [16]or
continuously during the whole session [11,13,14,18].
Since data gathered during experiments have to be pro-
cessed to be useful in further analysis, each registered
mouse movement signal is divided into small elements
representing various mouse actions. Among such elements,
several features can be distinguished, forming two types of
vectors: spatial and temporal. The first describes changes in
mouse position and includes mouse position coordinates;
mouse trajectory; angle of the path in various directions;
and curvature and its derivative. The second type of vectors
depicts quantities related to mouse movement like hori-
zontal, vertical, tangential and angular velocities, tangen-
tial acceleration and jerk.
The mouse movement dynamic has also been used in
research applying various fusion methods. For example, in
[19] a fusion of keystroke dynamics, mouse movement and
stylometry was studied. Keyboard and mouse dynamics
were also used in [20], yet this time were fused with
interface (GUI) interactions. Two types of fusion were
utilized: feature level fusion and decision level fusion.
We have also found studies in which: (1) two multi-
modal systems that combine pen/speech and mouse/key-
board modalities were evaluated [21]; and (2) fingerprint
technology and mouse dynamics were used [22]. A dif-
ferent type of mouse dynamic-related fusion was utilized in
[23]. This fusion considered only mouse movement, yet
divided it into independently classified feature clusters.
Subsequently, a score level fusion scheme was used to
make the final decision.
2.3 Eye movement biometrics
Eye movement biometrics have been studied for over 10
years [24,25] on the assumption that the way in which
people move their eyes is individual and may be used to
distinguish them from each other. Two aspects of eye
movement may be analyzed: the physiological, concerning
the way that a so-called oculomotor plant works, and the
behavioral, which focuses on the brain activity that forces
eye movement. Therefore, plenty of possible experiments
may be utilized.
The most popular experiments focus just on forcing eye
movements, as the physiological aspect seems easier to
analyze and more repeatable. The simplest example of such
an experiment is a so-called jumping point stimulus. Dur-
ing such a scenario, users must follow with their eyes a
point displayed on a screen periodically changing position
92 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

[24,26,27]. Studies with this kind of stimulus mostly
measure physiological aspects, as subjects are instructed
where to look and cannot make this decision
autonomously.
The other popular type of experiment is recording eye
movement while users are looking at a static image
[25,28,29]. The content of the image may differ, but the
most popular content so far is images with human faces.
This results from the conviction that the way in which faces
are observed is different for everyone [28,30,31]. A
changing scene (movie) is the other possible stimulus
[32,33].
Another kind of experiment is recording eye movement
while users fulfill some specific visual tasks. This seems to
be a promising scenario; however, there are only a few
research papers published so far including text reading
[34], following with eyes more complex patterns [35] and
normal activity like reading and sending emails [36].
When eye movement recordings are gathered, the next
problem is how to extract attributes that may be usable for
human identification. Various approaches have been pro-
posed, one of the most popular of which involves the
extraction of fixations (moments when an eye is relatively
still to enable the brain to acquire a part of an image) and
saccades (rapid movement from one fixation to another)
and performing different statistical analyses on them.
Simple statistics may be applied [37–39] or more sophis-
ticated, like comparisons of distributions used [40]. In ref.
[26], an interesting attempt to use eye movement data to
build a mathematical model of the oculomotor plant has
also been presented. Other approaches analyze the eye
movement signal using well-known transformations like
Fourier, wavelet or cepstrum [24,41,42]. There are also
some methods that take spatial positions of gaze data into
account to build and then analyze heat maps or scan paths
[28,30].
The results obtained in all the aforementioned experi-
ments are far from ideal. Additionally, it is difficult to
compare results of various experiments because scenarios,
hardware (i.e., eye tracker) and participants vary between
them all. Unfortunately, authors are reluctant to publish
their data, which would enable future comparisons. A
notable exception is the EMBD database (http://cs.txstate.
edu/*ok11/embd_v2.html) published by Texas State
University and databases used in publicly accessible Eye
Movement Verification and Identification Competitions:
EMVIC 2012 [27] and EMVIC 2014 [31].
Although it seems natural that the eye movement
modality may be combined with other modalities, to the
best of our knowledge there have been only two attempts to
provide eye movement biometrics in fusion with another
modality. In ref. [43], eye movements were combined with
keystroke dynamics, but the results showed that errors for
eye movements were very high and the improvement when
fusing both keystroke and eye movements was not signif-
icant. In ref. [44], eye movement biometrics were fused
with iris recognition using low-quality images recorded
with a cheap web camera.
2.4 Paper’s contribution
The analysis of the existing methods used for biometric
identification in both previously described areas encour-
aged the authors to undertake studies aimed at com-
pounding signals of eye and mouse movement in a user
authentication process. There are several reasons that such
studies are worth undertaking. Both signals stem from
human behavioral features, which are difficult to forge.
Their collection is easy and convenient for users, who
naturally use their eyes and a mouse to perform computer-
related tasks. Furthermore, the devices that acquire these
signals are simple and cheap, especially when built-in web
cameras are used, and can be easily incorporated in any
environment by installing the appropriate software. The
important feature of the considered solution is also the fact
that both signals can be registered simultaneously, which
makes data collection quicker. Additionally, if necessary,
the method may also be used for covert authentication.
A novel type of experiment that was based on entering a
PIN was designed for this purpose.
Data obtained from both eye and mouse movements
were processed to construct dissimilarity matrices [2] that
would provide a set of samples for training and testing
phases of a classification process. A similar approach was
used in [17] for mouse dynamics; however, it has never
been applied for eye movement data. Taking the above into
consideration, the research contribution may be listed as
follows:
•Introduces a new idea for biometric identification based
on fusion of eye and mouse movements that reduces
identity verification time and improves security.
•Elaborates a new experiment type which can be easily
applied in many environments.
•Applies a dissimilarity space using dynamic time
warping for extraction of features from eye movement
and mouse dynamics.
3 Experiment
This section describes the environment used for conducting
experiments. The test scenario and some quantitative
information about the data analyzed are presented.
Pattern Anal Applic (2018) 21:91–103 93
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

3.1 Scenario
All data were gathered with one experimental setup con-
sisting of a workstation system equipped with an optical
mouse and the Eye Tribe (www.theeyetribe.com) system for
recording eye movement signal at sampling rate of 30 Hz
and an accuracy error of less than 1. It is worth mentioning
that this eye tracker is affordable ($100) and convenient to
use, unlike most of the eye trackers used in the previous
research of eye movement biometrics. The eye tracker was
placed below a screen of size 30 50 cm. The users sat
centrally at a distance of 60 cm. Three such systems were
used simultaneously during the data collection phase. The
low frequency usage was motivated by the idea of checking
whether valuable data may be obtained even for frequencies
available to commonly used web cameras. Additionally,
mouse movements were recorded with the same frequency.
All tests were conducted in the same room. At the
beginning of each session, participants signed a consent
form and were informed about the purpose of the experi-
ment. Each session for each participant started with a
calibration process ensuring adjustment of an eye tracker to
the eye movement of the particular user. Users were asked
to follow a point on the screen with their eyes. After nine
locations, the eye tracker system was able to build a cali-
bration function and measure a calibration error. Only users
obtaining a calibration error value below 1were allowed
to continue the experiment.
In the next step, circles with 10 digits (0–9) were evenly
distributed over the screen, displayed (Fig. 1). The partic-
ipant’s task was to click these circles with the mouse to
enter a PIN number. The PIN was defined as a four-digit
sequence, for which every two consecutive digits were
always different. Both mouse positions and eye gaze
positions were recorded during this activity. It was
assumed that people look where they click with the mouse;
therefore, eye and mouse positions should follow more or
less the same path. One such recording of a PIN being
entered is called a trial in subsequent sections. A trial is a
completed task of entering one PIN, during which eye and
mouse movements were registered. To make simulation of
a genuine–impostor behavior possible, all participants
entered the same PIN sequence: 1–2–8–6.
There were several sessions with at least a 1-week
interval between sessions. During each session, the task
was to enter the same PIN three times in a row.
3.2 Collections used
A total of 32 participants took part in the experiments, and 387
trials were collected. As each user entered the PIN three times
during one experiment, the trials were grouped into sessions.
Each user’s session consisted of three subsequent trials. The
gathered trials were used toprepare three collections differing
in the number of sessions registered for one user:
•C4—24 users, four sessions per user, each containing
three trials,
•C3—28 users, three sessions per user, each containing
three trials,
•C2—32 users, two sessions per user, each containing
three trials.
4 Methods
The data gathered in the described experiment were then
processed to obtain information about people’s identity.
The process was divided into several phases:
•Preparation phase—when every trial was processed to
extract different signals,
•Feature extraction phase—when a sample was built on
the basis of features derived from signals (there are
three different approaches presented below),
•Training phase—when samples with known identity
were used to build a classification model,
•Testing phase—when the model was used to classify
samples with unknown identity,
•Evaluation phase—when the results of the testing phase
were analyzed.
This section describes all these steps in detail.
4.1 Preparation phase
The aim of the preparation phase was to separate different
signals from eye and mouse movements recorded during
the experiments. A signal is defined as a characteristic
feature that can be extracted from each trial. This analysis
concerned only parts of recordings collected between the
first and fourth mouse click.
Fig. 1 Example view of a screen with eye movement fixations
mapped to the chosen digits
94 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

As a result, 24 separate signals were calculated: 11
signals for mouse, 11 signals for gaze and two additional
signals representing mouse and eye position differences
(Table 1). Depending on the length of the recording, each
signal consisted of 105–428 values (from 5 to 21 s).
4.2 Feature extraction phase
The second step in the authentication process was to define
a set of samples that could be used as input for a classifier.
The input for this phase was the fusion of 24 mouse and
eye signals prepared for each trial earlier.
Three different feature extraction algorithms were used:
•Statistic values
•Histograms
•Distance matrix
The detailed description of each is presented in the fol-
lowing sections.
4.2.1 Features based on statistic values
The first of the applied methods is commonly used in many
studies [13,16,18]. It is based on statistical calculations
relating to previously extracted signals. For each, four
statistics were calculated independently for each trial: min,
max, avg, stdev. A sample in this method was defined as a
vector including statistics for all signals from one trial. As
the total number of signals was 24, a vector consisted of
24 4¼96 attributes (Fig. 2).
4.2.2 Histograms
In the second of the feature extraction methods, a sample is
represented by histograms built for each signal and eval-
uated for each trial separately. The frequencies of values
occurring in histogram bins were stored as sample attri-
butes. Because various numbers of bins (B) were consid-
ered—B2ð10;20;30;40;50Þ—a sample for one trial
consisted of 24 Battributes.
4.2.3 Distance matrix
In the last of the developed methods, the feature extraction
process was based on an evaluation of distances between
all training trials. While constructing relevant data struc-
tures, the signal-based description of a trial was taken into
account. Therefore, each signal (for instance x, vx, y, vy)
was treated individually and was used to build an inde-
pendent distance matrix. Let us recall that 24 signals were
Table 1 Set of signals extracted from eye and mouse movements
Signal Formula Description
x, y Xand YThe raw coordinates
vx, vy Vx¼ox
ot;Vy¼oy
otThe first derivative of Xand Y(i.e., vertical and horizontal velocities)
vxy V¼ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
V2
xþV2
y
qThe first derivative for absolute velocity
ax, ay V0
x¼oVx
ot;V0
y¼oVy
otThe second derivative of Xand Y(i.e., vertical and horizontal accelerations)
axy V0¼ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
V02
xþV02
y
qThe derivative of vxy
jx, jy V00
x¼oV0
x
ot;V00
y¼oV0
y
ot
The third derivative of Xand Y(jerk)
jxy V00 ¼ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
V002
xþV002
y
qThe derivative of axy
Diffmgx xmouse xgaze The difference between mouse and gaze positions—axis x
Diffmgy ymouse ygaze The difference between mouse and gaze positions—axis y
Fig. 2 Diagram of the statistic-
based feature extraction
algorithm
Pattern Anal Applic (2018) 21:91–103 95
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

determined in the preparation phase; thus, 24 distance
matrices were built. Further, for Ntraining trials, a matrix
consisting of Nrows and Ncolumns (NNcells) was
obtained to define distances for all training trials (Fig. 3).
Various metrics may be used when comparing distances
of two signals. Euclidean is most common, based on the
sum of all differences for every value registered for a
signal. However, the Euclidean metric is not robust when
comparing shapes of signals, which are shifted in time.
Therefore, it was decided to use a nonlinear dynamic time
warping distance metric for signal comparisons [45]. The
DTW algorithm first calculates distances between all val-
ues in both signals and then searches for a sequence of
point pairs (called the warping path) that minimizes the
warping cost (sum of all distances) and satisfies boundary,
continuity and monotonicity conditions [46]. The distance
for each signal was calculated as the sum of distances
between point pairs on the warping path (see Eq. 1).
DTW Tsignal
a;Tsignal
b

¼ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffi
X
K
k¼0
ðwkÞ=K
v
u
u
tð1Þ
where w0wKis a warping path consisting of K points
with (i,j) coordinates and
wk¼Tsignal
a½iTsignal
b½j

2ð2Þ
The DTW algorithm applied for two signals from two dif-
ferent trials Tiand Tjprovided one value representing their
distance Dsignal
ij . This value became an element of a distance
vector forming a sample of the analyzed signal. A similar
attempt limited to mouse dynamics signal was used in [17].
Dsignal ¼
D11  D1N
.
.
...
..
.
.
DN1 DNN


;signal 2124 ð3Þ
For classification purposes, every column of such a matrix
was treated as one feature. The rows of the matrices were
then used as training samples to train classifiers. The same
procedure was then repeated for every testing sample,
whose distances to all N training samples were calculated
and used as Nfeatures of that sample. The distances were
calculated for each of 24 signals forming 24 matrices.
4.3 Training and testing phase
At the end of the feature extraction phase, several sets of
samples were collected:
1. One set with statistic values as features—stat,
2. Five sets with histograms for 10, 20, 30, 40 and 50 bins
as features—histbin,
3. 24 sets with DTW distances as features—one for each
signal type—matrixsignal.
All these sets were built separately for all collections of
trials (C2, C3 and C4) described in Sect. 3.2. Each set,
divided into Ntraining and Mtesting samples, was then
evaluated using the cross-validation method (Table 2). It is
very important to emphasize that the division into training
and testing sets was not random. Consecutively collected
trials tend to be more similar to each other than trials
collected after longer intervals; therefore, due to the short-
term learning effect [47], including them in both training
and testing sets may produce improperly obtained better
accuracy results. Hence, the general rule was not to use
trials of the same user gathered in the same session for both
Fig. 3 Diagram of the feature
extraction algorithm based on a
distance matrix
Table 2 Number of training and testing samples for each collection
Collection Samples per
user
Training samples
(N)
Testing samples
(M)
C4 12 216 72
C3 9 168 84
C2 6 96 96
96 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

training and testing purpose. Detailed analysis of this
phenomenon can be found in Sect. 5.2.
Building a rule according to which a fold was related to
one session was a motivating factor. Therefore, collection
C4 was divided into fourfold representing four sessions. As
a result, all samples of one user from the same session were
always in the same fold and were used together as either
training or testing samples. A similar procedure was
applied for C3 and C2 collections, dividing them into three
and twofold, respectively. For such a folding strategy, a
testing set always contained three trials of each user
recorded during the same session (one by one).
A classification model was built based on N training
samples, with usage of an SVM classifier [48]. Using data
of a similar structure utilized in our previous research [49]
and a grid search algorithm, we obtained the best results for
the RBF kernel with gamma ¼29and C¼215. There-
fore, these values were used in the current research. The
sequential minimal optimization algorithm was used [50]
with the multiclass problem solved using pairwise coupling
[51]. The classification model was then used for classifi-
cation of Mtesting samples. For each of them, the classifier
returned a vector of probability values that a given sample
belongs to a particular user. If the number of users is
denoted by U, for every testing sample we obtain a U
element vector representing distribution of probabilities for
each of Upossible classes. A set of such Mvectors (for all
testing samples) forms a matrix of size MU.
Initially, during the testing phase, all trials in a testing set
were classified separately giving independent distributions
for each trial a: Ptriala. These distributions were subse-
quently summed up and normalized for trials related to the
same session (let us recall that there were three trials for one
session). Having probability vectors of three trials (a, b and c)
of the same user gathered during the same session, the
probability vector for the session was calculated as:
Psessionset
i¼ðPtrialset
aþPtrialset
bþPtrialset
cÞ
3ð4Þ
where set represents the set of samples used. Such a
probability vector was the outcome of the method using the
statistic features. However, an additional step was designed
for histbin and matrixsignal types as both corresponding
methods for the feature extraction define more than one set.
The histogram method provided different sets for a par-
ticular number of bins (10, 20, 30, 40 and 50)—altogether
five sets—whereas in the distance matrix approach we
obtained 24 sets, each for one signal. Hence, the result in
these cases was determined as a sum calculated for all bins
or signals sets. The vector of probability distribution, after
the last step, included values as those presented in Eq. 5,
where Xrepresented the number of sets used (a number of
bins or a number of signals, 5 or 24, respectively).
pi¼PX
j¼1Psessionsetj
i
X
ð5Þ
The result of this step was three probability distributions:
•One for statistic values.
•One for histogram values (normalized sum of results
for five histograms).
•One for distance matrix values (normalized sum of
results for matrices built for 24 signals).
These three distributions were then used in the subsequent
evaluation step to check their correctness. It should be
emphasized that in the process of the probability distribu-
tion evaluation, a fusion of features characterizing eye
movement and mouse dynamic was applied.
4.4 Evaluation phase
The last step of the classification process was to assess the
quality of models developed in the previous phases. The
result of the testing phase was probability distributions for
every possible class U (user identity). As was explained in
the previous section, distributions were calculated using
three trials from one session so the number of distributions
was S¼M=3, where Mwas the number of testing trials.
The result was a matrix P:½SU, where each element pi;j
represented the probability that the ith testing sample
belongs to user j.
In the evaluation phase, this matrix was used to calculate
accuracy (ACC), false acceptance rate (FAR) and false
rejection rate (FRR) for different rejection threshold th
values and finally to estimate equal error rate (EER) for
every collection and feature extraction method.
At first, the correctness of the classification c(i) for
every ith distribution on the basis of its correct class u(i)
was calculated as:
cðiÞ¼ 1pi;uðiÞ¼maxðpi;1...pi;uÞ
0 otherwise
(ð6Þ
Then, the accuracy of the classification for the whole
testing set was calculated:
accuracy ¼PS
i¼1cðiÞ
Sð7Þ
The next step was calculation of acceptance ai;jfor dif-
ferent thresholds th. The value of thresholds ranged from 0
to 1.
ai;jðthÞ¼ 1pi;j[th
0 otherwise
(ð8Þ
Based on this acceptance, it was possible to calculate FAR
and FRR for different thresholds.
Pattern Anal Applic (2018) 21:91–103 97
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

FRRðthÞ¼SPS
i¼1ai;uðiÞ
S
ð9Þ
FARðthÞ¼PS
i¼1PU
j¼1;j6¼uðiÞai;j
ðU1ÞSð10Þ
It can be easily predicted that all samples were accepted for
a rejection threshold th = 0; thus, FRR = 0 and FAR = 1.
When increasing the threshold, fewer samples were
accepted, hence FRR increased and FAR decreased. For th
= 1, no samples were accepted, consequently FRR = 1 and
FAR = 0. FAR and FRR dependency on rejection threshold
value is presented in Fig. 4.
Equal error rate (EER) was calculated for the rejection
threshold value for which FAR and FRR were equal (as
visible in Fig. 4).
5 Results
Feature extraction methods used in training and testing
phases and as presented in Sect. 4.2 were independently
evaluated for each collection of trials: C4, C3 and C2. As
was described earlier, they differed in the number of
recorded sessions, which amounted 4, 3 and 2 sessions
accordingly, whereas one session consisted of 3 trials. At
the end of the classification process, two values were
reported for each collection and each type of features (stat,
hist, matrix). These were Accuracy and ERR, calculated
according to methods described in evaluation phase sec-
tion. The results are presented in Table 3.
The best result was obtained for collection C4, when the
matrix type that was based on the fusion of distances of eye
and mouse features was applied. In this case, 4 different
sessions were available for each subject and the classifi-
cation model was trained using three of them each time (12
trials compared to 9 in C3 and 6 in C2). The hist type was
the best option also for collection C3, while the statistic
method gave the lowest errors for C2. However, the results
for collections C3 and C2 were significantly worse. The
ERR value was 31.15 % (C2 collection and a stat set),
which cannot be treated as a good outcome, especially as it
was not significantly better than other ERR values for this
collection. The probable reason of such findings was the
fact that to build a training model for each user, less data
were available (only two and one session accordingly).
The DET curves presenting the dependency of FRR and
FAR ratios are shown in Fig. 5.
5.1 Comparison of mouse and gaze
The next research question was to check whether a fusion
of gaze and mouse biometrics gives results better than a
single modality. For this purpose, two additional experi-
ments for the C4 dataset were performed: one using only
mouse-related signals and one using only gaze-related
signals. Both concerned only the matrix method, which
yielded the best outcomes in the previous tests. Table 4
presents a comparison of these results to the fusion of both
modalities.
The row denoted by ‘‘Gaze’’ corresponds to the effi-
ciency of the algorithm when only 11 signals derived from
eye movement were taken into account. The same regards
the ‘‘Mouse’’ row, which shows results for 11 signals
derived from mouse-related signals. The results presented
in the ‘‘Fusion’’ row are calculated on the basis of all 24
signals (11 mouse ?11 gaze related ?2 based on mouse–
gaze differences). All these outcomes revealed that mouse
dynamics gave better accuracy and lower errors than eye
movements. Most importantly, the fusion of mouse and
gaze gave results significantly better than both modalities
alone.
Fig. 4 Chart showing how FRR and FAR depend on the value of the
rejection threshold
Table 3 Results of identification (Accuracy) and verification (EER)
for different collections and sets
Collection Set Accuracy (%) EER (%)
C2 Stat 25.00 31.15
C2 Hist 21.88 34.78
C2 Matrix 15.62 34.59
C3 Stat 32.14 21.28
C3 Hist 32.14 20.68
C3 Matrix 46.43 16.78
C4 Stat 28.57 20.30
C4 Hist 57.14 10.32
C4 Matrix 92.86 6.82
98 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

5.2 Examining the learning effect
The learning effect is a phenomenon characteristic of
biometric modalities that measures changes of human
behavior over time [47]. It is sometimes treated as a kind of
well-known template aging problem, but its nature is
slightly different. While template aging is related to bio-
metric template changes over a long time (e.g., a face gets
older), the learning effect addresses short time changes in
human behavior. It is obvious that a tired or sad person
reacts differently than a rested and relaxed one. Various
beverages and food such as coffee or alcohol may also
influence people’s behavior. For this reason, it is very
important to register behavioral biometric templates with
some considerable time interval to avoid short-term simi-
larities and extract truly repeatable features. This phe-
nomenon has already been studied for eye movement, and
the results showed that eye movement samples collected at
intervals of less than 10 min are much more similar to each
other than samples collected at 1-week interval [52].
During the tests described in Sect. 4, we tried to avoid
this problem by the appropriate preparation of training and
testing folds of samples. We ensured that during the cross-
validation, samples related to a user’s session were never
split into two folds (see Sect. 4.3) and the time interval
between two sessions of the same user was never shorter
than 1 week. We called this folding strategy ‘‘session-
based folding,’’ as data for the whole session was always in
either a training or testing set.
However, we decided to raise the research question to
check whether mixing samples derived from one session in
training and testing sets did indeed result in better classi-
fication performance. Therefore, the additional cross-vali-
dation experiment was performed with a different fold
preparation strategy. As there were always three trials in
Fig. 5 DET curves for different feature extraction methods and collections C2, C3 and C4, respectively
Table 4 Results achieved for the matrix method for collection C4 for
different subsets of signals
Set Accuracy (%) EER (%)
Fusion 92.86 6.82
Gaze 64.29 16.79
Mouse 78.57 9.05
Pattern Anal Applic (2018) 21:91–103 99
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

each session, this time every set was divided into three
folds: The first trial of the session was in fold 1, the second
attempt in fold 2 and the third one in fold 3. We called this
folding strategy ‘‘mixed sessions folding,’’ as this time
trials from the same session were always divided into
separate folds.
Using such folds for cross-validation ensured that there
was always a sample of the same user from the same
session in both training and testing sets. The classification
results are compared to the previous ones and presented in
Table 5.
As could be expected, the accuracy for modified folds
was higher and errors were lower because it was easier for
the classifier to classify a trial with two other trials from the
same session (i.e., very similar). The errors were lower for
both modalities, but the difference for gaze-based bio-
metrics was more significant. As given in Table 5, accuracy
for the gaze was even better than for the mouse. Accuracy
for the fusion reached 100 % because the correct class had
the highest probability for every sample, but EER was not
0 % because it was not possible to find one threshold that
worked perfectly for every sample distribution. If a
threshold perfectly separated probabilities of genuine and
impostor classes for one sample, the same threshold did not
work perfectly for other samples.
6 Discussion
At the beginning of our research, we raised some research
questions that were answered one by one during consecu-
tive experiments. Our primary objective was to examine
the possibility of fusing eye and mouse characteristics to
define a robust authentication model. Accuracy of 92.86 %
and EER of 6.82 % seem to be very good results compared
to previous studies concerning both modalities indepen-
dently. Other advantage of our approach is the develop-
ment of an identification/verification scenario that is very
convenient for users and—very importantly compared to
other research in this field—it takes on average only 20 s to
collect biometric data. It must be mentioned that some
authors of mouse-related research reported lower error
rates, but these results were achieved for longer mouse
recordings, e.g., 2.46 % EER for 17 min of a signal reg-
istration in [14]. Recordings with comparable time yielded
results worse or comparable to ours, yet usually much more
training data were required. An extended comparison of
our method to others found in the literature is presented in
Table 6.
A similar analysis may be provided that considers the
second modality. The results obtained in our studies for
eye-movement-related biometrics are comparable in
performance to recent achievements. Yet, it is once
again important to emphasize that our experiments
required significantly shorter registration time. Another
advantage of our method is that results were achieved
for a very low frequency of eye movement recordings.
Obviously, a frequency of 30 Hz gives less data for
analysis; however, its advantage is that it can register
eye movements with classic low frequency web cam-
eras, which are built-in components of many computer
systems.
Broader summary of results published since 2012 is
found in Table 7.
On the basis of these comparisons, we may deduce that
our feature extraction method based on the fusion of dis-
tance matrices gives very good results, even when much
less data are available compared to previous research. On
the other hand, fusing eye movement with mouse dynamics
allows for further improvement of the overall results of the
whole biometric system. Deeper analysis of the results
reveals other important findings.
Table 5 Results achieved for the matrix method for collection C4 for
mixed session folding
Set Accuracy (%) EER (%)
Fusion 100 2.94
Gaze 92.86 9.37
Mouse 85.71 5.04
Table 6 Comparison of
outcomes of different mouse-
related research and the results
presented in this paper
References Testing sample duration (s) Equal error rate Training samples duration (s)
Gamboa et al. [13] 50 s (200 s) 2 % (0.2 %) 200 s
Hashiaa et al. [16] 20 s 15–20 % [HTERa] 400 s
Zheng et al. [15] 100 s–37 min 1.3 % 166 min–60 h
Feher et al. [18] 42 s (139 s) 10 % (7.5 %) n/a (15 h per user)
Shen et al. [17] 12 s 8.35 % [HTERa] 885 s
Our result (mouse) 20 s 9.05 % 60 s
Our result (fusion) 20 s 6.82 % 60 s
aHTER—half total error rate—(FAR?FRR)/2 for some threshold
100 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

(1) We discovered that a modality based on mouse
dynamics outperforms one based on eye movement;
yet, more importantly, a fusion of both characteris-
tics gives the best results.
(2) The conducted experiments were based on three
different feature extraction strategies. The distance
matrix-based feature extraction method outperforms
traditional methods based on statistics and his-
tograms with ERR of 6.82, 10.32, 20.30 %,
respectively.
(3) Tests considering several collections with different
numbers of trials, with the best results for those
consisting of 3 training and 1 testing sessions (C4),
showed that slightly increasing the number of
training samples influences performance
significantly.
(4) Last but not least of the findings, related to the
learning effect, confirmed the importance of correct
evaluation phase planning, which is especially
remarkable when cross-validation is used, as an
incorrect and unfair folding strategy may easily lead
to a model overfitting.
7 Summary
The research presented in this paper aimed to find a new
method for behavioral biometrics. The main objective of the
studies was to find a solution characterized with a relatively
short identity verification time and a low level of classifi-
cation errors. The results obtained during experiments con-
firmed that the objective was achieved. The paper showed
that the fusion of the mouse dynamics and eye movement
modalities may be used for this purpose. Furthermore, it
proved that such a fusion may be achieved in one experiment
that is both short and convenient for participants.
The novel feature extraction method, which was based
on fusion of distance matrices, yielded results comparable
or better than those previously published for both single
modalities. The algorithm applied in the method makes it
useful for any kind of modality fusion.
It is also worth mentioning that despite the 6 % error
rate, our method may be used in practical applications as a
part of a verification system. Participants of our experiment
entered a 4-digit PIN by clicking digits in the correct order
with a mouse. Because we were interested in the compar-
ison of eye and mouse movements only, all participants
entered the same PIN (namely the sequence 1–2–6–8).
However, in a real-life environment knowledge of a PIN
could be the first stage of verification. If a participant
entered the proper PIN, our algorithm would be activated
to check whether the participant’s identity claim was
genuine. The proper setting of the rejection threshold could
lower false rejections, as it is unlikely that an impostor
knows the PIN number and has similar mouse and eye
movement dynamics that characterize a genuine user.
To conclude the presented studies, we will summarize
the most important contributions of the paper:
1. The proposed feature extraction method using the
fusion of distance matrices gave results (92.86 %
accuracy and 6.82 % Equal Error Rate) which are
competitive compared to those already published in
this field, while less data were used for both training
and testing phases (about 60 and 20 s, accordingly).
This is the case for both eye movement and mouse
dynamics.
2. The paper showed that the fusion of the mouse
dynamics and eye movement modalities can be done
in one experiment which is both short and convenient
for participants.
3. We showed that the fusion of these two modalities may
lead to better results than for each single modality.
4. It was shown that eye movement data recorded with a
low frequency (30 Hz) may give information sufficient
to achieve equal error rates (16.79 %) comparable to
the state-of-the-art results.
Additionally, it should be noticed that the setup of the
experiment is not complicated and may be reconstructed
Table 7 Comparison of
different gaze-related research
with the results presented in this
paper
References Testing sample duration (s) Equal error rate (%) Recording frequency
Komogortsev et al. [53] 100 s 16 % 1000 Hz
Holland et al. [40] 60 s 16.5 % 1000 Hz
Holland et al. [40] 60 s 25.6 % 75 Hz
Rigas et al. [33] 60 s 12.1 % 1000 Hz
Cantoni et al. [30] 160 s 22.4 % 50 Hz
Tripathi et al [38] 60 s 37 % 1000 Hz
Our result (gaze) 20 s 16.79 % 30 Hz
Our result (fusion) 20 s 6.82 % 30 Hz
Pattern Anal Applic (2018) 21:91–103 101
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

easily. The only hardware requirements are a computer
equipped with a mouse and an eye tracker. The research
described in the paper showed that the frequency of com-
monly used webcams may provide satisfactory results. The
appropriate software (e.g., ITU Gaze Tracker) could be
used in this case. Another affordable solution is a low-cost
remote eye tracer, like that used in the experiments (i.e.,
Eye Tribe).
7.1 Future work
When designing our research, we decided to involve the
fusion technique on the decision level for the distance
matrix method and on the feature level for the statistic one
[3]. The next planned step is to extend all methods to
involve fusion on various levels. For this purpose, various
feature selection methods are also planned to be taken into
consideration.
Additionally, we plan to conduct the same experiments
for more participants. Data were collected for 32 participants
used during the experiment. Such a pool of data seem to be
enough to draw some meaningful conclusions; however, a
much larger pool is necessary to confirm our findings.
Moreover, our experiments showed that a higher number of
training samples guarantees better classification perfor-
mance. Therefore, it may be expected that more than three
training samples (as was for our best collection) should
improve the results. Five to six sessions are planned for each
participant. With more data to analyze, it would be possible
to calculate weights for each of the elements of the fusion.
Weighted fusion would probably give even better results.
Open Access This article is distributed under the terms of the
Creative Commons Attribution 4.0 International License (http://crea
tivecommons.org/licenses/by/4.0/), which permits unrestricted use,
distribution, and reproduction in any medium, provided you give
appropriate credit to the original author(s) and the source, provide a
link to the Creative Commons license, and indicate if changes were
made.
References
1. Porwik P, Doroz R, Wrobel K (2009) A new signature similarity
measure. In: IEEE world congress on nature and biologically
inspired computing, 2009. NaBIC 2009, pp 1022–1027. doi:10.
1109/NABIC.2009.5393858
2. Duin RP, Pekalska E (2012) The dissimilarity space: bridging
structural and statistical pattern recognition. Pattern Recognit Lett
33(7):826–832
3. Ross A, Jain A (2003) Information fusion in biometrics. Pattern
Recognit. lett. 24(13):2115–2125
4. Wang Y, Tan T, Jain AK (2003) Combining face and iris bio-
metrics for identity verification. In: Kittler J, Nixon MS (eds)
Audio-and video-based biometric person authentication.
Springer, Heidelberg, pp 805–813
5. Connaughton R, Bowyer KW, Flynn PJ (2013) Fusion of face and
iris biometrics. In: Handbook of Iris Recognition. Springer,
pp 219–237
6. Conti V, Militello C, Sorbello F, Vitabile S (2010) A frequency-
based approach for features fusion in fingerprint and iris multi-
modal biometric identification systems. Syst Man Cybern Part C
Appl Rev Trans 40(4):384–395
7. Mehrotra H, Rattani A, Gupta P (2006) Fusion of iris and fin-
gerprint biometric for recognition. In: Proceedings of interna-
tional conference on signal and image processing, pp 1–6
8. Marcialis GL, Roli F (2004) Fingerprint verification by fusion of
optical and capacitive sensors. Pattern Recognit Lett
25(11):1315–1322
9. Prabhakar S, Jain AK (2002) Decision-level fusion in fingerprint
verification. Pattern Recognit 35(4):861–874
10. Vatsa M, Singh R, Noore A (2008) Improving iris recognition
performance using segmentation, quality enhancement, match
score fusion, and indexing. Syst Man Cybern Part B Cybern IEEE
Trans 38(4):1021–1035
11. de Oliveira PX, Channarayappa V, ODonnel E, Sinha B,
Vadakkencherry A, Londhe T, Gatkal U, Bakelman N, Monaco
JV, Tappert CC (2013) Mouse movement biometric system. In:
Proceedings of CSIS Research Day
12. Jorgensen Z, Yu T (2011) On mouse dynamics as a behavioral
biometric for authentication In: Proceedings of the 6th ACM
symposium on information, computer and communications
security. ACM, pp 476–482
13. Gamboa H, Fred A (2004) A behavioral biometric system based
on human–computer interaction In: Defense and security. Inter-
national society for optics and photonics, pp 381–392
14. Ahmed AAE, Traore I (2007) A new biometric technology based
on mouse dynamics. Depend Secure Comput IEEE Trans
4(3):165–179
15. Zheng N, Paloski A, Wang H (2011) An efficient user verification
system via mouse movements. In: Proceedings of the 18th ACM
conference on computer and communications security. ACM,
pp 139–150
16. Hashiaa S, Pollettb C, Stampc M, Hall M (2005) On using mouse
movements as a biometric. In: Proceeding of the international
conference on computer science and its applications, vol 1
17. Shen C, Cai Z, Guan X, Du Y, Maxion RA (2013) User
authentication through mouse dynamics. Inf Forens Secur IEEE
Trans 8(1):16–30
18. Feher C, Elovici Y, Moskovitch R, Rokach L, Schclar A (2012)
User identity verification via mouse dynamics. Inf Sci 201:19–36
19. Calix K, Connors M, Levy D, Manzar H, MCabe G, Westcott S
(2008) Stylometry for e-mail author identification and authenti-
cation. In: Proceedings of CSIS research day, Pace University,
pp 1048–1054
20. Bailey KO, Okolica JS, Peterson GL (2014) User identification
and authentication using multimodal behavioral biometrics.
Comput Sec 43:77–89
21. Perakakis M, Potamianos A (2008) Multimodal system evalua-
tion using modality efficiency and synergy metrics. In: Pro-
ceedings of the 10th international conference on multimodal
interfaces. ACM, pp 9–16
22. Asha S, Chellappan C (2008) Authentication of e-learners using
multimodal biometric technology. In: Biometrics and Security
Technologies, ISBAST 2008. International Symposium on IEEE,
vol 2008, pp 1–6
23. Nakkabi Y, Traore
´I, Ahmed AAE (2010) Improving mouse
dynamics biometric performance using variance reduction via
extractors with separate features. Syst Man Cybern Part A Syst
Hum IEEE Trans 40(6):1345–1353
102 Pattern Anal Applic (2018) 21:91–103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

24. Kasprowski P, Ober J (2004) Eye movements in biometrics. In:
International workshop on biometric authentication. Springer,
Heidelberg, pp 248–258
25. Maeder AJ, Fookes CB (2003) A visual attention approach to
personal identification. In: Eighth australian and new zealand
intelligent information systems conference, pp 10–12
26. Komogortsev OV, Jayarathna S, Aragon CR, Mahmoud M (2010)
Biometric identification via an oculomotor plant mathematical
model. In: Proceedings of the 2010 symposium on eye-tracking
research and applications. ACM, pp 57–60
27. Kasprowski P, Komogortsev OV, Karpov A (2012) First eye
movement verification and identification competition at btas
2012. In: biometrics: theory, applications and systems (BTAS),
2012 IEEE fifth international conference on IEEE, pp 195–202
28. Rigas I, Economou G, Fotopoulos S (2012) Biometric identifi-
cation based on the eye movements and graph matching tech-
niques. Pattern Recognit Lett 33(6):786–792
29. Deravi F, Guness SP (2011) Gaze trajectory as a biometric
modality. In: Proceedings of the BIOSIGNALS conference,
Rome, Italy, pp 335–341
30. Cantoni V, Galdi C, Nappi M, Porta M, Riccio D (2015) Gant:
gaze analysis technique for human identification. Pattern
Recognit 48(4):1027–1038
31. Kasprowski P, Harezlak K (2014) The second eye movements
verification and identification competition. In: Biometrics (IJCB),
2014 IEEE international joint conference on IEEE, pp 1–6
32. Kinnunen T, Sedlak F, Bednarik R (2010) Towards task-inde-
pendent person authentication using eye movement signals. In:
Proceedings of the 2010 symposium on eye-tracking research and
applications. ACM, pp 187–190
33. Rigas I, Komogortsev OV (2014) Biometric recognition via
probabilistic spatial projection of eye movement trajectories in
dynamic visual environments. Inf Forensics Sec IEEE Trans
9(10):1743–1754
34. Holland C, Komogortsev OV (2011) Biometric identification via
eye movement scanpaths in reading. In: Biometrics (IJCB), 2011
international joint conference on IEEE, pp 1–8
35. Darwish A, Pasquier M (2013) Biometric identification using the
dynamic features of the eyes. In: Biometrics: theory, applications
and systems (BTAS), 2013 IEEE sixth international conference
on IEEE, pp 1–6
36. Biedert R, Frank M, Martinovic I, Song D (2012) Stimuli for gaze
based intrusion detection. In: Future information technology,
application, and service, ser. Lecture notes in electrical engi-
neering. Springer, the Netherlands, vol. 164, pp 757–763
37. Holland CD, Komogortsev OV (2012) Biometric verification via
complex eye movements: the effects of environment and stimu-
lus. In: Biometrics: theory, applications and systems (BTAS),
2012 IEEE fifth international conference on IEEE, pp 39–46
38. Tripathi B, Srivastava V, Pathak V (2013) Human recognition
based on oculo-motion characteristics. In: AFRICON IEEE 2013,
pp 1–5
39. Zhang Y, Juhola M (2012) On biometric verification of a user by
means of eye movement data mining. In: Proceedings of the 2nd
international conference on advances in information mining and
management
40. Holland CD, Komogortsev OV (2013) Complex eye movement
pattern biometrics: analyzing fixations and saccades. In: Bio-
metrics (ICB), 2013 International conference on IEEE, pp 1–8
41. Cuong NV, Dinh V, Ho LST (2012) Mel-frequency cepstral
coefficients for eye movement identification. In: Tools with
artificial intelligence (ICTAI), 2012 IEEE 24th international
conference on IEEE, vol. 1, pp 253–260
42. Bednarik R, Kinnunen T, Mihaila A, Fra
¨nti P (2005) Eye-
movements as a biometric. In: Image analysis. Springer,
pp 780–789
43. Silver DL, Biggs A (2006) Keystroke and eye-tracking biometrics
for user identification. In: International conference on artificial
intelligence (ICAI), pp 344–348
44. Komogortsev OV, Karpov A, Holland CD, Proenc¸a HP (2012)
Multimodal ocular biometrics approach: a feasibility study. In:
Biometrics: theory, applications and systems (BTAS), 2012 IEEE
fifth international conference on IEEE, pp 209–216
45. Berndt DJ, Clifford J (1994) Using dynamic time warping to find
patterns in time series. In: KDD workshop, vol. 10, no. 16.
Seattle, WA, pp 359–370
46. Keogh EJ, Pazzani MJ (2000) Scaling up dynamic time warping
for data mining applications In: Proceedings of the sixth ACM
SIGKDD international conference on knowledge discovery and
data mining. ACM, pp 285–289
47. Kasprowski P, Rigas I (2013) The influence of dataset quality on
the results of behavioral biometric experiments. In: Biometrics
special interest group (BIOSIG), 2013 international conference of
the IEEE, pp 1–8
48. Hearst MA, Dumais ST, Osman E, Platt J, Scholkopf B (1998)
Support vector machines. Intell Syst Appl IEEE 13(4):18–28
49. Kasprowski P and Harezlak K (2015) Using non-calibrated eye
movement data to enhance human computer interfaces. In:
Intelligent decision technologies. Springer, pp 347–356
50. Platt J et al (1999) Fast training of support vector machines using
sequential minimal optimization. In: Advances kernel methods
support vector learning, vo. 3
51. Hastie T, Tibshirani R et al (1998) Classification by pairwise
coupling. Ann Stat 26(2):451–471
52. Kasprowski P (2013) The impact of temporal proximity between
samples on eye movement biometric identification. In: Computer
information systems and industrial management. Springer,
pp 77–87
53. Komogortsev OV, Karpov A, Price LR, Aragon C (2012) Bio-
metric authentication via oculomotor plant characteristics. In:
Biometrics (ICB), 2012 5th IAPR international conference on
IEEE, pp 413–420
Pattern Anal Applic (2018) 21:91–103 103
123
Content courtesy of Springer Nature, terms of use apply. Rights reserved.

1.
2.
3.
4.
5.
6.
Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers and authorised users (“Users”), for small-
scale personal, non-commercial use provided that all copyright, trade and service marks and other proprietary notices are maintained. By
accessing, sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of use (“Terms”). For these
purposes, Springer Nature considers academic use (by researchers and students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and conditions, a relevant site licence or a personal
subscription. These Terms will prevail over any conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription
(to the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of the Creative Commons license used will
apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may also use these personal data internally within
ResearchGate and Springer Nature and as agreed share it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not
otherwise disclose your personal data outside the ResearchGate or the Springer Nature group of companies unless we have your permission as
detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial use, it is important to note that Users may
not:
use such content for the purpose of providing other users with access on a regular or large scale basis or as a means to circumvent access
control;
use such content where to do so would be considered a criminal or statutory offence in any jurisdiction, or gives rise to civil liability, or is
otherwise unlawful;
falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association unless explicitly agreed to by Springer Nature in
writing;
use bots or other automated methods to access the content or redirect messages
override any security feature or exclusionary protocol; or
share the content in order to create substitute for Springer Nature products or services or a systematic database of Springer Nature journal
content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a product or service that creates revenue,
royalties, rent or income from our content or its inclusion as part of a paid for service or for other commercial gain. Springer Nature journal
content cannot be used for inter-library loans and librarians may not upload Springer Nature journal content on a large scale into their, or any
other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not obligated to publish any information or
content on this website and may remove it or features or functionality at our sole discretion, at any time with or without notice. Springer Nature
may revoke this licence to you at any time and remove access to any copies of the Springer Nature journal content which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or guarantees to Users, either express or implied
with respect to the Springer nature journal content and all parties disclaim and waive any implied warranties or warranties imposed by law,
including merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published by Springer Nature that may be licensed
from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a regular basis or in any other manner not
expressly permitted by these Terms, please contact Springer Nature at
onlineservice@springernature.com