Science 7 - LAND and SEA BREEZE and its Characteristics
A Fuzzy System for Educational Tasks for Children with Reading Disabilities
1. @boscoCP
adalbertobosco@gmail.com
Adalberto Bosco C. Pereira
Leonardo B. Marques
Dionne C. Monteiro
Gilberto Nerino de Souz
Laboratory of Applied Artificial Intelligence (LAAI) – Institute of Exact and
Natural Sciences – Federal University (UFPA)
2. Agenda
INTRODUCTION
RELATED WORK
TEACHING PROGRAM
PROPOSAL
FUZZY SYSTEM
RESULTS
CONCLUSION
FUTURE STUDIES
LAAI - UFPA
4. RELATED WORK
GEIC
The “Gerenciador de Ensino Individualizado por
Computador” (GEIC - An Individualized Education
Manager for Computers)
The tasks are subdivided into types of combinations of
stimulus such as AB, BC and CB.
LAAI - UFPA
6. TEACHING PROGRAM
“Aprendendo a Ler e a Escrever em Pequenos Passos”
(ALEPP - Learning to Read and Write in Small Steps)
Matching to Sample (MTS)
LAAI - UFPA
9. Input Variable
PTT: Probability of hit with determined Task Type.
TTT: Hit Rate of Task Type.
PNC: Probability of hit with determined number of
Comparisons.
TNC: Hit Rate of number of Comparisons.
PPI: Probability of hit with determined incorrect
word.
TPI: Hit Rate with determined Incorrect Word.
LAAI - UFPA
11. Fuzzy Inference
As an example that points to a rule set for the task type
BC: “If the Probability of the Task Type BC is Low
(pertinence 85%) and the Hit Rate of Task Type is
High (63% pertinence) then the Need for Task Type
BC is Medium (pertinence 74%)”
LAAI - UFPA
13. Fuzzy Inference
Output Variable:
DTT: Need for Task Type.
DNC: Need for number of comparisons.
DPI: Need for incorrect word.
LAAI - UFPA
14. Defuzzification
No need to defuzzify.
Decision-making
Highest degree of activation and greater degree of
pertinence
LAAI - UFPA
15. Cronograma
Descrição das Atividades
Meses (Fevereiro de 2012 a Fevereiro de 2013)
F M A M J J A S O N D J F
1. Levantamento e análise dos
requisitos para a melhor escolha da
técnica de IA para geração automática
de fases.
2. Pesquisar e definir as tecnologias
que serão utilizadas para
desenvolvimento do protótipo do jogo.
3. Propor modelagem do sistema
inteligente.
4. Desenvolvimento do protótipo do
jogo.
6. Efetuar testes com os usuários.
7. Escrita da dissertação.
8. Defesa da dissertação.
16. RESULTS
1. The simulations were performed on three groups of
students:
1. Students with Learning Deficit
2. Students with Gradual Learning
3. Students with Consolidated Learning
2. Five words analyzed about the reading abilities:
1. bolo (cake)
2. tatu (armadillo)
3. apito (whistle)
4. tomate (tomato)
5. muleta (crutch)
LAAI - UFPA
18. FUTURE STUDIES
Generate writing and readingtasks.
Refine the inference rules.
Integrating with the game. (Partly ready)
Test in the classroom with students.
LAAI - UFPA
20. Artigos publicados
“Fuzzy System for Adapted Generation of Educational Tasks
for Children with Reading Disabilities” Workshop
Combinations of Intelligent Methods and Applications
(CIMA), evento: European Conference on Artificial
Intelligence (ECAI).
"Máquina de aprendizagem como ferramenta de auxílio na
análise comportamental no ensino da leitura” aceito para
apresentação no programa XIX Ciclo de Palestras Novas
Tecnologias na Educação.
"A AIED Game to help children with learning disabilities
in literacy in the Portuguese language" for
SBGames 2012 - Trilha de Computação
LAAI - UFPA
21. REFERENCES
[1] L. Xiangfeng, W. Xiao and Z. Jun ‘Guided Game-Based Learning’, Published
by IEEE Transactions on Learning Technologies, (2010).
[2] B.du Benedict. ‘What does the “AI” in AIED buy?’ Printed and published by
IEE, Savoy Place, London WC2R 0BL, U.K., 1997.
[5] D. Dormans and B. Sander, ‘Generating Missions and Spaces for Adaptable
Play Experiences”, Published by IEEE Transactions on Computational
Intelligence AI in Games, 2011.
[6] L. B. Marques, R. G. Meio, R. M. Maria, ‘Manual do Usuário de Programas de
Ensino via GEIC’ - Volume 1: ‘Aprendendo a Ler e Escrever em Pequenos Passos’.
São Carlos, 2011.
[7] M. A. Azevedo, M. L Marques, ‘Alfabetização hoje’. São Paulo: Cortez, 2001.
[8] E. S. Sarmanho, E. B. Sales, D. M. Cavalcante, L. B. Marques, ‘Um Jogo com
Reconhecedor de Voz para o Ensino de Crianças com Dificuldade de
Aprendizagem em Leitura e Escrita’. Published by Semish, 2011.
[13] J. C. Rose, D. G. Souza, A. L. Rossito, T. M. S. Rose, ‘Aquisição de leitura após
história de fracasso escolar: equivalência de estímulos e generalização’. In:
Psicologia: Teoria e Pesquisa, p.451-69. 1989.
LAAI - UFPA
22. [15] T. S. Reis, D. G. Souza, J. C. Rose, ‘Avaliação de um programa para o ensino
de leitura e escrita’. In: Estudos em Avaliação Educacional, 20, p.425-50. 2009.
[16] C. D. Pedro, J. O. Adriano, ‘Aprendizado de Regras Nebulosas em Tempo
Real para Jogos Eletrônicos’. XI Brazilian Symposium of Multimedia Systems
and Web. Games – II Brazilian Workshop of Games and Digital Entertainment,
2003.
[17] P. B. Moratori, M. V. Pedro, L. M. B. Manhaes, C. Lima, A. J. O. Cruz, E. B.
Ferreira, and L. C. V. de Andrade. ‘Analysis of the Stability of a Fuzzy Control
System Developed to Control a Simulated Robot,’ Fuzzy Systems, 2005. The
14th IEEE International Conference on Fuzzy, pp.726-730, 25-25 May 2005.
[18] L.B. MARQUES, ‘Variáveis Motivacionais no Ensino de Leitura: O jogo
como recurso complementar’, ed. São Carlos: UFSCar, 2009.
[19] Mamdani, E.H., "Advances in the linguistic synthesis of fuzzy controllers,"
International Journal of Man-Machine Studies, Vol. 8, pp. 669-678, 1976.
[20] R. J. Timothy Fuzzy Logic with Engineering Applications, Third Edition",
ISBN: 047074376X, Wi ey, 5, 117-148, 2010.
[14] de Souza, D. G., de Rose, J. C., Faleiros, T. C., Bortoloti, R., Hanna, E. S., &
McIlvane, W. J. Teaching Generative Reading Via Recombination of Minimal
Textual Units: A Legacy of Verbal Behavior to Children in Brazil. Revista
Internacional De Psicologia Y Terapia Psicologica - International Journal of
Psychology and Psychological Therapy, 9(1), pp 19–44, 2009.
23. @boscoCP
adalbertobosco@gmail.com
Adalberto Bosco C. Pereira
Leonardo B. Marques
Dionne C. Monteiro
Gilberto Nerino de Souz
Laboratory of Applied Artificial Intelligence (LAAI) – Institute of Exact and
Natural Sciences – Federal University (UFPA)
Editor's Notes
Hello, my name is Adalberto Bosco, I am here to introduce to you my latest work in development on my masters degree, which focuses on Generation of Learning Tasks Adapted for children who had reading disabilities Using Fuzzy System.
I will follow this schedule(agenda) to present to you our work.
Well, as the title suggests, the work treats from generations of teaching tasks, to implement these tasks, was defined in the project that we embark on a digital game, because the games are an excellent tool for many areas, for his playful character and motivating. We have increasingly in-depth studies in the so called Game-Based Learning that uses games to different types of teachings.
And based on the studies, the objective of the work I am presenting is directly linked to AIED Artificial Intelligence in Education.
We can see here on this figure the general functioning of the system under development. There are two systems, the Machine Learning which will be responsible for collecting and evaluating data of the student during the gameplay, after that the data will be passed to the fuzzy system so that it can generate a adapted task, this task will be converted to a level game and the cycle is repeated until the student has learned all the words in game.
In related work we have these two as the basis of the project, because the GEIC is a Computer Individualized Education Manager, is a computational teaching program system called ALEPP, for reading and writing, that will be better explained in following slides. The ALEPP studies is focused in adapted and individualized teaching for students at approximately 20 years. Although computerized, the GEIC strongly need of the aid from specialist, because it is they who will evaluate the student and decide their future tasks. Its automation is almost null.
The GEIC, As has been said, is a computerized form of ALEPP. Here we can see how the tasks are, MTS, that students must solve to be evaluated and taught reading and writing.
They are relations that are taught between the dictated words (A), representative figure of this word (B) and the printed word (C). The tasks that establish these relations are listed as tasks of type AB (dictated word-picture), CB (printed word-picture) and BC (picture-printed word).
The ALE-RPG is a gamification of the GEIC, but contains the same problems of the GEIC.
We can see here the ALE-RPG runing. In the first figure the child playing. In the second the student running a teaching task BC, and the last, a student walking by scenary of the game.
Azevedo in [7] discusses methods of teaching which, although of satisfactory standard, still present different efficiency levels for each student. This is discussed in examining the computational and educational resources and their degree of adaptability to the individual needs of each student.
Studies in the field of AIED [2] by B.du Benedict, state that the individualization of teaching instruction can be effective and is regarded by the author as the “Holy Grail of AIED”. This paper compares the educational differences in AI systems (AIED) with conventional educational systems used in the classroom or traditional methods of Computer-Assisted Instruction (CAI).
How mention earlier, our system is based on ALLEP, Learning to Read and Write in Small Steps, that uses the relationship between stimuli in tasks, Matching to Sample (MTS). This teaching program has been developed and refined over 20 years. The ALEPP aims a process of individualized teaching, in other words each child has its own education program, according to their difficulties and needs.
We can see here in more detail the proposal, This is the diagram of the project. The game begins, a set of tasks is run by following a logical order of words to be taught, after this pretest, the ML will do the evaluation of the student, These evaluation data will go to the fuzzy system, 5 which will generate the adapted task, then be transformed into a level of the game, the stages will only stop being generated when the ML decides that the student is already literate in each of the words registered in the system. and then the game is over.
Explicar aqui o que foi feito.
It is concluded that the project is viable, with positive results encouraging us to continue expanding the research to enable the game to teaching writing and seeking improvements for it.
Today it works for reading and writing, well as in the inference rules we have modifications and others that have been added. For future studies we intend to make the final adjustments in the game and test them in the classroom with students.
Here is a picture of the prototype of our game.
We can see here the references of the work.
So long, and thanks for all the fish!
Doubts? Questions?