Persistent robot tasking for environmental monitoring through crowd-sourcing

Persistent monitoring of the ocean is not optimally accomplished by repeatedly executing a fixed path in a fixed location. The ocean is dynamic, and so should the executed paths to monitor and observe it. An open question merging autonomy and optimal sampling is how and when to alter a path/decision, yet achieve desired science objectives. Additionally, many marine robotic deployments can last multiple weeks to months; making it very difficult for individuals to continuously monitor and retask them as needed. This problem becomes increasingly more complex when multiple platforms are operating simultaneously. There is a need for monitoring and adaptation of the robotic fleet via teams of scientists working in shifts; crowds are ideal for this task. In this paper, we present a novel application of crowd-sourcing to extend the autonomy of persistent-monitoring vehicles to enable nonrepetitious sampling over long periods of time. We present a framework that enables the control of a marine robot by anybody with an internet-enabled device. Voters are provided current vehicle location, gathered science data and predicted ocean features through the associated decision support system. Results are included from a simulated implementation of our system on a Wave Glider operating in Monterey Bay with the science objective to maximize the sum of observed nitrate values collected.

Report on a workshop to investigate the current status of environmental bio-acoustic monitoring

This workshop was supported by the Australian Centre for Ecological Analysis and Synthesis (ACEAS, http://www.aceas.org.au/), a facility of the Australian Government-funded Terrestrial Ecosystem Research Network (http://www.tern.org.au/), a research infrastructure facility established under the National Collaborative Research Infrastructure Strategy and Education Infrastructure Fund - Super Science Initiative, through the Department of Industry, Innovation, Science, Research and Tertiary Education. Hosted by: Queensland University of Technology, Brisbane, Queensland. (QUT, http://www.qut.edu.au/) Dates: 8-11 May 2012 Report Editors: Prof Stuart Parsons (Uni. Auckland, NZ) and Dr Michael Towsey (QUT). This report is a compilation of notes and discussion summaries contributed by those attending the Workshop. They have been assembled into a logical order by the editors. Another report (with photographs) can be obtained at: http://www.aceas.org.au/index.php?option=com_content&view=article&id=94&Itemid=96

Training-free probability models for whole-image based place recognition

Whole-image descriptors such as GIST have been used successfully for persistent place recognition when combined with temporal filtering or sequential filtering techniques. However, whole-image descriptor localization systems often apply a heuristic rather than a probabilistic approach to place recognition, requiring substantial environmental-specific tuning prior to deployment. In this paper we present a novel online solution that uses statistical approaches to calculate place recognition likelihoods for whole-image descriptors, without requiring either environmental tuning or pre-training. Using a real world benchmark dataset, we show that this method creates distributions appropriate to a specific environment in an online manner. Our method performs comparably to FAB-MAP in raw place recognition performance, and integrates into a state of the art probabilistic mapping system to provide superior performance to whole-image methods that are not based on true probability distributions. The method provides a principled means for combining the powerful change-invariant properties of whole-image descriptors with probabilistic back-end mapping systems without the need for prior training or system tuning.

Pattern-based topic models for information filtering

Topic modelling, such as Latent Dirichlet Allocation (LDA), was proposed to generate statistical models to represent multiple topics in a collection of documents, which has been widely utilized in the fields of machine learning and information retrieval, etc. But its effectiveness in information filtering is rarely known. Patterns are always thought to be more representative than single terms for representing documents. In this paper, a novel information filtering model, Pattern-based Topic Model(PBTM) , is proposed to represent the text documents not only using the topic distributions at general level but also using semantic pattern representations at detailed specific level, both of which contribute to the accurate document representation and document relevance ranking. Extensive experiments are conducted to evaluate the effectiveness of PBTM by using the TREC data collection Reuters Corpus Volume 1. The results show that the proposed model achieves outstanding performance.

Latex allergy : a perioperative environmental hazard

Latex allergy is a serious, possibly life threatening health hazard in the perioperative environment. Policy and procedures should be developed to identify patients who may be sensitive to latex and to ensure the avoidance of latex products in their care. Healthcare workers should also take steps to avoid exposure and protect themselves from hypersensitivity reactions.

Bayesian networks in environmental and resource management

This overview article for the special series “Bayesian Networks in Environmental and Resource Management” reviews 7 case study articles with the aim to compare Bayesian network (BN) applications to different environmental and resource management problems from around the world. The article discusses advances in the last decade in the use of BNs as applied to environmental and resource management. We highlight progress in computational methods, best-practices for model design and model communication. We review several research challenges to the use of BNs in environmental and resource management that we think may find a solution in the near future with further research attention.

Rethinking Invasion Ecologies from the Environmental Humanities

Research from a humanist perspective has much to offer in interrogating the social and cultural ramifications of invasion ecologies. The impossibility of securing national boundaries against accidental transfer and the unpredictable climatic changes of our time have introduced new dimensions and hazards to this old issue. Written by a team of international scholars, this book allows us to rethink the impact on national, regional or local ecologies of the deliberate or accidental introduction of foreign species, plant and animal. Modern environmental approaches that treat nature with naïve realism or mobilize it as a moral absolute, unaware or unwilling to accept that it is informed by specific cultural and temporal values, are doomed to fail. Instead, this book shows that we need to understand the complex interactions of ecologies and societies in the past, present and future over the Anthropocene, in order to address problems of the global environmental crisis. It demonstrates how humanistic methods and disciplines can be used to bring fresh clarity and perspective on this long vexed aspect of environmental thought and practice. Students and researchers in environmental studies, invasion ecology, conservation biology, environmental ethics, environmental history and environmental policy will welcome this major contribution to environmental humanities.

Can environmental history save the world?

As a ‘genre of history’ in Australia environmental history is relatively new, emerging in the 1960s and 70s from encounters between history, geography and the natural sciences in the context of growing environmental concern and activism. Interdisciplinary in orientation, the field also exhibited an unusually high level of engagement with current environmental issues and organisations. In this era of national research priorities and debates about the role and purpose of university-based research, it therefore seemed fair to ask: ‘can environmental history save the world?’ In response, a panel of new and established researchers offer their perspectives on issues of relevance and utility within this diverse and dynamic genre.

Environmental factors associated with active living in retirement village residents : findings from an exploratory qualitative enquiry

This exploratory enquiry employs qualitative methods to advance knowledge and understanding of physical environmental attributes related to active living among residents of Australian retirement villages. Six focus groups (n = 51 residents) were held and participants described how their current, and subsequently ideal, retirement village and neighborhood supported active lifestyles. Thematic analysis revealed three key environmental factors associated with active living: a positive social environment within the village; services and facilities provided in the village and wider neighborhood; and the presence of suitable pedestrian infrastructure. The unique discovery that environmental factors of both the retirement village and the surrounding neighborhood were associated with residents’ active living raises many questions for study. Findings informed the development of a survey instrument, and further understanding in this area has the potential to contribute to the design and siting practices of senior housing complexes within neighborhoods.

People living in hilly residential areas in metropolitan Perth have less diabetes : spurious association or important environmental determinant?

BACKGROUND: Variations in 'slope' (how steep or flat the ground is) may be good for health. As walking up hills is a physiologically vigorous physical activity and can contribute to weight control, greater neighbourhood slopes may provide a protective barrier to weight gain, and help prevent Type 2 diabetes onset. We explored whether living in 'hilly' neighbourhoods was associated with diabetes prevalence among the Australian adult population. METHODS: Participants ([greater than or equal to]25years; n=11,406) who completed the Western Australian Health and Wellbeing Surveillance System Survey (2003-2009) were asked whether or not they had medically-diagnosed diabetes. Geographic Information Systems (GIS) software was used to calculate a neighbourhood mean slope score, and other built environment measures at 1600m around each participant's home. Logistic regression models were used to predict the odds of self-reported diabetes after progressive adjustment for individual measures (i.e., age, sex), socioeconomic status (i.e., education, income), built environment, destinations, nutrition, and amount of walking. RESULTS: After full adjustment, the odds of self-reported diabetes was 0.72 (95% CI 0.55-0.95) and 0.52 (95% CI 0.39-0.69) for adults living in neighbourhoods with moderate and higher levels of slope, respectively, compared with adults living in neighbourhoods with the lowest levels of slope. The odds of having diabetes was 13% lower (odds ratio 0.87; 95% CI 0.80-0.94) for each increase of one percent in mean slope. CONCLUSIONS: Living in a hilly neighbourhood may be protective of diabetes onset or this finding is spurious. Nevertheless, the results are promising and have implications for future research and the practice of flattening land in new housing developments.

Innovation through action research in environmental education : from project to praxis

This thesis is a work-in-progress that articulates my research journey based on the development of a curriculum innovation in environmental education. This journey had two distinct, but intertwined phases: action research based fieldwork, conducted collaboratively, to create a whole school approach to environmental education curriculum planning; and a phase of analysis and reflection based on the emerging findings, as I sought to create personal "living educational theory" about change and innovation. A key stimulus for the study was the perceived theory-practice gap in environmental education, which is often presented in the literature as a criticism of teachers for failing to achieve the values and action objectives of critical environmental education. Hence, many programs and projects are considered to be superficial and inconsequential in terms of their ability to seriously address environmental issues. The intention of this study was to work with teachers in a project that would be an exemplar of critical environmental education. This would be in the form of a whole school "learnscaping" curriculum in a primary school whereby the schoolgrounds would be utilised for interdisciplinary critical environment education. Parallel with the three cycles of action research in this project, my research objectives were to identify and comment upon the factors that influence the generation of successful educational innovation. It was anticipated that the project would be a collaboration involving me, as researcher-facilitator, and many of the teachers in the school as active participants. As the project proceeded through its action cycles, however, it became obvious that the goal of developing a critical environmental education curriculum, and the use of highly participatory processes, were unrealistic. Institutional and organisational rigidities in education generally, teachers' day-to-day work demands, and the constant juggle of work, family and other responsibilities for all participants acted as significant constraints. Consequently, it became apparent that the learnscaping curriculum would not be the hoped-for exemplar. Progress was slow and, at times, the project was in danger of stalling permanently. While the curriculum had some elements of critical environmental education, these were minor and not well spread throughout the school. Overall, the outcome seemed best described as a "small win"; perhaps just another example of the theory-practice gap that I had hoped this project would bridge. Towards the project's end, however, my continuing reflection led to an exploration of chaos/complexity theory which gave new meaning to the concept of a "small win". According to this theory, change is not the product of linear processes applied methodically in purposeful and diligent ways, but emerges from serendipitous events that cannot be planned for, or forecast in advance. When this perspective of change is applied to human organisations - in this study, a busy school - the context for change is recognised not as a stable, predictable environment, but as a highly complex system where change happens all the time, cannot be controlled, and no one can be really sure where the impacts might lead. This so-called "butterfly effect" is a central idea of this theory where small changes or modifications are created - the effects of which are difficult to know, let alone determine - and which can have large-scale impacts. Allied with this effect is the belief that long term developments in an organisation that takes complexity into account, emerge by spontaneous self-organising evolution, requiring political interaction and learning in groups, rather than systematic progress towards predetermined goals or "visions". Hence, because change itself and the contexts of change are recognised as complex, chaos/complexity theory suggests that change is more likely to be slow and evolutionary - cultural change - rather than fast and revolutionary where the old is quickly ushered out by radical reforms and replaced by new structures and processes. Slow, small-scale changes are "normal", from a complexity viewpoint, while rapid, wholesale change is both unlikely and unrealistic. Therefore, the frustratingly slow, small-scale, imperfect educational changes that teachers create - including environmental education initiatives - should be seen for what they really are. They should be recognised as successful changes, the impacts of which cannot be known, but which have the potential to magnify into large-scale changes into the future. Rather than being regarded as failures for not meeting critical education criteria, "small wins" should be cause for celebration and support. The intertwined phases of collaborative action research and individual researcher reflection are mirrored in the thesis structure. The first three chapters, respectively, provide the thesis overview, the literature underpinning the study's central concern, and the research methodology. Chapters 4, 5, and 6 report on each of the three action research cycles of the study, namely Laying the Groundwork, Down to Work!, and The Never-ending Story. Each of these chapters presents a narrative of events, a literature review specific to developments in the cycle, and analysis and critique of the events, processes and outcomes of each cycle. Chapter 7 provides a synthesis of the whole of the study, outlining my interim propositions about facilitating curriculum change in schools through action research, and the implications of these for environmental education.

The development of a carrying capacity assessment model for the Australian socio-environmental context

A key aim of this research was to highlight how society's understanding of constraints to the productive capacity of its resource base is vital to its long-term survival. This was achieved through the development of an online model, the Carrying Capacity Dashboard. The Dashboard was developed to estimate how much land Australian populations require for the production of their food, textiles, timber and liquid fuel. Findings reveal that Australia's estimated carrying capacity is currently over 40 million people but longer-term and more regional analyses suggest a much smaller number. Carrying capacity assessment also indicates that optimal resource security is to be found in balancing both small and large-scale self-sufficiency.

Pattern-based topics for document modelling in information filtering

Many mature term-based or pattern-based approaches have been used in the field of information filtering to generate users’ information needs from a collection of documents. A fundamental assumption for these approaches is that the documents in the collection are all about one topic. However, in reality users’ interests can be diverse and the documents in the collection often involve multiple topics. Topic modelling, such as Latent Dirichlet Allocation (LDA), was proposed to generate statistical models to represent multiple topics in a collection of documents, and this has been widely utilized in the fields of machine learning and information retrieval, etc. But its effectiveness in information filtering has not been so well explored. Patterns are always thought to be more discriminative than single terms for describing documents. However, the enormous amount of discovered patterns hinder them from being effectively and efficiently used in real applications, therefore, selection of the most discriminative and representative patterns from the huge amount of discovered patterns becomes crucial. To deal with the above mentioned limitations and problems, in this paper, a novel information filtering model, Maximum matched Pattern-based Topic Model (MPBTM), is proposed. The main distinctive features of the proposed model include: (1) user information needs are generated in terms of multiple topics; (2) each topic is represented by patterns; (3) patterns are generated from topic models and are organized in terms of their statistical and taxonomic features, and; (4) the most discriminative and representative patterns, called Maximum Matched Patterns, are proposed to estimate the document relevance to the user’s information needs in order to filter out irrelevant documents. Extensive experiments are conducted to evaluate the effectiveness of the proposed model by using the TREC data collection Reuters Corpus Volume 1. The results show that the proposed model significantly outperforms both state-of-the-art term-based models and pattern-based models

Laser-to-radar sensing redundancy for resilient perception in adverse environmental conditions

This paper presents an approach to promote the integrity of perception systems for outdoor unmanned ground vehicles (UGV) operating in challenging environmental conditions (presence of dust or smoke). The proposed technique automatically evaluates the consistency of the data provided by two sensing modalities: a 2D laser range finder and a millimetre-wave radar, allowing for perceptual failure mitigation. Experimental results, obtained with a UGV operating in rural environments, and an error analysis validate the approach.