Review: Use of EEG on Measuring Stress Levels When Painting and
Nataliya Tupikina, Gcinizwe Dlamini
and Giancarlo Succi
Innopolis University, Russian Federation
Electroencephalography, Software Development, Stress, Painting.
For years, brain activity, stress level during programming and painting have been analyzed separately. As the
world gets more digital and human life gets more dependent on technology, it has become more important
to analyse the relationship between programming, software developers’ brain activity, creative practices (i.e
painting) and stress level. In this paper, we present the results of a systematic literature review whereby the
research questions are centred around analysing the relationship between stress levels and brain activity when
a person is painting or writing a piece of software. The search for relevant studies was done on google scholar
and IEEE Xplore. The results of our review show that: (1) EEG can be used to accurately measure stress
levels, (2) there is limited research in the analysis of stress level pattern of the stress level when people paint
depending on different situations and styles of painting. In light of the systematic literature review result,
using EEG we plan to conduct experiments to measure the stress level when a person is painting a picture or
In the era where technology has become the main in-
strument for a human being to accomplish daily tasks,
the demand for high-quality software is increasing
from day to day. The increase in high-quality soft-
ware has induced demand for software developers to
produce creative software in a limited time. Conse-
quently, this results in increased stress levels for pro-
grammers. The impact of certain stress levels can lead
to increased performance and productivity. However,
excessive stress levels can result in deterioration of
abilities (Hassan et al., 2006). Certain levels of stress
can impair technical skills, creativity skills, as well as
memory, concentration and other cognitive processes
(Hassan et al., 2006; Klein, 1996).
Stress is usually described as the condition when
threatened homeostasis happens in the body, followed
by the responses of two types: physiological as well
as behavioural (Chrousos, 1998). After the brain no-
tices the ’threat’, the hypothalamus, along with the pi-
tuitary gland, and also adrenal glands make the whole
body react by producing hormones and other things.
Centuries ago, by ’threat’ people usually meant
wild animals, feuding tribes. But today, when most
people work in safe conditions and can get food with-
out hunting by visiting the local shop, stress did not
disappear. Scientists analyse stress levels and emo-
tional well-being across many fields, involving the
Information Technology field, as many programmers
face burnout (Hetland et al., 2007). In our research,
we are curious to find out the impact of certain stress
levels on software quality and how it relates to creativ-
ity. In addition, we are aimed at analysing the brain
waves patterns when developing creative software.
Painting is one of many forms of art which evokes
creativity. Some do it for living, some do it for fun,
some do not do it at all. While painting can be taught
and the skill can be improved, in theory, almost any-
one can draw at least something. In another form of
art, such as playing music, it is hard to repeat a fa-
miliar melody without knowing the notes and how to
play correctly. However, with painting nearly anyone
can try to reproduce a picture that they see or some-
thing that they imagine. On the other hand, a person
can imagine and draw something that never existed
instead of reproducing a thing they have already seen.
This kind of creativity is to be adopted in software
development in order to produce useful technology.
Compared to painting, programming requires
some skill level to start writing. At least the knowl-
Tupikina, N., Dlamini, G. and Succi, G.
Review: Use of EEG on Measuring Stress Levels When Painting and Programming.
DOI: 10.5220/0011101200003179
In Proceedings of the 24th International Conference on Enterprise Information Systems (ICEIS 2022) - Volume 2, pages 374-380
ISBN: 978-989-758-569-2; ISSN: 2184-4992
2022 by SCITEPRESS Science and Technology Publications, Lda. All rights reserved
edge of the structure of some programming language
is required, and even the clear code may work incor-
rectly, possibly attributing to the stress level. Pro-
gramming still involves creativity as the program-
mer needs to plan everything ahead, creating a pro-
gram that was never done before. Painting would be
a suitable activity to be compared to programming,
since it also introduces some level of creativity, in-
stead of some monotonous routine. The questions be-
hind this research are : what exactly affects program-
mers’ stress levels? Could the programming itself
reduce or increase a person’s stress level? How can
we adopt some practices from painting and mimic the
state of mind observed during painting to produce cre-
ative software? To answer the aforementioned ques-
tions we decided to conduct a systematic literature re-
view whereby we defined our research questions as
RQ1. Can stress level be accurately measured using
an EEG device?
RQ2. What is the pattern of the stress level when peo-
ple paint depending on different situations and
styles of painting?
RQ3. Does the stress level of programmers somehow
follow some specific pattern during code writ-
RQ4. Can we draw a comparison between specific
situations or activities that are done while pro-
gramming and done while painting according
to the pattern of the level of stress?
The rest of this paper is organized as follows: Sec-
tion 2 presents background information on EEG to-
gether with related works. Section 3 outlines our
approach in answering the aforementioned research
questions (RQ1., RQ2., RQ3. and RQ4.). Section 4
and 5 presents the results together with the results dis-
cussions. Threats to validity are presented in section
6. Section 7 draws the conclusions and introduces fu-
ture work.
This section presents background on brain waves,
electroencephalography (EEG) analysis techniques
and studies related to stress measurement using EEG.
It can be skipped by readers already familiar with the
2.1 Brain Waves
Electroencephalography is a an approach for measur-
ing brain activity using electrodes attached to a scalp.
The brain activity is measured from from the elec-
tric signals produced by the firing of neurons in the
brain. The electrodes attached to the scalp capture os-
cillations at a range of frequencies. The oscillation
frequencies are classified into frequency ranges (i.e
delta, theta, alpha, beta, and gamma). Researchers
have suggested that the different frequencies captured
with neuroimaging device are correlated to different
mental states and has a biological significance (Im-
peratori et al., 2014; Imperatori et al., 2019).
2.2 Measuring Stress
Hans Seyle (Selye, 1985) initially defined stress as
the nonspecific result of any demand upon the body,
be the effect mental or somatic. Detecting stress and
identifying the effects of stress on daily life has been a
objective for researchers in the social science domain.
However recently software engineers have started in-
vestigating the impact of different mental states on
software quality and development process.
Some cross-sectional studies suggest an associa-
tion between brain activity, creativity and stress (An-
dersson et al., 2001). Over the years researchers have
proposed systems and approaches the human physical
and mental states such as stress in the working envi-
ronment using different biophysical signals. A new
apparatus (Andersson et al., 2001) was designed to
assess the stress levels of call-centre operators. The
study uses two types of sensors to monitor the work-
ing environment: environmental and physiological.
The evaluation of stress relies more on the latter sig-
nals. The goal of the authors was to design the system
to improve the well-being of the employees with the
application of multi-sensor analysis.
The portable system described in (Aljuaid, 2019)
measures biophysical signals in real-time and noti-
fies unwanted mental behaviour. The notifications are
sent in case the following conditions in the worker are
detected: 1) absent-minded/inattentive, 2) stressed, 3)
extreme fear, 4) anger, 5) stun/daze, 6) overloaded
with work, 7) drowsiness, and 8) dizziness. The au-
thor focuses on neuroergonomics as a primary field of
study. As well as the previous study, this one aimed
to design a system to predict human mental and phys-
ical state and increase productivity and well being at
work. However, the range of biological signals col-
lected was significantly broader than in (Andersson
et al., 2001) and brain, muscle activity analysis was
The device proposed in (Amores et al., 2018) de-
termines the relaxation level of the user. It consists
of the Virtual reality headset and the olfactory neck-
lace. The necklace changes the intensity of aroma,
Review: Use of EEG on Measuring Stress Levels When Painting and Programming
depending on the subjects’ EEG datagrams. In (Sai-
datul et al., 2011), mental stress was measured while
solving arithmetic tasks. The (Duraisingam et al.,
2017) detected the difficulty of program comprehen-
sion tasks among the students. The (Sun et al., 2015)
describes a method to determine the drivers’ vigilance
level. In the context of the studies mentioned above
the following biophysical signals were used:
heart rate (Aljuaid, 2019) (Andersson et al.,
galvanic skin resistance (Andersson et al., 2001)
body temperature (Aljuaid, 2019);
blood pressure (Aljuaid, 2019) - a sensor is placed
in the temple part of the head or in the upper part
of the shoulder depending on the type of device;
EEG (Aljuaid, 2019) (Amores et al., 2018) (Du-
raisingam et al., 2017) (Duraisingam et al., 2017)
EMG (Aljuaid, 2019);
Our proposed approach is a literature review to an-
swer the posed research questions. The following sec-
tions outline the details about each stage. Our litera-
ture review follows the approach defined in (Kitchen-
ham and Charters, 2007).
3.1 Search Strategy
To retrieve the literature to answer our research
questions, we used digital libraries namely: Google
Scholar and IEEE Xplore. Based on the research
questions, we compiled a set of keywords correspond-
ing to each RQ. Search strings were developed con-
sidering the keywords which were joined with the op-
erator OR and AND. Table 1 shows the overall key-
words, search queries and the corresponding research
RQ4. answer will be derived from RQ1., RQ2.
and RQ3., therefore we did not make keywords and
search query corresponding to the research question
(RQ4.). The search for publications was manual.
3.2 Data Extraction
The data retrieved from the selected digital libraries
were manually assessed and relevant information was
extracted and stored for further analysis. For each and
every retrieved study, the full names of all authors,
full titles, years of publication, publication journals
or conferences, abstracts information was stored in a
spreadsheet. As part of preprocessing the retrieved
data, we filtered out all duplicates to create a list of
studies for further analysis (i.e if the same article ap-
peared multiple times in different digital libraries en-
gines for one RQ or in the same search engine for
multiple RQs, it was only recorded once).
3.3 Inclusion and Exclusion Criteria
After compiling the data extracted using the specific
search queries, it is important to determine which
publications are relevant to the topic, since some ar-
ticles may include given keywords despite covering
a non-related topic (i.e the development of software
that analyses EEG results or covers art not related to
painting). For a study to be considered in our litera-
ture review, it should meet the following criterion:
1. The study should be available in the English lan-
2. The study should include experiments
3. These experiments should involve painting or pro-
4. The article must be published not more than 30
years ago
Moreover, some other studies were excluded
based on the following criterion:
1. The studies involving verbal creativity experi-
ments, imagination experiments must be omitted
2. The studies where no code is written during exper-
iments despite involving programmers or cover-
ing a topic related to software development (UML
creation, code analysis).
3.4 Quality Assessment
“Overview Quality Assessment Questionnaire
(OQAQ)” has been proposed by A.D.Oxman and
G.H.Guyatt to assess certain aspects of the scientific
quality of research overviews (Oxman, 1991). For
further and finer filtering of the retrieved publications
we applied a quality assessment using the following
QA1. Does the paper contain data resulting from the
experiments on stress authors had using EEG?
QA2. Do experiments involve more than 3 people?
QA3. Do the volunteers from the experiments belong
to the same age group?
Publications that are more suitable for further re-
view, should have more than 1.5 points after assigning
scores according to the criteria outlined below:
ICEIS 2022 - 24th International Conference on Enterprise Information Systems
Table 1: Keywords and Search Queries.
Research Questions Keywords Search Query
RQ1. Measuring, Monitoring, Stress, Devices,
“EEG” OR “devices” AND “stress”
AND “measuring” OR “monitoring”
RQ2. EEG, Painting, Pattern, Stress “EEG” OR “electroencephalogram”
AND “painting” AND “pattern” AND
RQ3. EEG, Programmers, Programming, De-
velopers, Stress, Pattern
“EEG” AND (“programming” OR “de-
velopers” OR “programmers”) AND “ex-
periment” AND “stress”
QA1. 1, does have experiment held by authors, 0
- authors analyse available data from experi-
ments related to other studies
QA2. 1, experiments involve more than 3 people, 0.5
- 3 people, 0 - less than 3 people
QA3. 1, all people involved in the experiments be-
long to the same age group, 0 - people in
experiments do not belong to the same age
This section presents the results achieved after follow-
ing the steps outlined in section 3. The studies that
were left after applying inclusion and exclusion crite-
ria along with quality assessment were considered to
be relevant to the discussed fields.
By using the keywords in Table 1 above, we found
74,900 articles on Google Scholar, applied inclusion
and exclusion criteria to 50 of them, performed qual-
ity assessment on 20 of them, and only 10 were as-
sumed to be relevant. The studies distributions ac-
cording to the year of publication is presented in Fig.
1. Tables 2, 3 and 4 present all the included studies
in correspondence to research questions together with
the quality assessment scores.
Table 2: Papers Related to RQ1 Which Passed the Quality
Names of authors Year QA1 QA2 QA3 Score
Hou et al. 2016 + + + 3
Hosseini and Khalilzadeh 2010 + + + 3
Jun and Smitha 2016 + + + 3
Saeed et al. 2015 + + + 3
Table 3: Papers Related to RQ2 Which Passed the Quality
Name of the paper Year QA1 QA2 QA3 Score
Zhang et al. 2021 + + - 2
Wang and Huang 2016 + + + 3
Wang and Shih 2016 + + + 3
Number of Papers
Before I/E and QA
After I/E and QA
Figure 1: Distribution Of The Reviewed Literature Ror SQ1
Over The Years.
Table 4: Papers Related to RQ3 Which Passed the Quality
Name of the paper Year QA1 QA2 QA3 Score
Salma et al. 2017 + + - 2
Yamamoto et al. 2016 + - + 2
Desai 2017 + + + 3
In this section, we discuss the answers to our research
RQ1. Can We Accurately Measure the Level of
Stress using EEG Devices?
Based on the data and experimental results
retrieved from selected studies, we conclude
that an EEG device is a reliable tool for mea-
suring stress levels with decent accuracy. Hou
et al. (Hou et al., 2015) and Jun (Jun and
Smitha, 2016) separately conducted experi-
ments based on the same test and classified
the results using the same classifier for dif-
ferentiating stress levels, each achieving ac-
Review: Use of EEG on Measuring Stress Levels When Painting and Programming
curacy higher than 75%. Hosseini (Hosseini
and Khalilzadeh, 2010) used the Elman clas-
sifier and the accuracy was 82.7%. Saeed et
al. (Saeed et al., 2015) used three different
classifiers, and every single one of them had
at least 64% accuracy. The high accuracy with
different types of classifiers shows that EEG is
an effective way to precisely record the brain
signals to measure the stress level.
RQ2. What is the Pattern of the Stress Level
When People Paint Depending on Different
Situations and Styles of Painting?
As noted by Wang and Huang (Wang, 2016b)
and also Wang and Shih (Wang, 2016a) dur-
ing one-time experiments, concrete figure
painting reduces stress despite using different
styles of art. Zhang et al. (Zhang et al., 2021)
proved via a long experiment with Chinese
bird painting that stress relief can help to cure
depression. The common outcome seems to
be that in all painting experiments, the draw-
ing which is not abstract and has many details
helps to decrease the stress level. But since
not many studies were found relevant and did
contain information on EEG experiments, we
can determine that the research gap is present.
RQ3. Does the Stress Level of Programmers
Somehow Follow Some Specific Pattern
during Code Writing?
Salma et al. (Salma et al., 2018) noted that
the stress level for the task with a time limit is
higher than for the task without a time limit.
Yamamoto et al. (Yamamoto et al., 2016)
proved that stress level is the same for the au-
thors of successful and unsuccessful solutions
if both have a time limit. Desai (Desai, 2017)
showed that extending the time limit reduces
stress and that certain programming languages
cause more stress with the same tasks. All
the found studies do not directly address the
question about the stress level pattern while
writing code. Therefore, we can conclude that
there is a need for additional research into the
stress patterns that occur while programming.
RQ4. Can We Draw a Comparison between Spe-
cific Situations or Activities That Are
Done While Programming and Done While
Painting According to the Pattern of the
Level of Stress?
To this end, we cannot make a concrete con-
clusion because of the lack of research that is
directed in the analysis of stress levels com-
parison for painting and painting. However,
from the retrieved studies in the study, we
noticed that painting reduces stress (Zhang
et al., 2021; Wang, 2016b; Wang, 2016a)
and programming may increase stress levels
(Salma et al., 2018),(Yamamoto et al., 2016),
the change during coding could be explained
by the presence of a time limit, which was
not present during art experiments. We re-
frain from making a solid conclusion since the
situations and types of tasks from the stud-
ies differ so much. There is a need for fur-
ther research in the covered fields using EEG
with similar setups and similar kinds of activ-
ities to analyse the stress levels change during
programming and painting properly and to be
able to compare them.
Here, we discuss the threats to the internal and ex-
ternal validity of our results. Based on Wohlin et
al. (Wohlin et al., 2012) the following subsections
present the different threats to validity.
6.1 Construct Validity
(Wohlin et al., 2012) defines construct validity threats
as threats linked to the generalization of the results to
the concepts behind the study. During the analysis of
selected studies, we noticed that some studies did not
give full details on the protocol and theoretical bases
for selecting specific techniques. To minimize the im-
pact of such issues we formulated a much more strict
quality assessment (i.e presented in section 3.4). In
addition, we carefully analysed the experiment proto-
col and research objective for each and every primary
6.2 Internal Validity
Internal validity threats may affect the results due
to incorrect conclusions. Guidelines proposed by
Kitchenham (Kitchenham and Charters, 2007) were
used to avoid this kind of risk. We defined a review
protocol to include all relevant EEG, stress and paint-
ing studies in the search. All the relevant and major
digital libraries related to brain waves analysis in soft-
ware engineering were selected as sources for studies
to minimize internal validity.
6.3 External Validity
These threats arise from the generalization of the re-
sults of the review to the real-world scenarios (Wohlin
ICEIS 2022 - 24th International Conference on Enterprise Information Systems
et al., 2012). In the review presented, we excluded
studies not written in English and this poses a lim-
itation on generalizing our results since in our data
retrieval and data analysis we found studies written in
other languages (i.e Russian). However, it is worth
noting that these studies written in Russian did not
meet the other inclusion/exclusion criterion as they
were analysed by the first author who is native a Rus-
sian language speaker.
6.4 Conclusion Validity
Similar to what is known as interpretive validity, con-
clusion validity is concerned with the formulation
of inaccurate conclusions from the given data. This
could be the small set of primary studies we have
collected. To mitigate the risk of excluding primary
studies we did the following: (i) the search strings
are defined by considering the concepts and their
acronyms, (ii) the related works of all the primary
studies are carefully analyzed, (iii) Duplicates were
removed based on the title, author, publisher, and year
of publication. The full text of selected studies was
carefully read through to mitigate misinterpretations
and extract accurate data.
The goal of this study was to find the relationship be-
tween observed stress levels while programming and
while painting a picture. The relationship was aimed
to be recognised at the mental state level with the
help of EEG. To achieve the aforementioned goals,
we conducted a systematic literature review using
guidelines proposed by Kitchenham (Kitchenham and
Charters, 2007). We formulated four research ques-
tions and based on inclusion/exclusion criteria and
quality assessment we found 14 studies that were used
to answer the research questions. The review shows
that EEG devices can be used to accurately measure
stress. Secondly, the review revealed that there exists
a research gap and there is a need to conduct more ex-
periments for analysis of the stress level pattern when
a programmer is writing the code.
For future works, we plan on conducting experi-
ments whereby we will focus on the comparison be-
tween specific situations or activities that are done
while programming and done while painting accord-
ing to the pattern of the level of stress. In addition, we
aim at analysing a specific pattern of stress levels of
programmers during code writing in the experiments.
Aljuaid, A. M. (2019). Theoretical design of eeg-based
neuroergonomics integrated portable system, apply-
ing direct psychophysiological indicators. In 2019 In-
dustrial & Systems Engineering Conference (ISEC),
pages 1–6. IEEE.
Amores, J., Richer, R., Zhao, N., Maes, P., and Eskofier,
B. M. (2018). Promoting relaxation using virtual re-
ality, olfactory interfaces and wearable eeg. In 2018
IEEE 15th international conference on wearable and
implantable body sensor networks (BSN), pages 98–
101. IEEE.
Andersson, M., Avamini, A., Colosimo, A., D’Amico, A.,
Davide, F., Di Natale, C., Ganci, S., Gutknecht, M.,
Holmberg, M., Mazzone, E., et al. (2001). Angelo
evaluation: application of a multisensor system for
psycho-physiological stress detection in working en-
vironments. In ICECS 2001. 8th IEEE International
Conference on Electronics, Circuits and Systems (Cat.
No. 01EX483), volume 3, pages 1509–1512. IEEE.
Chrousos (1998). Stressors, stress, and neuroendocrine in-
tegration of the adaptive response. the 1997 hans selye
memorial lecture. Annals of the New York Academy of
Sciences, 851:311–335.
Desai, A. R. (2017). Eeg-based evaluation of cognitive and
emotional arousal when coding in different program-
ming languages. University of Oulu.
Duraisingam, A., Palaniappan, R., and Andrews, S. (2017).
Cognitive task difficulty analysis using eeg and data
mining. In 2017 Conference on Emerging Devices and
Smart Systems (ICEDSS), pages 52–57. IEEE.
Hassan, I., Weyers, P., Maschuw, K., Dick, B., Gerdes,
B., Rothmund, M., and Zielke, A. (2006). Nega-
tive stress-coping strategies among novices in surgery
correlate with poor virtual laparoscopic performance.
Journal of British Surgery, 93(12):1554–1559.
Hetland, H., Sandal, G. M., and Johnsen, T. B. (2007).
Burnout in the information technology sector: Does
leadership matter? European Journal of Work and
Organizational Psychology, 16(1):58–75.
Hosseini, S. A. and Khalilzadeh, M. A. (2010). Emo-
tional stress recognition system using eeg and psy-
chophysiological signals: Using new labelling process
of eeg signals in emotional stress state. In 2010 Inter-
national Conference on Biomedical Engineering and
Computer Science, pages 1–6.
Hou, X., Liu, Y., Sourina, O., Tan, Y. R. E., Wang, L., and
Mueller-Wittig, W. (2015). Eeg based stress monitor-
ing. In 2015 IEEE International Conference on Sys-
tems, Man, and Cybernetics, pages 3110–3115.
Imperatori, C., Brunetti, R., Farina, B., Speranza,
A. M., Losurdo, A., Testani, E., Contardi, A.,
and Della Marca, G. (2014). Modification of eeg
power spectra and eeg connectivity in autobiograph-
ical memory: a sloreta study. Cognitive Processing,
Imperatori, C., Farina, B., Adenzato, M., Valenti, E. M.,
Murgia, C., Marca, G. D., Brunetti, R., Fontana, E.,
and Ardito, R. B. (2019). Default mode network alter-
ations in individuals with high-trait-anxiety: An eeg
Review: Use of EEG on Measuring Stress Levels When Painting and Programming
functional connectivity study. Journal of Affective
Disorders, 246:611 – 618.
Jun, G. and Smitha, K. G. (2016). Eeg based stress level
identification. In 2016 IEEE International Confer-
ence on Systems, Man, and Cybernetics (SMC), pages
Kitchenham, B. and Charters, S. (2007). Guidelines for per-
forming systematic literature reviews in software en-
Klein, G. (1996). The effect of acute stressors on decision
making. Stress and human performance, pages 49–88.
Oxman, G. (1991). Validation of an index of the quality
of review articles. Journal of Clinical Epidemiology,
Saeed, S. M. U., Anwar, S. M., Majid, M., and Bhatti, A. M.
(2015). Psychological stress measurement using low
cost single channel eeg headset. In 2015 IEEE Inter-
national Symposium on Signal Processing and Infor-
mation Technology (ISSPIT), pages 581–585.
Saidatul, A., Paulraj, M. P., Yaacob, S., and Yusnita, M. A.
(2011). Analysis of eeg signals during relaxation and
mental stress condition using ar modeling techniques.
In 2011 IEEE international conference on control
system, computing and engineering, pages 477–481.
Salma, N., Mai, B., and Namuduri, K. (2018). Using eeg
signal to analyze is decision making cognitive pro-
cesses. In Information Systems and Neuroscience,
pages 211–218. Springer International Publishing.
Selye, H. (1985). History and present status ofthe stress
concept. Stress andCoping: An Anthology, edited
by RS Lazarusand A. Monat. New York: Columbia
UniversityPress. SelyeHistory and Present Status of
the Stress Concept17Stress and Coping: An Anthol-
ogy1985, pages 17–29.
Sun, H., Bi, L., Lu, X., Fan, B., and Guo, Y. (2015). Vigi-
lance analysis based on eeg band power using support
vector machine. In 2015 8th International Congress
on Image and Signal Processing (CISP), pages 1090–
1094. IEEE.
Wang, S. (2016a). Researching the change of brainwave of
students with using wearable eeg to drawing coloring
books. 2016 International Conference on Advanced
Materials for Science and Engineering (ICAMSE),
Wang, Huang, S. (2016b). Using wearable eeg to research
the change of brainwave of teenagers drawing pic-
tures with mandala art. 2016 International Conference
on Advanced Materials for Science and Engineering
(ICAMSE), 25(2):581–584.
Wohlin, C., Runeson, P., H
ost, M., Ohlsson, M. C., Reg-
nell, B., and Wessl
en, A. (2012). Experimentation in
software engineering. Springer Science & Business
Yamamoto, A., Uwano, H., and Ikutani, Y. (2016). Pro-
grammer’s electroencephalogram who found imple-
mentation strategy. 2016 4th Intl Conf on Applied
Computing and Information Technology/3rd Intl Conf
on Computational Science/Intelligence and Applied
Informatics/1st Intl Conf on Big Data, Cloud Comput-
ing, Data Science & Engineering (ACIT-CSII-BCD),
pages 164–168.
Zhang, B., Chen, J., Huang, X., and Xu, W. (2021). Chinese
flower and bird painting: A new form of art therapy
for depression. SAGE Open, 11(2):2158–2166.
ICEIS 2022 - 24th International Conference on Enterprise Information Systems