Unsupervised Learning for Mental Stress Detection

Exploration of Self-organizing Maps

Dorien Huysmans

1,3

, Elena Smets

2,3

, Walter De Raedt

, Chris Van Hoof

2,3,4

, Katleen Bogaerts

5,6

Ilse Van Diest

and Denis Helic

KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems,

Signal Processing and Data Analytics, Leuven, Belgium

KU Leuven, Department of Electrical Engineering (ESAT), Leuven, Belgium

imec, Leuven, Belgium

imec, Holst Centre, Eindhoven, The Netherlands

REVAL - Rehabilitation Research Center, Faculty of Medicine and Life Sciences, Hasselt University, Diepenbeek, Belgium

Research Group on Health Psychology, Department of Psychology, KU Leuven, Leuven, Belgium

Knowledge Technologies Institute, Graz University of Technology, Graz, Austria

Keywords:

Mental Stress Detection, Skin Conductance, Electrocardiogram, Unsupervised Learning, SOM.

Abstract:

One of the major challenges in the ﬁeld of ambulant stress detection lies in the model validation. Commonly,

different types of questionnaires are used to record perceived stress levels. These only capture stress levels

at discrete moments in time and are prone to subjective inaccuracies. Although, many studies have already

reported such issues, a solution for these difﬁculties is still lacking. This paper explores the potential of unsu-

pervised learning with Self-Organizing Maps (SOM) for stress detection. In unsupervised learning settings,

the labels from perceived stress levels are not needed anymore. First, a controlled stress experiment was

conducted during which relax and stress phases were alternated. The skin conductance (SC) and electrocar-

diogram (ECG) of test subjects were recorded. Then, the structure of the SOM was built based on a training

set of SC and ECG features. A Gaussian Mixture Model was used to cluster regions of the SOM with similar

characteristics. Finally, by comparison of features values within each cluster, two clusters could be associated

to either relax phases or stress phases. A classiﬁcation performance of 79.0% (±5.16) was reached with a

sensitivity of 75.6% (±11.2). In the future, the goal is to transfer these ﬁrst initial results from a controlled

laboratory setting to an ambulant environment.

1 INTRODUCTION

The concept of stress is difﬁcult to capture because

stress has both psychological as well as physiological

aspects. Moreover, both of these aspects are complex

and are typically caused by multiple factors. The psy-

chological part has been described by multiple mo-

dels such as the Demand-Control Model (Karasek

and Theorell, 1992) and the Effort-Reward Imbalance

Model (Siegrist, 2010). Physiologically, stress can be

described by the activity and balance of the autono-

mic nervous system.

The interest in stress detection shifted from labo-

ratory conditions to ambulatory, enabled by the gro-

wth of wearable sensor technology (Fahrenberg et al.,

2007). Recently, wearables have been slowly introdu-

ced into daily-life studies of stress. This unveiled a

major problem concerning validation. Validating am-

bulant stress detections is not a clearly deﬁned pro-

cess as there is no precise recording of what the par-

ticipant’s activities are. The only apparent way for

validation are different types of questionnaires and di-

aries, ﬁlled in multiple times a day.

Kusserow et al. (2013) monitored the participants

by a diary of daily activities (e.g. working, transport,

conversation) and mood-state questionnaires which

had to be ﬁlled in as soon as possible after perceiving

stress arousal. However, most questionnaires were

completed randomly and could not be related to the

estimated stress-arousal phases.

Adams et al. (2014) performed an Experience

Sampling Method study, enabled by their speciﬁcally

Huysmans, D., Smets, E., Raedt, W., Hoof, C., Bogaerts, K., Diest, I. and Helic, D.

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps.

DOI: 10.5220/0006541100260035

In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 4: BIOSIGNALS, pages 26-35

ISBN: 978-989-758-279-0

designed smartphone app SESAME. Participants re-

ceived approximately every half hour a notiﬁcation to

ﬁll in the self-report and were free to ﬁll in additional

self-reports. In practice, many experience-sampling

responses were delayed due to practical reasons of the

application or occupation of the participants, or parti-

cipants did not respond at all to notiﬁcations. More-

over, periods of time associated with very high levels

of stress were under-reported.

Hovsepian et al. (2015) made an attempt to pro-

vide a gold standard for continuous stress measure-

ments from wearable sensors and presented a stress

model cstress. They prompted participants at random

15 times a day to ﬁll in an Ecological Momentary As-

sessment (EMA). This EMA self-report served as the

ground truth for ﬁeld validation. The cstress model

compensated for the arbitrary lag between the occur-

rence of a stressor and its self-report logging.

Validation of the ambulant data requires a diffe-

rent approach compared to lab studies. Labelling of

the physiological data is often nonexisting or inaccu-

rate . Although many studies have already repor-

ted these issues regarding stress level labelling in an

ambulant environment (Adams et al., 2014; Hovse-

pian et al., 2015), these problems are rarely addressed

in the analyses. This encourages the exploration of

unsupervised stress detection algorithms.

Medina (2009) identiﬁed stress states from ECG

signals using several unsupervised learning methods.

These are clustering algorithms (including K-means

and Spectral Clustering) and clustering ensemble

methods as well as dimensionality reduction techni-

ques (Principal Component Analysis and Forward Se-

quential Search) and evolutionary algorithms.

The study by Grigore and Bornoiu (2014) inves-

tigated stress detection by using electrodermal fea-

tures. Their evaluation method relied on observati-

ons of the SC signal by an expert observer, combined

with questions to the test subjects about their state, to

mark a recorded signal as stress or relax. An unsu-

pervised method was preferred and they proposed to

use a Kohonen Neural Network, also known as Self-

Organizing Map (SOM). Training the SOM was unsu-

pervised, though to point out regions of the SOM re-

lated to stress or relax phases, the authors compared

the neural activation patterns with the signal from the

expert observer. As such, quite elaborate expert infor-

mation was essential for marking of the SOM.

The application of unsupervised techniques are

relatively unexplored within the ﬁeld of mental

stress detection. The SOM in particular has been

successfully applied in many other ﬁelds such as

brain computer interfaces (Han and Kim, 2016) and

geophysics (Aguado et al., 2008; de Matos et al.,

2007; Bauer et al., 2012). In the current research

an algorithmic pipeline is explored based on the

unsupervised learning algorithm SOM. The purpose

is to rule out the use of labels. The pipeline’s input

are heart rate variability (HRV) and skin conduc-

tance response features. These are derived from

lab recorded ECG and SC signals during a series

of stress-inducing tasks. The algorithmic pipeline

only relies on the recorded physiological signals

and no expert observations are required for marking

stress and relax states within the SOM. The ﬁndings

will enhance our understanding of the link between

physiological signals and stressors and may advise

further strategies for stress detection in ambulatory

settings.

2 MATERIALS AND METHODS

2.1 Experimental Setup and Data Set

The goal is to deﬁne a psychophysiological stress

proﬁle of test persons. During laboratory experi-

ments, participants have to complete three different

stress-inducing tasks. During these tasks, the par-

ticipants were monitored with the NeXus-10KMII

(MindMedia, Herten, The Netherlands) and Health

Patch (imec, Leuven, Belgium) to measure skin con-

ductance (SC) and the electrocardiogram (ECG).

2.1.1 Test Subjects

The data set consisted of a group of 12 test subjects

(age 37.3 ±8.8). Within this group, there were ﬁve

male participants and seven female participants, re-

cruited at Tumi Therapeutics, a multidisciplinary am-

bulatory treatment center specialized in the treatment

of stress-related symptoms and syndromes. They

all reported stress-related complaints, suffering from

chronic stress, but were not diagnosed with any clini-

cal disorder (e.g. depression or burnout). This asses-

sment was performed by a therapist. One test subject

was not included for further analysis as the data re-

corded by Health Patch was too noisy.

2.1.2 Experimental Protocol

The laboratory experiment lasted for 14 minutes and

was set up as seen in Figure 1. The subjects had to

complete three stress tasks of two minutes. All three

tests are commonly used to induce stress in laboratory

settings (Liao and Carey, 2015). The tasks were each

separated by a two minutes resting phase. Before the

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps

Figure 1: Experimental protocol.

ﬁrst task a two minutes baseline was recorded. The

ﬁrst stress task was the Stroop Color Word Test (Van

der Elst et al., 2006), words of colours were written

in a different colour as the colour the word represent,

e.g. the word blue is printed in red ink. The test sub-

ject had to say the colour of the ink as correct and

as fast as possible. The challenge is to suppress the

instinctive response of saying the colour the word re-

presents. The correct answer is red in this example.

This is a commonly used stress task. Additional stress

could be added when the test supervisor urges the test

subject to be faster or to say wrong when a mistake

has been made.

The second test was a calculation test in which the

participant continuously had to subtract the number

7 from the number 1081. In the same manner as the

Stroop test, additional stress could be added by the

test supervisor.

The ﬁnal stress task was a stress talk, the partici-

pant had to talk about a very stressful or emotionally

negative event in his life and to recall his feelings re-

lated to this event. The test supervisor could ask que-

stions such as How did you feel?.

2.1.3 Sensors and Signals

Two sensors were applied: the NeXus-10MKII and

the Health Patch. The NeXus-10MKII (Mind Media

BV, Herten, The Netherlands), referred to as Nexus, is

not a wearable sensor, though highly accurate. There-

fore this sensor could serve as a gold standard to com-

pare measurements of other sensors. The following

signals were measured: blood volume pulse (BVP)

and skin conductance. BVP was sampled at 128Hz

and SC at 32Hz. The Health Patch is a wearable mo-

nitoring system developed by imec. The sensor is a

patch consisting of a sensor node and an electronic

module to record the electrocardiogram (ECG). Sam-

pling frequency was 256Hz.

Based on BVP of Nexus and the extracted heart

rate from the Health Patch signal, both sensors were

visually synchronised in time. The signals of 4 test

subjects could not be synchronised, as the Health Pa-

tch data lacked quality. Therefore the data set consis-

ted of 7 test subjects.

The BVP signal of Nexus was not further proces-

sed as more detailed HRV information can be extrac-

ted from the ECG signal.

2.2 Self-organizing Map

SOMs represent higher-dimensional data as a glo-

bally ordered two-dimensional map. The SOM can

be seen as an elastic grid of nodes ﬁtted to the input

signal space, while preserving the topological re-

lationships of the signal space (Kohonen et al., 2001) .

Here, the input signal space is an n-dimensional

feature space. Every node i is associated with a

weight vector w

= [µ

, µ

, ..., µ

]

∈ R

. The input

feature vector is x

stim

= [ξ

, ξ

, ..., ξ

]

∈R

(Arnrich

et al., 2010). The feature vector x

stim

is mapped to the

best-matching node c by comparing it with all weight

vectors w

. As a metric of similarity, the smallest Eu-

clidean distance is searched:

c = argmin

||x

stim

−w

||. (1)

During training, topological relationships of the input

feature space are projected onto the two-dimensional

SOM by adapting the weight vectors w

. Nodes that

are topographically close to the best-maching node c

are also activated to learn from the same input x

stim

This results in a smoothing effect on the weight vec-

tors of nodes in the neighbourhood and eventually le-

ads to global ordering of the map. Input vectors are

presented to the map in a random order. Given x

stim

time t, the update of the weight vector w

of node i is

as follows:

(t + 1) = w

(t) + h

(t)[x

stim

(t) −w

(t)]. (2)

The initial values of the w

(0) can be arbitrary.

BIOSIGNALS 2018 - 11th International Conference on Bio-inspired Systems and Signal Processing

Table 1: Feature set.

Physiological signal Feature Description

SC SC PH signal power in a phasic SC signal

SC SC RR SC responses rate

SC SC DIFF2 signal power in second difference from SC signal

SC SC MAG sum of the magnitudes of SC responses

SC SC DUR sum of the duration of SC responses

SC Slope slope of the regression line of the signal

SC PH %50 percentile 50 of peak height

SC PH %85 percentile 85 of peak height

ECG mean HR mean heart rate

ECG SDNN standard deviation of all normal RR intervals

(i.e. NN intervals)

ECG RMSSD root-mean-square successive difference

of all normal RR intervals

ECG LF HRV low frequency HRV (power in the 0.04-0.15 Hz band)

ECG HF HRV high frequency HRV (power in the 0.15-0.4 Hz band)

ECG LFHF HRV ratio (LF HRV) / ( HF HRV )

The neighbourhood function h

(t) can be deﬁned

in terms of the Gaussian function:

(t) = α(t) ·exp



−

||r

−r

2σ

(t)



, (3)

with 0 < α(t) < 1 the learning-rate factor and σ

the width of the kernel, both decreasing monotoni-

cally in time. r

∈ R

and r

∈ R

are the location

vectors in the SOM of nodes c and i, and with increa-

sing ||r

−r

||, h

→ 0.

After training, a test set can be mapped onto the

SOM to determine its set of best-matching nodes.

2.3 Training of SOM

The ﬁrst stage was mapping the higher-dimensional

feature space onto a two-dimensional grid, while pre-

serving the topological relationships within the data.

Measurement data was mapped by the SOM algo-

rithm to different areas on this grid. Component pla-

nes visualised the relationship between variables.

The SOM was trained using SC and ECG fea-

tures. In total 14 features were derived from SC

and ECG signals (Table 1) of the laboratory data-

set. This is a set of frequently applied features for

stress analysis found in literature. The studies of Bou-

csein (2012), Kappeler-Setz et al. (2010) and Wijs-

man et al. (2011) focus on SC analysis. Other re-

search focuses on stress reactions using HRV: Vrij-

kotte et al. (2000), Hjortskov et al. (2004), Melillo

et al. (2011) and Taelman et al. (2009). Additionally,

several studies apply a combination of physiological

signals (Zhai et al., 2005; Healey and Picard, 2005).

The calculation of features was performed with a win-

dow size of 50s and a step size of 20s. These parame-

ters were found to be optimal for performance after

cross validation. Additionally, features were normali-

sed within every test subject by Z-score standardiza-

tion to account for inter-subject variation.

The topology of the SOM lattice was chosen ac-

cording to Vesanto and Alhoniemi (2000) and Aguado

et al. (2008). The number of nodes M was heuristi-

cally determined as M = 5

√

N with N the number of

samples in the data set. The aspect ratio of the lattice

is the square root of the ratio of the two largest eigen-

values of the data set. As the average training data set

during cross validation consisted of 267 feature vec-

tors, the SOM topology contained 80 nodes [10 × 8].

Training of the SOM was performed by the SOM

functions of the PyMVPA package for multivariate

pattern analysis in Python (Hanke et al., 2008). The

learning rate α in Eq. 3 was by default set to 0.05.

The maximum number of iterations was set to 400,

at which the SOM should be converged. The nodes of

the SOM are settled at a location in feature space. The

value of each feature at every node can be visualised

as component planes. The advantage is that relations-

hips between features can be interpreted graphically.

2.4 Analysis of Trained SOM

The second stage consisted of exploring the patterns

emerged in the SOM during training. These patterns

were outlined by clustering. Every node of the SOM

was assigned to a cluster by the clustering method

Gaussian Mixture Models. The implementation was

based on the scikit-learn package of Gaussian Mixture

Models (Pedregosa et al., 2011). The main interest

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps

was ﬁnding a stress and a relax cluster. Therefore, the

number of components was set to two.

To determine the feasibility of the algorithmic pi-

peline for stress detection, it was validated by a leave-

one-participant-out (LOO) cross validation scheme.

This means the dataset was split in n folds, with n

being the number of participants. One fold contains

the data of one test person. With each iteration, the

SOM was trained by n-1 folds, leaving out the data

of one test person. The resulting trained SOM and its

clustering will differ slightly with every iteration.

The quality of the different clusters can be expres-

sed in terms of cohesion and separation of the clus-

ters. These factors are merged in the silhouette coefﬁ-

cient (Pedregosa et al., 2011; Rousseeuw, 1987). The

advantage of this performance characteristic is that it

does not rely on labels. The silhouette coefﬁcient s of

sample i is deﬁned as:

s(i) =

b(i) −a(i)

max(a, b)

, (4)

with a the mean intra-cluster distance and b the mean

distance to all samples of the nearest cluster. As only

two clusters are considered, b is simply the other clus-

ter than to which i is assigned to. The range of the

silhouette coefﬁcient is between -1 and 1. If s(i) ap-

proaches 1, it implies that a(i)  b(i) and the mean

intra-cluster distance is much smaller than the mean

distance to samples of the other cluster. Therefore,

sample i is well-clustered and assigned to the right

cluster. When s(i) is about zero, the sample i lies

equally far from both clusters and it is not clearly de-

ﬁned which is the right cluster. If s(i) is close to −1,

a(i)  b(i), this means that the sample is misclassi-

ﬁed. The ﬁnal silhouette score of the LOO cross vali-

dation is the average of n testing procedures.

To further analyse the clusters, the statistics of the

clusters were derived. Feature values of all nodes

within one cluster were gathered and represented in

a boxplot.

Additionally, labels were introduced exclusively

for performance calculations. Thereby, the procedure

presented in this paper can be compared to other su-

pervised methods. During the stress experiment, two

possible phases are alternated, a relax phase and a

stress phase. We assume that the stress tasks effecti-

vely induced stress as has been shown in earlier re-

search (Smets et al., 2016). The references therefore,

do not rely on subjectively reported stress levels. In

order to classify unseen data in these two phases, the

training data is split and labelled as data recorded du-

ring relax (label 0) or stress (label 1) phase. The la-

tency of stress onset after the start of a stress-inducing

task or the fading of a stress response after ending the

task are not taken into account. The classiﬁcation per-

formance is the average of sensitivity and speciﬁcity.

The ﬁnal classiﬁcation performance of the LOO cross

validation is the average of n testing procedures.

3 RESULTS AND DISCUSSION

3.1 SOM Structure

Component planes present graphically the value of

each feature at every node after training. For illus-

trative purpose, the SOM was trained by the whole

data set instead of partially by n −1 folds. The corre-

sponding components planes are depicted in Figure 2.

Colour bars next to every component indicate the va-

lue at the node, for which red means high and blue

low values.

Variables with similar colours in corresponding

regions are positively correlated. These correlations

are conﬁrmed in the correlation matrix (Figure 3). It

can be seen that components SCPh, SCRR, SCmag,

SCdur, PH %50, PH %85 and mean heart rate exhi-

bit low values at the lower central region of the SOM.

The upper left and right corners are dominated by

high values. These characteristics are related to an

elevated level of sympathetic activity of the autono-

mous nervous system (McCorry, 2007; Task Force of

the European Society of Cardiology the North Ame-

rican Society of Pacing Electrophysiology, 1996).

SCdiff2 and slope show correlation as well, for which

SCdiff2 contains more extreme positive values. This

is explained by the fact that slope is based on the ﬁrst

derivative of the SC signal and SCdiff2 on the second

derivative. Only the strongest variation in signal is re-

tained. Mean heart rate and RMSSD appear strongly

negatively correlated. Mathematically, these features

are calculated with a similar formula. Moreover, lite-

rature conﬁrms that an increase in heart rate and a lo-

wer vagal tone (RMSSD) are signs of stress (Vrijkotte

et al., 2000). LFHF has a positive correlation with

mean HR as seen centrally in the component plane,

with reduced values and in the upper left corner for

increased values. Furthermore, HF exhibits large re-

gions with a value below its average, especially in the

corners where other features have increased values.

The study of Hjortskov et al. (2004) conﬁrms these

observations as they found a reduction in the high-

frequency component of HRV and an increase in low-

to-high frequency ratio during a stress situation. Ad-

ditionally, a stable low-frequency component was re-

ported, which is not clear from the component plane

in this paper.

BIOSIGNALS 2018 - 11th International Conference on Bio-inspired Systems and Signal Processing

Figure 2: Component planes of trained SOM. Training was performed with whole data set for illustrative purpose.

Figure 3: Correlation values between variables.

3.2 Clusters

The outcome of clustering of the SOM trained on the

whole data set can be seen in Figure 4. A clear corre-

lation can be seen between the clusters and the com-

ponent planes of the SOM. The center of the SOM is

a cluster coloured in blue, which corresponds to re-

gions with low feature values observed in the com-

ponent planes. The second cluster is the surrounding

area, coloured in red. This corresponds to the com-

ponents planes of SCPh, SCRR and mean HR. This

visual observation is a ﬁrst quality check of the re-

sulting clusters.

The silhouette coefﬁcient after ten runs of LOO

validation was 0.301 (±0.0152). The standard de-

viation indicates that all silhouette coefﬁcients were

approximately equivalent. This outcome is accepta-

ble as it is sufﬁciently larger than zero, meaning most

samples were assigned to the right cluster.

Figure 4: Clustering of trained SOM.

3.3 Cluster Identiﬁcation

Boxplots of both clusters over different training folds

were compared. It was seen that these clusters do

not capture random patterns every training fold, yet

exhibit repeating patterns. This indicates that clusters

have similar characteristics.

Furthermore, as the training of the SOM was

unsupervised, it was not known to which state a clus-

ter belongs, stress or relax. From literature (Boucsein,

2012; Kappeler-Setz et al., 2010; Vrijkotte et al.,

2000; Hjortskov et al., 2004) it is known that during

stress both SCph values and mean HR are high. This

prior knowledge was applied onto the ﬁrst training

fold. The boxplots of leaving out test subject 1 were

taken as a reference and classiﬁed. Interestingly, the

pattern of all boxplot values corresponded to charac-

teristics that can be assigned to either stress or relax.

Cluster A was characterised by boxplots with nega-

tive feature averages, while these in cluster B were

positive or close to zero. Therefore cluster A could be

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps

associated to relax and cluster B to stress.

Cluster boxplots of other iterations were compa-

red to these classiﬁed boxplots. To determine cor-

responding boxplots, the Root Mean Squared Error

(RMSE) between the average of boxplots was compa-

red. Corresponding boxplots have a minimum RMSE

between them. Subsequently, corresponding boxplots

deﬁne corresponding states (stress or relax) of the

clusters. The results are depicted in Figure 5, 6, 7,

and 8, for SC features in cluster relax and stress and

for ECG features in cluster relax and stress respecti-

vely. Iteration 1 to 4 are depicted, while omitting ite-

ration 5 to 7 for improved readability of the ﬁgure.

It can be clearly observed that similar boxplot pat-

terns exist between training iterations. Boxplots of a

particular feature are within the same range over dif-

ferent training iterations. Moreover, within every trai-

ning iteration (compare Figure 5 with Figure 6 and

Figure 7 with Figure 8), it can be seen that the feature

values are low, i.e. under the zero mean, within the

relax cluster, and high, i.e. higher than the zero mean,

within the stress cluster. Exceptions are RMSSD and

HF, as expected from literature. The decrease of

HF in stress situations is less explicit compared to

RMSSD. These results were consistent with literature

and observations made for the component planes.

3.4 Performance

Test data points were mapped to the SOM to deter-

mine their best-matching nodes and predict the state

of stress or relax. The points were assigned to a state

corresponding to the cluster the node belongs too.

The clustering of the trained SOM with mapped test

data and their actual labels is depicted in Figure 9.

Label 1 corresponds to stress, label 0 to relax.

After ten runs of LOO validation, the average tes-

ting performance is 79.0% (±5.16). The testing per-

formance is the average of sensitivity and speciﬁ-

city. The sensitivity, indicating the ability to recog-

nize stress phases, has a value 75.6% (±11.2).

Grigore and Bornoiu (2014) applied SOM as well

for stress detection, using similar SC features and re-

ported an average recognition rate of 86.25%. Diffe-

rent was the their labelling system for validation of

their outcomes. An expert observer evaluated the SC

signal in combination with participant questionnaires

to manually label the input signal. Recognition rates

will be higher as labelling of the data is based on a

priori evaluation of the physiological signals. Furt-

hermore, it is not clear how their average recognition

rate is computed. Moreover, their number of partici-

pants is not reported for comparison.

Smets et al. (2016) had a similar experimental se-

tup and reported a maximum performance rate for

non-personalized models of 82.7% using SVM. Simi-

lar features for ECG and SC were applied, with ad-

ditional temperature and respiration features. This is

comparable to the performance in this paper. As unsu-

pervised techniques are generally harder to apply, the

potential of SOM for stress detection exists.

4 FUTURE WORK

This paper only covers data derived from laboratory

experiments, however the SOM technique has been

introduced to tackle problems in modelling and vali-

dation of ambulant data. Therefore, it would be of

great interest to apply this algorithmic pipeline onto

ambulant data and to further determine its feasibility.

Several papers apply an intermediate step between

training and clustering the SOM, namely the crea-

tion of a U-matrix followed by Kmeans clustering

(Aguado et al., 2008) or a gradient function of the

SOM followed by the watershed segmentation algo-

rithm (Bauer et al., 2012). The U-matrix or gra-

dient function displays the distance between neigbou-

ring nodes and allows visual delineation of the clus-

ters. The subsequent clustering or segmentation step

would only be performed in a two-dimensional space.

The approach with building a U-matrix has been per-

formed, though no clear conclusions could be drawn

from visual inspection of the U-matrix. Most proba-

bly the border between the stress and relax cluster

cannot be clearly drawn here. One of the reasons is

that physiological responses of the stress tests slowly

vanish into periods deﬁned as relax. Future models

would beneﬁt from taking into account response and

recovery periods.

Advances can be made in more detailed evalua-

tion of the clustering step. Other parameters or other

cluster algorithms could be explored to better sepa-

rate stress from relax clusters. An interesting aspect

would be to add more clusters to capture stress levels

directly from the SOM or determine the conﬁdence of

a predicted stress level. A ﬁrst step would be to add

a third cluster outlining intermediate values and focus

on the extreme values of stress and relax.

A limitation of the study was the size of the data

set which was rather small. For the current research,

this was not a major problem as it focussed on the

exploration of the algorithmic pipeline. For future va-

lidation, larger data sets are required.

BIOSIGNALS 2018 - 11th International Conference on Bio-inspired Systems and Signal Processing

Figure 5: Boxplots of SC feature values in cluster relax, with number referring to the training iteration.

Figure 6: Boxplots of SC feature values in cluster stress, with number referring to the training iteration.

Figure 7: Boxplots of ECG feature values in cluster relax, with number referring to the training iteration.

Figure 8: Boxplots of ECG feature values in cluster stress, with number referring to the training iteration.

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps

Figure 9: Clustered SOM with labels of projected testing

data. Red cluster indicates a region classiﬁed as stress and

blue for relax. Labels 1 indicate stress data points and labels

0 relax data points.

It is suggested to validate the developed model

of unsupervised learning with Self-Organizing Maps

against the ﬁeld-data and ﬁeld self-reports of ambu-

latory models such as the cStress model (Hovsepian

et al., 2015). This model aims to provide a gold

standard for continuous stress assessment of ambulant

data. Validation against this data set would contribute

to building a gold standard as more methods can be

compared in the future.

5 CONCLUSIONS

An unsupervised algorithmic pipeline based on SOM

and clustering has been introduced to explore the fe-

asibility of SOM for unsupervised stress detection. It

was tested on laboratory data. After ten runs of LOO

validation, the testing performance is 79.0% (±5.16).

As this was comparable to the performance of a su-

pervised algorithm on a very similar test setup, the

technique based on SOM is considered to be suitable

for mental stress detection. Future research should

investigate if the results obtained here in a controlled

laboratory setting can be transferred to an ambulant

environment.

ACKNOWLEDGEMENTS

We thank the therapists of Tumi Therapeutics for their

help in patient recruitment and data collection. The

authors report no conﬂict of interest with the cur-

rent manuscript. The research was partly funded by

a Ph.D. grant of the Flanders Innovation & Entrepre-

neurship agency (VLAIO) and by imec funds 2017.

REFERENCES

Adams, P., Rabbi, M., Rahman, T., Matthews, M., Voida,

A., Gay, G., Choudhury, T., and Voida, S. (2014). To-

wards personal stress informatics: Comparing mini-

mally invasive techniques for measuring daily stress

in the wild. In Proceedings of the 8th International

Conference on Pervasive Computing Technologies for

Healthcare, PervasiveHealth ’14, pages 72–79. ICST

(Institute for Computer Sciences, Social-Informatics

and Telecommunications Engineering).

Aguado, D., Montoya, T., Borras, L., Seco, A., and Ferrer,

J. (2008). Using som and pca for analysing and inter-

preting data from a p-removal sbr. Engineering Appli-

cations of Artiﬁcial Intelligence, 21(6):919 – 930.

Arnrich, B., Kappeler-Setz, C., La Marca, R., Tr

oster, G.,

and Ehlert, U. (2010). Self organizing maps for af-

fective state detection. In Machine Learning for As-

sistive Technologies.

Bauer, K., Muoz, G., and Moeck, I. (2012). Pattern re-

cognition and lithological interpretation of colloca-

ted seismic and magnetotelluric models using self-

organizing maps. Geophysical Journal International,

189(2):984–998.

Boucsein, W. (2012). Electrodermal Activity. Springer.

de Matos, M. C., Osorio, P. L. M., and Johann, P. R. S.

(2007). Unsupervised seismic facies analysis using

wavelet transform and self-organizing maps. Geophy-

sics, 72(1):9–21.

Fahrenberg, J., Myrtek, M., Related, K. P., and Perrez, M.

(2007). Ambulatory assessment - monitoring behavior

in daily life settings. European Journal of Psycholo-

gical Assessment, 23(4):206–213.

Grigore, O. and Bornoiu, I.-V. (2014). Kohonen neural net-

work stress detection using only electrodermal acti-

vity features. Advances in Electrical and Computer

Engineering, 14(3):71–78.

Han, J.-S. and Kim, G.-J. (2016). A method of unsuper-

vised machine learning based on self-organizing map

for bci. Cluster Computing, 19(2):979–985.

Hanke, M., Halchenko, Y. O., Sederberg, P. B., J.Hanson,

S., Haxby, J. V., and Pollmann, S. (2008). Pymvpa: A

python toolbox for machine-learning based data ana-

lysis. In annual meeting of the Society for Neuros-

cience.

Healey, J. A. and Picard, R. W. (2005). Detecting stress du-

ring real-world driving tasks using physiological sen-

sors. IEEE Transactions on Intelligent Transportation

Systems, 6:156 – 166.

Hjortskov, N., Riss

en, D., Blangsted, A. K., Fallentin, N.,

Lundberg, U., and Søgaard, K. (2004). The effect of

mental stress on heart rate variability and blood pres-

sure during computer work. European Journal of Ap-

plied Physiology, 92(1):84–89.

Hovsepian, K., al’Absi, M., Ertin, E., Kamarck, T., Naka-

jima, M., and Kumar, S. (2015). cstress: Towards a

gold standard for continuous stress assessment in the

mobile environment. In Proceedings of the 2015 ACM

International Joint Conference on Pervasive and Ubi-

BIOSIGNALS 2018 - 11th International Conference on Bio-inspired Systems and Signal Processing

quitous Computing, UbiComp ’15, pages 493–504,

New York, NY, USA. ACM.

Kappeler-Setz, C., Arnrich, B., Schumm, J., La Marca, R.,

oster, G., and Ehlert, U. (2010). Discriminating

stress from cognitive load using a wearable eda de-

vice. IEEE Transactions on Information Technology

in Biomedicine, 14(2):410–417.

Karasek, R. and Theorell, T. (1992). Healthy Work: Stress,

Productivity, and the Reconstruction of Working Life.

Basic Books.

Kohonen, T., Schroeder, M. R., and Huang, T. S. (2001).

Self-Organizing Maps. Springer-Verlag New York,

Inc, 3rd edition.

Kusserow, M., Amft, O., and Tr

oster, G. (2013). Monitoring

stress arousal in the wild. IEEE Pervasive Computing

Magazine, 12(2):28–37.

Liao, L. and Carey, M. (2015). Laboratory-induced men-

tal stress, cardiovascular response and psychological

characteristics. Reviews in Cardiovascular Medicine,

16(1):28–35.

McCorry, L. K. (2007). Physiology of the autonomic ner-

vous system. American Journal of Pharmaceutical

Education, 71.

Medina, L. (2009). Identiﬁcation of stress states from ecg

signals using unsupervised learning methods. In Por-

tuguese Conf. on Pattern Recognition - RecPad.

Melillo, P., Bracale, M., and Pecchia, L. (2011). Nonli-

near heart rate variability features for real-life stress

detection. case study: students under stress due to

university examination. BioMedical Engineering On-

Line, 10(1):96.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V.,

Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P.,

Weiss, R., Dubourg, V., Vanderplas, J., Passos, A.,

Cournapeau, D., Brucher, M., Perrot, M., and Du-

chesnay, E. (2011). Scikit-learn: Machine learning

in Python. Journal of Machine Learning Research,

12:2825–2830.

Rousseeuw, P. (1987). Silhouettes: A graphical aid to the in-

terpretation and validation of cluster analysis. J. Com-

put. Appl. Math., 20(1):53–65.

Siegrist, J. (2010). Effort-reward imbalance at work and

cardiovascular diseases. International Journal of

Occupational Medicine and Environmental Health,

23(3):279–285.

Smets, E., Casale, P., Großekath

ofer, U., Lamichhane,

B., De Raedt, W., Bogaerts, K., Van Diest, I., and

Van Hoof, C. (2016). Comparison of Machine Le-

arning Techniques for Psychophysiological Stress De-

tection, pages 13–22. Springer International Publis-

hing.

Taelman, J., Vandeput, S., Spaepen, A., and Van Huffel, S.

(2009). Inﬂuence of Mental Stress on Heart Rate and

Heart Rate Variability, pages 1366–1369. Springer

Berlin Heidelberg, Berlin, Heidelberg.

Task Force of the European Society of Cardiology the

North American Society of Pacing Electrophysiology

(1996). Heart rate variability standards of measure-

ment, physiological interpretation, and clinical use.

Van der Elst, W., Van Boxtel, M., Van Breukelen, G., and

Jolles, J. (2006). The stroop color-word test. Asses-

sment, 13(1):62–79. PMID: 16443719.

Vesanto, J. and Alhoniemi, E. (2000). Clustering of the self-

organizing map. IEEE Transactions on neural net-

works, 11(3):586–600.

Vrijkotte, T., Van Doornen, L., and De Geus, E. (2000). Ef-

fects of work stress on ambulatory blood pressure, he-

art rate, and heart rate variability. Hypertension, page

886.

Wijsman, J., Grundlehner, B., Liu, H., Hermens, H., and

Penders, J. (2011). Towards mental stress detection

using wearable physiological sensors. In 33rd An-

nual International Conference of the IEEE Engineer-

ing in Medicine and Biology Society, EMBC 2011, pa-

ges 1798–1801. IEEE Engineering in Medicine & Bi-

ology Society.

Zhai, J., Barreto, A., and Chin, C. (2005). Realization

of stress detection using psychophysiological signals

for improvement of human-computer interactions. In

Proceedings. IEEE SoutheastCon, 2005., pages 415–

420.

Unsupervised Learning for Mental Stress Detection - Exploration of Self-organizing Maps