E-learning is increasingly adopted to support face-to-face classroom-based learning or implemented as a complete standalone learning system. Its inherent adaptable nature and ability to provide learning anywhere, everywhere and anytime makes it a versatile tool for access to basic, professional and higher education. This research proposes and develops an adaptable e-learning approach, focusing on the learner's requirement specification and negotiation of course with multiple providers to improve online learning. This addresses issues of inflexible learning model, narrow coverage of subject domains in existing systems and ineffective use of educational resources, using design research methodology (DRM). The proposed Intelligent Learning approach provides learning support by applying collaborative and deliberative capabilities of software agents to e-learning systems. Designated learning support agents negotiate with providers on behalf of the learner for courses, matching specified requirements. This is achieved through agent negotiation strategies, devising dynamic learning plans (DPLAN) and online learning contract (or EContract) between the system and a range of providers, to harness the changing needs of the learner, hence, providing an Adaptive Agent Learner Plan (ADALP) approach. It develops and applies a 'Basic Requirements Learning' model, addressing specific learning objectives, supported by a two way evaluation process that enforces learning flexibility, empowering learners and accommodating a wide spectrum of learning needs. Unlike traditional Intelligent Tutoring System (ITS), learning objectives are not fixed and are constituted dynamically from learner specifications. The ADALP approach provides multiple provider support options, generating learner feedback for goal oriented, but flexible learning. This deviates from the traditional 'top-down' approach, where instructors and designers create fixed models of different categories of learners and their needs. The prototype of multi-agent system (MAS) demonstrates contributions of the approach, applying Multi-issue-Negotiation and Contracting Courses with Multiple Providers; devising dynamic personalised learning plans and learning commitment (or e-contracts) between learners and providers. It implements designated agents which generate tasks and sub-tasks corresponding to the learners' goals and objectives; 'biding' for learning and tutoring resources from multiple providers to deliver on the derived tasks. Personalised learning plan aligned with online learning contract is generated for each learner based on the specified requirements and learning goals, as a result. It is argued that the ADALP approach empowers learners and improves on similar approaches, in comparison to existing adaptive learning systems.

No description available.

Adaptyvus elektroninis mokymas - elektroninio mokymo rūšis kuri prisitaiko pagal besimokančiojo poreikius. Šis mokymas labiausiai panašus į tradicinį mokymą. Kiekvienais metais į universitetą įstoją skirtingas kompiuterio raštingumo žinias turintys studentai, todėl būtų naudinga kompensuoti trūkstamas studentų žinias. Studentai galėtų kompensuoti trūkstama žinias savarankiškai, panaudojant adaptyvų elektroninį kursą. Šiam tikslui pasiekti buvo nuspręsta kurti adaptyvaus elektroninio mokymo sistemą. Sistemos kūrimo metu atlikti tokie tyrimai: • atlikta apklausa, kurios metu išsiaiškintas žmonių požiūris į adaptyvų elektroninį mokymą; • išanalizuota esamos elektroninio mokymo kūrimo sistemos ir elektroninio mokymo kursai; • išanalizuotos galimo grįžtamojo ryšio rūšys; • sukurta sistemos duomenų bazė, kurioje bus saugomi pagrindiniai duomenys susiję su vartotoju ir vartotojo mokymosi įvertinimais; • sukurtas sistemos prototipas dviejų kurso dalių mokymuisi; • atliktas eksperimentas, kuriuo metu aštuoniolika žmonių mokėsi adaptyviu elektroniniu būdu. Jų rezultatai palyginti su tą pačią medžiagą besimokančiųjų rezultatais tradiciniu būdu. / Adaptive electronic learning – a kind of electronic learning that meets the learner`s requirements. This learning is the most similar to traditional learning. Students with different knowledge of computer literacy enter the university every year, so it would be useful to compensate the lack of their knowledge. Students could compensate the lack of knowledge on their own, by applying an adaptive electronic course. In order to achieve this goal, it was decided to create a system of adaptive electronic learning. Here are the analyses made while creating the system: • A survey that clarified people`s attitudes towards adaptive electronic learning was made; • An analysis of an existing system of electronic learning creation and courses of electronic learning was made; • The types of possible feedback were analysed; • A system database that keeps the main data related to the user and his learning evaluations was developed; • A system prototype for learning of two parts of the course was designed; • An experiment of 18 people taking adaptive electronic learning was carried out. The results were compared with those of learning the same material in traditional way.

Complex social problems are at the forefront of our awareness. We are witnessing intensifying political, social and environmental challenges and waning confidence in our ability to engineer solutions. We are also seeing a proliferation of large scale, multi-agency interventions that seek change at the level of systems, and through which actors pursue adaptive learning as a means to develop effective solutions. Proponents assert that the prediction and control on which conventional program design and evaluation are based are not available under complex conditions. They propose instead that learning through experience in a program’s own context can create more responsive, impactful and sustainable interventions. These ideas offer a potentially transformative opportunity. However, they need to be complemented with a better understanding of implementation - the ‘ways of doing things’ that bring them to life. This study focused on developmental evaluation as an example of an adaptive learning (AL) approach for the development of innovative social interventions. The study was informed by ‘sensemaking’ theories and research in organizational learning, knowledge mobilization and program evaluation. Through an exploratory lens and a mixed methods design, this study sheds light on the role of specialized intermediaries in an AL process; how the role is performed in practice; and what this implies for adaptive learning in the domain of social interventions. The study documents how an intermediary can help actors navigate recognized challenges of developing interventions under complex and dynamic conditions. The findings have implications for how an AL process is understood and implemented. They provide an empirical contribution to an emerging field of study on the design of AL systems, to support future research and real-world practice as AL approaches become mainstream.

Adaptive learning is a crucial part in intelligent tutoring systems. It provides students with appropriate tutoring interventions, based on students’ characteristics, status, and other related features, in order to optimize their learning outcomes. It is required to determine students’ knowledge level or learning progress, based on which it then uses proper techniques to choose the optimal interventions. In this dissertation work, I focus on these aspects related to the process in adaptive learning: student modeling, k-armed bandits, and contextual bandits. Student modeling. The main objective of student modeling is to develop cognitive models of students, including modeling content skills and knowledge about learning. In this work, we investigate the effect of prerequisite skill in predicting students’ knowledge in post skills, and we make use of the prerequisite performance in different student models. As a result, this makes them superior to traditional models. K-armed bandits. We apply k-armed bandit algorithms to personalize interventions for students, to optimize their learning outcomes. Due to the lack of diverse interventions and small difference of intervention effectiveness in educational experiments, we also propose a simple selection strategy, and compare it with several k-armed bandit algorithms. Contextual bandits. In contextual bandit problem, additional side information, also called context, can be used to determine which action to select. First, we construct a feature evaluation mechanism, which determines which feature to be combined with bandits. Second, we propose a new decision tree algorithm, which is capable of detecting aptitude treatment effect for students. Third, with combined bandits with the decision tree, we apply the contextual bandits to make personalization in two different types of data, simulated data and real experimental data.

Será que os estudantes de hoje têm habilidades para alternar o foco, dividindo seu tempo de estudo entre duas ou mais “fontes didáticas” às quais são expostos? Nesta tese se entende por “fonte didática” toda fonte de comunicação que pode passar informações através de pessoas ou máquinas, com intuito de ensinar um conceito. Assim, pesquisou-se através de experimentos em que os estudantes eram expostos às diferentes “fontes didáticas”, sendo medidos seus desempenhos por meio de testes como forma de entender suas capacidades de aprendizagem. As TICs têm possibilitado o acesso em simultâneo a várias “fontes didáticas” por um mesmo estudante ao mesmo tempo. Embora este acesso possa ocasionar um excesso de estímulos aos aprendizes, é preciso, então, pesquisar as consequências no processo de aprendizagem: um discente que está assistindo, por exemplo, a uma aula de um bom professor e, ao mesmo tempo, através de seu celular, consulta outras fontes didáticas disponíveis, ou simplesmente decide assistir dois objetos de aprendizagem ao mesmo tempo, sendo um interativo e outro visual, ou um visual e auditivo. Esta forma de estudo é, todavia, benéfica para seu processo de aprendizagem? É justamente na busca de respostas a estas perguntas que a presente tese de doutorado investigou a forma de navegação de estudantes quando expostos a duas apresentações paralelas multimídias e multimodais, considerando o conceito de trajetórias de aprendizagem em função dos tempos de estudo envolvidos. Este estudo tem como base teórica o construtivismo e o interacionismo de Piaget, neste contexto de exploração paralela ou alternada de vários objetos de aprendizagem. A pesquisa teve natureza explicativa, abordagem quantitativa e modalidade quase-experimental. Foi desenvolvido um sistema capaz de apresentar, ao mesmo tempo, dois objetos de aprendizagem para um mesmo estudante, e de monitorar a navegação desse aprendiz. O sistema desenvolvido no âmbito dessa tese foi denominado Apresentações Adaptativas Multimídias e Multimodais (AAMM), e foi implementado em HTML, PHP, AJAX e JavaScript. Nessa pesquisa foi avaliado o desempenho dos estudantes através de dois testes diferentes (pré-teste e pós-teste), mas com os mesmos níveis de dificuldade (um antes e outro após a exploração dos objetos de aprendizagem interativos e não interativos). Após o desenvolvimento do sistema AAMM e a realização do estudo piloto apresentado na proposta da tese, foram realizados dois experimentos com o objetivo de investigar a forma de navegação dos estudantes face a duas ou mais apresentações paralelas multimídia, considerando os estilos de aprendizagem preferenciais. Foram realizados testes estatísticos de Wilcoxon e Kruskal-Wallis, e os resultados das análises mostraram evidências para afirmar que em apresentações adaptativas multimídia compostas por objetos de aprendizagem interativos e não interativos é recomendável que se priorize os objetos de aprendizagem interativos seguidos dos não interativos; estudantes que efetuam múltiplas transições entre os materiais didáticos apresentam mau rendimento; o tempo que os estudantes levam a interagir com um objeto de aprendizagem não influencia no seu aproveitamento final, mas, quanto maior o tempo de dedicação aos objetos de aprendizagem interativos maior a probabilidade de se obter bom aproveitamento nos processos de ensino e aprendizagem. / Do students today have the ability to shift focus by dividing their study time between two or more didactic sources to which they are exposed? In this thesis is meant by "didactic source" all source of communication that can pass information through people or machines, in order to teach a concept. Thus, we investigated through experiments in which students were exposed to different "didactic sources", being measured their performances through tests as a way of understanding their learning abilities. ICTs have enabled simultaneous access to several didactic resources by the same student at the same time. Although this access may lead to an excess of stimuli for learners, it is necessary to investigate the consequences in the learning process: a student who is watching, for example, a lesson of a good teacher and, at the same time, through his Cell phone, consult other educational resources available, or simply decide to watch two learning objects at once, being an interactive and another visual, or a visual and auditory. Is this form of study, however, beneficial to his learning process? It is precisely in the search for answers to these questions that the present thesis investigated the way students navigate when exposed to two multimodal and multimodal parallel presentations, considering the concept of learning trajectories according to the study times involved. This study is based on Piaget’s constructivism and interactionism, in this context of a parallel or alternating exploration of several learning objects. The research had explanatory nature, quantitative approach, and quasi-experimental modality. A system was developed capable of presenting at the same time two learning objects for the same student, and of monitoring the navigation of this learner. The system developed under this thesis was called Multimedia and Multimodal Adaptive Presentations (AAMM), and was implemented in HTML, PHP, AJAX and JavaScript. In this research, students' performance was evaluated through two different tests (pre-test and post-test), but with the same levels of difficulty (one before and one after the exploration of interactive and non-interactive learning objects). After the development of the AAMM system and the pilot study presented in the thesis proposal, two experiments were carried out to investigate the way students navigate two or more parallel multimedia presentations, considering the preferred learning styles. Wilcoxon and Kruskal-Wallis statistical tests were performed, and The results of the analyses showed evidence to affirm that in multimedia adaptive presentations composed of interactive and noninteractive learning objects it is recommended that prioritized interactive learning objects followed by non-interactive ones; Students who carry out multiple transitions between didactic materials present poor performance; The time that students take to interact with a learning object does not influence their final achievement, but the longer the time of dedication to interactive learning objects the greater the likelihood of successful achievement in the learning process.

Students’ academic self-concepts (ASC) and their orientation towards self-regulated learning are important elements of success. Despite this fact, little work has been conducted exploring these areas medical students. Given the shifting priorities of medical education toward competency-based education and self-directed learning, the goals of this study were to validate an existing measure of ASC and to improve our measurement capabilities for understanding the Master Adaptive Learner (MAL). Evidence for validity and scale reliability was collected for the ASCS with this novel population and a range of motivational and self-regulative variables (Goal orientation, academic emotion regulation, and lifelong learning) were analyzed and reduced to produce a single scale for MAL. Surveys were administered to 203 medical students at an urban, Mid-Atlantic medical school and students’ grades were linked to survey responses. Results of a confirmatory factor analysis indicated that the original factor structure was not a good fit to the data for the current data. An exploratory factor analysis (EFA) was conducted to identify which structure fit better, and while a three-factor structure was produced, only one factor met reliability standards. This factor, confidence, was merged with items from the other surveys, and reliability scores for a composite MAL scale were identified. Based on these findings and the result of an EFA, the total item pool was reduced from 83 to 25. These 25 items discriminated between two clusters of students: MALs and others. Students’ membership in the MAL cluster predicted greater performance on the first exam in medical school, but not on any other grade outcomes. These results provide early evidence for the continued study of MAL and motivation in medical school, which will help researchers and curriculum designers support the development of future physicians.

我國專業晶圓代工產業已是全球半導體產業鏈中不可或缺一環，此創新之商業模式不但帶動了全球半導體產業鏈的重整，更為我國半導體產業奠定了雄厚的基礎。但是無法快速回應晶圓缺陷問題與縮短工程師培訓時間，卻仍是台灣半導體產業發展近四十幾年來的瓶頸。此問題的延誤不傴使晶圓廠耗損巨額的成本，更承擔喪失國際客戶訂單的風險。因此，如何使半導體工程師提升工作效率，與如何有效培養新進工程師，如今已成為半導體業界刻不容緩之議題。 在知識經濟時代中，為企業打造適宜之知識管理模式是產、官、學界所致力的目標。但多數的研究以資訊科技所主導的知識管理系統為範疇，鮮少研究去探索知識工作者陎臨求解問題的困境中，是如何依循著問題情境，如何在其中摸索，進而發展出解決方案的詳細過程。有鑑於此，本研究選擇以詮釋型個案研究方法，深入訪察半導體工程師工作實務，藉此瞭解工程師於維修情境中排除晶圓缺陷的樣貌。 經由探討排除晶圓缺陷的工作實務中發現，工程師具備了四禑與「情境」調適性學習(adaptive learning)((Tyre and von Hippel,1997)的歷程：第一、工程師必頇在問題情境中，辨認隱藏於情境當中之線索，並賦與線索意義而展開偵察行動。第二、工程師在偵察過程中，頇不斷地依情境調整收集資料技巧，挖掘出更多或更深層的資訊。第三、工程師適當的工具與資源，有效率地萃取更多的資訊。第四、工程師彼此之間依情境發展出最適行為模式，得以順利整合跨部門執行偵察行動。 本研究著重於解析工程師在問題情境中，不斷學習與調適之詳細過程，並指出調適性學習如何在排除晶圓異常工作中扮演重要的角色。最後，針對調適性學習行為提出具體的理論與實務意涵，以供組織未來進行人員培訓與知識管理之參考。

The self-organizing map (SOM) is an unsupervised learning algorithm which has been successfully applied to various applications. One of advantages of SOM is it maintains an incremental property to handle data on the fly. In the last several decades, there have been variants of SOM used in many application domains. In this dissertation, two new SOM algorithms are developed for image quantization and compression. The first algorithm is a sample-size adaptive SOM algorithm that can be used for color quantization of images to adapt to the variations of network parameters and training sample size. The sweep size of neighborhood function is modulated by the size of the training data. In addition, the minimax distortion principle which is modulated by training sample size is used to search the winning neuron. Based on the sample-size adaptive self-organizing map, we use the sampling ratio of training data, rather than the conventional weight change between adjacent sweeps, as a stop criterion. As a result, it can significantly speed up the learning process. Experimental results show that the proposed sample-size adaptive SOM achieves much better PSNR quality, and smaller PSNR variation under various combinations of network parameters and image size. The second algorithm is a novel classified SOM method for edge preserving quantization of images using an adaptive subcodebook and weighted learning rate. The subcodebook sizes of two classes are automatically adjusted in training iterations based on modified partial distortions that can be estimated incrementally. The proposed weighted learning rate updates the neuron efficiently no matter of how large the weighting factor is. Experimental results show that the proposed classified SOM method achieves better quality of reconstructed edge blocks and more spread out codebook and incurs a significantly less computational cost as compared to the competing methods.

近年來網路學習隨著網路的發展，逐漸受到重視。網路是一個開放式環境，擁有豐富的學習資源，並且突破學習時的空間限制、時間限制，讓使用者擁有較高的學習自主性。由於在網路學習環境中，學習者必須負擔選擇和學習的責任，容易有學習迷失的問題。因此，蘇俊銘等提出一個動態產生適性化教材順序的Instructional Activity Model(IAM)。更依據所提出的IAM，設計一個符合美國國防部所提出之SCORM標準的系統。 根據奧蘇伯爾在認知同化學習論中所提到，能力之間是會互相影響的。然而IAM並未考量能力與能力之間的相互影響關係。因此本研究將將結合奧蘇伯爾同化論，提出一個考慮能力與能力之間相互關係的適性化教學模型，提供學習路徑導引。期望藉由此模型，能夠提供E-learning環境設計者，設計更符合學習者能力狀況的適性化學習課程。 / E-Learning issues have been discussed and investigated recent years. Internet environment provides multiple choices of learning time and learning materials. Much research has been done on E-Learning. The standards of E-Learning platform have been developed to make the learning content sharable and reusable. Some research has been devoted to the design of adaptive Learning system for need of different users. The Instructional Activity Model (IAM) is a general-purpose model to generate an adaptive learning course, which is compatible with the SCORM standard. IAM is composed of related Activity Tree (AT tree) nodes and capability nodes. Prerequisites are capabilities supposed to posses before learning an AT tree while contributions are capabilities after learning an AT tree. IAM model supports the adaptive learning sequencing by considering the relationships between AT trees and capability nodes. However, the IAM model does not take the influence between capabilities into consideration, especially for the assimilation of capabilities. In this paper, we propose the mechanism to integrate the concept of assimilation theory to the IAM model. In our proposed mechanism, the relationships between capabilities are considered based on the similarity measure between capabilities. The selection process of IAM is also modified to reflect the relationships of capabilities. Simulation result shows that the proposed mechanism is helpful for the learning sequencing.