Search

This paper presents a pedagogical agent designed to support students in an embodied, discovery-based learning environment. Discovery-based learning guides students through a set of activities designed to foster particular insights. In this case, the animated agent explains how to use the Mathematical Imagery Trainer for Proportionality, provides performance feedback, leads students to have different experiences and provides remedial instruction when required. It is a challenging task for agent technology as the amount of concrete feedback from the learner is very limited, here restricted to the location of two markers on the screen. A Dynamic Decision Network is used to automatically determine agent behavior, based on a deep understanding of the tutorial protocol. A pilot evaluation showed that all participants developed movement schemes supporting proto-proportional reasoning. They were able to provide verbal proto-proportional expressions for one of the taught strategies, but not the other.

This paper presents a pedagogical agent designed to support students in an embodied, discovery-based learning environment. Discovery-based learning guides students through a set of activities designed to foster particular insights. In this case, the animated agent explains how to use the Mathematical Imagery Trainer for Proportionality, provides performance feedback, leads students to have different experiences and provides remedial instruction when required. It is a challenging task for agent technology as the amount of concrete feedback from the learner is very limited, here restricted to the location of two markers on the screen. A Dynamic Decision Network is used to automatically determine agent behavior, based on a deep understanding of the tutorial protocol. A pilot evaluation showed that all participants developed movement schemes supporting proto-proportional reasoning. They were able to provide verbal proto-proportional expressions for one of the taught strategies, but not the other.

The Internet of Things (IoT) is rapidly gaining ground as can be witnessed by the pervasive presence of the many things or objects around us that turn our surroundings into intelligent environments. These objects interact on a large scale in wired and wireless sensor and actuator networks using advanced communication protocols. Hence, IoT is an open ended and highly dynamic ecosystem with heterogeneous workloads and fluctuating resource availability. Distributed intelligence for smart objects and platforms is a vital enabling factor for IoT, but finding the best strategy to deploy and configure applications - especially those that require contextual intelligence - in a smart environment with dynamic and heterogeneous resource availability is far from straightforward.Our experiments using context-aware applications for intelligent environments show that many resource and performance trade-offs exist and that current deployment schemes for these kind of applications are rough around the edges. We illustrate how a modular design philosophy for smart IoT applications enables a more optimal deployments. Furthermore, we present a methodology to inspect and learn the trade-offs of different deployment schemes of IoT applications in order to autonomously optimize their configuration. We validated our methodology on different use cases and scenarios, and the results demonstrate the feasibility of our approach to automate the efficient deployment of IoT applications in the presence of multiple conflicting Quality of Service (QoS) objectives and varying runtime circumstances. [ABSTRACT FROM AUTHOR]

There has been an increasing interest in employing decision-theoretic framework for learner modeling and provision of pedagogical support in Intelligent Tutoring Systems (ITSs). Much of the existing learner modeling research work focuses on identifying appropriate learner properties. Little attention, however, has been given to leverage Dynamic Decision Network (DDN) as a dynamic learner model to reason and intervene across time. Employing a DDN-based learner model in a scientific inquiry learning environment, however, remains at infant stage because there are factors contributed to the performance the learner model. Three factors have been identified to influence the matching accuracy of INQPRO’s learner model. These factors are the structure of DDN model, the variable instantiation approach, and the weights assignment method for two consecutive Decision Networks (DNs). In this research work, a two-phase empirical study involving 107 learners and six domain experts was conducted to determine the optimal conditions for the INQPRO’s dynamic learner model. The empirical results suggested each time-slice of the INQPRO’s DDN should consist of a DN, and that DN should correspond to the Graphical User Interface (GUI) accessed. In light of evidence, observable variables should be instantiated to their observed states; leaving the remaining observable nodes uninstantiated. The empirical results also indicated that varying weights between two consecutive DNs could optimize the matching accuracy of INQPRO’s dynamic learner model. [Copyright &y& Elsevier]

This article aims at discussing how Dynamic Decision Network (DDN) can be employed to tackle the challenges in modeling temporally variable scientific inquiry skills and provision of adaptive pedagogical interventions in INQPRO, a scientific inquiry exploratory learning environment for learning O'level Physics. We begin with an overview of INQPRO and a highlight of the computer algorithm as well as the design of our proposed DDN model. We then present an instance of interactions with INQPRO to describe how the proposed model can be generated dynamically by aggregating different INQPRO Graphical User Interfaces (GUIs) in real-time basis to perform probabilistic assessments of the two scientific inquiry skills (Hypothesis Formulation ? and Variable Identification ?). In this study, we carried out a two-phase empirical evaluation to investigate the performance of the proposed DDN model in categorizing different groups of learners. The performance of the proposed DDN model is identified by its matching accuracies elicited from a total of 6 domain experts and 77 learners who participated in both evaluation phases. Based on the empirical results, we summarized that the proposed DDN model is practically sound as it has demonstrated acceptable estimation accuracies with reference to the classification results obtained from the pretest, posttest, and from domain experts. [ABSTRACT FROM AUTHOR]

Dynamic decision networks have been used in many applications and they are particularly suited for monitoring applications. However, the networks tend to grow very large resulting in significant performance degradation. In this paper, we study the degeneration of relevance of uncertain temporal information and propose an analytical upper bound for the relevance time of information in a restricted class of dynamic decision networks with sparse evidence. An empirical generalization of this analytical result is presented along with a series of experimental results to verify the performance of the empirical upper bound. By discarding irrelevant and weakly relevant evidence, the performance of the network is significantly improved. [ABSTRACT FROM AUTHOR]