Feature and Sensor Selection for Detection of Driver Stress
Simon Ollander
1
, Christelle Godin
1
, Sylvie Charbonnier
2
and Aur´elie Campagne
3
1
CEA, LETI, MINATEC Campus, F-38054 Grenoble, France
Univ. Grenoble Alpes, F-38000 Grenoble, France
2
Gipsa-Lab, Univ. Grenoble Alpes & CNRS, F-38402 Grenoble, France
3
LPNC, Univ. Grenoble Alpes, CNRS, F-38040 Grenoble, France
Keywords:
Stress, Features, Classification, Feature Selection, Sensor Selection, Driver Stress, Naive Bayes.
Abstract:
This study presents a real-life application-based feature and sensor relevance analysis for detecting stress in
drivers. Using the MIT Database for Stress Recognition in Automobile Drivers, the relevance of various
physiological sensor signals and features for distinguishing the driver’s state have been analyzed. Features
related to heart rate, skin conductivity, electromuscular activity, and respiration have been compared using
filter and wrapper selection methods. For distinguishing rest from activity, relevant sensors have been found
to be heart rate, skin conductivity, and respiration (giving up to 94.6± 1.9 % accuracy). For distinguishing
low stress from high stress, relevant sensors have been found to be heart rate and respiration (giving up to
78.1±4.1 % accuracy). In both cases, a multi-user model that requires only a calibration from the user in rest,
without prior knowledge of the user’s individual stress dynamics, resulted in a different optimal sensor and
feature configuration, giving 87.3±2.8 % and 72.1±4.3 % accuracy respectively.
1 INTRODUCTION
Driving a vehicle is a part of many people’s daily life,
which can generate a variety of stressful situations.
Examples are social stress from other nearby drivers
and time pressure due to the necessity of taking quick
driving decisions. Too great driver stress levels might
encourage aggressive driving, such as road rage (Hen-
nessy and Wiesenthal, 1999), exposing the driver and
other traffic for risk of physical harm. A part of the
solution to this problem is to automatically detect the
mental state of the driver using non-invasive sensors.
Depending on the driver’s stress state, the car could
automatically adapt e.g. the user interface and the
music, and advice the driver differently (Hernandez
et al., 2014).
Common physiological signals for detecting
driver stress include electrodermal activity (EDA),
electrocardiogram (ECG), electromuscular activity
(EMG), and respiration (Resp) (Rigas et al., 2012),
(Healey and Picard, 2000). Other examples are video
recordings tracking facial expressions (Gao et al.,
2014), speech (Boˇril et al., 2009), the CAN bus of
the vehicle (Boˇril et al., 2009), (Rigas et al., 2012),
and GPS information (Rigas et al., 2012). A review
of several studies on driver stress, comparing systems
and signals for monitoring can be found in (Singh and
Queyam, 2013). Examples of other sensors and sig-
nals that have been tried for stress detection are skin
temperature, eye tracking and pupil diameter (Palinko
et al., 2010), and behavioural measures such as ges-
tures and accelerometer data.
In this study, the signals of the MIT Stress Recog-
nition in Automobile Drivers Database (Healey and
Picard, 2008) have been analyzed to determine which
ones best distinguish the mental state of the driver in
rest versus driving, and highway versus city driving.
(Healey and Picard, 2005), (Akbas, 2011), (Queyam,
2013), and (Yong Deng, 2013) analyzed the same
database and reached up to 94.7 % of correct clas-
sification for different configurations.
We emphasize on the design of an automatic state
detector using physiological sensors. We consider
two classification problems: distinguishing rest from
activity, and low stress from higher stress. Calibra-
tion is a critical point when developing such a sys-
tem. Most of the previous studies consider samples
from all drivers in both the training and the valida-
tion steps. This supposes a use case where data from
a period when the subject is resting and from when
the subject is stressed is available, letting the model
adapt to individual stress dynamics by training a dif-
Ollander, S., Godin, C., Charbonnier, S. and Campagne, A.
Feature and Sensor Selection for Detection of Driver Stress.
DOI: 10.5220/0005973901150122
In Proceedings of the 3rd International Conference on Physiological Computing Systems (PhyCS 2016), pages 115-122
ISBN: 978-989-758-197-7
Copyright
c
2016 by SCITEPRESS Science and Technology Publications, Lda. All rights reserved
115
ferent model for each person (single-user). This cal-
ibration allows for high precision, however it is very
constraining, which makes it less useful for real-life
applications. In a final application it could also re-
quire embedding the training part of a machine learn-
ing algorithm. For these reasons, we also consider a
more realistic calibration case: multi-user. This case
creates one universal model, which would only re-
quire calibration from a resting period (for removing
individual baselines). This is more feasible in a real-
life situation, but it demands a more general model
than the single-user case.
Within this scope, we focus on selecting the set of
sensors and signal features that most accurately pre-
dicts driver stress. Firstly, the data is presented in Sec-
tion 2. Secondly, the classification problem is defined
in Section 3. Thirdly, all the features and their phys-
iological meaning are explained Section 4. Subse-
quently, Section 5 gives an overview of all the feature
selection methods used in this study. Finally, Sec-
tion 6 presents and discusses the results, while Sec-
tion 7 concludes this work.
2 THE DRIVE DATABASE
The MIT Stress Recognition in Automobile Drivers
Database (Healey and Picard, 2008) consists of phys-
iological data originating from drivers in the state of
rest, highway driving, or city driving. It contains a to-
tal of 16 data sets (drives), where 7 signals have been
recorded: ECG at 496 Hz, HR at 15.5 Hz, EMG at
15.5 Hz (placed at the left shoulder), SC at 31 Hz
(placed at left foot and hand), and respiration at 31
Hz. Additionally, there is a marker signal, which indi-
cates the phase of the experiment. Due to various ac-
quisition problems being present in some of the data
sets, only 9 of the drives were analyzed in this study.
3 CLASSIFICATION PROBLEM
The marker signal was used to separate the six phases
of the experimental phase, specified in Table 1. Fig-
ure 1 gives an example of the signals, for the Drive
15 data set. The start of the six phases are identi-
fied by a red vertical line. In this study, the phases
were grouped in two different ways. The first one,
rest vs. driving (RvsD) uses the data from the initial
rest to define the class “rest” (R), and the data from
all city and highway phases to define the class “drive”
(D). This corresponds to distinguishing a person that
is resting from when the person is doing an activity.
The second way of grouping the phases is highway vs.
Table 1: The six phases of each drive, their abbreviation and
their mean durations with standard deviation.
Phase Abbr. Duration µ ± σ
Initial rest R
1
15 m 7 s ± 21 s
City drive 1 C
1
14 m 59 s ± 2 m 5 s
Highway drive 1 H
1
7 m 59 s ± 1 m 14 s
City drive 2 C
2
6 m 50 s ± 1 m 47 s
Highway drive 2 H
2
7 m 17 s ± 28 s
City drive 3 C
3
11 m 23 s ± 3 m 0 s
city (HvsC). In this case, the first class consists of all
highway drives, and is called “highway” (H), while
the class “city” (C) consists of all city drives. The
idea of distinguishing between these states is based
upon the assumption that people find it more stressful
to drive in a city environment than on the highway.
This was confirmed by the questionnaires in (Healey
and Picard, 2005, p. 159).
4 FEATURES
The mean HR, along with HRV features measure the
variations of the inter-beat intervals (IBI) of an ECG,
and are known as relevant stress indicators (Sun et al.,
2010, p. 3). Activation of the sympathetic nervous
system ensures a more regular heart beat, which is
why features such as the root mean square (RMS) of
the difference between successive IBI are expected
to decrease in stressful situations. Similarly, HRV
power spectrum features are relevant, especially the
low frequency component, regulated by both the sym-
pathetic and parasympathetic nervous system, and the
high frequency component, regulated by the parasym-
pathetic nervous system. Their ratio is used as an in-
dex of the balance between the two nervous systems,
and is expected to decrease with increasing stress.
Another widely used measure in stress detection is
the electrodermal activity, which can be recorded us-
ing electrodes that measure the skin conductivity (SC)
or the skin resistance between so called active sites
on the inner surface of the hands or the feet. In this
work, the skin conductivity will be used. The SC is
purely regulated by the sympathetic nervous system,
and manifests itself by an increase in skin conduc-
tance level in stressful conditions, with rapidly rising
peaks that slowly return to base level (Kappeler-Setz
et al., 2010). Thus for detecting stress, features such
as the mean SC and features for distinguishing the
rising and falling parts of the signals (e.g. the mean
of the absolute derivative and proportions of positive
samples in derivative) can be used.
Furthermore EMG activity, e.g. in the trapezoid
muscle (Lundberg et al., 1994) are known to increase
PhyCS 2016 - 3rd International Conference on Physiological Computing Systems
116
500 1000 1500 2000 2500 3000 3500
-1
0
1
ECG [mV]
Drive 15 preprocessed
R1 C1 H1 C2 H2 C3
500 1000 1500 2000 2500 3000 3500
50
100
HR [bpm]
500 1000 1500 2000 2500 3000 3500
4
6
8
10
12
14
SC [µ S]
foot
hand
500 1000 1500 2000 2500 3000 3500
-20
0
20
EMG [mV]
500 1000 1500 2000 2500 3000 3500
time [s]
40
60
RESP [mV]
Figure 1: All physiological signals from Drive 15, preprocessed for artifact removal and split into 6 phases according to the
marker signal.
with stress, correspondingto muscle tension. This can
be observed by an increase in the signal energy.
A final physiological signal for detection of stress
is the respiration, usually measured by a band that
records chest expansion. This signal is highly cou-
pled with HR by respiratory sinus arrhythmia, which
decreases the HR while exhaling. The respiration
signal can thus be used to remove respiratory influ-
ence on the ECG signal, allowing for more relevant
HRV analysis in stress detection (Choi and Gutierrez-
Osuna, 2010). The same applies for the SC sig-
nal, which increases while breathing out (Cacioppo
et al., 2007, p. 239), making the respiration signal
useful combined with electrodermal activity (Bouc-
sein, 2012). Examples of respiration signal features
for stress detection include ones related to breath size
and its variability (e.g. the mean and standard devia-
tion of the signal), and energy in different frequency
bands (Yong Deng, 2013). Another example is the
respiration rate (Wijsman et al., 2011).
4.1 Feature Calculation
Firstly, all signals were visually inspected for arti-
facts, e.g. unreasonably high heart rates (above 220
bpm) or sensor contact problems. Secondly, the pre-
processed signals of each class were split into non-
overlapping time-windows of 60 seconds, each with
a label Y = 1 or Y = 1 depending on the class of
the time-window. For the RvsD classes, the number
of samples n
s
in each drive varied between 14 and 16
for class R and 37 n
s
52 for class D. Similarly,
for the HvsC classes, 13 n
s
17 in class H and
22 n
s
36 in class C. This means that the classes
were imbalanced, which will be dealt with further on.
The 14 selected features are specified in Table 2. The
SC features originated from the hand electrodes; the
foot SC signal was excluded due to it representing the
same measure as the SC hand signal, which gives un-
wanted side effects on wrapper feature selection algo-
rithms.
4.2 Normalization
To compensate for inter-individual differences (e.g.
different resting heart rates), the initial rest period R
1
was used for normalizing each feature F to F
n
accord-
ing to
F
n
=
F µ
R
n
σ
f
, (1)
where σ
f
represents the standard deviation of the fea-
ture across all users and periods and µ
R
n
represents
the mean of the feature during the last two time-
windows of the initial rest period. Only the last two
Feature and Sensor Selection for Detection of Driver Stress
117
Table 2: The features and their descriptions.
Feature Description
Signal: HR [bpm]
µ
HR
mean heart rate
RMS
IBIdif f
root mean square of successive
differences of inter-beat inter-
vals
LF
HR
sum of energy in low frequency
(LF) band (0.04 – 0.15 Hz)
HF
HR
sum of energy in high fre-
quency (HF) band (0.15 0.50
Hz)
LFHF
HR
ratio between energies in LF
and HF bands
Signal: SC [mV] (foot and hand)
µ
SC
mean skin conductance level
µ
SC
+ mean of positive derivative
µ
|SC
|
mean of absolute derivative
+/SC
proportion of positive samples
in derivative
max
SC
number of local maxima
Signal: EMG [mV]
RMS
EMG
root mean square of EMG
Signal: Resp [mV]
(max µ)
Resp
maximal respiration mean of
respiration (range)
F
Resp
respiration rate
σ
Resp
standard deviation of the respi-
ration
time-windows were used since R
1
is also a class in
the RvsD case. These two time-windows were sub-
sequently deleted from the RvsD R class, to prevent
their influence on the classifier accuracy. This means
that after normalization, in the RvsD case class R
contained 12 n
s
14. The reason for dividing by
the standard deviation across all features is to avoid
bias of choosing features with great variance without
involving any subject-specific data that could poten-
tially lead to overlearning.
5 METHOD
Having defined a set of features, it is important to
choose an optimal subset among them by different
feature selection methods. This serves two purposes:
training the most generalizable and accurate model,
and getting a better understanding of the relationship
between the physiological signals and the stress state
of the subject. This subset (the feature space), needs
to contain enough features to distinguish the classes,
but limiting its size is important to avoid overfitting.
This can be done by univariate (filter) methods, that
consider the features one by one, or by multivariate
(wrapper) methods, that try different combinations of
the features with the help of a classifier. The chosen
methods are presented in Sections 5.2 and 5.3. For all
feature selection methods, we define X as the features
and Y as the labels.
5.1 Use Cases
By combining the two calibration methods described
in Section 1 with the two previously explained class
definitions (RvsD and HvsC), we obtain four use
cases:
1. Rest versus driving, single-user
2. Rest versus driving, multi-user
3. Highway versus city, single-user
4. Highway versus city, multi-user
These four use cases were analyzed and compared, in
order to provide a basis for an optimal feature and sen-
sor choice for each of them. All the following meth-
ods have been applied to every use case.
5.2 Filter Feature Selection
This section presents all the filter feature selection
methods used in this work. Their common element
is that they test features individually, to get an idea
of their predictive power of stress levels one by one
(although some versions exist that are capable of an-
alyzing feature combinations). For all filter methods,
the single-user case means calculating the coefficients
for each drive, then averaging across all drives. The
multi-user case means putting the data from all drives
together in a large vector, then calculating the coeffi-
cients.
Pearson’s linear correlation coefficient r (Duda
et al., 2000, p. 614) is a simple tool for studying the
relevance of features. This can give a preliminary in-
dication of the importance of a feature, but one must
keep in mind that it only analyzes linear correlations.
Spearman’s rank correlation ρ (Spearman,
1904) measures the statistical dependence between
two variables by testing how well they can be re-
lated by a monotonic function. This has the advan-
tage of being capable of detecting non-linear depen-
dencies, as opposed to Pearsons linear correlation.
Kendall’s rank correlation coefficient (Kendall and
Gibbons, 1990) was also tested, with identical results.
The Fisher score F
s
(Arunasakthi et al., 2014) was
PhyCS 2016 - 3rd International Conference on Physiological Computing Systems
118
calculated for each feature. It is given by
F
s
=
(µ
(Y=1)
µ
(Y=1)
)
2
q
σ
2
(Y=1)
+ σ
2
(Y=1)
, (2)
where µ and σ correspond to the mean and the stan-
dard deviation of the feature over each class, re-
spectively. Features having means that differ greatly
across classes with low standard deviation will have
high Fisher scores.
A widely used tool in classification problems is
the receiver operating characteristic (ROC) (Han-
ley and Mcneil, 1982), which compares the number of
correctly predicted positive samples among all posi-
tive samples (true positive rate, TPR), versus the num-
ber of falsely predicted positive samples among all
positive samples (false positive rate, FPR). A ROC
curve can be obtained by letting a feature predict the
label when varying its threshold, followed by plotting
FPR against TPR for each threshold. A feature with
high predictive power will then maintain a high TPR
with a low FPR. The area under the ROC curve (AUC)
will thus increase, which is why it is an interesting
analysis for feature selection. The numerical integra-
tion of the area under the curve was calculated by the
trapezoid method.
5.3 Wrapper Feature Selection
Individually useless features can have a great pre-
dictive power when combined with other features in
classification algorithms. Furthermore, a safe way of
knowing that the feature subset is good, is letting the
classifier itself choose it. Wrapper feature selection
methods solve this problem by choosing feature com-
binations based upon their classification performance.
This has of course the disadvantage of introducing
a bias from the choice of classifier and its parame-
ters, as well as increasing the risk of overlearning the
model by adapting it too much to the data. For the
wrapper feature selection, in the single-user case a 5-
fold crossvalidation was performed, combined with
bootstrap aggregating (Duda et al., 2000, p. 474) re-
peated 100 times (to reduce the variance in perfor-
mance between the random crossvalidation subsets).
In the multi-user case, leave-one-drive-out cross val-
idation was used, by excluding one entire drive of
one participant, and learning with the remaining ones.
This gives the basis for a stress model that is generic
(capable of classifying the state of new drivers that
have not been used for training it). In multi-user, be-
fore the learning step, the minority class data was uni-
formly oversampled to achieve class balance, discour-
aging the model from always predicting only the ma-
jority class. Oversampling could not be done in the
single-user validation since both classes are not guar-
anteed to be represented in every bootstrap configura-
tion.
5.3.1 The Naive Bayes Classifier
In this study, we use the naive Bayes (NB) classi-
fier, a simple probabilistic classifier (Hastie et al.,
2009, p. 210-211). Based upon the feature vector
X = X
1
,.. .,X
n
f
(containing n
f
features), it calculates
the posterior probability P(Y
c
|X) of X belonging to
class Y
c
(among a total of n
c
classes) using Bayes’
theorem:
P(Y
c
|X) =
P(Y
c
)P(X|Y
c
)
P(X)
. (3)
The prior probability P(Y
c
) is simply the frequency
of class Y
c
. The evidence P(X) is the frequency of
the feature, which is irrelevant for the classification
problem. The NB classifier assumes conditional in-
dependence of all features X in class c, i.e. that no
correlations exist between them. The likelihood P(X)
can thus be written as
P(X|Y
c
) =
n
f
f=1
P(X
f
|Y
c
). (4)
Assuming a normal distribution of the data (Gaussian
naive Bayes), the learning step consists of calculating
the mean µ
f,c
and the standard deviation σ
f,c
of each
feature f over each class c. The likelihood of a new
observation X belonging to class Y
c
is then given by
P(X
f
|Y
c
) =
1
q
2πσ
2
f,c
e
(X
f
µ
f,c
)
2
2σ
2
f,c
. (5)
The class of X is finally predicted as the one with the
highest posterior probability:
ˆ
Y = argmax
Y
c
P(Y
c
|X). (6)
The motivebehind choosing the naive Bayes classifier
is that it is parameterless (unlike e.g. support vector
machines (SVM), (Hastie et al., 2009, p. 417-419)).
An SVM requires choosing an appropriate kernel and
tuning a parameter, which will not necessarily be the
same for all our use cases.
5.3.2 Performance Measure
To measure the classifier performance, we define the
balanced accuracy
a
b
=
TPR+ TNR
2
, (7)
Feature and Sensor Selection for Detection of Driver Stress
119
TNR being the true negative rate, the amount of cor-
rectly predicted negatives among all negative sam-
ples. The balanced accuracy punishes misclassifica-
tion of minority class samples more heavily, compen-
sating for the fact that the classes are not represented
by the same number of samples. Upon a
b
, the margin
of error at 95 % is defined:
m = 1.96
s
a
b
(1 a
b
)
n
s
, (8)
where n
s
represents the total number of samples used
in the cross-validated prediction.
5.3.3 Exhaustive Feature Selection
The absolutely safest way of choosing an optimal fea-
ture space is to test the classification performance
of all possible subsets, i.e. exhaustive feature selec-
tion. This quickly becomes very computationally ex-
pensive. To reduce this problem, an exhaustive fea-
ture selection was performed within the features of
each sensor, giving an optimal subset of features from
every sensor signal. To decide whether adding an
additional feature gave a significant improvement or
not, Student’s paired t-test (Kreyszig, 1970, p. 206)
was performed on all cross-validated performances,
with a significativity threshold set at 0.05. Similarly,
Student’s paired t-test was performed to decide if
each performance was significantly greater than pure
guessing (a
b
= 50 %), denoted t
50
, also with a signi-
ficativity threshold set at 0.05.
5.3.4 Sensor Selection
When an optimal subset for each individual sensor
had been defined, the respective subsets were com-
bined. This resulted in six sensor pairs, four sensor
triples and finally one combination where all four sen-
sors were represented. The combination with the best
classification performance was then chosen for each
use case. t
50
was also calculated for each sensor com-
bination, to determine if its performance was superior
to random guessing.
6 RESULTS AND DISCUSSION
The results of the previously mentioned feature se-
lection methods are presented and discussed in this
section. Table 3 summarizes the best 5 features ac-
cording to the filter feature selection methods. For
each method and use case, the features have been
given a rank (descending order through the 14 tested
features), depending on their filter feature selection
score. The mean of all ranksµ
rank
has then been calcu-
lated, to give a notion of the combined score for each
feature across all the methods. Table 4 presents the
optimal combination of features extracted from each
sensor (exhaustively selected). The “Sensors” row
then specifies the optimal sensor combination. Re-
sults upon validation data are presented for each op-
timal feature combination, using the balanced accu-
racy a
b
. Across the two tables, seven features are fre-
quently represented: max
SC
, µ
HR
, µ
SC
, µ
|SC
|
, +/SC
,
(maxµ)
Resp
, and σ
Resp
. To a lesser extent, five other
features can also be found: RMS
EMG
, F
Resp
, µ
SC
+ ,
LF
HR
, and HF
HR
. In terms of sensor choice, the HR
sensor is consistently chosen across all cases, often
with support of SC and/or respiration respiration mea-
sures. The EMG sensor is chosen only in one of the
cases. As in (Akbas, 2011) and (Queyam, 2013), the
mean heart rate and the mean SC level prove them-
selves relevant. Like in (Healey and Picard, 2005)
and (Yong Deng, 2013), µ
SC
is among the top choices.
σ
Resp
is not present in previous studies on the same
database, which primarily favor the respiration rate.
Concerning the classification performances, RvsD
is a quite easy task, even in multi-user. Using only
the respiration signal, reasonable accuracy is reached.
HvsC is naturally more difficult, reaching significant
accuracy in the single-user case, while the multi-user
case is just slightly above random guessing for some
sensors. Compared to previous studies (e.g. 94.7 % in
(Healey and Picard, 2005)), the classification perfor-
mances are quite low, at least for the HvsC. However
in terms of calibration, cross-validation method and
signal segmentation with respect to the experimental
phases, this study corresponds to a more realistic ap-
plication.
To further validate the results, the same study with
other classifier algorithms should be done. No com-
plete exhaustive feature selection is performed, since
this is firstly done within each sensor. This means that
not all feature combinations are considered, and fea-
ture combinations that might improve accuracy could
be excluded. It would however be extremely time-
consuming to try all feature combinations, which is
why we perform a subselection within each sensor
firstly. Furthermore, when selecting sensors it is im-
portant to point out that an EMG sensor is compli-
cated to equip and can be quite invasive, which is also
true for the respiration sensor to a certain extent. It is
mainly the HR and SC signals that can be acquired by
simple wearable sensors with the current technology,
which is important to point out when selecting them.
PhyCS 2016 - 3rd International Conference on Physiological Computing Systems
120
Table 3: Top 5 ranked features for each use case, according
to the filter methods.
Feature r ρ F
s
AUC µ
rank
Rest vs. driving, single-user
µ
SC
2 2 2 1 1.75
+/SC
3 3 3 2 2.75
max
SC
1 1 1 11 3.5
µ
|SC
|
5 4 6 3 4.5
µ
HR
4 6 4 6 5
Rest vs. driving, multi-user
max
SC
1 1 1 1 1
µ
SC
3 2 3 2 2.5
+/SC
2 3 2 3 2.5
µ
HR
4 5 4 5 4.5
µ
|SC
|
5 4 5 4 4.5
Highway vs. city, single-user
max
SC
1 2 1 2 1.5
σ
Resp
2 1 3 1 1.75
µ
SC
3 4 2 3 3
µ
|SC
|
5 3 5 4 4.25
+/SC
4 6 4 6 5
Highway vs. city, multi-user
max
SC
1 2 1 2 1.5
σ
Resp
2 1 3 1 1.75
µ
|SC
|
4 3 4 3 3.5
+/SC
3 5 2 5 3.75
(max µ)
Resp
5 4 5 4 4.5
7 CONCLUSIONS
In terms of classification, learning one model per user
yields better accuracy than creating a universal multi-
user model. Moreover, classifying rest from activity
is easier than classifying a less stressful task from a
more stressful one. Independentlyof the classification
problem (rest from activity or low stress from high
stress) and independently of the calibration method,
seven features have been found to be robust across
both filter and wrapper methods: max
SC
, µ
HR
, µ
SC
,
µ
|SC
|
, +/SC
, (maxµ)
Resp
, and σ
Resp
. The filter fea-
ture selection used in this study has given a good pre-
liminary idea of the usefulness of each feature, but to
deal with feature combinations wrapper methods are
necessary.
A problem with the MIT Stress Recognition in
Automobile Drivers Database is that it consists solely
of one type of stress. For a robust real-time algorithm
to work in daily life, one needs to identify stress char-
acteristics from several different stress types. This is
the purpose of an experimental database currently in
development, where laboratory stressors correspond-
Table 4: Exhaustive feature selection and sensor selection
results.
Signal Optimal content a
b
± m [%] t
50
Rest vs. driving, single-user
HR µ
HR
, LF
HR
,
HF
HR
82.3 ± 3.3 1
SC µ
SC
, µ
SC
+ ,
+/SC
93.2 ± 2.2 1
EMG RMS
EMG
87.5 ± 2.8 1
Resp (max µ)
Resp
,
F
Resp
, σ
Resp
89.3 ± 2.7 1
Sensors HR + SC 94.6 ± 1.9 1
Rest vs. driving, multi-user
HR µ
HR
76.0 ± 3.6 1
SC max
SC
83.6 ± 3.2 1
EMG RMS
EMG
66.6 ± 4.0 1
Resp (max µ)
Resp
,
F
Resp
, σ
Resp
85.3 ± 3.0 1
Sensors HR + SC + Resp 87.3 ± 2.8 1
Highway vs. city, single-user
HR µ
HR
, LF
HR
64.8 ± 4.7 1
SC µ
SC
, µ
SC
+ , µ
|SC
|
,
max
SC
74.9± 4.3 1
EMG RMS
EMG
59.4 ± 4.8 1
Resp (max µ)
Resp
,
F
Resp
, σ
Resp
71.2 ± 4.4 1
Sensors HR + SC + Resp 78.1 ± 4.1 1
Highway vs. city, multi-user
HR µ
HR
60.1 ± 4.7 1
SC µ
SC
, µ
|SC
|
,
max
SC
65.0 ± 4.6 1
EMG RMS
EMG
57.7 ± 4.7 1
Resp (max µ)
Resp
,
F
Resp
, σ
Resp
71.8 ± 4.3 1
Sensors HR + EMG +
Resp
72.1 ± 4.3 1
ing to different stress types are applied to subjects
equipped with a similar sensor configuration. Addi-
tionally, an experiment is planned where the subjects
are equipped with wearable sensors every day for a
week, allowing an analysis of physiological reactions
to daily events, including transport and driving. Fu-
ture work includes acquiring and analyzing this data,
for further validation of the most relevant sensors and
features in stress detection.
ACKNOWLEDGEMENTS
This project has received funding from the European
Union’s Horizon 2020 research and innovation pro-
gramme under grant agreement No 635867.
Feature and Sensor Selection for Detection of Driver Stress
121
REFERENCES
Akbas, A. (2011). Evaluation of the Physiological Data In-
dicating the Dynamic Stress Level of Drivers. Scien-
tific Research and Essays, 6(2):430 – 439.
Arunasakthi, K., KamatchiPriya, L., and Askerunisa, A.
(2014). Fisher Score Dimensionality Reduction
for Svm Classification. In International Confer-
ence on Innovations in Engineering and Technology
(ICIET14), pages 1900–1904. International Journal
of Innovative Research in Science, Engineering and
Technology.
Boucsein, W. (2012). Electrodermal Activity. The Springer
series in behavioral psychophysiology and medicine.
Springer US.
Boˇril, H., Boyraz, P., and Hansen, J. H. (2009). Towards
Multi-Modal Drivers Stress Detection. In 4th Biennial
Workshop on DSP for In-Vehicle Systems and Safety,
Dallas, TX, USA.
Cacioppo, J. T., Tassinary, L. G., and Berntson, G., editors
(2007). Handbook of Psychophysiology. Cambridge
University Press, third edition. Cambridge Books On-
line.
Choi, J. and Gutierrez-Osuna, R. (2010). Estimating Mental
Stress Using a Wearable Cardio-respiratory Sensor. In
Proceedings of IEEE Sensors, pages 150–154. IEEE.
Duda, R. O., Hart, P. E., and Stork, D. G. (2000). Pattern
Classification. Wiley-Interscience, second edition.
Gao, H., Yuce, A., and Thiran, J.-P. (2014). Detecting
Emotional Stress from Facial Expressions for Driv-
ing Safety. In Image Processing (ICIP), 2014 IEEE
International Conference on, pages 5961–5965.
Hanley, J. A. and Mcneil, B. J. (1982). The Meaning and
Use of the Area Under a Receiver Operating Charac-
teristic (ROC) Curve. Radiology, 143:29–36.
Hastie, T., Tibshirani, R., and Friedman, J. (2009). The El-
ements of Statistical Learning. Springer, second edi-
tion.
Healey, J. and Picard, R. (2000). SmartCar: Detecting
Driver Stress. In Pattern Recognition, 2000. Proceed-
ings. 15th International Conference on, volume 4,
pages 218–221.
Healey, J. and Picard, R. W. (2008). Stress Recogni-
tion in Automobile Drivers (drivedb). Available at
http://physionet.org/cgi-bin/atm/ATM.
Healey, J. A. and Picard, R. W. (2005). Detecting Stress
During Real-World Driving Tasks Using Physiologi-
cal Sensors. Intelligent Transportation Systems, IEEE
Transactions on, 6(2):156–166.
Hennessy, D. A. and Wiesenthal, D. L. (1999). Traffic Con-
gestion, Driver Stress, and Driver Aggression. Ag-
gressive Behavior, 25(6):409–423.
Hernandez, J., McDuff, D., Benavides, X., Amores, J.,
Maes, P., and Picard, R. (2014). AutoEmotive: Bring-
ing Empathy to the Driving Experience to Manage
Stress. In Proceedings of the 2014 Companion Pub-
lication on Designing Interactive Systems, DIS Com-
panion ’14, pages 53–56, New York, NY, USA. ACM.
Kappeler-Setz, C., Arnrich, B., Schumm, J., La Marca, R.,
Tr¨oster, G., and Ehlert, U. (2010). Discriminating
Stress From Cognitive Load Using a Wearable EDA
Device. IEEE Transactions on Information Technol-
ogy in Biomedicine, 14(2):410–417.
Kendall, M. and Gibbons, J. (1990). Rank Correlation
Methods. A Charles Griffin Book. E. Arnold.
Kreyszig, E. (1970). Introductory Mathematical Statistics:
Principles and Methods. Wiley.
Lundberg, U., Kadefors, R., Melin, B., Palmerud, G.,
Hassm´en, P., Engstr¨om, M., and Elfsberg Dohns, I.
(1994). Psychophysiological Stress and EMG Activ-
ity of the Trapezius Muscle. International Journal of
Behavioral Medicine, 1(4):354–370.
Palinko, O., Kun, A. L., Shyrokov, A., and Heeman, P.
(2010). Estimating Cognitive Load Using Remote Eye
Tracking in a Driving Simulator. In Proceedings of the
2010 Symposium on Eye-Tracking Research &
Applications, ETRA ’10, pages 141–144, New York,
NY, USA. ACM.
Queyam, A. B. (2013). A Novel Method of Stress Detec-
tion using Physiological Measurements of Automo-
bile Drivers. Master’s thesis, Thapar University.
Rigas, G., Goletsis, Y., and Fotiadis, D. (2012). Real-Time
Driver’s Stress Event Detection. Intelligent Trans-
portation Systems, IEEE Transactions on, 13(1):221–
234.
Singh, M. and Queyam, A. B. (2013). Stress Detection in
Automobile Drivers using Physiological Parameters:
A Review. International Journal of Engineering Edu-
cation, 5(2):1 –5.
Spearman, C. (1904). The Proof and Measurement of As-
sociation Between Two Things. American Journal of
Psychology, 15:88–103.
Sun, F., Kuo, C., Cheng, H., Buthpitiya, S., Collins, P., and
Griss, M. L. (2010). Activity-Aware Mental Stress
Detection Using Physiological Sensors. In Mobile
Computing, Applications, and Services - Second In-
ternational ICST Conference, MobiCASE 2010, Santa
Clara, CA, USA, October 25-28, 2010, Revised Se-
lected Papers, pages 211–230.
Wijsman, J., Grundlehner, B., Liu, H., Hermens, H., and
Penders, J. (2011). Towards Mental Stress Detec-
tion Using Wearable Physiological Sensors. In Engi-
neering in Medicine and Biology Society,EMBC, 2011
Annual International Conference of the IEEE, pages
1798–1801.
Yong Deng, Zhonghai Wu, C.-H. C. Q. Z. D. F. H. (2013).
Sensor Feature Selection and Combination for Stress
Identification Using Combinatorial Fusion. Interna-
tional Journal of Advanced Robotic Systems, 10.
PhyCS 2016 - 3rd International Conference on Physiological Computing Systems
122