Orchestration of e-learning services for automatic evaluation of programming exercises

Managing programming exercises require several heterogeneous systems such as evaluation engines, learning objects repositories and exercise resolution environments. The coordination of networks of such disparate systems is rather complex. These tools would be too specific to incorporate in an e-Learning platform. Even if they could be provided as pluggable components, the burden of maintaining them would be prohibitive to institutions with few courses in those domains. This work presents a standard based approach for the coordination of a network of e-Learning systems participating on the automatic evaluation of programming exercises. The proposed approach uses a pivot component to orchestrate the interaction among all the systems using communication standards. This approach was validated through its effective use on classroom and we present some preliminary results.

Data gathering approach in dense sensor networks

Sensor/actuator networks promised to extend automated monitoring and control into industrial processes. Avionic system is one of the prominent technologies that can highly gain from dense sensor/actuator deployments. An aircraft with smart sensing skin would fulfill the vision of affordability and environmental friendliness properties by reducing the fuel consumption. Achieving these properties is possible by providing an approximate representation of the air flow across the body of the aircraft and suppressing the detected aerodynamic drags. To the best of our knowledge, getting an accurate representation of the physical entity is one of the most significant challenges that still exists with dense sensor/actuator network. This paper offers an efficient way to acquire sensor readings from very large sensor/actuator network that are located in a small area (dense network). It presents LIA algorithm, a Linear Interpolation Algorithm that provides two important contributions. First, it demonstrates the effectiveness of employing a transformation matrix to mimic the environmental behavior. Second, it renders a smart solution for updating the previously defined matrix through a procedure called learning phase. Simulation results reveal that the average relative error in LIA algorithm can be reduced by as much as 60% by exploiting transformation matrix.

Automatic learning for the classification of chemical reactions and in statistical thermodynamics

This Thesis describes the application of automatic learning methods for a) the classification of organic and metabolic reactions, and b) the mapping of Potential Energy Surfaces(PES). The classification of reactions was approached with two distinct methodologies: a representation of chemical reactions based on NMR data, and a representation of chemical reactions from the reaction equation based on the physico-chemical and topological features of chemical bonds. NMR-based classification of photochemical and enzymatic reactions. Photochemical and metabolic reactions were classified by Kohonen Self-Organizing Maps (Kohonen SOMs) and Random Forests (RFs) taking as input the difference between the 1H NMR spectra of the products and the reactants. The development of such a representation can be applied in automatic analysis of changes in the 1H NMR spectrum of a mixture and their interpretation in terms of the chemical reactions taking place. Examples of possible applications are the monitoring of reaction processes, evaluation of the stability of chemicals, or even the interpretation of metabonomic data. A Kohonen SOM trained with a data set of metabolic reactions catalysed by transferases was able to correctly classify 75% of an independent test set in terms of the EC number subclass. Random Forests improved the correct predictions to 79%. With photochemical reactions classified into 7 groups, an independent test set was classified with 86-93% accuracy. The data set of photochemical reactions was also used to simulate mixtures with two reactions occurring simultaneously. Kohonen SOMs and Feed-Forward Neural Networks (FFNNs) were trained to classify the reactions occurring in a mixture based on the 1H NMR spectra of the products and reactants. Kohonen SOMs allowed the correct assignment of 53-63% of the mixtures (in a test set). Counter-Propagation Neural Networks (CPNNs) gave origin to similar results. The use of supervised learning techniques allowed an improvement in the results. They were improved to 77% of correct assignments when an ensemble of ten FFNNs were used and to 80% when Random Forests were used. This study was performed with NMR data simulated from the molecular structure by the SPINUS program. In the design of one test set, simulated data was combined with experimental data. The results support the proposal of linking databases of chemical reactions to experimental or simulated NMR data for automatic classification of reactions and mixtures of reactions. Genome-scale classification of enzymatic reactions from their reaction equation. The MOLMAP descriptor relies on a Kohonen SOM that defines types of bonds on the basis of their physico-chemical and topological properties. The MOLMAP descriptor of a molecule represents the types of bonds available in that molecule. The MOLMAP descriptor of a reaction is defined as the difference between the MOLMAPs of the products and the reactants, and numerically encodes the pattern of bonds that are broken, changed, and made during a chemical reaction. The automatic perception of chemical similarities between metabolic reactions is required for a variety of applications ranging from the computer validation of classification systems, genome-scale reconstruction (or comparison) of metabolic pathways, to the classification of enzymatic mechanisms. Catalytic functions of proteins are generally described by the EC numbers that are simultaneously employed as identifiers of reactions, enzymes, and enzyme genes, thus linking metabolic and genomic information. Different methods should be available to automatically compare metabolic reactions and for the automatic assignment of EC numbers to reactions still not officially classified. In this study, the genome-scale data set of enzymatic reactions available in the KEGG database was encoded by the MOLMAP descriptors, and was submitted to Kohonen SOMs to compare the resulting map with the official EC number classification, to explore the possibility of predicting EC numbers from the reaction equation, and to assess the internal consistency of the EC classification at the class level. A general agreement with the EC classification was observed, i.e. a relationship between the similarity of MOLMAPs and the similarity of EC numbers. At the same time, MOLMAPs were able to discriminate between EC sub-subclasses. EC numbers could be assigned at the class, subclass, and sub-subclass levels with accuracies up to 92%, 80%, and 70% for independent test sets. The correspondence between chemical similarity of metabolic reactions and their MOLMAP descriptors was applied to the identification of a number of reactions mapped into the same neuron but belonging to different EC classes, which demonstrated the ability of the MOLMAP/SOM approach to verify the internal consistency of classifications in databases of metabolic reactions. RFs were also used to assign the four levels of the EC hierarchy from the reaction equation. EC numbers were correctly assigned in 95%, 90%, 85% and 86% of the cases (for independent test sets) at the class, subclass, sub-subclass and full EC number level,respectively. Experiments for the classification of reactions from the main reactants and products were performed with RFs - EC numbers were assigned at the class, subclass and sub-subclass level with accuracies of 78%, 74% and 63%, respectively. In the course of the experiments with metabolic reactions we suggested that the MOLMAP / SOM concept could be extended to the representation of other levels of metabolic information such as metabolic pathways. Following the MOLMAP idea, the pattern of neurons activated by the reactions of a metabolic pathway is a representation of the reactions involved in that pathway - a descriptor of the metabolic pathway. This reasoning enabled the comparison of different pathways, the automatic classification of pathways, and a classification of organisms based on their biochemical machinery. The three levels of classification (from bonds to metabolic pathways) allowed to map and perceive chemical similarities between metabolic pathways even for pathways of different types of metabolism and pathways that do not share similarities in terms of EC numbers. Mapping of PES by neural networks (NNs). In a first series of experiments, ensembles of Feed-Forward NNs (EnsFFNNs) and Associative Neural Networks (ASNNs) were trained to reproduce PES represented by the Lennard-Jones (LJ) analytical potential function. The accuracy of the method was assessed by comparing the results of molecular dynamics simulations (thermal, structural, and dynamic properties) obtained from the NNs-PES and from the LJ function. The results indicated that for LJ-type potentials, NNs can be trained to generate accurate PES to be used in molecular simulations. EnsFFNNs and ASNNs gave better results than single FFNNs. A remarkable ability of the NNs models to interpolate between distant curves and accurately reproduce potentials to be used in molecular simulations is shown. The purpose of the first study was to systematically analyse the accuracy of different NNs. Our main motivation, however, is reflected in the next study: the mapping of multidimensional PES by NNs to simulate, by Molecular Dynamics or Monte Carlo, the adsorption and self-assembly of solvated organic molecules on noble-metal electrodes. Indeed, for such complex and heterogeneous systems the development of suitable analytical functions that fit quantum mechanical interaction energies is a non-trivial or even impossible task. The data consisted of energy values, from Density Functional Theory (DFT) calculations, at different distances, for several molecular orientations and three electrode adsorption sites. The results indicate that NNs require a data set large enough to cover well the diversity of possible interaction sites, distances, and orientations. NNs trained with such data sets can perform equally well or even better than analytical functions. Therefore, they can be used in molecular simulations, particularly for the ethanol/Au (111) interface which is the case studied in the present Thesis. Once properly trained, the networks are able to produce, as output, any required number of energy points for accurate interpolations.

Towards e-learning 2.0: case study of an e-learning environment

In these days the learning experience is no longer confined within the four walls of a classroom. Computers and primarily the internet have broadened this horizon by creating a way of delivering education that is known as e-learning. In the meantime, the internet, or more precisely, the Web is heading towards a new paradigm where the user is no longer just a consumer of information and becomes an active part in the communication. This two-way channel where the user takes the role of the producer of content triggered the appearance of new types of services such as Social Networks, Blogs and Wikis. To seize this second generation of communities and services, educational vendors are willing to develop e-learning systems focused on the new and emergent users needs. This paper describes the analysis and specification of an e-learning environment at our School (ESEIG) towards this new Web generation, called PEACE – Project for ESEIG Academic Environment. This new model relies on the integration of several services controlled by teachers and students such as social networks, repositories libraries, e-portfolios and e-conference sytems, intelligent tutors, recommendation systems, automatic evaluators, virtual classrooms and 3D avatars.

Modelling an e-learning environment for learning programming languages

It is widely accepted that solving programming exercises is fundamental to learn how to program. Nevertheless, solving exercises is only effective if students receive an assessment on their work. An exercise solved wrong will consolidate a false belief, and without feedback many students will not be able to overcome their difficulties. However, creating, managing and accessing a large number of exercises, covering all the points in the curricula of a programming course, in classes with large number of students, can be a daunting task without the appropriated tools working in unison. This involves a diversity of tools, from the environments where programs are coded, to automatic program evaluators providing feedback on the attempts of students, passing through the authoring, management and sequencing of programming exercises as learning objects. We believe that the integration of these tools will have a great impact in acquiring programming skills. Our research objective is to manage and coordinate a network of eLearning systems where students can solve computer programming exercises. Networks of this kind include systems such as learning management systems (LMS), evaluation engines (EE), learning objects repositories (LOR) and exercise resolution environments (ERE). Our strategy to achieve the interoperability among these tools is based on a shared definition of programming exercise as a Learning Object (LO).

Using the learning tools interoperability framework for LMS integration in service oriented architectures

The LMS plays an indisputable role in the majority of the eLearning environments. This eLearning system type is often used for presenting, solving and grading simple exercises. However, exercises from complex domains, such as computer programming, require heterogeneous systems such as evaluation engines, learning objects repositories and exercise resolution environments. The coordination of networks of such disparate systems is rather complex. This work presents a standard approach for the coordination of a network of eLearning systems supporting the resolution of exercises. The proposed approach use a pivot component embedded in the LMS with two roles: provide an exercise resolution environment and coordinate the communication between the LMS and other systems exposing their functions as web services. The integration of the pivot component with the LMS relies on the Learning Tools Interoperability. The validation of this approach is made through the integration of the component with LMSs from two vendors.

Interoperability on e-learning 2.0: the PEACE case study

The confluence of education with the evolution of technology boosted the paradigm shift of the face-to-face learning to distance learning. In this scenario e-Learning plays an essential role as a facilitator of the teaching/learning process. However new demands associated with the new Web paradigm require that existent e-Learning environments characterized mostly by monolithic systems begin interacting with new specialized services. In this decentralized scenario the definition of a strategy of interoperability is the cornerstone to ensure the standardization communication among systems. This paper presents a definition of an interoperability strategy for an e-Learning environment at our School (ESEIG) called PEACE – Project for ESEIG Academic Content Environment. This new interoperability model relies on the application of several coordination and integration standards on several services, controlled by teachers and students, and included in the PEACE environment such as social networks, repositories, libraries, e-portfolios, intelligent tutors, recommendation systems and virtual classrooms.

Solar Intensity Forecasting using Artificial Neural Networks and Support Vector Machines

This paper presents several forecasting methodologies based on the application of Artificial Neural Networks (ANN) and Support Vector Machines (SVM), directed to the prediction of the solar radiance intensity. The methodologies differ from each other by using different information in the training of the methods, i.e, different environmental complementary fields such as the wind speed, temperature, and humidity. Additionally, different ways of considering the data series information have been considered. Sensitivity testing has been performed on all methodologies in order to achieve the best parameterizations for the proposed approaches. Results show that the SVM approach using the exponential Radial Basis Function (eRBF) is capable of achieving the best forecasting results, and in half execution time of the ANN based approaches.

High-Content Analysis of Breast Cancer Using Single-Cell Deep Transfer Learning

High-content analysis has revolutionized cancer drug discovery by identifying substances that alter the phenotype of a cell, which prevents tumor growth and metastasis. The high-resolution biofluorescence images from assays allow precise quantitative measures enabling the distinction of small molecules of a host cell from a tumor. In this work, we are particularly interested in the application of deep neural networks (DNNs), a cutting-edge machine learning method, to the classification of compounds in chemical mechanisms of action (MOAs). Compound classification has been performed using image-based profiling methods sometimes combined with feature reduction methods such as principal component analysis or factor analysis. In this article, we map the input features of each cell to a particular MOA class without using any treatment-level profiles or feature reduction methods. To the best of our knowledge, this is the first application of DNN in this domain, leveraging single-cell information. Furthermore, we use deep transfer learning (DTL) to alleviate the intensive and computational demanding effort of searching the huge parameter's space of a DNN. Results show that using this approach, we obtain a 30% speedup and a 2% accuracy improvement.

Learning Activities with Semantic. Hypermedia in Higher Education

The increasing use of information and communication technologies (ICT) in diverse professional and personal contexts calls for new knowledge, and a set of abilities, competences and attitudes, for an active and participative citizenship. In this context it is acknowledged that universities have an important role innovating in the educational use of digital media to promote an inclusive digital literacy. The educational potential of digital technologies and resources has been recognized by both researchers and practitioners. Multiple pedagogical models and research approaches have already contributed to put in evidence the importance of adapting instructional and learning practices and processes to concrete contexts and educational goals. Still, academic and scientific communities believe further investments in ICT research is needed in higher education. This study focuses on educational models that may contribute to support digital technology uses, where these can have cognitive and educational relevance when compared to analogical technologies. A teaching and learning model, centered in the active role of the students in the exploration, production, presentation and discussion of interactive multimedia materials, was developed and applied using the internet and exploring emergent semantic hypermedia formats. The research approach focused on the definition of design principles for developing class activities that were applied in three different iterations in undergraduate courses from two institutions, namely the University of Texas at Austin, USA and the University of Lisbon, Portugal. The analysis of this study made possible to evaluate the potential and efficacy of the model proposed and the authoring tool chosen in the support of metacognitive skills and attitudes related to information structuring and management, storytelling and communication, using computers and the internet.

The Visual and Virtual in Contemporary European Learning Contexts

Special issue of Anthropology in Action originated from the Working Images Conference, a joint meeting of TAN and VAN EASA networks

Blogues. Reflexões em ambientes de e-learning pela prática

Esta dissertação tem como referência o trabalho que realizamos no Ministério Público de Pernambuco, onde temos a oportunidade de observar e conhecer os serviços de acolhimento institucional para crianças e adolescentes, bem como da atuação de outros atores que atuam nesta área de medida protetiva, no Estado de Pernambuco. Aqui articularemos esta prática com os achados históricos, teóricos e legais vigentes em busca de estabelecer estratégias e ações de intervenção, para atuarmos neste contexto que geograficamente tem pontos de articulações distantes. Buscamos neste estudo analisar todos os lados de uma construção para a execução de uma plataforma que possa oferecer um serviço de capacitação em e-learning aos profissionais que atuam na área protetiva. Para isto precisaremos identificar o perfil destes profissionais e reconhecer que se, mesmo diante das dificuldades de sua profissão, eles se dispõem em participar de capacitação on-line voltado para a prática. Analisou-se o blog como um sistema adequado para se trabalhar com e-learning recorrendo à literatura para identificar quais os critérios, parâmetros e indicadores que faz um blog institucional de qualidade. Dando corpo ao nosso intento, faremos um percurso pelas teorias da aprendizagem buscando consistência para investigarmos se novas abordagens como o Conectivismo, responde ou não aos nossos anseios de formação continuada na prática e pela prática.

The World Health Organization Multi-Professional Patient Safety Curriculum : implementation of key modules and its impact on patient safety knowledge, skills, and attitudes of medical students at the University of Algarve

ABSTRACT - Objectives: We attempted to show how the implementation of the key elements of the World Health Organization Patient Safety Curriculum Guide Multi-professional Edition in an undergraduate curriculum affected the knowledge, skills, and attitudes towards patient safety in a graduate entry Portuguese Medical School. Methods: After receiving formal recognition by the WHO as a Complementary Test Site and approval of the organizational ethics committee , the validated pre-course questionnaires measuring the knowledge, skills, and attitudes to patient safety were administered to the 2nd and3rd year students pursuing a four-year course (N = 46). The key modules of the curriculum were implemented over the academic year by employing a variety of learning strategies including expert lecturers, small group problem-based teaching sessions, and Simulation Laboratory sessions. The identical questionnaires were then administered and the impact was measured. The Curriculum Guide was evaluated as a health education tool in this context. Results: A significant number of the respondents, 47 % (n = 22), reported having received some form of prior patient safety training. The effect on Patient Safety Knowledge was assessed by using the percentage of correct pre- and post-course answers to construct 2 × 2 contingency tables and by applying Fishers’ test (two-tailed). No significant differences were detected (p < 0.05). To assess the effect of the intervention on Patient Safety skills and attitudes, the mean and standard deviation were calculated for the pre and post-course responses, and independent samples were subjected to Mann-Whitney’s test. The attitudinal survey indicated a very high baseline incidence of desirable attitudes and skills toward patient safety. Significant changes were detected (p < 0.05) regarding what should happen if an error is made (p = 0.016), the role of healthcare organizations in error reporting (p = 0.006), and the extent of medical error (p = 0.005). Conclusions: The implementation of selected modules of the WHO Patient Safety Curriculum was associated with a number of positive changes regarding patient safety skills and attitudes, with a baseline incidence of highly desirable patient safety attitudes, but no measureable change on the patient safety knowledge, at the University of Algarve Medical School. The significance of these results is discussed along with implications and suggestions for future research.

Predicting market movement with Artificial Neural Networks

This paper presents an application of an Artificial Neural Network (ANN) to the prediction of stock market direction in the US. Using a multilayer perceptron neural network and a backpropagation algorithm for the training process, the model aims at learning the hidden patterns in the daily movement of the S&P500 to correctly identify if the market will be in a Trend Following or Mean Reversion behavior. The ANN is able to produce a successful investment strategy which outperforms the buy and hold strategy, but presents instability in its overall results which compromises its practical application in real life investment decisions.

Um modelo para a gestão do conhecimento organizacional no contexto dos serviços partilhados com recurso à utilização do e-Learning

Tese de Doutoramento em Tecnologias e Sistemas de Informação