Evaluation of four supervised learning methods for benthic habitat mapping using backscatter from multi-beam sonar

An understanding of the distribution and extent of marine habitats is essential for the implementation of ecosystem-based management strategies. Historically this had been difficult in marine environments until the advancement of acoustic sensors. This study demonstrates the applicability of supervised learning techniques for benthic habitat characterization using angular backscatter response data. With the advancement of multibeam echo-sounder (MBES) technology, full coverage datasets of physical structure over vast regions of the seafloor are now achievable. Supervised learning methods typically applied to terrestrial remote sensing provide a cost-effective approach for habitat characterization in marine systems. However the comparison of the relative performance of different classifiers using acoustic data is limited. Characterization of acoustic backscatter data from MBES using four different supervised learning methods to generate benthic habitat maps is presented. Maximum Likelihood Classifier (MLC), Quick, Unbiased, Efficient Statistical Tree (QUEST), Random Forest (RF) and Support Vector Machine (SVM) were evaluated to classify angular backscatter response into habitat classes using training data acquired from underwater video observations. Results for biota classifications indicated that SVM and RF produced the highest accuracies, followed by QUEST and MLC, respectively. The most important backscatter data were from the moderate incidence angles between 30° and 50°. This study presents initial results for understanding how acoustic backscatter from MBES can be optimized for the characterization of marine benthic biological habitats. © 2012 by the authors.

Readiness for interprofessional learning : a cross-faculty comparison between architecture and occupational therapy students

Health and wellbeing includes a need for built environments to accommodate and be inclusive of the broadest range of people and a corresponding need to ensure graduates are ready to engage in this field of interprofessional and inter-industry practise. All too often, interprofessional education in higher education is neglected with a tendency towards educational silos, particularly at a cross-faculty level. This paper reports on an initiative that embedded universal design practice education into the curricula of first year architecture and third year occupational therapy students and evaluated the impact on students’ readiness for interprofessional learning. The Readiness for Interprofessional Learning Scale (RIPLS) was given to students at the beginning and end of the semester during which students participated in a variety of online and face-to-face curriculum initiatives. Results showed that at the beginning of semester, occupational therapy students were significantly more positive about interprofessional learning than their architecture counterparts. Post-results showed that this trend continued but that occupational therapy students became less positive on some items after the interprofessional learning experience. This study provides insights into the interprofessional learning experiences of a group of students who have not previously been studied within the available literature.

Navigating 21st century multimodal textual environments : a case study of digital literacy

In the 21st Century young people have the opportunity to create texts that were unimaginable for previous generations. Today’s children live and learn while immersed in a technological world that is fast paced and constantly in a state of change. As technology becomes more and more accessible and specifically marketed to children of the 21st century, educators are challenged to re-consider the literacy skills required to be successfully and safely literate, and the repertoire of literacy pedagogies teacher must have to effectively engage these young people in learning. While there is much evidence to suggest that schools and teachers are not all meeting this challenge, there are some inspiring examples in which schools, communities and teachers are taking up the challenge. This paper presents one case study, which is explored through a 21st century literacy framework that allows us to interpret and analyse the multimodal texts and the processes students use in their creation. Attention is paid to how the case study teacher created meaningful learning experiences and opportunities for them to create and interact within multimodal communications environments, both within and beyond the school.

Applied learning educators breaching boundaries storming barriers

This paper provides discussion of learning experienced by Applied Learning Educators in a workplace context where everyday teaching activities can involve undertaking unfamiliar tasks to the extent that the concept of ‘crossing boundaries’, or acting outside ‘comfort zones’ becomes ‘normalised’. This perspective arises from consideration of extensive interviews with Applied Learning Educators who work in the Victorian Certificate of Applied Learning (VCAL), a senior years’ pathway in Victoria. The pathway is available in settings of schools, Adult Community Education (ACE) and Technical and Further Education (TAFE) and designed to support the engagement of young people in education and their subsequent transition into further study or meaningful work. VCAL Educators use Applied Learning pedagogy in the development of curriculum content that promotes employability skills, connectedness to community and has grounding in student interests and needs. Subsequently student learning in VCAL occurs in and out of classrooms. Applied Learning Educators frequently navigate institutional boundaries in the process of negotiating and developing partnerships with industry and community organisations to enable learning to be undertaken in meaningful and relevant environments. In this paper Boundary Crossing is used as a concept for discussing the wide-ranging nature of VCAL educators’ everyday practice as they respond to the needs of the cohort and requirements of the curriculum. Collegial learning is considered using the notion of Communities of Practice.

Transfer learning using the online Fuzzy Min-Max neural network

In this paper, we present an empirical analysis on transfer learning using the Fuzzy Min–Max (FMM) neural network with an online learning strategy. Three transfer learning benchmark data sets, i.e., 20 Newsgroups, WiFi Time, and Botswana, are used for evaluation. In addition, the data samples are corrupted with white Gaussian noise up to 50 %, in order to assess the robustness of the online FMM network in handling noisy transfer learning tasks. The results are analyzed and compared with those from other methods. The outcomes indicate that the online FMM network is effective for undertaking transfer learning tasks in noisy environments.

Designing blended spaces to maximise student learning in work integrated learning programs

This paper describes a case study at a large metropolitan university in Australia where a range of technology-enabled blended spaces are used for interaction, communication and reflection between the work and university environments to enrich students' learning experiences during their work placement year. Blended space design requirements to maximise the learning experience of students undertaking work integrated learning are identified

Capacity-building in nonprofit organizations : Is there a blended learning paradigm for the sector?

Blended learning models are widely-used, successful training vehicles for e-learning and workplace training, in corporate as well as higher education environments. Increasingly, Web 2.0 applications, imbedded within blended learning models, are being recognized for their utility in these settings. Concern for the sustainability and relevance of nonprofit organizations has sharpened the interest in building effective capacity-building models for the sector. Can Web 2.0 technologies enhance capacity-building models in the Third Sector? Because blended learning is a remarkably adaptable and fluid model, its potential for transforming capacity-building models in the nonprofit sector is thought to be significant. This paper introduces the concept of transformational approaches to capacity-building and asks if blended learning paradigms that incorporate interactive next-generation technologies might strike a responsive chord in the sector. The authors present research to date on blended learning and capacity-building to lay the foundation for the introduction of one blended learning model for training and education in the nonprofit sector. While the authors suggest that blended learning, as it is evolving, is the key to driving innovation in capacity-building models, they recognize that tailoring blended learning to the audience is critical in achieving success. It is suggested that for optimal results, capacity-building efforts should be built on holistic approaches to the integration of individual self-actualization goals with mechanisms for organizational and sector empowerment, using the technologies imbedded with blended learning. © 2011 Springer-Verlag.

Capacity-building in nonprofit organizations using blended learning as a gateway to practitioner education

Experience to date in for-profit as well as in educational settings has demonstrated that blended learning models are effective training vehicles for online instruction and workplace training. Increasingly, technology is playing a critical role in how e-learning is being delivered. Concern for the sustainability and relevance of nonprofit organizations has heightened interest in building effective capacity-building models for the sector. Because blended learning is a remarkably adaptable and fluid model, its potential for transforming capacity-building models in the nonprofit sector can be significant. Are web-based technologies enhancing capacity-building models in the Third Sector? This chapter explores the use of blended learning models within different educational environments to provide the context for asking the question: can blended learning paradigms that incorporate interactive next-generation technologies be widely accepted and implemented in the Third Sector? To establish a baseline for future studies, researchers surveyed nonprofit practitioners in Western Pennsylvania, US and Victoria, Australia. Results from three surveys conducted in 2011 reflect an awareness of the value of web-based training and education for nonprofit practitioners, but do not provide evidence of widespread usage. © 2013 Nova Science Publishers, Inc. All rights reserved.

The Harbour outdoors: Investigating how children and educators engage with the outdoor learning space at the Harbour Family and Children's Centre

The aim of the research was to carry out an in-depth case study of the outdoor space at a purposively designed outdoor learning space in a demonstration childcare program in an Australian city. The design of the outdoor space emphasises natural elements and sustainability, while the program uses an indoor/outdoor approach with multi-age sharing of the space. The report included staff, management and researcher perspectives on how the outdoor space worked for children and staff, and provided findings that could inform the ongoing professional processes of reflection on the learning environment at the centre. In addition, the researchers also sought the views of the original designers of the outdoor space, and od centre management at the time when outdoor space was being designed and built. The researchers considered that their perspectives, along with those of current management and staff, could assist in addressing questions of long-term sustainability and practicality in the design of outdoor spaces in childcare centres.

Learning latent activities from social signals with hierarchical dirichlet processes

Understanding human activities is an important research topic, most noticeably in assisted-living and healthcare monitoring environments. Beyond simple forms of activity (e.g., an RFID event of entering a building), learning latent activities that are more semantically interpretable, such as sitting at a desk, meeting with people, or gathering with friends, remains a challenging problem. Supervised learning has been the typical modeling choice in the past. However, this requires labeled training data, is unable to predict never-seen-before activity, and fails to adapt to the continuing growth of data over time. In this chapter, we explore the use of a Bayesian nonparametric method, in particular the hierarchical Dirichlet process, to infer latent activities from sensor data acquired in a pervasive setting. Our framework is unsupervised, requires no labeled data, and is able to discover new activities as data grows. We present experiments on extracting movement and interaction activities from sociometric badge signals and show how to use them for detecting of subcommunities. Using the popular Reality Mining dataset, we further demonstrate the extraction of colocation activities and use them to automatically infer the structure of social subgroups. © 2014 Elsevier Inc. All rights reserved.

Remixing to design learning: social media and peer-to-peer interaction

Social and participatory media offer opportunities to interact and share user-generated content. After some investigation and research, the authors are in their initial stages of using such media to provide a pathway for thinking about learning design in higher education. Using the concept of remixing, the authors aim to creatively blend and manipulate ideas to build a sustainable approach to course/program enhancement. Remixing is touted as one of the most important practices within the field of open educational resources, but it is not mainstream practice in educational thinking or design. This article highlights the authors’ approach and uses their pre-service teacher education program and their previous high school study as an example of remixing. The high school study involved the integration of social and participatory media into the face-to-face classroom; Author 1 was the practitioner researcher in the high school study. This article articulates the use of online social environments at the high school level to highlight concepts of sharing and remixing as a creative and social approach to designing learning in higher education. It also attempts to consider this within a course-wide approach.

Interprofessional learning at work: what spatial theory can tell us about workplace learning in an acute care ward

It is widely recognized that every workplace potentially provides a rich source of learning. Studies focusing on health care contexts have shown that social interaction within and between professions is crucial in enabling professionals to learn through work, address problems and cope with challenges of clinical practice. While hospital environments are beginning to be understood in spatial terms, the links between space and interprofessional learning at work have not been explored. This paper draws on Lefebvre’s tri-partite theoretical framework of perceived, conceived and lived space to enrich understandings of interprofessional learning on an acute care ward in an Australian teaching hospital. Qualitative analysis was undertaken using data from observations of Registered Nurses at work and semi-structured interviews linked to observed events. The paper focuses on a ward round, the medical workroom and the Registrar’s room, comparing and contrasting the intended (conceived), practiced (perceived) and pedagogically experienced (lived) spatial dimensions. The paper concludes that spatial theory has much to offer understandings of interprofessional learning in work, and the features of work environments and daily practices that produce spaces that enable or constrain learning.

Designing blended spaces to maximise student learning in work integrated learning programs

This paper describes a case study at a large metropolitan university in Australia where a range of technology-enabled blended spaces are used for interaction, communication and reflection between the work and university environments to enrich students' learning experiences during their work placement year. Blended space design requirements to maximise the learning experience of students undertaking work integrated learning are identified. © 2009 Friederika Kaider, Kathy Henschke, Joan Richardson and Mary Paulette Kelly.

A machine learning approach to measure and monitor physical activity in children to help fight overweight and obesity

Physical Activity is important for maintaining healthy lifestyles. Recommendations for physical activity levels are issued by most governments as part of public health measures. As such, reliable measurement of physical activity for regulatory purposes is vital. This has lead research to explore standards for achieving this using wearable technology and artificial neural networks that produce classifications for specific physical activity events. Applied from a very early age, the ubiquitous capture of physical activity data using mobile and wearable technology may help us to understand how we can combat childhood obesity and the impact that this has in later life. A supervised machine learning approach is adopted in this paper that utilizes data obtained from accelerometer sensors worn by children in free-living environments. The paper presents a set of activities and features suitable for measuring physical activity and evaluates the use of a Multilayer Perceptron neural network to classify physical activities by activity type. A rigorous reproducible data science methodology is presented for subsequent use in physical activity research. Our results show that it was possible to obtain an overall accuracy of 96 % with 95 % for sensitivity, 99 % for specificity and a kappa value of 94 % when three and four feature combinations were used.