A Proﬁle Recognition System Based on Emotions for Children with ASD

in an Interactive Museum Visit

Nicol

as Araya

, Javier Gomez

and Germ

an Montoro

Escuela Polit

ecnica Superior, Universidad Aut

onoma de Madrid, Madrid, Spain

Keywords:

Autism, Leisure, Interaction, User Model, Mobile Application.

Abstract:

Children with Autism Spectrum Disorder (ASD) may experience difﬁculties in doing some activities on their

own as they are likely to be more sensitive to visual or auditory stimuli. This may limit their selection of

activities, and these must be adapted for them and their companions. One of the most important issues for

this group is to be able to manage and recognise their emotions, which leads to a better understanding of

themselves and their surroundings.

In recent years, information technology has helped to develop assistance tools for education and daily habits.

However, research in emotional management in children with ASD has not been fully explored for leisure and

cultural activities.

In this paper we present a proposal for a user model and a mobile application intended to assist children

with ASD when visiting a leisure space and assess the emotional impact as they go through the different

attractions. Users will respond to a questionnaire based on the basic emotions in an itinerary suitable for their

general behaviour.

The methodology is validated by a non-proﬁt organisation, who helped to create a case study, intended to

provide guidance for recommendations on leisure activities for these children and their caregivers.

1 INTRODUCTION

Autism Spectrum Disorder (ASD) is a neurodevel-

opmental disorder, characterised by deﬁcits of social

communication and social interaction, along with re-

stricted and repetitive patterns in behaviours, activi-

ties and interests (First, 2013). It is an umbrella term

that refers to multiple manifestations ranging from

very mild to severe, though certain symptomatology

is shared along these individuals (Lord et al., 2018).

The DSM-5 (First, 2013) describes some common

signs and symptoms of ASD, which may come more

mild or severe depending on the diagnosis and treat-

ment depends on this, though most people require a

lifelong support (Lord et al., 2018).

Some of them include deﬁcits in social emo-

tional reciprocity and non-verbal communicative be-

haviours, low comprehension of general social stimuli

(Bandr

es et al., 2021), hyperreactivity or hyporeactiv-

ity to sensory input and unusual interests in sensory

https://orcid.org/0000-0002-7623-7835

https://orcid.org/0000-0002-7496-7965

https://orcid.org/0000-0001-7393-1226

aspects of the environment (First, 2013; Grzadzinski

et al., 2013; Lord et al., 2018).

For instance, a child diagnosed with ASD may

feel overwhelmed by lights or loud noises, which

may affect how they feel in certain situations. Be-

cause of this, children need the company of a tutor for

their daily activities, and this could affect their par-

ticipation and choice for cultural or playful activities

(Huang and Kang, 2021).

Given the quick and simple access to technology,

a wide range of mobile applications has been devel-

oped to improve accessibility of people with special

sociability needs and their families (Gallardo-Montes

et al., 2021). Generally, they provide assistance in

the ﬁelds of education, communication skills, and

therapy(Cibrian et al., 2022; Krause and Neto, 2021;

Fletcher-Watson, 2014).

Information and Communication Technologies

(ICTs) have therefore become a useful tool for chil-

dren with ASD in their education process meant for

lifetime use (Dratsiou et al., 2021). These users are

keen to visual and sensory stimuli, therefore, new

technologies of digital transformation such as Aug-

mented Reality, Computer Vision and gamiﬁcation

Araya, N., Gomez, J. and Montoro, G.

A Proﬁle Recognition System Based on Emotions for Children with ASD in an Interactive Museum Visit.

DOI: 10.5220/0011780000003414

In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 5: HEALTHINF, pages 507-513

ISBN: 978-989-758-631-6; ISSN: 2184-4305

 2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

507

across different contexts have made a trend in recent

years (Krause and Neto, 2021; Lian and Sunar, 2021;

Mubin et al., 2020; Torrado et al., 2019; Grossard

et al., 2017).

Some of the main problems covered by these ap-

plications include ASD diagnosis, adaptive learning

and emotional recognition (Krause and Neto, 2021).

This study will focus on the latter.

According to psychologist Robert Plutchik, there

are 8 basic emotions deﬁned by joy, trust, fear, sur-

prise, sadness, anticipation, anger, and disgust. The

rest are deﬁned as a combination of these primary

emotions and, similarly to the colour palette, a wheel

of emotions is proposed, referred as Plutchik’s Emo-

tion Wheel (Plutchik, 2001).

Children and adolescents with ASD have more

difﬁculties than typically developing group pairs for

emotion recognition and management (Papoutsi et al.,

2018). Hence, therapy for people with ASD involves

a process of emotion identiﬁcation and recognition,

and in recent years this has been mediated with the

use of technology (Rashidan et al., 2021).

On the other hand, interactive museums may offer

an interesting option for participation in leisure yet

ordered activities, as they can be ordered in different

itineraries or attractive points depending on the visi-

tors’ interests (Yates et al., 2022). If a child with ASD

gets affected by any stimuli, it is relevant to commu-

nicate their emotions well to their caregiver.

All in all, there is room for investigation within

the context of emotional perception by children with

ASD as an interactive experience. We propose an

adaptation of a user model for proﬁle assignment

based on the user perception when visiting interactive

attractions, the idea is to compare this information to

a pre-evaluation made from experts, to see if they ﬁt.

2 RELATED WORK AND

MOTIVATION

Some notable applications involving the use of smart-

phones as assistance tools in museum visits or emo-

tional recognition for children with ASD are sum-

marised as follows.

ARtis (Vita et al., 2021) is a mobile application

that facilitates the accessibility and visit of muse-

ums for children with ASD and their tutors by over-

lapping virtual content with the surrounding reality.

Through the smartphone camera, it creates a path in-

side a museum to help the user orientate and “experi-

ence” an appealing and interactive visit. It is guided

by a friendly 3D avatar that follows a path guided with

GPS tracking, it allows users to interact with different

points of interest of the museum.

The main goal of ARTis is to provide an experi-

ence centred on the end-user for a tailored cultural

experience that can help to increase and improve so-

cial skills, through a greater sense of self–efﬁcacy

and autonomy(Lorenzo et al., 2019). With the use

of Augmented Reality (AR) and Internet of Things

(IoT) applied in the use of games, pop-up videos and

visual content, it makes the cultural tour more enjoy-

able and motivating, although certain research proto-

cols for usability testing have to be worked on as well

as extension to other contexts (Vita et al., 2021).

Tobias in the Zoo (Carvalho et al., 2015) presents

an AR application in the form of a GameBook to as-

sist children with ASD to recognise and acquire emo-

tions by engaging their attention and motivation. It

shows the story of Tobias, a virtual character who

has adventures during a zoo park visit along 5 sce-

narios. Each stage interacts with virtual animals and

real-world situations which will conduct the children

to become involved on ﬁctional contents associated

with emotions.

In each GameBook chapter, Tobias identiﬁes ﬁve

emotions (happiness, anger, sadness, fear and disgust)

and narrates examples of it as a part of the story. At

the end of each chapter, a mini game for emotion as-

sociation is prompted to the user in the form of a ques-

tionnaire based on a situation description and an im-

age of Tobias expressing the emotion. At the end of

the book it has an evaluation of all presented emotions

in a memory game (Carvalho et al., 2015).

Guess What? (Kalantarian et al., 2019) is a mo-

bile charade-style game available in iOS and Android

platforms, made for emotion association training to

children with ASD.

With the use of image pattern recognition, it has

been designed to be a shared experience between the

child, who attempts to enact the prompt shown on the

screen through gestures and facial expressions, and

the parent, who is tasked with guessing the word as-

sociated with the prompt during a 90s game session

(Kalantarian et al., 2020).

All in all, these projects show how the use of

games intended for assistance and emotional learning

can be suited for children with ASD, presenting good

results in terms of their behaviour. However, these

tools work with a learning mechanism where emo-

tions are taught by repetition or common face patterns

but are not necessarily experienced by the users them-

selves.

We propose a tool where users associate their feel-

ings to a given emotion as they go through an interac-

tive experience, so that recognition comes ﬁrst hand

rather than given by a storybook or character.

HEALTHINF 2023 - 16th International Conference on Health Informatics

508

As for visual learners such as them, it is key to

maintain innovative and yet simple interfaces in order

to draw their attention. Also, applications should pro-

vide an enhanced experience for the child and their

family. To this matter, these tools should not only be

thought of as playful activities, it is also important to

understand the outcomes of their opinions in order to

improve future recommendations and decisions based

on their motivations.

The value of deciding which activity is appropri-

ate is key for therapists and caregivers when they have

to propose them for children with restricted interests,

so our proposal aims to establish common patterns

that may improve that decision.

3 METHODOLOGY

In this section, we describe the proposed user model

and evaluation strategy for a leisure visit tailored for

children with ASD. The main goal is to monitor their

perceptions and recommend future activities based on

previous patterns deﬁned by experts from a local or-

ganisation that plans leisure visits for families with

children diagnosed with ASD.

3.1 User Proﬁles

In order to prepare for the visit, therapists have de-

scribed common behaviour patterns that children fol-

low as they participate in leisure activities. These

have been reduced to four major proﬁle characteriza-

tions.

Adventurous. Children with this proﬁle prefer activ-

ities that dare them to be stimulated and hyped.

They show interest in dynamic attractions that re-

quire active participation, involving movement,

lights or sound. Usually, they tend to have an au-

tonomous yet impulsive behaviour and don’t pay

attention to instructions carefully, so may need re-

inforcement of them.

Viewer. Children with this proﬁle tend to more

calmed activities that do not require major move-

ment or active participation, they prefer to watch

or have a demonstration of an action. They

are also keener to learn and ask questions about

the context, as they keep their concentration for

longer periods, as well as comment on what they

perceive with their companions.

Participative. Children with this proﬁle represent an

intermediate point as they enjoy dynamic and

more calm activities equally. In principle, it is

hard to determine what plans they could enjoy

most, depending on what entertains them at any

given moment. They like to be accompanied by

their tutors as they feel supported if they feel in-

secure.

Little Interested. Children with this proﬁle don’t

feel highly motivated and rather scared by the ac-

tivities, as it triggers them to have a higher reactiv-

ity to sensory stimuli, insecurities or don’t show

interest at all. Perhaps their time or concentration

span may be lower and generally depend on their

tutor for most of their communication. Familiar

activities may be repeated rather than exploring

something new.

Even though, as we deﬁned, ASD covers a wide

range of manifestations, these proﬁles serve as an ap-

proach for organising future activities. Some other

things should be considered.

For instance, proper and clear itineraries should be

deﬁned and presented in advance, as they need to feel

secure in their space. Also, the environment should be

nice and comfortable, lights and noises must be con-

trolled and any other possible distractions. Finally, a

help system should be provided as well as a protocol

if they don’t feel comfortable enough to keep up with

the activity.

3.2 AVI Model for Emotion Recognition

As for the division of the previous proﬁles, a selected

criteria is deﬁned according to an adaptation of the

motivational dimension model by Zhang in (Zhang

et al., 2020) and the emotional mapping proposed by

Park in (Park et al., 2019). These models were cho-

sen as they allow to quantify some common emotions

so it can be parameterized according to valence and

arousal levels.

According to experts, four major emotions tend

to be the most frequent: fear, happiness, sadness and

tiredness. These emotions were ordered according

to both mentioned models, representing one in each

quadrant in the Cartesian plane, with axis of arousal

and valence, as it shows in ﬁgure 1. Therefore, we

propose the AVI (acronym for Arousal, Valence and

Interest) model that connects these three parameters

with the four emotions raised by the opinion of ex-

perts. As for the arousal and valence factors, possible

values are given by -1 and 1, in order to maintain the

bidimensional plane.

Additionally, a third parameter that represents the

interest of the activity is added to have a model de-

pendent of three parameters as that should broaden

the scope of action. This parameter represents how an

activity can be appealing in three levels, low, medium

A Proﬁle Recognition System Based on Emotions for Children with ASD in an Interactive Museum Visit

509

and high, respectively represented by the values -1, 0

and 1.

The idea is that therapists give a punctuation for

each proﬁle, which is stored in a number vector. This

vector will be used to determine the shortest distance

between the points represented by the vectors, using

the Euclidean distance.

Figure 1: AVI Model of Emotions.

3.3 Before the Visit

Due to their behaviour, as a general rule, people with

ASD and their companions need to be informed of

visit details in advance. For this, experts prepare use-

ful information guides with the use of adequate and

visual content, to provide details such as the address,

working hours of the visiting space and other relevant

suggestions, as well as contact information if addi-

tional assistance is needed.

In this phase, itineraries for the visit are deﬁned in

accordance with the available options. Each itinerary

is tailored for each user proﬁle and it is added in the

preparation guides.

All of this material is included in the mobile appli-

cation so it can be consulted in advance by the fami-

lies. Important information such as the address, work-

ing hours of the museum and a map of the itineraries

is provided for maintaining a correct pattern of visit,

as well as contact information if additional assistance

is needed.

Firstly, we conduct a session along with the thera-

pists to describe eight user personas, two for each user

proﬁle, giving them a name, age, and descriptions of

their diagnosis, interests and general behaviour. Later,

the discussion moves to estimating the corresponding

values for the AVI vectors of each user persona for the

itinerary corresponding to their proﬁle.

3.4 During the Visit

The leisure place is selected depending on the avail-

ability, attractions and adaptation for people with spe-

cial needs, some common places tend to be art gal-

leries, museums or interactive spaces.

In a general visit, a main protocol and data protec-

tion consent must be deﬁned to secure the information

and assure that all information collected is for aca-

demic use only. Small groups are preferred in order

to maintain a calm environment as well as selecting

a time period where the space is not crowded, and if

possible, to book a time just for this evaluation.

Prior to the visit, experts will discuss the sug-

gested proﬁle for every child, depending on their be-

haviour on previous leisure activities, and will assign

a corresponding itinerary to each.

As for the day of the visit, a member of the ac-

companying family group will be responsible for pro-

viding the information for this evaluation, in the name

of its child. This person will be instructed on how to

use the application and respond to the questionnaires

as they move along the proposed itinerary, according

to their proﬁle. For this, mobile phones with the ap-

plications will be provided and with their consent, the

data of the questions will be registered anonymously,

as shown in table 1.

Finally, each user will represent a given proﬁle

that will be contrasted to the AVI vectors provided

by the experts in the user persona evaluation. Metrics

for accuracy and consistency are proposed in order to

determine the comparison overall.

4 MOBILE APPLICATION FOR

THE VISIT

We propose an application for registration of the user

evaluation of the AVI model as they pass through dif-

ferent attractions deﬁned in an itinerary of attractions.

The main sections of the app include: Guides (maps

and important information about the visit location),

Surveys (questionnaires for storing information of the

AVI model) and a Proﬁle (detailing a description of

the proposed proﬁles and recommendations).

Guides. As people with ASD tend to follow struc-

tured routines, the preparation guides give them

an anticipation of what to expect in their visit.

Contains maps, pictures and any other import in-

formation about the visit location, also the proto-

cols that will be used.

Surveys. Contains questionnaires for registration of

the AVI model, meant to be answered by the care-

givers or family members in charge of the child

after they visit an attraction. See ﬁgures 2 and 3.

Proﬁle. Contains a description of the proposed pro-

ﬁle according to experts evaluation, its corre-

HEALTHINF 2023 - 16th International Conference on Health Informatics

510

sponding itinerary and associated recommenda-

tions. See ﬁgure 4 .

Figure 2: Emotions questionnaire.

Figure 3: Emotions questionnaire.

Figure 4: Adventurous proﬁle description example.

5 A CASE STUDY

The user model and strategy are meant for any inter-

active museum visit, though an example case study is

provided for better understanding and generating con-

sequent results.

With the help of a local organisation, we managed

to plan the visit for the Illusions Museum of Madrid.

This space provides optical illusions, rooms with mir-

rors and entertaining attractions meant for children to

learn by playing and learning science through an artis-

tic environment. It is a space that induces different

emotions to visitors, and the organisation has teamed

up for a special visit for people with autism and their

families.

5.1 Preparation Phase

According to the methodology, experts work in the

preparation guides for the visit, and elaborate the cor-

responding itineraries for each of the four user pro-

ﬁles. This visual material is included in the Guides

section of the mobile application.

In the session with experts, we elaborate a descrip-

tion for the eight user personas and ask them to com-

plete the questionnaires as if they were in the child’s

position. These answers were later discussed as a

group to give a ﬁnal score for each user persona, that

will serve to contrast it with the information given by

the ﬁnal users.

We have recruited a group of 6 children with their

families that wish to participate in exchange for a free

visit to the museum. The organisation has helped to

book the visit and review all corresponding material,

including protocols and user consents. Experts of the

organisation also assign a user proﬁle and itinerary

for each child, corresponding to their diagnosis back-

ground and perceived interests.

5.2 Museum Visit

In the visit itself, instructions will be given to all par-

ticipant groups regarding the overall experience, use

of the application and main museum guidelines. A

mobile phone with the tool will be handed to a fam-

ily member of each group, provided their agreement

to participate in the evaluation. This person will be in

charge of answering the questionnaires as they move

along the proposed itinerary, according to their pro-

ﬁle. An example of some response answers is shown

in table 1.

Table 1: Example of user evaluation.

Proﬁle Attraction Emotion Interest

Viewer

Optical room

Kaleidoscope

Mirrors room

Holograms room

Happy

Bored

Sad

-1

6 CONCLUSIONS

People diagnosed with ASD have difﬁculties in so-

cial communication and interaction contexts, which

is rooted in different symptoms such as hyperreactiv-

ity or hyporeactivity to sensory stimuli, repetitive pat-

A Proﬁle Recognition System Based on Emotions for Children with ASD in an Interactive Museum Visit

511

terns in restricted activities and interests. Therefore,

the presence of a tutor is essential, and, in leisure ac-

tivities which are not always adapted for these end

users.

As people with ASD usually have challenges to

identify the emotions of their own and from their

peers, many research applications have been made for

emotional recognition but only few of them have been

targeted for leisure or cultural activities.

This paper proposes an innovative application for

museum visits suited for children with ASD, with a

focus on emotional recognition about their artistic ex-

perience. The goal is to assess how they feel when

moving along the different attractions of a leisure

place, based on the completion of questionnaires that

measure four basic emotions.

To this extent, a correct user model would help

caregivers to decide on what activities are best suited

for their children and also to have better planning with

the help of an assistance mobile application, which is

portable and more attractive for visual learners.

This paper presents the corresponding tool, that

provides the preparation guidelines for a visit and the

data collect system that provides feedback for experts

that work with planning leisure activities for children

with ASD.

7 FUTURE WORK

The proposed case study will be applied in accor-

dance to the proposed work plan, the current stage

is pending to ﬁnd an available time according to the

schedule of the local non-proﬁt organisation and the

participant museum.

All information will be protected according to eth-

ical guidelines and accessed only for research pur-

poses. It will be used for a user model based on their

answers and to assign an emotional proﬁle which may

help for future museum visits and help to guide other

activities of the organisation.

Future work will test the usability of mobile ap-

plications like these and deﬁne a framework for ex-

tending the emotional impact in other leisure contexts

such as restaurants, theatres or cinemas. This way, a

correct adaptation should provide a better user model

and help them to enjoy the activities based on how

they feel, which contributes to a more pleasant user

experience.

ACKNOWLEDGEMENTS

The authors acknowledge the eMadrid Network (e-

Madrid-CM project), which is funded by the Madrid

Regional Government (Comunidad de Madrid) with

grant No. S2018/TCS-4307, a project which is

co-funded by the European Structural Funds (FSE

and FEDER). This work also received partial sup-

port from the Project Indigo! (Ministry of Sci-

ence and Innovation with reference number PID2019-

105951RB-I00 / AEI / 10.13039 / 501100011033).

REFERENCES

Bandr

es, S. C., Toledo, S. V., Or

us, M. L., and Baldas-

sarri, S. (2021). La potencialidad de la tecnolog

ıa

en la medici

on del desarrollo de habilidades so-

ciales en ni

nos con tea: un an

alisis desde par

ametros

ﬁsiol

ogicos. Revista de Investigaci

on Educativa,

39:445–462. cited By 0.

Carvalho, V. H., Brand

ao, J., Cunha, P., Vasconcelos, J.,

and Soares, F. (2015). Tobias in the Zoo – A Serious

Game for Children with Autism Spectrum Disorders.

International Journal of Advanced Corporate Learn-

ing (iJAC), 8(3):23.

Cibrian, F. L., Lakes, K. D., Schuck, S. E. B., and Hayes,

G. R. (2022). The potential for emerging technolo-

gies to support self-regulation in children with adhd:

A literature review. International Journal of Child-

Computer Interaction, 31. cited By 0.

Dratsiou, I., Metaxa, M., Romanopoulou, E., Dolianiti, F.,

Spachos, D., and Bamidis, P. D. (2021). Eliminat-

ing the gap between the use of assistive technologies

and the inclusion of people with intellectual disabili-

ties in leisure activities. Health Informatics Journal,

27:146045822110050.

First, M. B. (2013). DSM–5 handbook of differential diag-

nosis. American Psychiatric Pub.

Fletcher-Watson, S. (2014). A targeted review of computer-

assisted learning for people with autism spectrum

disorder: Towards a consistent methodology. Re-

view Journal of Autism and Developmental Disorders,

1(2):87–100.

Gallardo-Montes, C. d. P., Caurcel Cara, M. J., and

Rodr

ıguez Fuentes, A. (2021). Technologies in the

education of children and teenagers with autism: eval-

uation and classiﬁcation of apps by work areas. Edu-

cation and Information Technologies, pages 1–29.

Grossard, C., Grynspan, O., Serret, S., Jouen, A. L., Bailly,

K., and Cohen, D. (2017). Serious games to teach

social interactions and emotions to individuals with

autism spectrum disorders (ASD). Computers and Ed-

ucation, 113:195–211.

Grzadzinski, R., Huerta, M., and Lord, C. (2013). Dsm-

5 and autism spectrum disorders (asds): an opportu-

nity for identifying asd subtypes. Molecular autism,

4(1):1–6.

HEALTHINF 2023 - 16th International Conference on Health Informatics

512

Huang, C.-C. and Kang, L.-J. (2021). Participation in play

and leisure activities of young children with autism

spectrum disorder and typically developing children

in taiwan: A preliminary study. International Jour-

nal of Environmental Research and Public Health,

18(11):5787.

Kalantarian, H., Jedoui, K., Washington, P., and Wall, D. P.

(2020). A Mobile Game for Automatic Emotion-

Labeling of Images. IEEE Transactions on Games,

12(2):213–218.

Kalantarian, H., Washington, P., Schwartz, J., Daniels, J.,

Haber, N., and Wall, D. P. (2019). Guess What?: To-

wards Understanding Autism from Structured Video

Using Facial Affect. Journal of Healthcare Informat-

ics Research, 3(1):43–66.

Krause, M. and Neto, M. A. C. (2021). Systematic mapping

of the literature on mobile apps for people with autis-

tic spectrum disorder. In Proceedings of the Brazilian

Symposium on Multimedia and the Web, pages 45–52.

Lian, X. and Sunar, M. S. (2021). Mobile augmented re-

ality technologies for autism spectrum disorder inter-

ventions: A systematic literature review. Applied Sci-

ences, 11(10):4550.

Lord, C., Elsabbagh, M., Baird, G., and Veenstra-

Vanderweele, J. (2018). Autism spectrum disorder.

The lancet, 392(10146):508–520.

Lorenzo, G., G

omez-Puerta, M., Arr

aez-Vera, G., and

Lorenzo-Lled

o, A. (2019). Preliminary study of aug-

mented reality as an instrument for improvement of

social skills in children with autism spectrum disorder.

Education and Information Technologies, 24(1):181–

204.

Mubin, S. A., Thiruchelvam, V., and Andrew, Y. W. (2020).

Extended reality: How they incorporated for asd in-

tervention. In 2020 8th International Conference

on Information Technology and Multimedia (ICIMU),

pages 262–266. IEEE.

Papoutsi, C., Drigas, A., and Skianis, C. (2018). Mobile ap-

plications to improve emotional intelligence in autism

- a review. International Journal of Interactive Mobile

Technologies, 12:47–61. cited By 6.

Park, C. H., Javed, H., and Jeon, M. (2019). Consensus-

based human-agent interaction model for emotion reg-

ulation in asd. Communications in Computer and In-

formation Science, 1032:295–301.

Plutchik, R. (2001). The nature of emotions: Human emo-

tions have deep evolutionary roots. American Scien-

tist, 89(4):344–350.

Rashidan, M. A., Sidek, S. N., Yusof, H. M., Khalid, M.,

Dzulkarnain, A. A. A., Ghazali, A. S., Zabidi, S.

A. M., and Sidique, F. A. A. (2021). Technology-

assisted emotion recognition for autism spectrum dis-

order (asd) children: A systematic literature review.

IEEE Access, 9:33638–33653. cited By 0.

Torrado, J. C., Gomez, J., and Jaccheri, L. (2019). Sup-

porting self-evaluation for children with mental dis-

abilities through augmented reality. In Proceedings

of the 18th ACM International Conference on Interac-

tion Design and Children, pages 635–641.

Vita, S., Borrelli, L. O., Canniello, F., Mennitto, A., and

Iovino, L. (2021). Artis: how ar supports the guided

experience in museums for people with autism. In

teleXbe.

Yates, E., Szenasi, J., Smedley, A., Glynn, K., and Hem-

mings, M. (2022). Children as experiencers: Increas-

ing engagement, participation and inclusion for young

children in the museum. Childhood, 29:58–74.

Zhang, H., Yin, J., and Zhang, X. (2020). The study of a

ﬁve-dimensional emotional model for facial emotion

recognition. Mobile Information Systems, 2020:1–10.

A Proﬁle Recognition System Based on Emotions for Children with ASD in an Interactive Museum Visit

513