The influence of a novel simulated learning environment upon student clinical subjective refraction performance: A pilot study

Background: Optometry students are taught the process of subjective refraction through lectures and laboratory based practicals before progressing to supervised clinical practice. Simulated learning environments (SLEs) are an emerging technology that are used in a range of health disciplines, however, there is limited evidence regarding the effectiveness of clinical simulators as an educational tool. Methods: Forty optometry students (20 fourth year and 20 fifth year) were assessed twice by a qualified optometrist (two examinations separated by 4-8 weeks) while completing a monocular non-cycloplegic subjective refraction on the same patient with an unknown refractive error simulated using contact lenses. Half of the students were granted access to an online SLE, The Brien Holden Vision Institute (BHVI®) Virtual Refractor, and the remaining students formed a control group. The primary outcome measures at each visit were; accuracy of the clinical refraction compared to a qualified optometrist and relative to the Optometry Council of Australia and New Zealand (OCANZ) subjective refraction examination criteria. Secondary measures of interest included descriptors of student SLE engagement, student self-reported confidence levels and correlations between performance in the simulated and real world clinical environment. Results: Eighty percent of students in the intervention group interacted with the SLE (for an average of 100 minutes); however, there was no correlation between measures of student engagement with the BHVI® Virtual Refractor and speed or accuracy of clinical subjective refractions. Fifth year students were typically more confident and refracted more accurately and quickly than fourth year students. A year group by experimental group interaction (p = 0.03) was observed for accuracy of the spherical component of refraction, and post hoc analysis revealed that less experienced students exhibited greater gains in clinical accuracy following exposure to the SLE intervention. Conclusions: Short-term exposure to a SLE can positively influence clinical subjective refraction outcomes for less experienced optometry students and may be of benefit in increasing the skills of novice refractionists to levels appropriate for commencing supervised clinical interactions.

Multiple instance dictionary learning for activity representation

This paper presents an effective feature representation method in the context of activity recognition. Efficient and effective feature representation plays a crucial role not only in activity recognition, but also in a wide range of applications such as motion analysis, tracking, 3D scene understanding etc. In the context of activity recognition, local features are increasingly popular for representing videos because of their simplicity and efficiency. While they achieve state-of-the-art performance with low computational requirements, their performance is still limited for real world applications due to a lack of contextual information and models not being tailored to specific activities. We propose a new activity representation framework to address the shortcomings of the popular, but simple bag-of-words approach. In our framework, first multiple instance SVM (mi-SVM) is used to identify positive features for each action category and the k-means algorithm is used to generate a codebook. Then locality-constrained linear coding is used to encode the features into the generated codebook, followed by spatio-temporal pyramid pooling to convey the spatio-temporal statistics. Finally, an SVM is used to classify the videos. Experiments carried out on two popular datasets with varying complexity demonstrate significant performance improvement over the base-line bag-of-feature method.

Blended learning in medical imaging pre-clinical skills training – does it work?

Undergraduate Medical Imaging (MI)students at QUT attend their first clinical placement towards the end of semester two. Students undertake two (pre)clinical skills development units – one theory and one practical. Students gain good contextual and theoretical knowledge during these units via a blended learning model with multiple learning methods employed. Students attend theory lectures, practical sessions, tutorial sessions in both a simulated and virtual environment and also attend pre-clinical scenario based tutorial sessions. The aim of this project is to evaluate the use of blended learning in the context of 1st year Medical Imaging Radiographic Technique and its effectiveness in preparing students for their first clinical experience. It is hoped that the multiple teaching methods employed within the pre-clinical training unit at QUT builds students clinical skills prior to the real situation. A quantitative approach will be taken, evaluating via pre and post clinical placement surveys. This data will be correlated with data gained in the previous year on the effectiveness of this training approach prior to clinical placement. In 2014 59 students were surveyed prior to their clinical placement demonstrated positive benefits of using a variety of learning tools to enhance their learning. 98.31%(n=58)of students agreed or strongly agreed that the theory lectures were a useful tool to enhance their learning. This was followed closely by 97% (n=57) of the students realising the value of performing role-play simulation prior to clinical placement. Tutorial engagement was considered useful for 93.22% (n=55) whilst 88.14% (n=52) reasoned that the x-raying of phantoms in the simulated radiographic laboratory was beneficial. Self-directed learning yielded 86.44% (n=51). The virtual reality simulation software was valuable for 72.41% (n=42) of the students. Of the 4 students that disagreed or strongly disagreed with the usefulness of any tool they strongly agreed to the usefulness of a minimum of one other learning tool. The impact of the blended learning model to meet diverse student needs continues to be positive with students engaging in most offerings. Students largely prefer pre -clinical scenario based practical and tutorial sessions where 'real-world’ situations are discussed.

Efficient algorithms for learning kernels from multiple similarity matrices with general convex loss functions

In this paper we consider the problem of learning an n × n kernel matrix from m(1) similarity matrices under general convex loss. Past research have extensively studied the m = 1 case and have derived several algorithms which require sophisticated techniques like ACCP, SOCP, etc. The existing algorithms do not apply if one uses arbitrary losses and often can not handle m > 1 case. We present several provably convergent iterative algorithms, where each iteration requires either an SVM or a Multiple Kernel Learning (MKL) solver for m > 1 case. One of the major contributions of the paper is to extend the well knownMirror Descent(MD) framework to handle Cartesian product of psd matrices. This novel extension leads to an algorithm, called EMKL, which solves the problem in O(m2 log n 2) iterations; in each iteration one solves an MKL involving m kernels and m eigen-decomposition of n × n matrices. By suitably defining a restriction on the objective function, a faster version of EMKL is proposed, called REKL,which avoids the eigen-decomposition. An alternative to both EMKL and REKL is also suggested which requires only an SVMsolver. Experimental results on real world protein data set involving several similarity matrices illustrate the efficacy of the proposed algorithms.

Learning polyhedral classifiers using logistic function

In this paper we propose a new algorithm for learning polyhedral classifiers. In contrast to existing methods for learning polyhedral classifier which solve a constrained optimization problem, our method solves an unconstrained optimization problem. Our method is based on a logistic function based model for the posterior probability function. We propose an alternating optimization algorithm, namely, SPLA1 (Single Polyhedral Learning Algorithm1) which maximizes the loglikelihood of the training data to learn the parameters. We also extend our method to make it independent of any user specified parameter (e.g., number of hyperplanes required to form a polyhedral set) in SPLA2. We show the effectiveness of our approach with experiments on various synthetic and real world datasets and compare our approach with a standard decision tree method (OC1) and a constrained optimization based method for learning polyhedral sets.

Learning from positive and unlabelled examples using maximum margin clustering

Learning from Positive and Unlabelled examples (LPU) has emerged as an important problem in data mining and information retrieval applications. Existing techniques are not ideally suited for real world scenarios where the datasets are linearly inseparable, as they either build linear classifiers or the non-linear classifiers fail to achieve the desired performance. In this work, we propose to extend maximum margin clustering ideas and present an iterative procedure to design a non-linear classifier for LPU. In particular, we build a least squares support vector classifier, suitable for handling this problem due to symmetry of its loss function. Further, we present techniques for appropriately initializing the labels of unlabelled examples and for enforcing the ratio of positive to negative examples while obtaining these labels. Experiments on real-world datasets demonstrate that the non-linear classifier designed using the proposed approach gives significantly better generalization performance than the existing relevant approaches for LPU.

Natural actor and belief critic: Reinforcement algorithm for learning parameters of dialogue systems modelled as POMDPs

This article presents a novel algorithm for learning parameters in statistical dialogue systems which are modeled as Partially Observable Markov Decision Processes (POMDPs). The three main components of a POMDP dialogue manager are a dialogue model representing dialogue state information; a policy that selects the system's responses based on the inferred state; and a reward function that specifies the desired behavior of the system. Ideally both the model parameters and the policy would be designed to maximize the cumulative reward. However, while there are many techniques available for learning the optimal policy, no good ways of learning the optimal model parameters that scale to real-world dialogue systems have been found yet. The presented algorithm, called the Natural Actor and Belief Critic (NABC), is a policy gradient method that offers a solution to this problem. Based on observed rewards, the algorithm estimates the natural gradient of the expected cumulative reward. The resulting gradient is then used to adapt both the prior distribution of the dialogue model parameters and the policy parameters. In addition, the article presents a variant of the NABC algorithm, called the Natural Belief Critic (NBC), which assumes that the policy is fixed and only the model parameters need to be estimated. The algorithms are evaluated on a spoken dialogue system in the tourist information domain. The experiments show that model parameters estimated to maximize the expected cumulative reward result in significantly improved performance compared to the baseline hand-crafted model parameters. The algorithms are also compared to optimization techniques using plain gradients and state-of-the-art random search algorithms. In all cases, the algorithms based on the natural gradient work significantly better. © 2011 ACM.

Temporal difference models describe higher-order learning in humans.

The ability to use environmental stimuli to predict impending harm is critical for survival. Such predictions should be available as early as they are reliable. In pavlovian conditioning, chains of successively earlier predictors are studied in terms of higher-order relationships, and have inspired computational theories such as temporal difference learning. However, there is at present no adequate neurobiological account of how this learning occurs. Here, in a functional magnetic resonance imaging (fMRI) study of higher-order aversive conditioning, we describe a key computational strategy that humans use to learn predictions about pain. We show that neural activity in the ventral striatum and the anterior insula displays a marked correspondence to the signals for sequential learning predicted by temporal difference models. This result reveals a flexible aversive learning process ideally suited to the changing and uncertain nature of real-world environments. Taken with existing data on reward learning, our results suggest a critical role for the ventral striatum in integrating complex appetitive and aversive predictions to coordinate behaviour.

Freedom to learn: a radically revised pedagogy to facilitate lifewide learning in the academic curriculum.

Higher education has progressed fairly steadily to a common pedagogical approach which centres on the idea of alignment. In this arrangement, intended learning outcomes are identified and declared; learning activities which will enable the desired learning and development to be achieved are conceived and undertaken with the support of appropriate and effective teaching; and assessment which calls for these outcomes is (ideally) carefully designed and implemented. All three elements are aligned in advance. The same principles and practices underpinned by notions of alignment have been applied to date in most of the purposeful schemes for personal development planning. In this chapter I argue that lifewide learning, wherein learning and development often occur incidentally in multiple and varied real-world situations throughout an individual’s life course, calls for a different approach, and a different pedagogy. Higher education should therefore visualise lifewide learning as an emergent phenomenon wherein the outcomes of learning emerge later on, and are often unintended. Consequently, they cannot be defined in advance of the activities through which they are formed. The main purpose of this chapter is to offer some practical ideas to support the development of pedagogies that would enable programme designers to embed in their programmes the principle and practice of lifewide education.

Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics

Meng, Q., & Lee, M. (2005). Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics. Wermter, S., Palm, G., & Elshaw, M. (Eds.), In: Biomimetic Neural Learning for Intelligent Robots: Intelligent Systems, Cognitive Robotics, and Neuroscience. (pp. 315-332). (Lecture Notes in Computer Science). Springer Berlin Heidelberg.

Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics

Q. Meng and M. H. Lee, Novelty and Habituation: the Driving Forces in Early Stage Learning for Developmental Robotics, AI-Workshop on NeuroBotics, University of Ulm, Germany. September 2004.

Leveraging lessons learned in organizations through implementing practice-based organizational learning and performance improvement - An opportunity for context-based intelligent assistant support (CIAS)

Organizations that leverage lessons learned from their experience in the practice of complex real-world activities are faced with five difficult problems. First, how to represent the learning situation in a recognizable way. Second, how to represent what was actually done in terms of repeatable actions. Third, how to assess performance taking account of the particular circumstances. Fourth, how to abstract lessons learned that are re-usable on future occasions. Fifth, how to determine whether to pursue practice maturity or strategic relevance of activities. Here, organizational learning and performance improvement are investigated in a field study using the Context-based Intelligent Assistant Support (CIAS) approach. A new conceptual framework for practice-based organizational learning and performance improvement is presented that supports researchers and practitioners address the problems evoked and contributes to a practice-based approach to activity management. The novelty of the research lies in the simultaneous study of the different levels involved in the activity. Route selection in light rail infrastructure projects involves practices at both the strategic and operational levels; it is part managerial/political and part engineering. Aspectual comparison of practices represented in Contextual Graphs constitutes a new approach to the selection of Key Performance Indicators (KPIs). This approach is free from causality assumptions and forms the basis of a new approach to practice-based organizational learning and performance improvement. The evolution of practices in contextual graphs is shown to be an objective and measurable expression of organizational learning. This diachronic representation is interpreted using a practice-based organizational learning novelty typology. This dissertation shows how lessons learned when effectively leveraged by an organization lead to practice maturity. The practice maturity level of an activity in combination with an assessment of an activity’s strategic relevance can be used by management to prioritize improvement effort.

A critical realist examination of the inhibitors of double loop learning in an agile adoption

The original solution to the high failure rate of software development projects was the imposition of an engineering approach to software development, with processes aimed at providing a repeatable structure to maintain a consistency in the ‘production process’. Despite these attempts at addressing the crisis in software development, others have argued that the rigid processes of an engineering approach did not provide the solution. The Agile approach to software development strives to change how software is developed. It does this primarily by relying on empowered teams of developers who are trusted to manage the necessary tasks, and who accept that change is a necessary part of a development project. The use of, and interest in, Agile methods in software development projects has expanded greatly, yet this has been predominantly practitioner driven. There is a paucity of scientific research on Agile methods and how they are adopted and managed. This study aims at addressing this paucity by examining the adoption of Agile through a theoretical lens. The lens used in this research is that of double loop learning theory. The behaviours required in an Agile team are the same behaviours required in double loop learning; therefore, a transition to double loop learning is required for a successful Agile adoption. The theory of triple loop learning highlights that power factors (or power mechanisms in this research) can inhibit the attainment of double loop learning. This study identifies the negative behaviours - potential power mechanisms - that can inhibit the double loop learning inherent in an Agile adoption, to determine how the Agile processes and behaviours can create these power mechanisms, and how these power mechanisms impact on double loop learning and the Agile adoption. This is a critical realist study, which acknowledges that the real world is a complex one, hierarchically structured into layers. An a priori framework is created to represent these layers, which are categorised as: the Agile context, the power mechanisms, and double loop learning. The aim of the framework is to explain how the Agile processes and behaviours, through the teams of developers and project managers, can ultimately impact on the double loop learning behaviours required in an Agile adoption. Four case studies provide further refinement to the framework, with changes required due to observations which were often different to what existing literature would have predicted. The study concludes by explaining how the teams of developers, the individual developers, and the project managers, working with the Agile processes and required behaviours, can inhibit the double loop learning required in an Agile adoption. A solution is then proposed to mitigate these negative impacts. Additionally, two new research processes are introduced to add to the Information Systems research toolkit.

Learning Bayesian networks from data: An information-theory based approach

This paper provides algorithms that use an information-theoretic analysis to learn Bayesian network structures from data. Based on our three-phase learning framework, we develop efficient algorithms that can effectively learn Bayesian networks, requiring only polynomial numbers of conditional independence (CI) tests in typical cases. We provide precise conditions that specify when these algorithms are guaranteed to be correct as well as empirical evidence (from real world applications and simulation tests) that demonstrates that these systems work efficiently and reliably in practice.