The use of learning management systems: A Longitudinal Case Study

In this article the use of Learning Management Systems (LMS) at the School of Engineering, University of Borås, in the year 2004 and the academic year 2009-2010 is investigated. The tools in the LMS were classified into four groups (tools for distribution, tools for communication, tools for interaction and tools for course administration) and the pattern of use was analyzed. The preliminary interpretation of the results was discussed with a group of teachers from the School of Engineering with long experience of using LMS. High expectations about LMS as a tool to facilitate flexible education, student centered methods and the creation of an effective learning environment is abundant in the literature. This study, however, shows that in most of the surveyed courses the available LMS is predominantly used to distribute documents to students. The authors argue that a more elaborate use of LMS and a transformation of pedagogical practices towards social constructivist, learner centered procedures should be treated as an integrated process of professional development.

An analysis of the moderating effects of age in the acceptance of learning management systems

El presente estudio analiza las intenciones de los usuarios acerca del uso de sistemas de tele-enseñanza LMS (Learning Management Systems, basándose en un modelo que integra el Modelo de Aceptación Tecnológica (TAM, Technology Acceptance Model, la Teoría del Comportamiento Percibido (TPB, Theory of Planned Behavior) y la Teoría Unificada de la Aceptación y Uso de la Tecnología (UTAUT, Unified Theory of Acceptance and Use of Technology), tomando la edad como variable moderadora. Así, este artículo estudia la influencia de la intención conductual, la actitud hacia el uso, la facilidad de uso percibida, la utilidad percibida, la norma subjetiva y la influencia social en la intención de utilizar sistemas e-learning LMS. Como antecedentes de estos factores de influencia se plantean las características del sistema y del usuario. El resultado de la revisión teórica es un modelo unificado que ha sido validado con datos recogidos de 94 estudiantes a través de un cuestionario en línea. Estos datos han sido analizados utilizando la técnica de mínimos cuadrados parciales, y los principales resultados confirman la relevancia predictiva del modelo para usuarios de entre 26 y 35 años y de entre 36 y 45 años.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

Learning Management Systems (LMS) and e-learning management: an integrative review and research agenda

Information Technology (IT) can be an important component for innovation since enabling e-learning it can provide conditions to which the organization can work with new business and improved processes. In this regard, the Learning Management Systems (LMS) allows communication and interaction between teachers and students in virtual spaces. However the literature indicates that there are gaps in the researches, especially concerning the use of IT for the management of e-learning. The purpose of this paper is to analyze the available literature about the application of LMS for the e-learning management, seeking to present possibilities for researches in the field. An integrative literature review was performed considering the Web of Science, Scopus, Ebsco and Scielo databases, where 78 references were found, of which 25 were full papers. This analysis derives interesting characteristics from scientific studies, highlighting gaps and guidelines for future research.

'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus learning can amount to 'counting' in the case of multinomial distributions. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

Evolving Distributed Algorithms with Genetic Programming

Distributed systems are one of the most vital components of the economy. The most prominent example is probably the internet, a constituent element of our knowledge society. During the recent years, the number of novel network types has steadily increased. Amongst others, sensor networks, distributed systems composed of tiny computational devices with scarce resources, have emerged. The further development and heterogeneous connection of such systems imposes new requirements on the software development process. Mobile and wireless networks, for instance, have to organize themselves autonomously and must be able to react to changes in the environment and to failing nodes alike. Researching new approaches for the design of distributed algorithms may lead to methods with which these requirements can be met efficiently. In this thesis, one such method is developed, tested, and discussed in respect of its practical utility. Our new design approach for distributed algorithms is based on Genetic Programming, a member of the family of evolutionary algorithms. Evolutionary algorithms are metaheuristic optimization methods which copy principles from natural evolution. They use a population of solution candidates which they try to refine step by step in order to attain optimal values for predefined objective functions. The synthesis of an algorithm with our approach starts with an analysis step in which the wanted global behavior of the distributed system is specified. From this specification, objective functions are derived which steer a Genetic Programming process where the solution candidates are distributed programs. The objective functions rate how close these programs approximate the goal behavior in multiple randomized network simulations. The evolutionary process step by step selects the most promising solution candidates and modifies and combines them with mutation and crossover operators. This way, a description of the global behavior of a distributed system is translated automatically to programs which, if executed locally on the nodes of the system, exhibit this behavior. In our work, we test six different ways for representing distributed programs, comprising adaptations and extensions of well-known Genetic Programming methods (SGP, eSGP, and LGP), one bio-inspired approach (Fraglets), and two new program representations called Rule-based Genetic Programming (RBGP, eRBGP) designed by us. We breed programs in these representations for three well-known example problems in distributed systems: election algorithms, the distributed mutual exclusion at a critical section, and the distributed computation of the greatest common divisor of a set of numbers. Synthesizing distributed programs the evolutionary way does not necessarily lead to the envisaged results. In a detailed analysis, we discuss the problematic features which make this form of Genetic Programming particularly hard. The two Rule-based Genetic Programming approaches have been developed especially in order to mitigate these difficulties. In our experiments, at least one of them (eRBGP) turned out to be a very efficient approach and in most cases, was superior to the other representations.

Investigating scaling of an abstracted LCS utilising ternary and S-Expression alphabets

Utilising the expressive power of S-Expressions in Learning Classifier Systems often prohibitively increases the search space due to increased flexibility of the endcoding. This work shows that selection of appropriate S-Expression functions through domain knowledge improves scaling in problems, as expected. It is also known that simple alphabets perform well on relatively small sized problems in a domain, e.g. ternary alphabet in the 6, 11 and 20 bit MUX domain. Once fit ternary rules have been formed it was investigated whether higher order learning was possible and whether this staged learning facilitated selection of appropriate functions in complex alphabets, e.g. selection of S-Expression functions. This novel methodology is shown to provide compact results (135-MUX) and exhibits potential for scaling well (1034-MUX), but is only a small step towards introducing abstraction to LCS.

Lernen mit einer Hybride aus Lernendem Klassifizierendem System und Selbstorganisierender Karte

Im Forschungsgebiet der Künstlichen Intelligenz, insbesondere im Bereich des maschinellen Lernens, hat sich eine ganze Reihe von Verfahren etabliert, die von biologischen Vorbildern inspiriert sind. Die prominentesten Vertreter derartiger Verfahren sind zum einen Evolutionäre Algorithmen, zum anderen Künstliche Neuronale Netze. Die vorliegende Arbeit befasst sich mit der Entwicklung eines Systems zum maschinellen Lernen, das Charakteristika beider Paradigmen in sich vereint: Das Hybride Lernende Klassifizierende System (HCS) wird basierend auf dem reellwertig kodierten eXtended Learning Classifier System (XCS), das als Lernmechanismus einen Genetischen Algorithmus enthält, und dem Wachsenden Neuralen Gas (GNG) entwickelt. Wie das XCS evolviert auch das HCS mit Hilfe eines Genetischen Algorithmus eine Population von Klassifizierern - das sind Regeln der Form [WENN Bedingung DANN Aktion], wobei die Bedingung angibt, in welchem Bereich des Zustandsraumes eines Lernproblems ein Klassifizierer anwendbar ist. Beim XCS spezifiziert die Bedingung in der Regel einen achsenparallelen Hyperquader, was oftmals keine angemessene Unterteilung des Zustandsraumes erlaubt. Beim HCS hingegen werden die Bedingungen der Klassifizierer durch Gewichtsvektoren beschrieben, wie die Neuronen des GNG sie besitzen. Jeder Klassifizierer ist anwendbar in seiner Zelle der durch die Population des HCS induzierten Voronoizerlegung des Zustandsraumes, dieser kann also flexibler unterteilt werden als beim XCS. Die Verwendung von Gewichtsvektoren ermöglicht ferner, einen vom Neuronenadaptationsverfahren des GNG abgeleiteten Mechanismus als zweites Lernverfahren neben dem Genetischen Algorithmus einzusetzen. Während das Lernen beim XCS rein evolutionär erfolgt, also nur durch Erzeugen neuer Klassifizierer, ermöglicht dies dem HCS, bereits vorhandene Klassifizierer anzupassen und zu verbessern. Zur Evaluation des HCS werden mit diesem verschiedene Lern-Experimente durchgeführt. Die Leistungsfähigkeit des Ansatzes wird in einer Reihe von Lernproblemen aus den Bereichen der Klassifikation, der Funktionsapproximation und des Lernens von Aktionen in einer interaktiven Lernumgebung unter Beweis gestellt.

Integration of e-learning systems with repositories of learning objects

This paper describes a communication model to integrate repositories of programming problems with other e-Learning software components. The motivation for this work comes from the EduJudge project that aims to connect an existing repository of programming problems to learning management systems. When trying to use the existing repositories of learning objects we realized that they are mainly specialized search engines and lack features for integration with other e-Learning systems. With this model we intend to clarify the main features of a programming problem repository, in order to enable the design and development of software components that use it. The two main points of this model are the definition of programming problems as learning objects and the definition of the core functions exposed by the repository. In both cases, this model follows the existing specifications of the IMS standard and proposes extensions to deal with the special requirements of automatic evaluation and grading of programming exercises. In the definition of programming problems as learning objects we introduced a new schema for meta-data. This schema is used to represent meta-data related to automatic evaluation that cannot be conveniently represented using the standard: the type of automatic evaluation; the requirements of the evaluation engine; or the roles of different assets - tests cases, program solutions, etc. In the definition of the core functions we used two different web services flavours - SOAP and REST - and described each function as an operation for each type of interface. We describe also the data types of the arguments of each operation. These data types consist mainly on learning objects and their identifications, but include also usage reports and queries using XQuery.

Integrating the LMS in service oriented e-learning systems

Learning management systems are routinely used for presenting, solving and grading exercises with large classes. However, teachers are constrained to use questions with pre-defined answers, such as multiple-choice, to automatically correct the exercises of their students. Complex exercises cannot be evaluated automatically by the LMS and require the coordination of a set of heterogeneous systems. For instance, programming exercises require a specialized exercise resolution environment and automatic evaluation features, each provided by a different type of system. In this paper, the authors discuss an approach for the coordination of a network of eLearning systems supporting the resolution of exercises. The proposed approach is based on a pivot component embedded in the LMS and has two main roles: 1) provide an exercise resolution environment, and 2) coordinate communication between the LMS and other systems, exposing their functions as web services. The integration of the pivot component in the LMS relies on Learning Tools Interoperability (LTI). This paper presents an architecture to coordinate a network of eLearning systems and validate the proposed approach by creating such a network integrated with LMS from two different vendors.

Personal learning environments: integration of Web 2.0 applications and content management systems

This paper presents an ongoing project that implements a platform for creating personal learning environments controlled by students, integrating Web 2.0 applications and content management systems, enabling the safe use of content created in Web 2.0 applications, allowing its publication in the infrastructure controlled by the HEI. Using this platform, students can develop their personal learning environment (PLE) integrated with the Learning Management System (LMS) of the HEI, enabling the management of their learning and, simultaneously, creating their e-portfolio with digital content developed for Course Units (CU). All this can be maintained after the student completes his academic studies, since the platform will remain accessible to students even after they leave the HEI and lose access to its infrastructure. The platform will enable the safe use of content created in Web 2.0 applications, allowing its protected publication in the infrastructure controlled by HEI, thus contributing to the adaptation of the L&T paradigm to the Bologna process.

Scalable Intelligence for Scheduling Systems

A personalização é um aspeto chave de uma interação homem-computador efetiva. Numa era em que existe uma abundância de informação e tantas pessoas a interagir com ela, de muitas maneiras, a capacidade de se ajustar aos seus utilizadores é crucial para qualquer sistema moderno. A criação de sistemas adaptáveis é um domínio bastante complexo que necessita de métodos muito específicos para ter sucesso. No entanto, nos dias de hoje ainda não existe um modelo ou arquitetura padrão para usar nos sistemas adaptativos modernos. A principal motivação desta tese é a proposta de uma arquitetura para modelação do utilizador que seja capaz de incorporar diferentes módulos necessários para criar um sistema com inteligência escalável com técnicas de modelação. Os módulos cooperam de forma a analisar os utilizadores e caracterizar o seu comportamento, usando essa informação para fornecer uma experiência de sistema customizada que irá aumentar não só a usabilidade do sistema mas também a produtividade e conhecimento do utilizador. A arquitetura proposta é constituída por três componentes: uma unidade de informação do utilizador, uma estrutura matemática capaz de classificar os utilizadores e a técnica a usar quando se adapta o conteúdo. A unidade de informação do utilizador é responsável por conhecer os vários tipos de indivíduos que podem usar o sistema, por capturar cada detalhe de interações relevantes entre si e os seus utilizadores e também contém a base de dados que guarda essa informação. A estrutura matemática é o classificador de utilizadores, e tem como tarefa a sua análise e classificação num de três perfis: iniciado, intermédio ou avançado. Tanto as redes de Bayes como as neuronais são utilizadas, e uma explicação de como as preparar e treinar para lidar com a informação do utilizador é apresentada. Com o perfil do utilizador definido torna-se necessária uma técnica para adaptar o conteúdo do sistema. Nesta proposta, uma abordagem de iniciativa mista é apresentada tendo como base a liberdade de tanto o utilizador como o sistema controlarem a comunicação entre si. A arquitetura proposta foi desenvolvida como parte integrante do projeto ADSyS - um sistema de escalonamento dinâmico - utilizado para resolver problemas de escalonamento sujeitos a eventos dinâmicos. Possui uma complexidade elevada mesmo para utilizadores frequentes, daí a necessidade de adaptar o seu conteúdo de forma a aumentar a sua usabilidade. Com o objetivo de avaliar as contribuições deste trabalho, um estudo computacional acerca do reconhecimento dos utilizadores foi desenvolvido, tendo por base duas sessões de avaliação de usabilidade com grupos de utilizadores distintos. Foi possível concluir acerca dos benefícios na utilização de técnicas de modelação do utilizador com a arquitetura proposta.

Beneath a learning management system: understanding the human information interaction in information systems

Studies on learning management systems have largely been technical in nature with an emphasis on the evaluation of the human computer interaction (HCI) processes in using the LMS. This paper reports a study that evaluates the information interaction processes on an eLearning course used in teaching an applied Statistics course. The eLearning course is used as a synonym for information systems. The study explores issues of missing context in stored information in information systems. Using the semiotic framework as a guide, the researchers evaluated an existing eLearning course with the view to proposing a model for designing improved eLearning courses for future eLearning programmes. In this exploratory study, a survey questionnaire is used to collect data from 160 participants on an eLearning course in Statistics in Applied Climatology. The views of the participants are analysed with a focus on only the human information interaction issues. Using the semiotic framework as a guide, syntactic, semantic, pragmatic and social context gaps or problems were identified. The information interactions problems identified include ambiguous instructions, inadequate information, lack of sound, interface design problems among others. These problems affected the quality of new knowledge created by the participants. The researchers thus highlighted the challenges of missing information context when data is stored in an information system. The study concludes by proposing a human information interaction model for improving the information interaction quality issues in the design of eLearning course on learning management platforms and those other information systems.

An approach to implement data fusion techniques in wireless sensor networks using genetic machine learning algorithms

Wireless Sensor Networks (WSNs) can be used to monitor hazardous and inaccessible areas. In these situations, the power supply (e.g. battery) of each node cannot be easily replaced. One solution to deal with the limited capacity of current power supplies is to deploy a large number of sensor nodes, since the lifetime and dependability of the network will increase through cooperation among nodes. Applications on WSN may also have other concerns, such as meeting temporal deadlines on message transmissions and maximizing the quality of information. Data fusion is a well-known technique that can be useful for the enhancement of data quality and for the maximization of WSN lifetime. In this paper, we propose an approach that allows the implementation of parallel data fusion techniques in IEEE 802.15.4 networks. One of the main advantages of the proposed approach is that it enables a trade-off between different user-defined metrics through the use of a genetic machine learning algorithm. Simulations and field experiments performed in different communication scenarios highlight significant improvements when compared with, for instance, the Gur Game approach or the implementation of conventional periodic communication techniques over IEEE 802.15.4 networks. © 2013 Elsevier B.V. All rights reserved.