In this dissertation, several approaches I have taken to build upon the student learning model are described. There are two focuses of this dissertation. The first focus is on improving the accuracy with which future student knowledge and performance can be predicted by individualizing the model to each student. The second focus is to predict how different educational content and tutorial strategies will influence student learning. The two focuses are complimentary but are approached from slightly different directions. I have found that Bayesian Networks, based on belief propagation, are strong at achieving the goals of both focuses. In prediction, they excel at capturing the temporal nature of data produced where student knowledge is changing over time. This concept of state change over time is very difficult to capture with classical machine learning approaches. Interpretability is also hard to come by with classical machine learning approaches; however, it is one of the strengths of Bayesian models and aids in studying the direct influence of various factors on learning. The domain in which these models are being studied is the domain of computer tutoring systems, software which uses artificial intelligence to enhance computer based tutorial instruction. These systems are growing in relevance. At their best they have been shown to achieve the same educational gain as one on one human interaction. Computer tutors have also received the attention of White House, which mentioned an tutoring platform called ASSISTments in its National Educational Technology Plan. With the fast paced adoption of these data driven systems it is important to learn how to improve the educational effectiveness of these systems by making sense of the data that is being generated from them. The studies in this proposal use data from these educational systems which primarily teach topics of Geometry and Algebra but can be applied to any domain with clearly defined sub-skills and dichotomous student response data. One of the intended impacts of this work is for these knowledge modeling contributions to facilitate the move towards computer adaptive learning in much the same way that Item Response Theory models facilitated the move towards computer adaptive testing.

Submitted by Maicon Juliano Schmidt (maicons) on 2015-06-09T17:46:58Z No. of bitstreams: 1 Henrique Manfron Seffrin_.pdf: 4996070 bytes, checksum: facf64690edf2c78dfd329c9ec67d18c (MD5) / Made available in DSpace on 2015-06-09T17:46:58Z (GMT). No. of bitstreams: 1 Henrique Manfron Seffrin_.pdf: 4996070 bytes, checksum: facf64690edf2c78dfd329c9ec67d18c (MD5) Previous issue date: 2015-02-20 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / CNPQ – Conselho Nacional de Desenvolvimento Científico e Tecnológico / Pesquisas têm mostrado que os alunos apresentam ganhos mais significativos de aprendizagem através do ensino individualizado, pois o professor pode se focar nas dificuldades de cada um. Por ser uma estratégia de custo elevado, os Sistemas Tutores Inteligentes (STI) oferecem uma alternativa mais viável. Esses sistemas, através de técnicas de Inteligência Artificial, são capazes de se adaptar às características de cada aluno, provendo assistência individualizada. Esta adaptação personalizada é fornecida pelo componente Modelo de Aluno, que é capaz de avaliar e mapear o conhecimento de cada estudante. Na literatura, são encontrados diversos trabalhos que lidam com a questão de avaliação de conhecimento do aluno, dentre os quais encontram-se alguns trabalhos relacionados ao domínio de álgebra. Estes trabalhos, geralmente, apresentam modelagens com redes Bayesianas, que são estruturas probabilísticas amplamente utilizadas por apresentarem resultados muito interessantes no que se refere à avaliação do conhecimento dos estudantes. No entanto, nestes trabalhos, estas estruturas relacionam apenas os conceitos algébricos, ou modelam relações entre operações algébricas, com suas principais propriedades e falsas concepções. Esses trabalhos não buscam definir as relações entre os conceitos algébricos e as respectivas operações, e como os primeiros podem estar interferindo, positivo ou negativamente, na aprendizagem dos segundos. Por exemplo, na álgebra, há conceitos chave, como incógnita e a igualdade entre os lados da equação, que interferem diretamente na compreensão de certas operações algébricas. Se um estudante não os compreende, dificilmente ele será capaz de aplicar corretamente as operações relacionadas em todas as situações. Desse modo, é desejável que os modelos de inferência sejam capazes de identificar se o estudante compreende tais conceitos. Além disso, outra limitação dos trabalhos relacionados de modelos de alunos voltados para a álgebra se refere a como eles tratam as evidências. Como estes trabalhos utilizam os itens de avaliação para isto, a cada novo exercício, é necessário inserir um novo nodo na rede, e estabelecer as relações com cada conceito abordado por este item. Isso torna o projeto da rede trabalhoso e dependente de cada exercício aplicado no STI. Nesse contexto, este trabalho propõe um modelo de aluno algébrico que além de inferir o conhecimento algébrico dos estudantes de conceitos (como incógnita, igualdades, operações inversas), habilidades (operações algébricas) e falsas concepções, busca definir as relações entre conceitos e habilidades. Como foco inicial deste trabalho serão utilizadas as equações de 1o grau. Para a inferência, será empregada a estrutura de Redes Bayesianas Dinâmicas (RBD), usando como evidência a operação aplicada pelo aluno em cada passo da resolução de uma equação. Nesta estrutura de RBD, cada time slice corresponde à resolução de um passo, o que torna o modelo proposto independente dos exercícios aplicados pelo STI. Dessa forma, o modelo de inferência proposto pode ser utilizado em qualquer equação algébrica, sem a necessidade de qualquer alteração na rede, como ocorre nos outros trabalhos relacionados. Visando verificar a capacidade de inferência desta rede, foram conduzidas avaliações. A partir dos históricos dos alunos, que utilizaram o PAT2Math, foram obtidas as evidências para a rede; e a partir dos dados dos pós-testes, realizados pelos mesmos alunos, formam obtidos os percentuais a serem comparados com a inferência da rede. Como os resultados não foram satisfatórios, empregou-se a regra do limiar, instanciando toda a variável que o ultrapassasse. Avaliada sob os limiares de 96% e 98%, a rede demostrou resultados mais precisos com o limiar de 96%, no qual as diferenças entre os resultados da rede e os percentuais dos pós-testes permaneceram, em sua maioria, em até 5%. / Students learn more through personalized instruction, because the teacher can focus on each learner. Being a impracticable strategy in terms of cost, Intelligent Tutoring Systems (ITS) offers a feasible alternative. By using Artificial Intelligence techniques, these systems are able to adapt themselves to the students, providing individualized instruction. Such adaptation is provided by the Student Model, which is able to assess and map the knowledge of each student. In the literature there are several studies that deal with knowledge evaluation in ITS, some of them are related to algebra. These studies present a Bayesian Network modeling, probabilistic structures that are widely used because of their interesting results concerning the evaluation of the student knowledge. However, in this studies, the network structure only models algebraic concepts, or only model a relationship between algebraic operations and its main properties and common misconceptions. These studies do not aim to represent the relationship between concepts and algebraic operations and how the former can be interfering, in a positive or negative way, on the learning of the second one. For example, in algebra, there are key concepts, such as the unknown and equality among sides of the equation, which directly interferes with the understanding of some algebraic operations. If a student does not understand these concepts, he would hardly be able to apply correctly the related operations in every situation. Thus, it is desirable that the inference model be able to identify if the student understands such concepts. In addition, another limitation of the related work of algebraic student models refers to how they deal with the evidence. As these studies use the assessment items for evidence, for each new exercise, it is necessary to insert a new node in the network, and establish relationships with each concept addressed by this item. This makes the network design laborious and dependent on each ITS exercise. In this context, this work proposes an algebraic student model that, in addition to infer the student knowledge of algebraic concepts (as unknown, equality, inverse operation), skills (algebraic operations) and common misconceptions, defines the relationship between concepts and skill. An initial focus of this study will be the 1st degree equations. For the inference model we use the Dynamic Bayesian Networks (DBN), in which the evidences are the operations applied by the student to solve each equation step. In this structure of DBN, each time slice corresponds to a resolution step, which makes the proposed model independent of the ITS exercises. Thus, the proposed inference model can be used in every algebraic equation, without need to make changes in the network, as occurs with other works.In order to verify the inference capacity of the network, evaluations were conducted. From the resolution history of the students, that interact with PAT2Math, the evidences for the network were obtained; and from the post-test data, solved by the same students, the percentages to compare with the results of the network were obtained. As the results aren’t very satisfactory, we applied the threshold rule, every variable that exceeded this value are instantiated. The network were evaluated under the threshold of 96% and 98%. The proposed DBN has shown more accurate inference with the 96% threshold, in which the differences between the results of the network and the percentages of the post-test remained mostly with ceiling of 5%.

Submitted by William Justo Figueiro (williamjf) on 2015-07-06T22:22:41Z No. of bitstreams: 1 03a.pdf: 2459401 bytes, checksum: 4be1a43d873e5061b50682baa16f9ead (MD5) / Made available in DSpace on 2015-07-06T22:22:41Z (GMT). No. of bitstreams: 1 03a.pdf: 2459401 bytes, checksum: 4be1a43d873e5061b50682baa16f9ead (MD5) Previous issue date: 2013 / FINEP - Financiadora de Estudos e Projetos / A Lógica é uma ciência de índole matemática que está fortemente ligada à Filosofia, cuidando das leis do raciocínio, ou do pensar correto, sendo, portanto, um instrumento do pensar. Assim o aprendizado da lógica se faz necessário para garantir que nossos pensamentos se realizem de forma correta a fim de produzir conhecimentos verdadeiros. A lógica estuda os princípios e métodos usados para distinguir o raciocínio correto do incorreto. Desta forma, a Lógica é uma disciplina fundamental para os cursos acadêmicos de Ciência da Computação. No entanto, uma persistência de altos níveis de reprovação ou desistências prematuras mostra que há um amplo espaço para melhorar o processo de ensino desta disciplina. Nesse contexto, um tema particularmente crítico da Lógica e que causa sérias dificuldades aos alunos é a aprendizagem dos processos de dedução formal. Tendo essa questão em vista, o presente trabalho tem por objetivo propor um modelo computacional de mediação apropriado para o ensino da Dedução Natural para a Lógica Proposicional, incorporado na forma de um agente pedagógico que auxilie o aluno em seu processo de aprendizagem, servindo como ferramenta de apoio para esse processo. Este agente é parte de um projeto de pesquisa, denominado Heráclito, que visa integrar e aplicar as tecnologias de Objetos Inteligentes de Aprendizagem e Agentes Pedagógicos no ensino de Lógica. / Logic is a mathematical science of nature that is strongly linked to Philosophy, tending the laws of reasoning, or right thinking, therefore, an instrument of thought. So learning the logic is necessary to ensure that our thoughts are carried correctly to produce true knowledge. Logic studies the methods and principles used to distinguish correct from incorrect reasoning. Thus, the logic is a fundamental discipline for academic courses of Computer Science. However, the persistence of high levels of premature failure or dropouts shows that there is ample room for improving the process of teaching this subject. In this context, a particularly critical of Logic and causing severe difficulties for students is learning the processes of formal deduction. With this question in mind, this paper aims to propose a computational model of mediation appropriate for the teaching of Natural Deduction for Propositional Logic, incorporated as a pedagogical agent to assist students in their learning process, serving as a tool support for this process. This agent is part of a research project, named Heraclitus, which aims to integrate and apply the technologies of Smart Objects Learning and Pedagogical Agents in teaching Logic.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2015-10-27T12:41:16Z No. of bitstreams: 1 Tiago Roberto Kautzmann_.pdf: 8317737 bytes, checksum: 0d711a62eccda40c8169142262126010 (MD5) / Made available in DSpace on 2015-10-27T12:41:16Z (GMT). No. of bitstreams: 1 Tiago Roberto Kautzmann_.pdf: 8317737 bytes, checksum: 0d711a62eccda40c8169142262126010 (MD5) Previous issue date: 2015-07-28 / Nenhuma / Alunos conscientes de seus processos cognitivos apresentam melhores desempenhos e são mais estratégicos do que alunos que não possuem essa consciência. O conhecimento de uma pessoa sobre os próprios processos cognitivos é chamado de metacognição. É um construto fundamental para a aprendizagem autorregulada, em que o próprio aluno define suas metas de aprendizagem, planeja e seleciona estratégias de estudo, monitora e avalia o seu desempenho e controla sua aprendizagem. Mais especificamente, a habilidade metacognitiva fundamental para as demais habilidades é a de monitoramento do conhecimento, a capacidade de uma pessoa de identificar o que sabe e o que não sabe. Os processos metacognitivos podem ser melhorados através de treinamento. Os trabalhos relacionados treinam habilidades metacognitivas, porém, apresentam, no mínimo, alguma das seguintes lacunas: não incitar o aluno, explicitamente, a refletir sobre seu conhecimento; não explicitar a importância da habilidade de monitoramento do conhecimento; não avaliar a habilidade de monitoramento do conhecimento. Além disso, nenhum dos trabalhos adapta ao aluno a etapa da instrução que incita o monitoramento do conhecimento. O presente trabalho propõe um modelo de agente pedagógico para treinar, explicitamente, a habilidade do aluno de monitorar o seu conhecimento. O modelo adapta a quantidade e o conteúdo da instrução metacognitiva ao aluno, a fim de fazê-lo: ter uma atitude menos reativa, refletindo sobre seu conhecimento antes de resolver uma tarefa; refletir sobre o conhecimento já demonstrado; refletir sobre tarefas similares resolvidas anteriormente. O modelo pode ser integrado a Sistemas Tutores Inteligentes do tipo step-based que forneçam informações sobre o conhecimento do aluno no domínio, o histórico de resolução de tarefas e o conhecimento possível de ser aplicado em um próximo passo de tarefa. O agente foi implementado e integrado ao STI de álgebra PAT2Math para uma avaliação experimental com 63 alunos. Os resultados da avaliação apresentaram evidências indicando que a instrução do agente pode melhorar a habilidade de monitoramento do conhecimento do aluno. Os resultados também indicaram que a instrução do agente pode melhorar o desempenho do aluno no domínio. Além disso, foi encontrada uma alta correlação entre a habilidade metacognitiva e o desempenho do aluno no domínio. / Students who are aware of their metacognitive processes have better performance and are more strategic than students who do not have this awareness. Metacognition is the knowledge of a person on their own cognitive processes. It is a fundamental construct for self-regulated learning, in which the students define their learning goals, plans and select study strategies, monitor and evaluate their performance and control their learning. More specifically, a fundamental metacognitive skill is knowledge monitoring, that is, a person's ability to identify what she knows and what she does not know. The metacognitive processes can be improved through training. Some related works have sought to train learner’s metacognitive skills, however, they have at least some of the following shortcomings: do not incite the student to reflect on their knowledge explicitly; do not explain the importance of metacognitive skills; do not evaluate the knowledge monitoring skill. In addition, none of the work adapts the instruction step that incites the monitoring of knowledge to student’s knowledge and metacognitive skills. The present work proposes a pedagogical agent model to train, explicitly, the student’s ability to monitor his knowledge. The model adapts the quantity and content of metacognitive instruction to the student, so that: he would have a less reactive attitude, he would reflect on their knowledge before solving a task; he would reflect on the knowledge already demonstrated; he would reflect on similar tasks resolved earlier. The model can be integrated with step-based Intelligent Tutoring Systems that provide information about the student's knowledge in the domain, the solving task history and the possible knowledge to be applied in a next step. The agent was implemented and integrated into an algebra STI for an experimental evaluation with 63 students. Evaluation results presented evidences indicating that the instruction of the agent can improve the student's knowledge monitoring ability. The results also indicated that the agent's instruction can improve student performance in the domain. In addition, a high correlation between metacognitive level and performance in the domain was found.

<p>Disertacija se bavi problematikom unapređenja informatičkih kompetencija studenata. Osnovna funkcija sistema je personalizacija nastavnih sadržaja prema trenutnom nivou znanja studenta. Na osnovu toga dizajniran je model inteligentnog tutorskog sistema koji se sastoji od osnovnih funkcionalnih dijelova: modela Tutor, modela Student i mehanizma za zaključivanje. U sistemu su razvijeni moduli za procjenu znanja studenta, isporuku nastavnih sadržaja, unapređenja kompetencija i automatsku sintezu IF...THEN pravila. Procjena znanja vr&scaron;i se pomoću Mamdani fazi inferentnog metoda. Mehanizam za isporuku nastavnih sadržaja radi na principu Alfa algoritma. Automatska sinteza IF...THEN pravila bazirana je na Teoriji grubih skupova. Unapređenje kompetencija vr&scaron;i se pomijeranjem u desno parametara funkcije pripadnosti koja predstavlja studentove kompetencije. Eksperimentalno testiranje rada sistema izvr&scaron;eno je na Java programskom jeziku.</p> / <p>The present dissertation deals with the issue of upgrading the students&rsquo; ICT competencies. The fundamental function of the system is aimed at personalization of educational contents in accordance with the student&rsquo;s current level of knowledge. On the basis of this, a model of the intelligent tutoring system that consists of basic functional components &ndash; the Tutor model, the Student model and a deduction mechanism &ndash; has been designed. Within this system the modules for assessing students&rsquo; knowledge, delivery of educational contents, competence upgrading and automatic synthesis of IF ... THEN rules have been developed. The knowledge assessment is carried out by means of a Mamdani&rsquo;s fuzzy inference method. The mechanism for educational content delivery operates on the principle of an Alpha algorithm. The automatic synthesis of IF ... THEN rules is based on a rough set theory. The upgrading of the competencies is performed by moving to the right the parameters of a membership function which represents the student&#39;s competence. Experimental testing of the system was carried out using the Java programming language.</p>

Abstract not available

One of the established strengths of human tutors is their ability to recognise and adapt to the emotions of students. This is a skill that has traditionally been lacking from Intelligent Tutoring Systems (ITSs); despite their ability to intelligently model and adapt to aspects of the student’s cognitive state, ITSs are generally completely unable to detect or adapt to aspects of the student’s affective state. In response to this shortcoming, this thesis explores the pioneering development of an emotion-sensitive ITS. With the empathy of effective human tutors as our blueprint, we investigate how an artificial tutor should adapt to the affective state of students, and develop an original affective tutoring strategies method. As a validation of the feasibility of an emotion-sensitive tutoring system, we implement and test our method in a functional Affective Tutoring System (ATS) for counting and addition, Easy with Eve, featuring an empathetic animated pedagogical agent, Eve. Eve is able to detect student affect using an in-house real time facial expression analysis system. To inform the system’s adaptation to student affect, the novel method for student modelling and emotion-sensitive tutoring strategies has been developed using a fuzzy, case-based reasoning approach. This approach is used to mine data about human tutor adaptations to student affect that was generated by an observational study of human tutors that was carried out in a local primary school. To test the impact of emotion detection and the presence of the animated agent, four different versions of the ATS were tested in local primary schools with a total of 59 participants. The findings from the study indicate that adding the detection of facial expressions to the student model did not improve student short-term performance, but there was mixed evidence that the presence of the animated agent Eve may cause students to perceive the system slightly more positively (a persona effect). This effect was marginally greater when the animated agent was enabled to detect and adapt to the affective state of students, which tentatively shows that emotion detection in an ATS may have a positive effect on student motivation.

Τα Ευφυή Συστήματα Διδασκαλίας (Intelligent Tutoring Systems) είναι συστήματα που χρησιμοποιούν μεθόδους Τεχνητής Νοημοσύνης για την παροχή εξατομικευμένης διδασκαλίας, τα τελευταία χρόνια και μέσω Διαδικτύου. Τα συστήματα αυτά προσφέρουν δηλαδή μάθηση προσαρμοζόμενη στις δυνατότητες και της ανάγκες των μαθητών-φοιτητών. Ένα σημαντικό τμήμα των συστημάτων αυτών αφορά την αξιολόγηση των μαθητών. Η αξιολόγηση αφορά τον προσδιορισμό του επιπέδου γνώσης ενός μαθητή. Αυτό συνήθως γίνεται με την μέτρηση της απόδοσης του μαθητή σ’ ένα ή περισσότερα τεστ που περιέχουν ερωτήσεις-ασκήσεις που αναφέρονται σε ένα σύνολο εννοιών και είναι διαφόρων επιπέδων δυσκολίας. Ένα σημαντικό στοιχείο στην υπόθεση αυτή είναι ο σωστός προσδιορισμός του επιπέδου δυσκολίας των ερωτήσεων-ασκήσεων. Ένα δεύτερο στοιχείο είναι ο σωστός σχεδιασμός των τεστ ώστε να ανταποκρίνεται στις ανάγκες του κάθε μαθητή, ανάλογα με την μελέτη που έχει κάνει. Ένα τρίτο στοιχείο αφορά τις ευφυείς μεθόδους που θα χρησιμοποιηθούν για την επίτευξη των παραπάνω δύο στοιχείων. Συνήθως χρησιμοποιούνται απλές μέθοδοι, όπως π.χ. κανόνες παραγωγής ή σημαντικά δίκτυα. Μια ενδιαφέρουσα ερευνητική κατεύθυνση είναι η χρήση υβριδικών ευφυών τεχνικών, δηλαδή τεχνικών που συνδυάζουν δύο τουλάχιστον γνωστές ευφυείς τεχνικές, όπως είναι π.χ. ο συνδυασμός κανόνων παραγωγής και γενετικών αλγορίθμων. Το αντικείμενο αυτής της μεταπτυχιακής διπλωματικής εργασίας είναι: (α) η εύρεση μιας μεθόδου για ρεαλιστικότερο προσδιορισμό του επιπέδου δυσκολίας των ερωτήσεων-ασκήσεων, (β) η εύρεση μιας μεθόδου για προσαρμοστικό σχεδιασμό των τεστ αξιολόγησης των μαθητών, ώστε να ανταποκρίνονται στις ανάγκες και δυνατότητες του καθενός χωριστά, (γ) η χρήση υβριδικών ευφυών τεχνικών και (δ) η εφαρμογή των παραπάνω σ’ ένα υπάρχον ευφυές σύστημα διδασκαλίας θεμάτων τεχνητής νοημοσύνης. / Intelligent Tutoring Systems (ITSs) are systems that use AI techniques in order to provide adaptive assessment. ITSs adapt the course material to the student's needs, based on his/her profile and knowledge level. An important function of such systems is student evaluation. Student evaluation refers to the evaluation of the knowledge level of a student after having dealt with a learning page. This is achieved by processing the results of the exercises offered at the end of a learning page. Estimation of the knowledge level of a concept is based, among others, on the difficulty level of the correctly answered exercises included in the test. So, the right determination of the difficulty level of an exercise is very important. Another important issue is the design of the tests in order to correspond student's needs based on their study. Feedback from the students saved in the student model should be taken into account for determination of the difficulty levels of the questions/exercises that will be chosen from each concept. A third important issue is the use of Hybrid Intelligent Methods to achieve the two mentioned issues. Most ITSs use simple methods like semantic networks or production rules. An interesting research direction is the useof hybrid AI methods which combine at least two well known AI techniques like production rules and genetic algorithms. The scope of this paper is (a) the determination of a realistic method for exercise difficulty level adaptation (b) the determination of a method for the personalized assessment of the learner according to a student model (c) the use of Hybrid Intelligent Methods and (d) the implementation of all the above in an Artificial Intelligence Teaching System of the course of "Artificial Intelligence".

Le module de l'apprenant est l'une des composantes les plus importantes d’un Système Tutoriel Intelligent (STI). L'extension du modèle de l'apprenant n'a pas cessé de progresser. Malgré la définition d’un profil cognitif et l’intégration d’un profil émotionnel, le module de l’apprenant demeure non exhaustif. Plusieurs senseurs physiologiques sont utilisés pour raffiner la reconnaissance des états cognitif et émotionnel de l’apprenant mais l’emploi simultané de tous ces senseurs l’encombre. De plus, ils ne sont pas toujours adaptés aux apprenants dont les capacités sont réduites. Par ailleurs, la plupart des stratégies pédagogiques exécutées par le module du tuteur ne sont pas conçues à la base d’une collecte dynamique de données en temps réel, cela diminue donc de leur efficacité. L’objectif de notre recherche est d’explorer l’activité électrique cérébrale et de l’utiliser comme un nouveau canal de communication entre le STI et l’apprenant. Pour ce faire nous proposons de concevoir, d’implémenter et d’évaluer le système multi agents NORA. Grâce aux agents de NORA, il est possible d’interpréter et d’influencer l’activité électrique cérébrale de l’apprenant pour un meilleur apprentissage. Ainsi, NORA enrichit le module apprenant d’un profile cérébral et le module tuteur de quelques nouvelles stratégies neuropédagogiques efficaces. L’intégration de NORA à un STI donne naissance à une nouvelle génération de systèmes tutoriels : les STI Cérébro-sensibles (ou STICS) destinés à aider un plus grand nombre d’apprenants à interagir avec l’ordinateur pour apprendre à gérer leurs émotions, maintenir la concentration et maximiser les conditions favorable à l’apprentissage. / The learner module is the most important component within an Intelligent Tutoring System (ITS). The extension of the learner module is still in progress, despite the integration of the cognitive profile and the emotional profile, it is not yet exhaustive. To improve the prediction of the learner’s emotional and cognitive states, many physiological sensors have been used, but all of these sensors are cumbersome. In addition, they are not always adapted to the learners with reduced capacities. Beside, most of the pedagogical strategies that are executed by the tutor module are based on no-live collections of data. This fact reduces their efficiency. The objective of our research is to explore the electrical brain activity and use it as a communication channel between a learner and an ITS. To reach this aim, we suggest to conceive, to implement and to evaluate the multi-agent system NORA. Integrated to an ITS, this one became a Brain Sensitive Intelligent Tutoring System (BS-ITS). Agents of NORA interpret the learner’s brain electrical signal and react to it. The new BS-ITS is the extension of an ITS and enrich the learner module with the brain profile and the tutor module with a new Neuropedagogical Strategies. We aim to reach more categories of learners and help them to manage their stress, anxiety and maintain the concentration, the attention and the interest.

The dissertation examines the problem of students’ training and testing. To solve the problem, new model, algorithms and system have been developed and adapted. The developed system enables organizing of individual and group train-ing and self-control process. Integrated intelligent search subsystem helps to de-velop the study plan for the themes of interest. The system continuously moni-tors the user and can respond to his failure. The developed built environment computer learning subsystem performs practical calculations to assess the built environment projects. The main problem solved by development of the subsystem is reduction of time needed for users to create their own systems. Knowledge database created during the system devel-opment can be a good source of knowledge for new or similar projects evalua-tions. Calculation results can be saved for further research or shared with other users of the system. The dissertation consists of Introduction, 4 Chapters, Conclusions, Refer-ences, and List of Author’s Publications. The introduction reveals the investigated problem, importance of the thesis and the object of research and describes the purpose and tasks of the dissertation, research methodology, scientific novelty, the practical significance of results examined in the dissertation and defended statements. The introduction ends in presenting the author’s publications on the subject of the defended dissertation, offering the material of made presentations in conferences... [to full text] / Disertacijoje nagrinėjama studentų mokymo ir testavimo problema. Problemai spręsti buvo sukurti ir pritaikyti nauji modeliai, algoritmai ir sistema. Sukurta sistema leidžia organizuoti individualų ir grupinį mokymo ir savikontrolės procesą. Integruota intelektinė paieškos posistemė leidžia sudaryti dominančios tematikos mokymosi planą. Sistema nuolat stebi vartotoją ir gali reaguoti į jo mokymosi nesėkmes. Sukurta kompiuterinio mokymo posistemė, skirta statiniams ir jų aplinkai, atlieka praktinį statinių ir jų aplinkos projektų vertinimą. Pagrindinė išspręsta problema kuriant posistemę yra laiko sąnaudų mažinimas, kurių reikėtų kuriant atskiras sistemas. Žinių bazė, kuri buvo sudaryta kuriant sistemą gali tapti pagrindu naujiems ar panašiems projektams vertinti. Skaičiavimo rezultatai gali būti išsaugoti tolesniems tyrimams atlikti arba jais galima dalintis su kitais sistemos vartotojais. Disertaciją sudaro įvadas, keturi skyriai, rezultatų apibendrinimas, naudotos literatūros sąrašas ir autoriaus publikacijų disertacijos tema sąrašas. Įvade aptariama tiriamoji problema, darbo aktualumas, aprašomas tyrimų objektas, formuluojamas darbo tikslas bei uždaviniai, aprašoma tyrimų metodika, darbo mokslinis naujumas, darbo rezultatų praktinė reikšmė, ginamieji teiginiai. Įvado pabaigoje pristatomos disertacijos tema autoriaus paskelbtos publikacijos bei pranešimai konferencijose ir disertacijos struktūra. Pirmame disertacijos skyriuje atliekama literatūros apžvalga. Nagrinėjama... [toliau žr. visą tekstą]