Learning-based Relevance Feedback for Web-based Relation Completion

In a pilot application based on web search engine calledWeb-based Relation Completion (WebRC), we propose to join two columns of entities linked by a predefined relation by mining knowledge from the web through a web search engine. To achieve this, a novel retrieval task Relation Query Expansion (RelQE) is modelled: given an entity (query), the task is to retrieve documents containing entities in predefined relation to the given one. Solving this problem entails expanding the query before submitting it to a web search engine to ensure that mostly documents containing the linked entity are returned in the top K search results. In this paper, we propose a novel Learning-based Relevance Feedback (LRF) approach to solve this retrieval task. Expansion terms are learned from training pairs of entities linked by the predefined relation and applied to new entity-queries to find entities linked by the same relation. After describing the approach, we present experimental results on real-world web data collections, which show that the LRF approach always improves the precision of top-ranked search results to up to 8.6 times the baseline. Using LRF, WebRC also shows performances way above the baseline.

Can playing Monopoly™ enhance learning for property students

This paper outlines the initial results from a pilot study into the educational use of the board game Monopoly City™ in a first year property economics unit. This game play was introduced as a fun and interactive way of achieving a number of desired outcomes including: enhanced engagement of first year students; introduction of foundational threshold concepts in property education; introduction of problem solving and critical analysis skills; early acculturation of property students to enhance student retention; and early team building within the Property Economics cohort, all in an engaging and entertaining way. Preliminary results in this research project are encouraging. The students participating in this initial cycle have demonstrated explicit linkages between their Monopoly City™ experiences and foundation urban economic and valuation theories. Students are also recognising the role strategy and chance play in the property sector. However, linking Monopoly City™ activities to assessment has proved important in student attendance and hence engagement.

Machine learning for activity recognition : hip versus wrist data

Problem addressed Wrist-worn accelerometers are associated with greater compliance. However, validated algorithms for predicting activity type from wrist-worn accelerometer data are lacking. This study compared the activity recognition rates of an activity classifier trained on acceleration signal collected on the wrist and hip. Methodology 52 children and adolescents (mean age 13.7 +/- 3.1 year) completed 12 activity trials that were categorized into 7 activity classes: lying down, sitting, standing, walking, running, basketball, and dancing. During each trial, participants wore an ActiGraph GT3X+ tri-axial accelerometer on the right hip and the non-dominant wrist. Features were extracted from 10-s windows and inputted into a regularized logistic regression model using R (Glmnet + L1). Results Classification accuracy for the hip and wrist was 91.0% +/- 3.1% and 88.4% +/- 3.0%, respectively. The hip model exhibited excellent classification accuracy for sitting (91.3%), standing (95.8%), walking (95.8%), and running (96.8%); acceptable classification accuracy for lying down (88.3%) and basketball (81.9%); and modest accuracy for dance (64.1%). The wrist model exhibited excellent classification accuracy for sitting (93.0%), standing (91.7%), and walking (95.8%); acceptable classification accuracy for basketball (86.0%); and modest accuracy for running (78.8%), lying down (74.6%) and dance (69.4%). Potential Impact Both the hip and wrist algorithms achieved acceptable classification accuracy, allowing researchers to use either placement for activity recognition.

Prediction of activity type in preschool children using machine learning techniques

Objectives Recent research has shown that machine learning techniques can accurately predict activity classes from accelerometer data in adolescents and adults. The purpose of this study is to develop and test machine learning models for predicting activity type in preschool-aged children. Design Participants completed 12 standardised activity trials (TV, reading, tablet game, quiet play, art, treasure hunt, cleaning up, active game, obstacle course, bicycle riding) over two laboratory visits. Methods Eleven children aged 3–6 years (mean age = 4.8 ± 0.87; 55% girls) completed the activity trials while wearing an ActiGraph GT3X+ accelerometer on the right hip. Activities were categorised into five activity classes: sedentary activities, light activities, moderate to vigorous activities, walking, and running. A standard feed-forward Artificial Neural Network and a Deep Learning Ensemble Network were trained on features in the accelerometer data used in previous investigations (10th, 25th, 50th, 75th and 90th percentiles and the lag-one autocorrelation). Results Overall recognition accuracy for the standard feed forward Artificial Neural Network was 69.7%. Recognition accuracy for sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running was 82%, 79%, 64%, 36% and 46%, respectively. In comparison, overall recognition accuracy for the Deep Learning Ensemble Network was 82.6%. For sedentary activities, light activities and games, moderate-to-vigorous activities, walking, and running recognition accuracy was 84%, 91%, 79%, 73% and 73%, respectively. Conclusions Ensemble machine learning approaches such as Deep Learning Ensemble Network can accurately predict activity type from accelerometer data in preschool children.

The Artful Interpretation of Science through Picture Books

Science picture books offer pleasurable and educational reading experiences. These texts open up opportunities for cross-curriculum teaching and learning and a means for developing students’ visual literacy skills, aesthetic appreciation, and higher level thinking skills. Picture books demonstrate how one mode or semiotic system (visual and verbal) mediates the other, often complementing, extending, and filling-in the gaps between words and images. Students’ meaning making is further extended when they can understand the subtleties and effects (and affects) of the visual elements of art and design, and the different styles of writing and language use.

Incorporating anchored learning in a C# intelligent tutoring system

This research showed that one solution that can be used to help the students learn how to program is by providing a system that can behave like a tutor to teach the students individually. An intelligent tutoring system named CSTutor was built in this research to assist the students. CSTutor asks the student to write programs in a role playing environment, presenting the most appropriate tasks to the students, and provides help to the students' problems.

Factors influencing Saudi Arabian optometry candidates' career choices and institution of learning. Why do Saudi students choose to study optometry?

Optometry is a primary health-care profession (PHCP) and this study aimed to elucidate the factors influencing the choice of optometry as a career for Saudi students, the students' perceptions of optometry and the effect of gender. METHODS Two hundred and forty-seven students whose average age was 21.7 ± 1.5 (SD) years and who are currently enrolled in two colleges of optometry in Saudi Arabia--King Saud University (KSU) and Qassim University (QU)--completed self-administered questionnaires. The survey included questions concerning demography, career first choice, career perception and factors influencing career choices. RESULTS The response rate was 87.6 per cent and there were 161 male (64.9 per cent) students. Seventy-nine per cent of the participants were from KSU (males and females) and 20.6 per cent were from QU (only males). Seventy-three per cent come from Riyadh and 19 per cent are from Qassim province. Regarding the first choice for their careers, the females (92 per cent) were 0.4 times more likely (p = 0.012) to choose optometry than males (78.3 per cent). The males were significantly more likely to be influenced by the following factors: the Doctor of Optometry (OD) programs run at both universities, good salary and prospects (p < 0.05, for all). The women were significantly less likely to be influenced by another individual (p = 0.0004). Generally, more than two-thirds of the respondents viewed the desire to help others, professional prestige and the new OD programs as the three most influential factors in opting for a career in optometry. CONCLUSION Females were more likely to opt for a career in optometry and males were more likely to be influenced by the new OD programs, good salary and job prospects. Service provision to others in the community was a primary motivation to opt for a career in optometry among young Saudis.

Dynamic digital posters : making the most of collaborative learning spaces

Academic and professional staff at Queensland University of Technology (QUT) have been faced with the challenge of how to create engaging student experiences in collaborative learning spaces. In 2013 a new Bachelor of Science course was implemented focusing on inquiry-based, collaborative and active learning. Student groups in two of the first year units carried out a poster assessment task. This paper provides a preliminary evaluation of the assessment approach used, whereby students created dynamic digital posters to capitalise on the affordances of the learning space.

Designing for collaborative learning spaces : an academic staff development pilot program

To prepare for the delivery of new Bachelor of Science units in collaborative learning spaces, academic and professional staff at Queensland University of Technology piloted an academic development program over the period of a semester. The program was informed by Rogers’ theory of innovation and diffusion (2003) and structured according to Wilson’s framework for faculty development (2007). Through a series of workshops and group mentoring activities, the program modelled inquiry-based learning in a collaborative learning space, and the participants designed and practiced the delivery of teaching activities. This paper provides a preliminary evaluation of the effectiveness of the pilot based on survey responses from participants, notes from the development team who coordinated the program and audience feedback from the final showcase session. The design and structure of the program is discussed as well as possible future directions.

'Women on a Wiki’ : the role of interactive websites in reflective learning practices for undergraduate women’s health students

Aim Our pedagogical research addressed the following research questions: 1) Can shared ‘cyber spaces’, such as a ‘wiki’, be occupied by undergraduate women’s health students to improve their critical thinking skills? 2) What are the learning processes via which this occurs? 3) What are the implications of this assessment trial for achieving learning objectives and outcomes in future public health undergraduate courses? Methods The students contributed written, critical reflections (approximately 250 words) to the Wiki each week following the lecture. Students reflected on a range of topics including the portrayal of women in the media, femininity, gender inequality, child bearing and rearing, domestic violence, mental health, Indigenous women, older women, and LGBTIQ communities. Their entries were anonymous, but visible to their peers. Each wiki entry contained a ‘discussion tab’ wherein online conversations were initiated. We used a social constructivist approach to grounded theory to analyse the 480 entries posted over the semester. (http://pub336womenshealth.wikispaces.com/) Results The social constructivist approach initiated by Vygotsky (1978) and further developed by Jonasson (1994) was used to analyse the students’ contributions in relation to four key thematic outcomes including: 1) Complexities in representations across contexts; 2) Critical evaluation in real world scenarios; 3) Reflective practice based on experience, and; 4) Collaborative co-construction of knowledge. Both text and image/visual contributions are provided as examples within each of these learning processes. A theoretical model depicting the interactive learning processes that occurred via discussion of the textual and visual stimulus is presented.

Collaborative learning in the rural Indonesian craft industry

The research explores the potential for participatory and collaborative approaches in working with the Indonesian glass-bead rural craft industry, which currently struggles to sustain its business. Contextual inquiry and participatory action research were used to understand the local context, including motivations, barriers and opportunities and to collaboratively develop strategies for advancement and innovation. The study documents participatory design projects undertaken to make, sell and promote hedonic products. It identifies the importance of understanding local context and individual craftsperson aspirations in designing collaborative support programs. It also provides an in depth insight into the Indonesian rural craft industry.

Selection procedures for module discovery : exploring evolutionary algorithms for cognitive science

Evolutionary algorithms are playing an increasingly important role as search methods in cognitive science domains. In this study, methodological issues in the use of evolutionary algorithms were investigated via simulations in which procedures were systematically varied to modify the selection pressures on populations of evolving agents. Traditional roulette wheel, tournament, and variations of these selection algorithms were compared on the “needle-in-a-haystack” problem developed by Hinton and Nowlan in their 1987 study of the Baldwin effect. The task is an important one for cognitive science, as it demonstrates the power of learning as a local search technique in smoothing a fitness landscape that lacks gradient information. One aspect that has continued to foster interest in the problem is the observation of residual learning ability in simulated populations even after long periods of time. Effective evolutionary algorithms balance their search effort between broad exploration of the search space and in-depth exploitation of promising solutions already found. Issues discussed include the differential effects of rank and proportional selection, the tradeoff between migration of populations towards good solutions and maintenance of diversity, and the development of measures that illustrate how each selection algorithm affects the search process over generations. We show that both roulette wheel and tournament algorithms can be modified to appropriately balance search between exploration and exploitation, and effectively eliminate residual learning in this problem.

Factors influencing robustness and effectiveness of conditional random fields in active learning frameworks

Active learning approaches reduce the annotation cost required by traditional supervised approaches to reach the same effectiveness by actively selecting informative instances during the learning phase. However, effectiveness and robustness of the learnt models are influenced by a number of factors. In this paper we investigate the factors that affect the effectiveness, more specifically in terms of stability and robustness, of active learning models built using conditional random fields (CRFs) for information extraction applications. Stability, defined as a small variation of performance when small variation of the training data or a small variation of the parameters occur, is a major issue for machine learning models, but even more so in the active learning framework which aims to minimise the amount of training data required. The factors we investigate are a) the choice of incremental vs. standard active learning, b) the feature set used as a representation of the text (i.e., morphological features, syntactic features, or semantic features) and c) Gaussian prior variance as one of the important CRFs parameters. Our empirical findings show that incremental learning and the Gaussian prior variance lead to more stable and robust models across iterations. Our study also demonstrates that orthographical, morphological and contextual features as a group of basic features play an important role in learning effective models across all iterations.

Unsupervised online learning of condition-invariant images for place recognition

This paper presents an online, unsupervised training algorithm enabling vision-based place recognition across a wide range of changing environmental conditions such as those caused by weather, seasons, and day-night cycles. The technique applies principal component analysis to distinguish between aspects of a location’s appearance that are condition-dependent and those that are condition-invariant. Removing the dimensions associated with environmental conditions produces condition-invariant images that can be used by appearance-based place recognition methods. This approach has a unique benefit – it requires training images from only one type of environmental condition, unlike existing data-driven methods that require training images with labelled frame correspondences from two or more environmental conditions. The method is applied to two benchmark variable condition datasets. Performance is equivalent or superior to the current state of the art despite the lesser training requirements, and is demonstrated to generalise to previously unseen locations.

Preparing pre-service teachers to teach primary science : an integrated approach using the theme of sustainability

An integrated approach to assessment afforded pre-service teachers the opportunity to learn about a local sustainability issue through three learning areas: science and technology,the arts and studies of society and environment (SOSE). Three sustainability issues chosen by the pre-service teachers are presented in this paper highlighting the science concepts explored. Affordances and constraints of the integrated task are discussed in the conclusion.