The role of regulation in medical student learning in small groups: Regulating oneself and others’ learning and emotions

This study examines the role of regulatory processes in medical students as they learn to deliver bad news to patients in the context of an international web-based problem based learning environment (PBL). In the PBL a medical facilitator and students work together to examine video cases on giving bad news and share their perspectives on what was done effectively and what could be done differently. We examine how regulation occurs within this collaboration. A synchronous computer-supported collaborative learning environment (CSCL) facilitated peer discussion at a distance using a combination of tools that included video-conferencing, chat boxes, and a shared whiteboard to support collaborative engagement. We examine regulation along a continuum, spanning from self- to co-regulation, in situations where medical students learn how to manage their own emotions and adapt their responses to patient reactions. We examine the nature of the discourse between medical students and facilitators to illustrate the conditions in which metacognitive, co-regulation and social emotional activities occur to enhance learning about how to communicate bad news to patients.     

Boosting learning and inference in Markov logic through metaheuristics

Markov Logic (ML) combines Markov networks (MNs) and first-order logic by attaching weights to first-order formulas and using these as templates for features of MNs. State-of-the-art structure learning algorithms in ML maximize the likelihood of a database by performing a greedy search in the space of structures. This can lead to suboptimal results because of the incapability of these approaches to escape local optima. Moreover, due to the combinatorially explosive space of potential candidates these methods are computationally prohibitive. We propose a novel algorithm for structure learning in ML, based on the Iterated Local Search (ILS) metaheuristic that explores the space of structures through a biased sampling of the set of local optima. We show through real-world experiments that the algorithm improves accuracy and learning time over the state-of-the-art algorithms. On the other side MAP and conditional inference for ML are hard computational tasks. This paper presents two algorithms for these tasks based on the Iterated Robust Tabu Search (IRoTS) metaheuristic. The first algorithm performs MAP inference and we show through extensive experiments that it improves over the state-of-the-art algorithm in terms of solution quality and inference time. The second algorithm combines IRoTS steps with simulated annealing steps for conditional inference and we show through experiments that it is faster than the current state-of-the-art algorithm maintaining the same inference quality.     

Can differences in learning strategies explain the benefits of learning from static and dynamic visualizations?

The effects of dynamic and static visualizations in understanding physical principles of fish locomotion were investigated. Seventy-five students were assigned to one of three conditions: a text-only, a text with dynamic visualizations, or a text with static visualizations condition. During learning, subjects were asked to think aloud. Learning outcomes were measured by tests assessing verbal factual knowledge, pictorial recall as well as transfer. Learners in the two visualization conditions outperformed those in the text-only condition for transfer and pictorial recall tasks, but not for verbal factual knowledge tasks. Analyses of the think-aloud protocols revealed that learners had generated more inferences in the visualization conditions as opposed to the text-only condition. These results were mirrored by students’ self-reported processing demands. No differences were observable between the dynamic and the static condition concerning any of the learning outcome measures. However, think-aloud protocols revealed an illusion of understanding when learning with dynamic as opposed to static visualizations. Furthermore, learners with static visualizations tended to play the visualizations more often. The results stress the importance of not only using outcome-oriented, but also process-oriented approaches to gain deeper insight into learning strategies when dealing with various instructional materials.     

Estimating variable structure and dependence in multitask learning via gradients

We consider the problem of hierarchical or multitask modeling where we simultaneously learn the regression function and the underlying geometry and dependence between variables. We demonstrate how the gradients of the multiple related regression functions over the tasks allow for dimension reduction and inference of dependencies across tasks jointly and for each task individually. We provide Tikhonov regularization algorithms for both classification and regression that are efficient and robust for high-dimensional data, and a mechanism for incorporating a priori knowledge of task (dis)similarity into this framework. The utility of this method is illustrated on simulated and real data.     

The use of machine learning and deep learning algorithms in functional magnetic resonance imaging—A systematic review

Functional Magnetic Resonance Imaging (fMRI) is presently one of the most popular techniques for analysing the dynamic states in brain images using various kinds of algorithms. From the last decade, there is an exponential rise in the use of the machine and deep learning algorithms of artificial intelligence for analysing fMRI data. However, it is a big challenge for every researcher to choose a suitable machine or deep learning algorithm for analysing fMRI data due to the availability of a large number of algorithms in the literature. It takes much time for each researcher to know about the various approaches and algorithms which are in use for fMRI data. This paper provides a review in a systematic manner for the present literature of fMRI data that makes use of the machine and deep learning algorithms. The major goals of this review paper are to (a) identify machine learning and deep learning research trends for the implementation of fMRI; (b) identify usage of Machine Learning Algorithms and deep learning in fMRI, and (c) help new researchers based on fMRI to put their new findings appropriately in existing domain of fMRI research. The results of this systematic review identified various fMRI studies and classified them based on fMRI types, mental diseases, use of machine learning and deep learning algorithms. The authors have provided the studies with the best performance of machine learning and deep learning algorithms used in fMRI. The authors believe that this systematic review will help incoming researchers on fMRI in their future works.     

Fault detection in autonomous robots based on fault injection and learning

In this paper, we study a new approach to fault detection for autonomous robots. Our hypothesis is that hardware faults change the flow of sensory data and the actions performed by the control program. By detecting these changes, the presence of faults can be inferred. In order to test our hypothesis, we collect data from three different tasks performed by real robots. During a number of training runs, we record sensory data from the robots while they are operating normally and after a fault has been injected. We use back-propagation neural networks to synthesize fault detection components based on the data collected in the training runs. We evaluate the performance of the trained fault detectors in terms of number of false positives and time it takes to detect a fault. The results show that good fault detectors can be obtained. We extend the set of possible faults and go on to show that a single fault detector can be trained to detect several faults in both a robot’s sensors and actuators. We show that fault detectors can be synthesized that are robust to variations in the task, and we show how a fault detector can be trained to allow one robot to detect faults that occur in another robot.

Simulation-based learning: The learning–forgetting–relearning process and impact of learning history

The results of empirical experiments evaluating the effectiveness and efficiency of the learning–forgetting–relearning process in a dynamic project management simulation environment are reported. Sixty-six graduate engineering students performed repetitive simulation-runs with a break period of several weeks between the runs. The students used a teaching tool called the project management trainer (PMT) that simulates a generic dynamic, stochastic project management environment. In this research, we focused on the effect of history recording mechanism on the learning forgetting process. Manual or automatic history recording mechanisms were used by the experimental group, while the control group did not use any history recording mechanism. The findings indicate that for the initial learning phase, the manual mechanism is better than the automatic mechanism. However, for the relearning phase, the break period length influenced the performance after the break. When the break period is short, the manual history keeping mechanism is better, but for a long period break, there is no significant difference. A comparison between the experimental group and the control group revealed that using any history recording mechanism reduced forgetting. Based on the findings, some practical implications of using simulators to improve the learning–forgetting process are discussed.     

A quantitative multimodal discourse analysis of teaching and learning in a web-conferencing environment – The efficacy of student-centred learning designs

This paper presents a quantitative approach to multimodal discourse analysis for analyzing online collaborative learning. The coding framework draws together the fields of systemic functional linguistics and Activity Theory to analyze interactions between collaborative-, content- and technology-related discourse. The approach is used to examine how the task subject matter, the activity design, and the choice of interface affected interaction and collaboration for a computing course conducted in a web-conferencing environment. The analysis revealed the critical impact of activity design on the amount and type of discourse that transpired. Student-centred designs resulted in over six times more student discourse as compared to teacher-centred designs and created a learning environment where students took greater ownership over the tasks and contributed more to the content-based discussion. The paper also incorporates a rationale for the approach to coding and a reflection on its efficacy for discourse analysis in technology-based learning environments.     

Applying online externally-facilitated regulated learning and computational thinking to improve students’ learning

This study aims to explore, via quasi-experiments, the effects of online externally-facilitated regulated learning (ERL) and computational thinking (CT) on improving students’ computing skills in a blended learning environment. Four classes in a one-semester course entitled ‘Applied Information Technology: Data Processing’ were the samples for this research. The first class (C1, ERL&CT group) simultaneously received the interventions regarding online ERL and CT, the second class (C2, CT group) received the intervention regarding online CT, and the third class (C3, ERL group) received the intervention regarding online CT, while the last group (C4, control group) received a traditional teaching method, although teaching was also conducted in a blended computing class. Students in ERL&CT group and CT group came from the Department of Finance, while the ERL group and control group came from the Department of Law at a comprehensive university. According to the posttest analysis, the results indicate that students who received the intervention of online ERL had statistically better development of computing skills for using Excel by semester-end than those without. In addition, this study also reveals that the application of online CT alone could be helpful in students’ development of computing skills. Furthermore, the results indicate that students’ computing skills could be improved under the condition of simultaneously applying ERL and CT. Based on the findings of this study, the authors present implications for online teachers and educators, particularly for those teaching computing courses.     

Re-transfer learning and multi-modal learning assisted early diagnosis of Alzheimer’s disease

Nowadays more and more elderly people are suffering from Alzheimer’s disease (AD). Finely recognizing mild cognitive impairment (MCI) in early stage of the symptom is vital for AD therapy. However, brain image samples are relatively scarce, meanwhile have multiple modalities, which makes finely classifying brain images by computers extremely difficult. This paper proposes a fine-grained brain image classification approach for diagnosing Alzheimer’s disease, with re-transfer learning and multi-modal learning. First of all, an end-to-end deep neural network classifier CNN4AD is designed to finely classify diffusion tensor image (DTI) into four categories. And according to the characteristics of multi-modal brain image dataset, the re-transfer learning method is proposed based on transfer learning and multi-modal learning theories. Experimental results show that the proposed approach obtain higher accuracy with less labeled training samples. This could help doctors diagnose Alzheimer’s disease more timely and accurately.

     

QSIA – a Web-based environment for learning,assessing and knowledge sharing in communities

This paper describes a Web-based and distributed system named QSIA that serves as an environment for learning, assessing and knowledge sharing. QSIA – Questions Sharing and Interactive Assignments – offers a unified infrastructure for developing, collecting, managing and sharing of knowledge items. QSIA enhances collaboration in authoring via online recommendations and generates communities of teachers and learners. At the same time, QSIA fosters individual learning and might promote high-order thinking skills among its users. QSIA's community, conceptual architecture, structure overview and implementations are discussed.     

Impact of hand-assisted viewing on user performance and?learning patterns in virtual environments

The ability to locate, select and interact with objects is fundamental to most Virtual Reality (VR) applications. Recently, it was demonstrated that the virtual hand metaphor, a technique commonly used for these tasks, can also be employed to control the virtual camera, resulting in improved performance and user evaluation in visual search tasks.     

Pre-service teachers’ skills and perceptions about the use of virtual learning environments to improve teaching and learning

This paper explores data retrieved from Educational Immersive Virtual Worlds to describe pre-service teachers’ skills and perceptions about the simulation tasks. This project had 10 participants who were immersed for 3 years in the Technology and Pedagogical Models in Immersive Worlds island, a multi-user virtual environment in Second Life and Open Simulator. In this project, we evaluated how three-dimensional virtual environments can facilitate the achievement of teaching and learning processes. Based on quantitative and qualitative methodologies, two data collection instruments were applied. Through observation grids and personal log books, professional performance of the 18 pedagogical challenges implemented was collected. The statistical analysis shows that the students improved their technology skills and educational aspects about good practices in classes, regardless of the type of platform used. The analysis through Constant Comparing Method reported a positive assessment of the use of virtual environments, especially about the use of teaching strategies. Main conclusions regarding the pedagogical context reflect the importance of peer assessment on teaching performance, as well as the complexity of role-plays as intellectual challenges to enhance pre-service teachers’ skills. The main difficulties identified during the development of the activities were technical in nature, reporting hardware and connectivity issues.     

An optimization methodology for machine learning strategies and?regression problems in ballistic impact scenarios

In domains with limited data, such as ballistic impact, prior researches have proven that the optimization of artificial neural models is an efficient tool for improving the performance of a classifier based on MultiLayer Perceptron. In addition, this research aims to explore, in the ballistic domain, the optimization of other machine learning strategies and their application in regression problems. Therefore, this paper presents an optimization methodology to use with several approaches of machine learning in regression problems, maximizing the limited dataset and locating the best network topology and input vector of each network model. This methodology is tested in real regression scenarios of ballistic impact with different artificial neural models, obtaining substantial improvement in all the experiments. Furthermore, the quality stage, based on criteria of information theory, enables the determination of when the complexity of the network design does not penalize the fit over the data and thereby the selection of the best neural network model from a series of candidates. Finally, the results obtained show the relevance of this methodology and its application improves the performance and efficiency of multiple machine learning strategies in regression scenarios.     

Mining students’ behavior in web-based learning programs

There has been a proliferation of web-based learning programs (WBLPs). Unlike traditional computer-based learning programs, WBLPs are used by a population of learners who have diverse background. How different learners access the WBLPs has been investigated by several studies, which indicate that cognitive style is an important factor that influences learners’ preferences. However, these studies mainly use statistical methods to analyze learners’ preferences. In this paper, we propose to analyze learners’ preferences with a data mining technique. Findings in our study show that Field Independent learners frequently use backward/forward buttons and spent less time for navigation. On the other hand, Field Dependent learners often use main menu and have more repeated visiting. Implications for these findings are discussed.     

Efficient behavior learning in human–robot collaboration

We present a novel method for a robot to interactively learn, while executing, a joint human–robot task. We consider collaborative tasks realized by a team of a human operator and a robot helper that adapts to the human’s task execution preferences. Different human operators can have different abilities, experiences, and personal preferences so that a particular allocation of activities in the team is preferred over another. Our main goal is to have the robot learn the task and the preferences of the user to provide a more efficient and acceptable joint task execution. We cast concurrent multi-agent collaboration as a semi-Markov decision process and show how to model the team behavior and learn the expected robot behavior. We further propose an interactive learning framework and we evaluate it both in simulation and on a real robotic setup to show the system can effectively learn and adapt to human expectations.     

Has Web 2.0 revitalized informal learning? The relationship between Web 2.0 and informal learning

Learning is becoming increasingly self‐directed and often occurs away from schools and other formal educational settings. The development of a myriad of new technologies for learning has enabled people to learn anywhere and anytime. Web 2.0 technology allows researchers to shed a new light on the importance and prevalence of informal learning. However, there are few empirical studies that support the claim that this technology facilitates informal learning. The present study investigates the relationship between Web 2.0 levels and the evaluation of informal learning websites. For this purpose, 287 informal learning websites were selected and their Web 2.0 levels were rated based upon eight criteria proposed in the Web 2.0 exploratory literature. In addition, previously examined informal learning evaluation results were employed. The results showed that current informal learning websites have moderately adopted the most heavily promoted features of Web 2.0. Correlation analyses showed a positive relationship between Web 2.0 features and informal learning website ratings. The implications for the relationship and internal correlations of variables were summarized and discussed.     

Implementing digital game-based learning in schools: augmented learning environment of ‘Europe 2045’

It is widely agreed that the traditional process of schooling can benefit from the usage of computers as supportive tools. Of various approaches using computers in education over the last decade, e-learning and edutainment have become the most prominent. Recently, a number of authors have criticised these approaches arguing that they conserve traditional ‘drill and practice’ behaviouristic methods of teaching instead of enhancing and augmenting them. It has been proposed that a ‘paradigm shift’ is needed and that this shift may come through utilizing all the advantages of full-fledged video games, so-called digital game-based learning (DGBL). However, several case studies reported serious problems with the DGBL. Among the most notable issues are the lack of acceptance of games as an educational tool, problems with integration of games into formal schooling environments, and the so-called transfer problem, which is the problem of the inherent tension between game play and learning objectives, the tension that mitigates the ability of students to transfer knowledge gained in the video game to the real-world context. Here, we present a framework for an augmented learning environment (ALE), which verbalises one way of how these problems can be challenged. The ALE framework has been constructed based on our experience with the educational game, Europe 2045, which we developed and which has been implemented in a number of secondary schools in the Czech Republic during 2008. The key feature of this game is that it combines principles of on-line multi-player computer games with social, role-playing games. The evaluation which we present in this paper indicates the successful integration of the game and its acceptance by teachers and students. The ALE framework isolates key principles of the game contributing to this success, abstracts them into theoretical entities we call action-based spaces and causal and grounding links, and condenses them in a coherent methodological structure, which paves the way for further exploitation of the DGBL by educational game researchers and designers.     

Centroid-based memetic algorithm – adaptive Lamarckian and Baldwinian learning

The application of specific learning schemes in memetic algorithms (MAs) can have significant impact on their performances. One main issue revolves around two different learning schemes, specifically, Lamarckian and Baldwinian. It has been shown that the two learning schemes are better suited for different types of problems and some previous studies have attempted to combine both learning schemes as a means to develop a single optimisation framework capable of solving more classes of problems. However, most of the past approaches are often implemented heuristically and have not investigated the effect of different learning scheme on noisy design optimisation. In this article, we introduce a simple probabilistic approach to address this issue. In particular, we investigate a centroid-based approach that combines the two learning schemes within an MA framework (centroid-based MS; CBMA) through the effective allocation of resources (in terms of local search cost) that are based on information obtained during the optimisation process itself. A scheme that applies the right learning scheme (Lamarckian or Baldwinian) at the right time (during search) would lead to higher search performance. We conducted an empirical study to test this hypothesis using two different types of benchmark problems. The first problem set consists of simple benchmark problems whereby the problem landscape is static and gradient information can be obtained accurately. These problems are known to favour Lamarckian learning while Baldwinian learning is known to exhibit slower convergence. The second problem set consists of noisy versions of the first problem set whereby the problem landscape is dynamic as a result of the random noise perturbation injected into the design vector. These problems are known to favour learning processes that re-sample search points such as Baldwinian learning. Our experiments show that CBMA manages to adaptively allocate resources productively according to problem in most of the cases.