1,720,971 research outputs found
Annotated video footage for automated identification and counting of fish in unconstrained marine environments
No full textComputer vision techniques such as deep learning have quickly become of interest to ecologists for automatically processing large volumes of video and image-based data. However, training deep learning models often require large volumes of manually annotated footage to create a robust and accurate model. The collection and annotation of these training datasets can incur high initial labour cost and may not be feasible for some research projects. The accessibility of publicly available datasets that are pre-annotated for easy implementation is imperative for continued research and understanding of computer vision technology as a viable method to automate the processing of visual data. In this report, we provide a dataset containing ~ 9,000 annotated fish in unconstrained conditions in a key coastal habitat - seagrass meadows - collected via remote underwater video. These images include object instance annotations which consist of a corresponding image, label, bounding box and segmentation mask. These data can be used for training several different computer vision models and for investigating the effects of pre- or post-processing steps to improve model performance when predicting data in awuatic habitats. The purpose of this report, in conjunction with the annotated dataset, is to advance the use of CV techniques and further the growth in labelled fish datasets publicly available
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Measuring cross-habitat movements among habitat hotspots of fish with artificial intelligence
No full textConnectivity, defined as the movement of individuals among populations or habitats, is a crucial ecological process that underpins the function of ecosystems. Animal movements promote a wide array of ecological outcomes, from genetic diversity to ecosystem recovery after disturbance. Therefore, it is necessary to have a clear understanding of the capabilities, scale, frequency, and locations of animal movements. In aquatic ecosystems, obtaining and analysing movement data is challenging because constantly changing environmental conditions hamper the use of traditional frameworks and methods. The study of animal movement in dynamic aquatic ecosystems also requires large volumes of data because animal movements cover different magnitudes, directions, and spatial levels of ecological organisation. As a result, new data collection and processing technologies are being developed to increase our understanding of this complex ecological process. Among new technologies, computer vision, machine learning and deep learning have received increased attention for their robust capabilities for rapidly processing large volumes of underwater imagery. Computer vision (CV) techniques are particularly suited to animal movement research because they can capture and process large amounts of raw data from underwater imagery. Despite their potential, CV techniques are only now beginning to be assessed in studies of aquatic animal movement, and their integration with appropriate statistical frameworks for behavioural analyses is required. In this thesis, I aim to identify, develop and apply CV techniques to measure animal movement in aquatic ecosystems. The focus is on measuring fish movements in connectivity corridors in estuarine systems. Fish movement research provides fundamental information about fisheries stocks, the status of protected areas, and the impact of habitat loss. Connectivity corridors are hotspots of fish migration, colonisation, feeding and reproduction. Yet much of fish behaviour in aquatic ecosystems remains hard to observe and timeconsuming to document manually. Connectivity corridors are a challenging but useful case study to test novel computer vision techniques for tracking fish. I first explored the current uses of CV techniques in fish movement studies and identified the benefits of CV for fish movement research. While the uptake of CV in fish movement studies has been slow, CV techniques provide two key benefits: 1) rapid, accurate and reliable datasets and 2) complementary information with traditional data collection techniques. Then, I developed a CV pipeline that automatically detects and tracks fish from underwater imagery. The pipeline has an 84% accuracy at detecting and subsequently tracking fish and provides large, raw movement datasets useful for ecological insight. To translate the raw movement data into behavioural events, I developed a new methodology for applying structural equation models to infer latent behavioural states of fish from observations of behavioural indicators. The statistical models accurately predicted behavioural events such as foraging (a slow, sinuous movement near the substrate) and fine-scale migrations (a fast, directional movement near the surface). Finally, I applied the CV pipeline to study the fine-scale movement and predation dynamics of fish at piped weirs in multiple estuaries. I used multi-species occupancy models to characterise fine-scale temporal changes in predator-prey co ccurrence and determined if behavioural differences could be detected at different categories of predator-prey co-occurrences. The fine-scale temporal changes of predator-prey co-occurrence varied among sampling days and locations, but I nevertheless identified that prey exhibited significantly different behaviours that depended on the probability of co-occurring predators. Overall, I bridged the gap between the development and application of new technologies for ecological research. CV can help us improve our understanding of critical interconnections among habitats and help researchers and managers increase data availability into conservation ecology and decision making. CV has the capacity to inform data-driven decisions that directly influence the health and productivity of marine ecosystems.Thesis (PhD Doctorate)Doctor of Philosophy (PhD)School of Environment and ScScience, Environment, Engineering and TechnologyFull Tex
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
EcoCommons: Advancing Global Environmental Modelling with Open-Access Solutions
No full textUnderstanding and mitigating the impacts of global change on ecosystems requires not only advanced environmental models but also accessible platforms that enable their application across diverse datasets and research needs. For the past 10 years, EcoCommons Australia (https://www.ecocommons.org.au/), a research initiative supported by Australia’s National Collaborative Research Infrastructure Strategy and Australian Research Data Commons, has provided environmental modellers with the tools to tackle challenges across the entire Australian continent.In 2024, building on EcoCommons’ success, the team expanded its services and open-sourced a variety of environmental modelling and technology solutions through a GitHub repository. These solutions include previously advanced algorithms and scalable cloud infrastructure, now simplified into easy-to-use EcoCommons Notebooks that can be deployed on commercial clouds or local machines. EcoCommons technology empowers users to perform species distribution modelling, habitat suitability analyses, and climate change projections, providing a comprehensive toolkit for global environmental research.The platform’s scientific foundations and methodologies have been recognised in the peer-reviewed journal Environmental Modelling and Software (https://doi.org/10.1016/j.envsoft.2024.106255), affirming its credibility and contributions to the field. This recognition underscores the platform’s robust scientific background and the assumptions underpinning its algorithms and solutions. EcoCommons’ GitHub repository serves as a global hub for interaction, where users from around the world can engage with the notebooks, report issues, and contribute their research to this vibrant community. This collaborative environment fosters innovation and ensures that the platform evolves in response to the needs of its diverse user base.With more than 2,000 users, EcoCommons technology has supported research across Africa, Europe, Latin America, and Oceania. These international collaborations highlight the platform’s versatility and its impact on global environmental research.Moreover, the technology behind EcoCommons is integral to supporting national environmental reporting in Australia, solidifying its value in real-world management and conservation actions. By providing the tools necessary for accurate environmental reporting, EcoCommons plays a crucial role in shaping policy and conservation strategies. In this session, we will discuss the lessons and challenges of building Australia’s largest environmental modelling platform. We will present case studies that demonstrate EcoCommons’ application to large-scale questions both in Australia and globally, and showcase the scalability and reproducibility of EcoCommons Notebooks
- …
