ArticlePDF Available

Artificial intelligence in special education: A decade review

Authors:

Abstract

Athanasios Drigas, Eleni Ioannidou Artificial Intelligence (AI) technology has developed computer tools for carrying out a number of tasks, simulating the intelligent way of problem solving by humans. AI techniques have also been identified as one of the most valuable applications in the field of special educational needs (SEN). The goal of these tools is to enhance the way children interact with their environment to promote learning and to enrich their daily life. Due to the implicit characteristics of special educational needs, the diagnosis has been an issue of major importance. At the same time intervention strategies need to be highly individualized to be effective. In this report we introduce some of the most representative studies over the last decade (2001–2010), which use AI methods in making accurate diagnosis and prompt intervention action. Keywords: artificial intelligence; special educational needs; diagnosis; intervention
Artificial Intelligence in Special Education:
A Decade Review*
ATHANASIOS S. DRIGAS and RODI-ELENI IOANNIDOU
N.C.S.R. Demokritos, Institute of Informatics and Telecommunications, Telecoms Lab—Net Media Lab,
Ag. Paraskevi, 15310, Athens, Greece. E-mail: dr@iit.demokritos.gr, elena.ioan@hotmail.com
Artificial Intelligence (AI) technology has developed computer tools for carrying out a number of tasks, simulating the
intelligent way of problem solving by humans. AI techniques have also been identified as one of the most valuable
applications in the field of special educational needs (SEN). The goal of these tools is to enhance the way children interact
with their environment to promote learning and to enrich their daily life. Due to the implicit characteristics of special
educational needs, the diagnosis has been an issue of major importance. At the same time intervention strategies need to be
highly individualized to be effective. In this report we introduce some of the most representative studies over the last decade
(2001–2010), which use AI methods in making accurate diagnosis and prompt intervention action.
Keywords: artificial intelligence; special educational needs; diagnosis; intervention
1. Introduction
The steady progress in the area of technology has
devolved computing power into many aspects of
our daily life. Across the educational sector there
has been an increased trend to increase the accessi-
bility of education. A large volume of research is
currently addressing the use of computers in educa-
tion in order to develop learning environments,
which support the learning process in different
settings [1]. Several years ago various researchers
and specialists of computing science have started to
study the implementation of Artificial Intelligence
techniques in education.
Artificial Intelligence (AI) has been an active area
of research for over fifty years [2]. It is usually
defined as the study and development of intelligence
agents that can perceive their environment and take
actions that increase their possibilities of success [3].
Artificial intelligence agents can be either in a
physical form of the device (e.g. humanoid robots)
or in software form with ‘intellectual’ capacity (e.g.
a virtual avatar). The nature of technology has
changed since a few years later Artificial Intelligence
in Education (AIE) was conceptualized as separate
research community. AI techniques in education
were claimed to create powerful learning environ-
ments and to increase positive interactive experi-
ences for all students. Some of the most typical AI
applications in the educational field involve knowl-
edge representation, intelligent tutoring, natural
language processing, autonomous agents etc.
The benefits of A.I. in education have been
acknowledged for many years. However, during
the previous decade’s one of the research commu-
nities of Artificial Intelligence in Education deals
with the intersection of A.I. and Special Education
[4]. The benefits of AI techniques have been gradu-
ally used to improve the life of those people with
special educational needs.
The field of ‘Special Educational Needs’ covers a
large number of difficulties which can cause pro-
blems during the learning process. Even though
various terms of special educational needs have
been presented during the past years, experts in
this field have not yet completely reach an agree-
ment. Terms like ‘Learning Difficulties’ or ‘Learn-
ing Disabilities’ are also widely used [5]. Our scoping
study drew upon the various national and interna-
tional publications and we decided to use the defini-
tion of the 2001 Special Educational Needs Code of
Practice, as a framework for organizing the litera-
ture under a manageable number of headings.
According to the 2001 SEN Code of Practice the
areas of needs are: Communication and Interaction,
Cognition and Learning, Behavior and Emotional
and Social Development, Sensory and/or Physical
[6]. Moreover, the Code of Practice highlights the
fact that not all children will progress at the same
rate and that each child is an individual, with
different strengths and needs. It is then necessary
to understand and model learners and the settings
where they interact in a way that enable us to
develop and evaluate technology to most efficiently
support learning across multiple contexts, subjects
and time [7].
Recent development in the area of Artificial
Intelligence and Special Education may enable
development of collaborative interactive environ-
ments and facilitate the life of individuals with
special educational needs and the people around
them. Our goal in this paper is to explore the
* Accepted 27 July 2012.1366
International Journal of Engineering Education Vol. 28, No. 6, pp. 1366–1372, 2012 0949-149X/91 $3.00+0.00
Printed in Great Britain # 2012 TEMPUS Publications.
potential of the most representative of AI applica-
tions of the last decade. The studies that will be
presented in the following sections deal with diag-
nostic and intervention tools of some of the most
common learning difficulties. These proposed
models can be used from teachers, special educa-
tors, psychologists, therapists and parents as well.
Due to the implicit characteristics of learning diffi-
culties, their high similarities and comorbidity of
their symptoms, AI assessment tools may be one
way to improve the teacher or parent capabilities
when evaluating the child. These tools can help
them observe the child’s academic level and if
necessary they will consider taking appropriate
decisions to advise a specialist if there is any
difficulty. AI training interventions are an impor-
tant part of the education of children of special
educational needs since they are able to integrate the
freedom of action of the student with a more explicit
control and guide [8]. This paper will introduce
diagnostic and intervention tools developed in the
last decade for every one of the following categories
2. Sensory and/or physical impairments
Learners with long-term or more complex physical
impairments require educational services that will
help them to maintain their independence and well-
being, and to lead as fulfilling a life as possible. In
most cases physical and sensory impairments are
assessed from doctors during the first years of their
lives. This is why AI applications concerning par-
ents and teachers mostly aim at training students
rather than diagnosing their needs.
Georgopoulos et al., 2003 presented a fuzzy
cognitive map approach for differential diagnosis
of specific language impairment (SLI). Fuzzy cog-
nitive maps are a soft computing methodology that
uses a symbolic representation for the description
and modeling of complex systems. The aim of this
tool is to provide the specialists with a differential
diagnosis of SLI from dyslexia and autism, since in
many cases SLI is difficult to be discerned due to its
similar symptoms to other disorders. The system
has been tested on four clinical cases with promising
results [9].
In the same year Schipor et al., (2003) attempted
to create a Computer Based Speech Therapy
(CBST) system using a fuzzy expert system for
helping learners with speech disorders. The aim of
this approach was to suggest optimal therapeutic
actions for every pupil based on the information
selected, so they designed an improved CBST
system, called LOGOMON (Logopedics Monitor)
and developed its classical architecture with a fuzzy
expert system based on forward chaining. The role
of the expert system was to store the precise evolu-
tion and progress of each child and adapt the
exercises to each child’s current level and progress.
The validation of LOGOMON was performed by a
three month experiment which involved two equiva-
lent children groups, taken from the Regional
Speech Therapy Center of Suceava in Romania.
The first group used LOGOMON, but the expert
system was deactivated and all therapeutically deci-
sions were taken only by the speech therapist. The
second group used LOGOMON with inference
facilities, so that, a part of therapeutically decisions
was provided by expert system and the other one
was provided by speech therapist . The results indi-
cated no significant difference between the two
groups. However, there were other advantages
using the expert system such as more therapy time,
predictability and the explanation of results [10].
Pavlopoulos et al., (2008) implemented a neural
network approach for the self-assessment for the
learners, optimized with the aid of Genetic Pro-
gramming. The purpose of this method is to assess
the user’s answers from both single and multiple
questions in an e-learning environment. Test data of
this application evaluate the answers against the five
areas of learning: grammar/sentence structure,
reading, writing, letter recognition and alphabetical
order, spelling/vocabulary. The implementation of
the Genetic Programming Neural Network
(GPNN) methodology for e-learning purposes is
effective for all students who exhibit difficulties in
the above areas but can be specifically appropriate
for individuals with physical or sensory impair-
ments. This platform was applied and evaluated
successfully the user’s answers, while the general-
ization of the assessment process could later lead to
the development of an intelligent e-tutor [11].
In 2008 Drigas et al., presented ‘Dedalos’ project
which deals with the teaching of the English lan-
guage as a second language to hearing impaired
people, whose mother language is the Greek sign
language. In an educational e-content adapted to
the needs of every user, the whole procedure consists
of audits and evaluation of the linguistic abilities of
the e-learners. The system uses an intelligence
taxonomy system which is developed for the evalua-
tion of the pupil and the setting of pedagogic
material. The approach promotes a complete sup-
port system for the education of hearing impaired
Greek students while at the same time opens the way
for their inclusion [12].
3. Learners with Autistic Spectrum
Disorders
Autism Spectrum Disorder (ASD) is a pervasive
developmental disorder characterized by the ‘triad’
of impairme nts. Children with ASD exhibit impair-
Artificial Intelligence in Special Education: A Decade Review 1367
ments in social skills, language and communication
skills and a tendency towards repetitive patterns of
interest and behavior [13]. AI techniques can facil-
itate early intervention and provide specialists with
robust tools indicating the person’s autism spec-
trum disorder level.
In 2006 Sebe et al., implemented an emotion
recognition computerized tool based on joint
visual and audio cues. This human-computer inter-
action application besides the 6 universal emotions
(happy, surprise, angry, disgust, fear and sad) is able
to recognize other affective states such as interest,
boredom, confusion and frustration. It can be used
from all children but it can be very affective in
children with speech problems as well as in training
children with ASD since they display difficulties
understanding other people’s emotion. This
approach analyzes 11 affective states, on 38 subjects
by applying Bayesian Networks for bimodal fusion.
In addition, a variable is integrated into a Bayesian
Network which indicates whether the user is speak-
ing or not. Once the model is fitted, head motion and
local deformations of the facial features such as the
eyebrows, eyelids, and mouth can be tracked. The
recovered motions are shown in terms of magni-
tudes of some predefined motion of various facial
characteristics. This system was tested on 38 grad-
uate and undergraduate students in various fields.
The results indicated that emotion recognition
accuracy is greatly improved when both visual and
audio information are applied in classification [14].
In 2007 Riedl et al, designed a platform which can
aid adolescents with High Functioning Autistic
Spectrum Disorders (HFASD) rehearse and learn
social skills with reduced help from parents, tea-
chers, and therapists. A social scenario game is
presented— for example going to a movie theater-
which challenges learners with HFASD to role-play
and complete tasks involving social situations.
Artificial Intelligence is used to assist the above
groups with the authoring of tailored social scenar-
ios. An A.I. system automatically examines the
causal form of the narrative plan, searching for
points at which a student’s actions can undo
causal relationships. The alternative narrative sce-
nario is a branch developed for handling the con-
tingency of the learner’s action. This Artificial
Intelligence tool embed in this particular platform
decreases the manual authoring burden where
application of intervention strategies can be
handled by specialists. This social scenario inter-
vention approach is complete and currently under-
going evaluation with promising results [15].
Arthi and Tamilarasi (2008) introduced a model
which helps in the diagnosis of autism in children by
applying Artificial Neural Networks (ANN) tech-
nique. The model converts the original autistic data
into suitable fuzzy membership values and these are
given as input to the neural network architecture.
Moreover, a pseudo algorithm is created for apply-
ing back propagation algorithm in predicting the
autistic disorder. This approach is proposed to
support apart from medical practitioners, psychol-
ogists and special educators who are involved is
assessing children. Experimental results indicated
an 85–90% accuracy of this method. In future the
autistic disorder could be predicted using k-nearest
neighbor algorithm for a comparative research [16].
4. Learners with reading, writing and
spelling difficulties
Within a classroom there is an incredible spread in
reading, writing and spelling abilities among the
pupils [17, 18]. Each and every student requires
support at their own level and for their own specific
needs. These kinds of problems tend to be diagnosed
when children reach scholar age. In most institu-
tions there are not specialist staff in learning diffi-
culties, it is then desirable that teachers have access
in some diagnostic and intervention tools to better
care of the students’ problems.
Srihari et al., (2008) presented two computational
method of automatic scoring of short handwritten
essays in reading comprehension tests. The aim of
this system is to assign to each handwritten response
a score which is comparable to that of a human
scorer. This tool has to contend with not only the
standard difficulties of recognizing handwriting but
also the writing skills of children. Assessing reading
comprehension tests will not only allow timely
feedback to students but also can provide feedback
to education researchers, parents and teachers. In
this study two systems are described. The first is
based on latent semantic analysis (LSA), which
needs a reasonable level of handwriting recognition
performance. The second developed an artificial
neural network (ANN) which is based on features
collected from the handwriting image. Both systems
were trained and evaluated using a test-bed of essays
written in response to prompts in statewide reading
comprehension tests and scored by humans. Even
though there were observed errors in word recogni-
tion during the evaluation of this platform scoring
performance still remains a promising tool [19].
Jain et al., (2009) proposed a model called Per-
ceptron based Learning Disability Detector
(PLEDDOR). It is an artificial neural network
model for identifying difficulties in reading (dys-
lexia), in writing (dysgraphia) and in mathematics
(dyscalculia) using curriculum based test conducted
by special educators. This computational diagnostic
tool consists of a single input layer with eleven units
that correspond to different sections of a conven-
Athanasios S. Drigas and Rodi-Eleni Ioannidou1368
tional test and one output unit. The system was
tested on 240 children collected from schools and
hospitals in India and was evaluated as simple and
easy to replicate in huge volumes, but provides
comparable results based on accepted detection
measures [20].
Herna
´
ndez et al., (2009) introduced SEDA (‘Sis-
tema Experto de Dificultades para el Aprendizaje’
or ‘Expert System for Learning Difficulties’ in
English) a diagnostic tool for Learning Difficulties
in children’s basic education. It is developed using
the Expert Systems design methodologies which
include a knowledge base consisting of a series of
strategies for Psycopedagogy evaluation; trying to
identify the relationships between input variables
(e.g. age, sex, educational level, reading, perception,
understanding) and the output systems (psychomo-
tor aspect, intellectual aspect, perceptual aspect,
language aspect, personal aspect). All of the above
provides the expert system’s users the possibility of
acknowledge the psychological profile of the pupil.
80% of the evaluators rated the system as Efficient
using an estimation scale of: Poor, Moderately
Efficient and Efficient [21, 22].
In 2010 Baschera and Gross introduced an adap-
tive spelling training system which can be used from
all students who exhibit spelling difficulties. This
platform is based on an inference algorithm
designed to manage unclassified input with multiple
errors defined by independent mal-rules. The infer-
ence algorithm based on a Poisson regression with a
linear link function, estimates the pupil’s difficulties
with each individual mal-rule, based on the
observed error behavior. This knowledge represen-
tation was implemented in a student model for
spelling training such as optimized word selection
and lessons for individual mal-rules to pupil
adjusted repetition of erroneously spelled words.
This system was tested on a two large-scale user
studies and showed an important increase in the
learner’s performance, induced by the student
adapted training actions [23].
5. Learners with dyslexia
Dyslexia is one of the most common and most
studied cases of Develop mental Disorders causing
troubles in literacy and especially in reading, writing
and spelling. It is neurologically based and lifelong
condition [24]. Diagnosing dyslexia is a complex
process that depends on many different indicators.
Even though applying artificial intelligence techni-
ques for identifying dyslexia can be a complex
procedure, the preliminary results of recent studies
are satisfactory and open new ways in the field of
diagnosis.
In the same year Palacios et al., presented a rule-
based classifier for the diagnosis of dyslexia with low
quality data with genetic fuzzy systems in early
childhood. It can be used by parents and school
staff for detecting those symptoms that will suggest
taking the child to a specialist for a more thorough
examination. This application consists of a fuzzy
rule based system (FRBS), whose knowledge base
is to be obtained from a sample of data by means
of a genetic cooperative-competitive algorithm
(GCCL). The FRBS includes collected data from
65 schoolchildren in Spain whose answers were
comprised to graphical tests (e.g. BENDER,
ABC) while the output variable for each dataset is
a subset of labels; no dyslexic, control and revision,
dyslexic, inattention/hyperactivity or other pro-
blems. This genetic fuzzy system can operate with
the above low quality data and provide us the
appropriate results for determining whether the
student should visit an expert. The experimental
results indicated that the FRBS from low quality
data can provide the unqualified personnel with a
diagnosis. However the percentage of misclassifica-
tions was high and future improvements need to be
made [25, 26].
Kohli et al., (2010) introduced a systematic
approach for identification of dyslexia at an early
stage by using artificial neural networks (ANN).
This approach is amongst the first attempts which
have been made for addressing the dyslexia identi-
fication problems with the use of ANN. Moreover,
it can be distinguished from other platforms of its
kind because it is based on test data, covering the
evaluation results of potential dyslexic pupils,
between the years 2003– 2007. These test data
consist of the input data of the system while the
output results classify the students in two categories
(dyslexic and non-dyslexic). An error back-propa-
gation algorithm is responsible for mapping college
performance to the underlying characteristics. The
initial results obtained using test data were fairly
accurate and suggest the application of this plat-
form to real data as well [27].
6. Learners with difficulties in mathematics
Mathematical skills are essential to all students and
they are also a subject where many students display
various difficulties. During the latest years methods
and techniques of artificial intelligence were devel-
oped to assess the mathematical level of pupils and
to also help them acquire specifics skills [28].
Melis et al., (2001) introduced ActiveMath, a
web-based intelligent tutoring system for mathe-
matics. ActiveMath is an Intelligence Tutoring
System (ITS), which allows the students to learn in
their own environment whenever it is convenient for
them. It uses a number of Artificial Intelligence
Artificial Intelligence in Special Education: A Decade Review 1369
techniques to realize adaptive course generation,
student modeling, feedback, interactive exercises
and a knowledge representation which is appropri-
ate for the semantic Web. In ActiveMath the user
starts his/her own student model by self-assessment
of his/her mastering level of concepts and later
chooses learning goals and scenario, for instance,
the preparation for an exam. The capabilities of the
student are adapted in course generation and in the
suggestion mechanism as well. Moreover, a ‘poor
man’s eye-tracker’ is designed which is able to trace
child’s attention and reading time in detail. This
application has reported many positive outcomes in
the following years by a large number of studies, all
of them supporting the effect of this ITS during the
learning process [29–31].
Livne et al., (2007) implemented an online parsing
system that automatically assesses students’ con-
structed responses to mathematics questions, based
on the errors in each response. A parser is the basic
element of a free college readiness website in mathe-
matics. During learning sessions, users are asked to
provide constructed answers to mathematical ques-
tions. The parser analyzes the students’ answers,
gives immediate feedback on their errors and pro-
vides accurate partial-credit scoring as well. This
tool apart from providing a good match to human
grader scoring, it reflects the overall response and it
also distinguishes the types of errors into two types:
conceptual and computational. The parser clearly
illustrates that natural languages and artificial intel-
ligence principles can be applied successfully to
detect student error patterns. Overall, the system’s
total scoring closely matched human scoring, but
the parser was found to surpass humans in system-
atically distinguishing between students’ error pat-
terns [32].
Anthony et al., (2008) designed an Intelligent
Tutoring System (ITS) for students learning algebra
equation-solving. Algebra is one of the subjects in
which students display several difficulties. This plat-
form aims at improving student performance via
ITSs that accept natural handwriting input. The
type of ITS used in this method is known as
‘Cognitive Tutors’, who pose authentic problems
to students and give emphasis to learn-by-doing. In
Cognitive Tutor Algebra, students represent a given
scenario, graph functions and solve equation while
the tutor provides help and feedback. A Freehand
Formula Entry System recognizer is also used,
which has been trained from data derived from
over 40 high school and middle school algebra
students. Results from this study showed benefits
for general usability and for learning. In addition,
this platform is likely to generalize to other types of
mathematics and to other levels of learners [33].
Gonzalez et al, (2010) designed an automatic
platform for the detection and analysis of errors in
mathematical problems to support the personalized
feedback of pupils. This method is referred to all
students and particularly to students with special
educational needs such as those with Down syn-
drome, who exhibit difficulties in the arithmetic
operations of addition and subtraction. An error
detection algorithm was developed which is able to
analyze the data gathered as a result of the interac-
tion between the students and the platform, while
afterwards the output of the error is available to the
teachers about the specific difficulties and to allow
them to personalize the instruction. Moreover, they
designed a model which returns the set of errors
made by the pupils in the corrected exercises so as
the students can learn from their own mistakes. The
system was tested on a group of students with Down
syndrome and the results confirm that the module
exhibits the proper behavior [34].
7. Attention Deficit Hyperactivity
Disorder (ADHD) and Attention Deficit
Disorder (ADD) learners
The terms ADHD and ADD refer to a wide range of
difficulties that become apparent at some stage
during the developmental period in a child’s life.
They are usually characterized by a set of behavior
problems of inattention, hyperactivity and impul-
sivity or their combination. These problems usually
show up in early childhood and more specifically
they should be present before the age of seven in
order for a diagnosis to be made [35, 36]. The use of
artificial intelligence applications has offered some
improved diagnostic and intervention tools of these
behavior difficulties.
In 2004 Rebolledo-Mendez and Freitas presented
the NeuroSky MindSet (MS) which is able to detect
attention levels in an assessment exercise by com-
bining performance data with user-generated data,
taken from interaction. NeuroSky consists of a
headset with three electrodes, which are put beneath
the ears and on the forehead. The electrical signals
read at the above locations are used as inputs by
NeuroSky’s algorithms to assess the attention
levels. An A.I. driven avatar was also designed to
pose questions and have limited conversation with
the users. It is a low-cost, non-clinical and easy to
use tool designed for leisure. This model was tested
on first-year undergraduate students in the follow-
ing years and the results indicated that there is a
positive relation between measured and self-
reported levels of attention [37, 38].
Aguilar et al., (2006) designed a fuzzy instruc-
tional planner, which models the tutor module in an
intelligent tutorial system (ITS). It is an interactive
instructional method which uses a combination of
Athanasios S. Drigas and Rodi-Eleni Ioannidou1370
text, graphics, sound and video in the learning
procedure. It is especially useful for students who
have with ADHD or attention difficulties as well as
in distance learning situations. The fuzzy instruc-
tional planner consists of a rule base, an inference, a
fuzzification interface and a defuzzification inter-
face. The aim of this system is to mimic the behavior
of the teacher able to manage learning process
satisfactorily. The input information is derived
from human expert who supplied linguistic infor-
mation. The ITS is a flexible system which adapts
the teacher’s rules to the student’s performance and
it has been shown useful in several applications with
promising results [39].
Anuradha et al., (2010) developed a platform for
a more accurate and less time consuming diagnosis
of Attention Deficit Hyperactivity Disorder
(ADHD). They used one well-known Artificial
Intelligence technique, the SVM algorithm. Accord-
ing to the authors, this is the first attempt at
identifying ADHD using SVM algorithm. Support
vector machines (SVMs) are a set supervised learn-
ing techniques suitable for classification and regres-
sion. A data-set which was verified by a doctor
including the results of a questionnaire used by the
doctors to diagnose the disorder was given to the
SVM module. After that the data-set was intro-
duced and afterwards returned to the SVM module,
which finally provides us with the diagnosis. The
most important advantage of applying the SVM
algorithm is that it can control the complexity of the
diagnostic process. This method was tested on
children between the ages six to eleven years old
and the results indicated a percentage of 88,674%
success in diagnosing [40].
In the same year Delavarian et al., (2010) intro-
duced a decision support system to distinguish
children with ADHD from other similar children
behavioral disorders such as depression, anxiety,
comorbid depression and anxiety and conduct dis-
order based on the signs and symptoms. A differ-
ential diagnosis of the above mentioned behavioral
disorders is of major importance and practically
difficult due to their similarities and comorbidity of
their symptoms. This tool was initially developed in
assisting psychiatrists but it can also be used in
schools for a more specific examination of high-
risk students. For designing the decision support
system two types of neural networks were com-
pared: radial basis function (RBF) and multilayer
perceptron (MLP) neural networks. The system was
trained and validated to assist the diagnosis of the
disorders. The system was tested on 294 children of
12 elementary schools. The classification by MLP
networks achieved 95.50% while the RBF classifier
reached 96.62%. The limited number of diagnostic
errors compared to the errors done by specialists
indicated a system that can work as a reliable and
valid tool for ADHD assessment [41].
8. Conclusions
During the last decade an important number of
studies are currently addressing the use of Artificial
Intelligence systems in the education of students
with special educational needs. This paper drew
upon the most representative studies that try to
solve major issues in diagnosis and intervention of
specific difficulties. AI application tools have suc-
cessfully been applied to solve problems in the field
of special education. Based on the studies presented
in this work, it was concluded that there is a need to
support teachers, parents and therapists in the
appropriate care to students with special educa-
tional needs, particularly in assessment and treat-
ment methods. Saving time and cost, gaining more
therapy time, increasing the early diagnosis and
intervention efficiency by creating more efficient
learning environments are some major advantages
that AI computational tools offers us. However, the
issues to be covered in special education are still
plenty due to the wide range of difficulties and the
various needs of every individual. Further research
across all types of learning difficulties and nationally
regulated adaptations of diagnostic tools have to be
resolved in order to relieve teachers and parents
workload. Nevertheless, artificial intelligence has
been considered as a promising educational aiding
tool for all children who call for an embracing and
cooperative approach to service delivery.
References
1. L. Nanni and A. Lumini, Ensemble generation and feature
selection for the identification of students with learning
disabilities, Expert Systems with Applications, 36, 2008, pp.
3896–3900.
2. B. G. Buchanan, A very brief history of artificial intelligence,
Artificial Intelligence Magazine, 25th anniversary issue, 2005,
pp. 53–60.
3. S. J. Russell and P. Norvig, Artificial Intelligence: A Modern
Approach (2nd ed.), New Jersey, 2003.
4. T. K. Wu, Y. R. Meng and S. C. Huang, Application of
Artificial Neural Network to the Identification of Students
with Learning Disabilities, International Conference on Arti-
ficial Intelligence, 2006, pp. 162–168.
5. J. M. Fletcher, W. Coulter, D. J. Reschly and S. Vaughn,
Alternative approach to the definition and identification of
learning disabilities: some questions and answers, Annals of
dyslexia, 54(2), 2004, pp. 304–331.
6. Department for Education and Skills, Special Educational
Needs Code of Practice, London: DfES, 2001.
7. J. Brodin, Can ICT give children with disabilities equal
opportunities in school? Improving Schools, 13(1), 2010,
pp. 99–112.
8. R. Lanzilotti and T. Roselli, An Experimental Evaluation of
Logiocando, an Intelligent Tutoring Hypermedia System,
International Journal of Artificial Intelligence in Education,
17, 2007, pp. 41–56.
9. V. C. Georgopoulos, G. A. Malandraki, C. D. Stylios, A
fuzzy cognitive map approach to differential diagnosis of
Artificial Intelligence in Special Education: A Decade Review 1371
specific language impairment. Artificial Intelligence in Med-
icine, 29, 2003, pp. 261–278.
10. O. A. Schipor, S. G. Pentiuc and M. D. Schipor, Improving
computer based speech therapy using a fuzzy expert system.
Computing and Informatics, 22, 2003, pp. 1001–1016.
11. J. Pavlopoulos, J. Vrettaros, G. Vouros and A. S. Drigas, The
Development of a Self-assessment System for the Learners
Answers withthe Use of GPNN. WSKS, (1), 2008, pp. 332–340.
12. A. S. Drigas, D. Kouremenos and J. Vrettaros, Teaching of
English to Hearing Impaired Individuals Whose Mother
Language is the Sigh Language. In: M. D. Lytras et al.
(eds), 2008, pp. 263–270.
13. I. Rapin and R. F. Tuchman, Autism: Definition, neurobiol-
ogy, screening, diagnosis. Pediatric Clinics of North America,
55(5), 2008, pp. 1129–1146.
14. N. Sebe, I. Cohen, T. Gevers and T. S. Huang, Emotion
Recognition Based on Joint Visual and Audio Cues, Proceed-
ings of the 18th International Conference on Pattern Recog-
nition, 2006.
15. M. Riedl, R. Arriaga, F. Boujarwah, H. Hong, J. Isbell and
L. J. Heflin, Graphical Social Scenarios: Toward Interven-
tion and Authoring for Adolescents with High Functioning
Autism, Virtual Healthcare Interaction, Papers from the
AAAI Fall Symposium, 2007.
16. K. Arthi and A. Tamilarasi, Prediction of autistic disorder
using neuro fuzzy system by applying ANN technique,
International Journal of Developmental Neuroscience, 26,
2008, pp. 699–704.
17. B. M. Macmillan, Rhyme and reading: A critical review of
the research methodology, Journal of Research in Reading,
25(1), 2002, pp. 4–42.
18. L. Roberts and S. McDougall, Explaining Performance in
the Orthographic Analogy Task: Phonological Priming,
Phonological Skills and Letter-sound Knowledge. Journal
of Experimental Child Psychology, 84(4), 2003, pp. 310–337.
19. S. Srihari, J. Collins, R. Srihari, H. Srinivasan, S. Shetty and
J. Brutt-Griffler, Automated scoring of handwritten essays in
reading comprehension tests, Artificial Intelligence, 172,
2008, pp. 300–324.
20. K. Jain, P. Manghirmalani, J. Dongardive and S. Abraham,
Computational Diagnosis of Learning Disability, Interna-
tional Journal of Recent Trends in Engineering, 2(3), 2009.
21. J. Hernadez, G. Mousalli and F. Rivas, Expert System for the
Diagnosis of Learning Difficulties in Children’s Basic Educa-
tion, Proceedings of the 8th WSEAS International Confer-
ence on Applied Computer and Applied Computational
Science, Italy, 2008.
22. J. Hernadez, G. Mousalli and F. Rivas, Learning Difficulties
Diagnosis for Children’s Basic Education using Expert
Systems. WSEAS Transactions on Information Science and
Applications, 7(6), 2009.
23. G. M. Baschera and M. Gross, Poisson-Based Inference for
Perturbation Models in Adaptive Spelling Training. Inter-
national Journal of Artificial Intelligence in Education, 20,
2010, pp. 1–31.
24. P. Thomson and P. Gilchrist, Dyslexia: A Multidisciplinary
Approach, Nelson Thornes, 1996.
25. A. M. Palacios, L. Sanchez and I. Couso, Extending a simple
genetic cooperative-competitive learning fuzzy classifier to
low quality datasets, Evolutionary Intelligence, 2(1), 2009, pp.
73–90.
26. A. M. Palacios, L. Sanchez and I. Couso, Diagnosis of
dyslexia with low quality data with genetic fuzzy systems.
International Journal of Approximate Reasoning, 51, 2010,
pp. 993–1009.
27. M. Kohli and T. V. Prasad, Identifying Dyslexic Students by
Using Artificial Neural Networks, Proceedings of the World
Congress on Engineering, London, U.K., 1, 2010.
28. R. Abbott, Automated expert modeling for automated
student evaluation. In Intelligent tutoring systems, eighth
international conference, ITS 2006, Jhongli, Taiwan, June
26–30, 2006, proceedings, pp. 1–10. Lecture Notes in Com-
puter Science 4053, Springer.
29. E. Melis, E. Andres, J. Budenbender, A. Frischauf, G.
Goguadze, P. Libbrecht, M. Pollet and C. Ullrich, ACTI-
VEMATH, A Generic and Adaptive Web-Based Learning
Environment, International Journal of Artificial Intelligence,
24(4), 2001, pp. 1–25.
30. E. Melis and J. Siekmann, ActiveMath: An intelligent
tutoring system for mathematics. In L. Rutkowski, J. Siek-
mann, R. Tadeusiewicz, & L. A. Zadeh (Eds.), Seventh
international conference artificial intelligence and soft com-
puting (ICAISC), pp. 91–101. Springer-Verlag, 2004.
31. P. Libbrecht and E. Melis, Methods to Access and Retrieve
Mathematical Content in ActiveMath. Lecture Notes in
Computer Science, 2006, 4151, pp. 331–342.
32. N. Livne, L. Nava, O. Livne and C. Wight, Can automated
scoring surpass hand grading of students’ constructed
responses and error patterns in mathematics? MERLOT
Journal of Online Learning and Teaching, 3(3), 2007.
33. L. Anthony, J. Yang and K. R. Koedinger, Toward Next-
Generation Intelligent Tutors: Adding Natural Handwriting
Input, IEEE Multimedia, 15(3), 2008, pp. 64–68.
34. C. S. Gonzalez, D. Guerra, H. Sanabria, L. Moreno, M. A.
Noda and A. Bruno, Automatic system for the detection and
analysis of errors to support the personalized feedback.
Expert Systems with Applications, 37, 2010, pp. 140–148.
35. World Health Organisation, International Classification of
Diseases, Tenth Revision (ICD-10). Chapter V: Mental and
Behavioural Disorders. Geneva: World Health Organisa-
tion, 1993.
36. American Psychiatric Association, Diagnostic and Statistical
Manual of Mental Disorders (DSM 4th edn), Washington,
DC: APA, 1994.
37. G. Rebolledo-Mendez and S. De Freitas, Attention model-
ing using inputs from a Brain Computer Interface and user-
generated data in Second Life. In: The Tenth International
Conference on Multimodal Interfaces (ICMI 2008), Crete,
Greece, 2008.
38. G. Rebolledo-Mendez, I. Dunwell, E. A. Martı
´
nez-Miro
´
n,
M. D. Vargas-Cerda
´
n, S. de Freitas, F. Liarokapis, A. R.
Garcı
´
a-Gaona, Assessing Neurosky’s Usability to Detect
Attention Levels in an Assessment Exercise, Human Compu-
ter Interaction, 5610(1), 2009, pp. 149–158.
39. R. M. Aguilar, V. Munoz, M. Noda, A. Bruno, L. Moreno,
Teacher Strategies Simulation by Using Fuzzy Systems,
Computer Applications in Engineering Education, 18(1),
2010, pp. 183–192.
40. J. Anuradha, Tisha, V, Ramachandran, K. V. Arulalan, B.
K. Tripathy, Diagnosis of ADHD using SVM algorithm, In
Proceedings of the Third Annual ACM Bangalore Confer-
ence, 2010.
41. M. Delavarian, F. Towhidkhah, P. Dibajnia, S. Gharibza-
deh, Designing a decision support system for distinguishing
ADHD from similar children behavioral disorders. Journal
of Medical Systems, 2010 [Epub ahead of print].
Athanasios Drigas is a Senior Researcher at N.C.S.R. Demokritos. He is the Coordinator of Telecoms Lab and founder of
Net Media Lab since 1996. From 1985 to 1999 he was the Operational manager of the Greek Academic network. He has
been the Coordinator of Several International Projects, in the fields of ICTs, and e-services (e-learning, e-psychology,
e-government, e-inclusion, e-culture etc). He has published more than 200 articles, 7 books, 25 educational CD-ROMs and
several patents. He has been a member of several International committees for the design and coordination of Network and
ICT activities and of international conferences and journals.
Rodi-Eleni Ioannidou is a special education teacher. She has participated in various research projects regarding the use of
Information and Communication Technologies (ICTs) in special education.
Athanasios S. Drigas and Rodi-Eleni Ioannidou1372
... The incorporation of digital technologies in various aspects of education domain including mental training and breathing training is very productive, successful and facilitates and improves the educational procedures via Mobiles [88][89][90][91][92][93][94][95][96][97], various ICTs applications , AI & STEM [131][132][133][134][135][136][137][138][139][140][141], and games [142][143][144][145][146][147]. Additionally, the combination of ICTs with theories and models of metacognition, mindfulness, meditation, and emotional intelligence cultivation as well as with environmental factors and nutrition [84][85][86][87], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
The purpose of the current review study is to shed light on the relationship between breathing and learning disabilities, to investigate the efficacy of breathwork as an intervention strategy, and finally, to identify the role of assistive technologies in breathing training interventions. The results of this study revealed a close relationship between breathing problems and learning, mental or/and behavioral disorders. In addition, it was found that breath-control training can help people with various disorders to improve cognitive and metacognitive abilities, to better manage emotional and behavioral problems, and achieve better learning outcomes. Technologies such as robots, virtual reality, mobile apps, and digital games were found to assist breathing training in various ways fostering therapeutic outcomes. We conclude that breathing training should constitute not just an alternative method of intervention but an essential practice for prevention and intervention in daily life, in school settings, at home, and workplace. It is essential to train appropriate breathing habits as early as possible in young children because many of the damaging effects on cognitive functions by disordered breathing can have lasting consequences.� v
... The incorporation of digital technologies in education domain is very productive, successful and facilitates and improves the educational procedures via Mobiles [58][59][60][61][62][63][64][65][66][67][68], various ICTs applications , AI & STEM [113][114][115][116][117][118][119][120][121][122][123][124][125][126][127][128][129], and games [130][131][132][133][134][135]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation as well as with environmental factors and nutrition [54][55][56][57], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
Educators define three factors of interaction or as they refer to the 3 C's in education: Children (children), Community (communication), and Computer (computers) [1]. Information and Communication Technologies are an integral tool of the educational process for modern educational systems, helping the learning process to turn from passive to active, pushing each student to learn independence and autonomy. In recent years, the sciences of education have turned their attention and have already recognized the importance of games and even digital games as a learning tool, emphasizing the benefits for students with or without educational needs.
... The incorporation of digital technologies in education domain is very productive, successful, facilitates and improves the educational procedures via Mobiles [32][33][34][35][36][37][38][39][40][41], various ICTs applications , AI & STEM [75][76][77][78][79][80][81][82][83][84][85], and games [86][87][88][89][90][91]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation as well as with environmental factors and nutrition [28][29][30][31], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
In recent years worldwide, the use of Information and Communication Technologies (ICT) contributes significantly to the learning process, especially for students with special needs, arguing that a special aspect of ICT in the digital game, as it can be a part from a means of entertainment and personal satisfaction of each student, an excellent tool for their education. Also, Research from the National Coalition for Parent Involvement in Education shares that "no matter their income or background, students with involved parents are more likely to have higher grades and test scores, attend school regularly, have better social skills, show improved behavior and adapt well to school.”, especially in the specialty of people with autism. In the work that follows, parents' views on educating their children with ASD using a digital game are recorded.
... Studying the above results shows that the key to observation by recording the behavior of the students towards the teacher and himself but also the manifestation of his emotions, conclusions are drawn and information is recorded that together with other data collection tools will help the teacher or the researcher to design an A student's individualized education program to train him/her in deficit areas or behaviours. Moreover the combination of the above with digital technologies in education domain, could be very productive, successful and facilitates and improves the educational procedures via Mobiles [16][17][18][19][20][21][22][23][24][25], various ICTs applications , AI & STEM [67][68][69][70][71][72][73][74][75][76][77][78][79][80][81], and games [82][83][84][85][86][87][88]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation as well as with environmental factors and nutrition [12][13][14][15], accelerates and improves more over the educational practices, results and the design of personalized educational procedures. ...
Article
Full-text available
Children on the autism spectrum present significant difficulties in recognizing, understanding, and expressing emotions and, consequently, in their socialization. The teachers, to create a personalized education program for the students, record, through direct or systematic observation, important information regarding the manifestation of these emotions. KEY is also a recording tool OBSERVATION BEHAVIOR DEVELOPMENT DISORDERS: Key observation behavioral developmental disorders: Cohen, Stem, & Balaban (1995) (trans. D. Evangelou, ed. S. Bosniadou) in the field of emotion expression. In this paper, the observation key was administered to teachers teaching students with ASD, completed, its results are analyzed and conclusions are drawn
... The incorporation of digital technologies in education domain is very productive, successful, facilitates and improves the educational procedures via Mobiles [46][47][48][49][50][51][52][53][54][55], various ICTs applications , AI & STEM [97][98][99][100][101][102][103][104][105][106][107][108][109][110][111], and games [112][113][114][115][116][117][118]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation as well as with environmental factors and nutrition [42][43][44][45], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
Down syndrome is considered to be one of the most prevalent genetic causes of intellectual disability, derived from chromosomal disorder, which accounts for dysfunctions in many organs and has a characteristic phenotype, which consists of physical and behavioral features. Many studies have shown that language is one of the most impaired areas of function in Down syndrome and perhaps, the highest barrier for their substantial inclusion into formal education and community. The aim of this paper is to investigate the specific features of this linguistic phenotype, presenting the strengths and weaknesses of their language, as well as the factors that contribute to their formation, compared to normally developing children. In addition, it scopes to highlight the role of educational mobile apps, as innovative and interactive tools for the developmental learning of Down syndrome children. The results of the research indicate that their language goes through the same, with typical development sequences, but progressively erases a slowing trajectory and results in lower performance. However, the use of mobile apps can significantly improve their cognitive functioning, in order to acquire academic and social skills that will ensure them an independent and quality life.
... The role of mobile Applications in ADHD The of digital technologies in education domain is very productive, successful, facilitates and improves the educational procedures via Mobiles [55][56][57][58][59][60][61][62][63], various ICTs applications , AI & STEM [99][100][101][102][103][104][105][106][107][108][109][110][111], and games [112][113][114][115][116][117]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation [118][119][120][121][122][123][124][125][126][127][128][129][130][131] as well as with environmental factors and nutrition [52][53][54], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
Proper nutrition and physical activity over time are alternative interventions for children with ADHD and are recognized in many European countries. Can be applied as an educational and therapeutic practice both in a school environment and in a therapeutic context adjunct to other forms of therapy. THE planning of these interventions aims, on the one hand, to promote its health by reducing the symptoms of ADHD (hyperactivity, behavioral problems) and on the other hand in the development of social and emotional skills such as socializing, playing, and h self-esteem. The purpose of this paper is to record research data on the implementation of diet and exercise programs in the world through a review of the literature. Specifically, many foods have been studied to help children with ADHD, some others are classified as toxic agents and various approaches to physical activity. The results showed that they do exist dietary interventions and physical activity programs that are applied in many countries with positive results in all aspects of the behavior of children with ADHD. The most common foods that help are those high in omega-3 and zinc and those that pose a risk are those that contain sugar and artificial substances. On the other hand, it was checked that they offer positively to children with ADHD approaches such as aerobic exercise and psychomotor activities. Regarding the participants in the interventions, the samples were students with neurodevelopmental disorders studied. The frequency of its application consumption of the labeled foods must be consumed consistently and daily after examinations such as o control ferritin. An aerobic program with a frequency of twice a week and psychomotor intervention once or twice a week is very helpful. In addition, gadgets are listed in this review for the proper organization and regulation of children to cover the difficulties they have, which is very important.
... Specifically, it was revealed that subliminal messages have the following positive influences: The incorporation of digital technologies in the education domain is very productive, and successful, facilitates and improves the educational procedures via Mobiles [71][72][73][74][75][76][77][78][79][80], various ICTs applications , AI & STEM [116][117][118][119][120][121][122][123][124][125][126][127][128], and games [129][130][131][132][133][134]. Additionally, the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation [135][136][137][138][139][140][141][142][143][144][145][146][147][148][149][150] as well as with environmental factors and nutrition [68][69][70], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
Traditionally, metacognition & higher mental abilities are thought to be exclusively linked to consciousness. However, a growing number of researchers support the idea that nonconscious processes may hold the keys to higher forms of intelligence. Subliminal messages expose individuals to visual or/and auditory stimuli below the threshold of conscious perception. The current review aims to explore the effectiveness of subliminal cues on fundamental aspects of metacognition such as higher cognitive and emotional meta-abilities, affective and behavioral regulation, and academic achievement. In this context, we search for and classify the existing subliminal training techniques, while evaluating the usability of ICTs such as artificial intelligence, virtual reality, mobile apps, steam and software in subliminal learning and training. The results of this review revealed that subliminal techniques improve all those aspects that assure metacognitive improvements in terms of self- & emotional regulation, higher mental abilities, and behavioral modification. Subliminal cues lower people's shields and update filtering mechanisms enabling people to focus on positive rather than negative interpretations. Subliminal techniques are under the umbrella of metacognitive strategies since they can be used consciously to increase self-regulation capacity as well as expand the horizons of consciousness. Subliminal teaching techniques can be used by teachers and parents in general and special education to instill higher-level needs & motives, accelerate students’ performance, reduce gender stereotypes and unfold students’ existing but underdeveloped abilities. Therapists can also utilize these methods to help patients with phobia, anxiety and depression to overcome fear. Subliminal techniques can be also utilized as a strategy by leaders, mentors, and employees to build trust, inspire and provide humanity with innovative ideas. ICTs provide the ideal environment for implementing subliminal training. However, more research is needed.
... The exploitation of ICTs in education domain is very productive, successful, facilitates and improves the educational procedures via Mobiles [37][38][39][40][41][42][43][44][45][46], various ICTs applications , AI & STEM [82][83][84][85][86][87][88][89][90][91][92][93][94][95], and games [96][97][98][99][100][101]. Additionally the combination of ICTs with theories and models of metacognition, mindfulness, meditation and emotional intelligence cultivation [102][103][104][105][106][107][108][109][110][111][112][113][114][115][116][117][118] as well as with environmental factors and nutrition [34][35][36], accelerates and improves more over the educational practices and results. ...
Article
Full-text available
Children on the autism spectrum have significant difficulties in recognizing, I understanding, and expressing emotions and and consequently in their socialization [1], [2] [3] [4] [5] . To assess the ability to understand emotions, the following is used: The emotion comprehension test (Test of Εmotional Comprehension, TEC ) [6] in preschool children. In the present work, the TEC was administered to students with ASD and the results of the evaluation are analyzed and conclusions are drawn. Keywords. Autism spectrum, Emotional Intelligence, TEC
Article
Full-text available
The following study examines the neuroscience of attachment and the role of mindfulness and metacognition. First, the importance of mindfulness is discussed, which is strongly found in people with attachment, particularly in twins. Next, mindfulness in people with autism is examined. More specifically, the purpose of the research is to draw conclusions about the emotional intelligence that individuals with ASD develop and the levels of mindfulness and metacognition that they are able to achieve. In the course of the study, reference is made to the factors that influence their emotional development such as stress and vortices, where its role seems to be different compared to typically developing individuals because individuals with autism follow a different developmental and cognitive trajectory. Then, topic is made to the essential role of AI( artificial intelligence), which seems contribute positively to the cognitive and emotional development of children with autism as various important technologies are used, such as specially constructed and functional robots, which contribute to both the treatment and diagnosis of autism. From the present study, it was found that all the above methods contribute to improve the cognitive level of individuals with autistic disorder and to raise them to the levels of metacognition pyramid and knowledge-cognition pyramid. Finally, the role of ICT and AI is particularly helpful in achieving this ascent
Article
Full-text available
Attention deficit hyperactivity disorder (ADHD) is a childhood neurobiological disorder that occurs in 5-7% of the student population. The purpose of this research was to design and develop a novel digital tool (serious game) for the treatment of attention difficulties in schoolchildren with ADHD. Primary school children (n=36), aged 6-12 (10.4±1.69) participated in the study. To assess the tool, the questionnaire of the Greek Rating Scale of ADHD-IV was administered to teachers and parents of the children before and after the intervention. In the ADHD-IV questionnaire assessed by teachers, the score of the experimental group (Educ8) (MeanDiff=0.71, pretest: 14.76±4.34 vs post-test:14.05±4.93) showed a greater improvement than the control group (CG) (MeanDiff=0.63, pre-test:21.18±2.63 vs post-test:20.55±5.52), p<0.05. In the ADHD-IV questionnaire assessed by parents, the score of the Educ8 group (MeanDiff=1.26, pre- test:15.53±5.90 vs post-test:14.27±5.55) showed a greater improvement than the CG (MeanDiff=1.23, pre-test:20.38±3.15 vs posttest: 19.15±5.52), p<0.05. From the answers of the teachers, but also those of parents, attention deficit of the children in the Educ8 group had a greater improvement in relation to the improvement in CG who used an online game.
Article
Full-text available
In the vast and complex world of educational work, every day it is highlighted the importance of special education in all its dimensions, with time it have been better known learning problems and the inescapable responsibility of each specialist in making accurate diagnostics and prompt remedial action. Psycopedagogy evaluation for diagnosis becomes focus of this expert system, in response to the concern of many career teachers, who for various reasons expressed difficulty when preparing assertive diagnostic describing Learning Difficulties of their students. SEDA (Expert System for Learning Difficulties or "Sistema Experto de Dificultades para el Aprendizaje" in spanish), is a software designed using the Expert Systems design methodologies, which will generate a knowledge base comprising a series of strategies for Psycopedagogy evaluation, as well as providing tools that allow the teacher to discuss psycofunctions and basic skills for learning.
Article
Full-text available
SEDA (Expert System for Learning Difficulties or "Sistema Experto de Dificultades para el Aprendizaje" in spanish), is a software designed using the Expert Systems design methodologies, which contain a knowledge base comprising a series of strategies for Psycopedagogy evaluation, as well as providing tools that allow the teacher to discuss psycofunctions and basic skills for learning. In the vast and complex world of educational work, every day it is highlighted the importance of special education in all its dimensions; across the time it have been better known learning problems and the inescapable responsibility of each specialist in making accurate diagnostics and prompt remedial action. Psycopedagogy evaluation for diagnosis becomes focus of this expert system, in response to the concern of many career teachers, who for various reasons expressed difficulty when preparing assertive diagnostic describing Learning Difficulties of their students.
Article
Full-text available
Opportunities for children with disabilities to participate in school on equal conditions as others are often stressed, while reality shows that many children with disabilities are still segregated. Information and Communication Technology (ICT) has been highlighted as a tool for communication and inclusion for children with disabilities but from research it appears that implementation of technology in children’s everyday life (e.g. in school) is difficult. The positive expectations of ICT are thus not met. This article is based on a study aimed at ascertaining whether ICT can promote inclusion of children with motor disabilities and contribute to equal opportunities in school. Focus was on parents’ views. The study was based on a questionnaire with 16 parents and interviews with the children. In this article the results of the parental questionnaire and one of the interviews with a 15-year-old pupil, Adam, is reported. Two schools where ICT and computers were used as pedagogical tools to promote inclusion were involved. Both schools had and still have the intention to be considered a school for all children. One conclusion is that there is a need for both technical and social support in school if ICT should function as a bridge for inclusion of all pupils.
Article
Full-text available
Fuzzy system technologies are of emerging interest in the specification and implementation of complex systems. This article introduces fuzzy instructional planner, which models the tutor module in a intelligent tutorial system (ITS). The behaviour of this system is defined by strategies which adapt the learning process for individual students by applying appropriate pedagogical methodologies. For this reason, the purpose of a instructional planner is to mimic the behaviour of the teacher able to control learning process satisfactorily. The knowledge acquisition is based on the reasoning carried out by the teacher in a learning process. Usually, this information is obtained from human expert who supplied linguistic information. The capacity to use linguistic information is specific to fuzzy inference systems. © 2010 Wiley Periodicals, Inc. Comput Appl Eng Educ 18: 183–192, 2010; Published online in Wiley InterScience (www.interscience.wiley.com); DOI 10.1002/cae.20128
Article
The study of errors in learning and the search for patterns to explain their causes have always been of great interest to researchers and educators alike. Mistakes are a constant in students’ solutions to mathematical problems and are inseparable from the learning process. It is essential, then, to diagnose and address the mistakes made by students so as to allow them to reflect on their errors and adjust their knowledge. To this end, we have created a system that tracks all the actions carried out by a student when solving a mathematical algorithm, not just the final results, and which is capable of diagnosing the faults and possible causes. It can also recommend the actions to be taken based on the individual difficulties encountered. In short, we have created a personalized teaching system whose features could be particularly useful for special-needs students, such as those with Down syndrome. This paper explains the error detection modules in the addition, subtraction and error-adapted assistance algorithms. This work is part of a multidisciplinary research effort financed by R&D project called “Divermates”, of the Ministry of Labor and Social Affairs, and involving personnel from the Computer Engineering and Mathematics and Fine Arts Education Departments of the University of La Laguna, as well as professionals from the Tenerife Trisomic 21 Association (ATT21).